Abidhan - JRMGE

Journal of Rock Mechanics and Geotechnical Engineering xxx (xxxx) xxx
Contents lists available at ScienceDirect
Journal of Rock Mechanics and

Geotechnical Engineering
journal homepage: www.jrmge.cn
Hybrid ensemble soft computing approach for predicting penetration rate

of tunnel boring machine in a rock environment
Abidhan Bardhan a, *, Navid Kardani b, Anasua GuhaRay c, Avijit Burman a, Pijush Samui a,
Yanmei Zhang d, **
a
National Institute of Technology Patna, Patna, Bihar, India
b
Civil and Infrastructure Engineering Discipline, School of Engineering, Royal Melbourne Institute of Technology (RMIT), Victoria, 3001, Australia
c
Department of Civil Engineering, BITS-Pilani Hyderabad Campus, Hyderabad, Telangana, India
d
College of Aerospace Engineering, Chongqing University, Chongqing, 400044, China
a r t i c l e i n f o a b s t r a c t
Article history: This study implements a hybrid ensemble machine learning method for forecasting the rate of pene-
Received 21 April 2021 tration (ROP) of tunnel boring machine (TBM), which is becoming a prerequisite for reliable cost
Received in revised form assessment and project scheduling in tunnelling and underground projects in a rock environment. For
24 June 2021
this purpose, a sum of 185 datasets was collected from the literature and used to predict the ROP of TBM.
Accepted 24 June 2021
Initially, the main dataset was utilised to construct and validate four conventional soft computing (CSC)
Available online xxx
models, i.e. minimax probability machine regression, relevance vector machine, extreme learning ma-
chine, and functional network. Consequently, the estimated outputs of CSC models were united and
Keywords:
Tunnel boring machine (TBM)
trained using an artificial neural network (ANN) to construct a hybrid ensemble model (HENSM). The
Rate of penetration (ROP) outcomes of the proposed HENSM are superior to other CSC models employed in this study. Based on the
Artificial intelligence experimental results (training RMSE ¼ 0.0283 and testing RMSE ¼ 0.0418), the newly proposed HENSM is
Artificial neural network (ANN) potential to assist engineers in predicting ROP of TBM in the design phase of tunnelling and underground
Ensemble modelling projects.
2021 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by
Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/
licenses/by-nc-nd/4.0/).
1. Introduction method is a well-developed technology, professionals are imple-

menting mechanical excavation in underground construction
In the field of civil engineering, there is an endless growing (Armaghani et al., 2017). A tunnel boring machine (TBM) is an
demand due to rapid industrialisation. The construction industry essential tool used for tunnelling in underground projects. TBMs
plays a vital role in the development of the country in the field of offer copious advantages over the drilling and blasting method
transportation, hydropower, mining, and underwater construction. (Javad and Narges, 2010). It should be noted that TBMs are gigantic
In several areas such as rail, metro, and hydropower, construction machines and during the course of excavation, TBMs are extremely
projects are underway across the world. In recent decades, rapid sensitive to conditions of rock mass throughout the path (Zhou
industrialisation is ongoing on a fast-track basis to reduce the et al., 2021). Though TBM is the best option for tunnelling in a
overall development costs and timely completion of projects. In rocky medium, insufficient information and unknown rock mass
most heavy and civil engineering projects, tunnelling works are conditions can lead to a decline in the safety and efficiency of the
now being carried out to avoid open excavation and blasting tunnelling operation. Therefore, proper planning and accurate
(Mahdevari et al., 2014). Even though the drilling and blasting estimation are required to adopt the best construction techniques
and to predict the performance of TBMs in a rock environment
(Zhou et al., 2021).
Prediction of TBM performance is an important factor to esti-
* Corresponding author.
mate project duration, project cost, project schedule, and pro-
** Corresponding author.
E-mail addresses: abidhan@nitp.ac.in (A. Bardhan), zhangym@cqu.edu.cn
curement schedule of bulk materials (Yagiz et al., 2009).
(Y. Zhang). Theoretically, the performance of a TBM is measured in terms of
Peer review under responsibility of Institute of Rock and Soil Mechanics, Chi- rate of penetration (ROP), which is the ratio of excavation distance
nese Academy of Sciences.
https://doi.org/10.1016/j.jrmge.2021.06.015
1674-7755 2021 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-
NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Please cite this article as: Bardhan A et al., Hybrid ensemble soft computing approach for predicting penetration rate of tunnel boring machine
in a rock environment, Journal of Rock Mechanics and Geotechnical Engineering, https://doi.org/10.1016/j.jrmge.2021.06.015
2 A. Bardhan et al. / Journal of Rock Mechanics and Geotechnical Engineering xxx (xxxx) xxx
to continuous operation time of TBM (Mahdevari et al., 2014). 2013; Armaghani et al., 2017; Koopialipoor et al., 2019; Xu et al.,
Several factors, such as intact rock properties, rock mass properties, 2019), ANFIS (Salimi et al., 2016), SVM/SVR (Martins and Miranda,
cutter geometry, and specification of TBMs, influence the perfor- 2013; Mahdevari et al., 2014; Salimi et al., 2016; Xu et al., 2019),
mance of TBMs (Zeng et al., 2021). Proper application of TBM to any least-squares support vector machine (LS-SVM) (Zhang et al.,
tunnelling projects depends on the parameters mentioned above, 2020a), GEP (Armaghani et al., 2018), RVM/RVR (Fattahi, 2019;
and hence a detailed assessment is required to compute the ROP of Zhang et al., 2020a), and DNN (Koopialipoor et al., 2019). Xu et al.
TBMs. (2019) also used KNN, CHAID, and CART to predict the ROP of
Predicting the performance of TBMs in a rocky medium is a TBM and attained a significant accuracy level (based on the deter-
complex task compared to that in a soil medium. Thus, researchers mination coefficient (R2) value) in many cases. These CSC models
investigated the inter-relationship between the rock properties and have also been successfully employed to solve problems in different
ROP of TBMs (Graham, 1976; Farmer and Glossop, 1980; Cassinelli engineering fields (Zhang and Goh, 2013, 2016; Chen et al., 2020;
et al., 1982). Based on the findings, it is clear that there is neither Goh et al., 2020; Ghani and Kumari, 2021; Ghani et al., 2021a;
an exclusive way nor a fixed technique for predicting the ROP of Kardani et al., 2021a; Kumar et al., 2021c). Despite the good per-
TBM in practice (Zhang et al., 2020a). Methods implemented by the formance of ANN, SVM, ANFIS, and many of the other conventional
researchers can be broadly categorised into three clusters: (i) methods, they are considered black-box models (Alavi and
theoretical and empirical, (ii) statistical, and (iii) computational. Gandomi, 2011; Mohammadzadeh et al., 2014; Bui et al., 2018).
These methods are developed from laboratory experiments and Also, the overfitting and local minima trapping issues limit their
field observation, a set of mathematical rules, and several soft applicability for further analysis, which are considered as the main
computing techniques, respectively. As mentioned by Gao et al. disadvantages of CSC algorithms (Armaghani et al., 2014; Roy and
(2020), TBM’s ROP estimation using theoretical and empirical Singh, 2020; Bardhan et al., 2021a).
models give relatively low accuracy, and hence new methods need Therefore, to circumvent the limitations of the CSC models,
to be developed. On the other hand, a comprehensive review of recent studies have resorted to hybrid soft computing model as
previous studies reveals that the performance of statistical models potential alternatives to predict the desired output (Bui et al., 2018;
(i.e. simple and multiple linear regression models) is relatively low Bardhan et al., 2021b). An amalgamation of meta-heuristic opti-
compared to the theoretical and empirical models (Koopialipoor misation algorithms and CSC models yields high-performance
et al., 2019; Shahrour and Zhang, 2021; Zhang et al., 2021a). Thus, computational models, which balance the exploration and exploi-
recent studies have resorted to soft computing techniques as po- tation processes during the course of optimisation, and offers a
tential alternatives to improve the reliability and exactness of the bendy and powerful method for solving high-dimensional and
existing empirical and statistical models (Grima et al., 2000; complex problems (Mohammadzadeh et al., 2014; Bui et al., 2018).
Benardos and Kaliampakos, 2004; Yagiz et al., 2009; Javad and For predicting the performance of TBM, Armaghani et al. (2017)
Narges, 2010; Yagiz and Karahan, 2011; Martins and Miranda, used two ANN-based hybrid models, i.e. particle swarm optimisa-
2013; Mobarra et al., 2013; Ghasemi et al., 2014; Mahdevari et al., tion (PSO)-ANN (ANN optimised with PSO) and imperialism
2014; Salimi et al., 2016; Armaghani et al., 2017, 2018; Fattahi, competitive algorithm (ICA)-ANN (ANN optimised with ICA), Zhang
2019; Koopialipoor et al., 2019; Xu et al., 2019; Gao et al., 2020; et al. (2020a) proposed a hybrid method of RVM and PSO; Zeng
Zhang et al., 2020a, b; Li et al., 2021; Zhou et al., 2021). et al. (2021) used six hybrid PSO-ELM techniques; Zhou et al.
Soft computing algorithms, with their ability in nonlinear (2021) used three hybrid SVM models, i.e. grey wolf optimisation
modelling, provide feasible tools for understanding and simulating (GWO)-SVM, whale optimisation algorithm (WOA)-SVM, and moth
diverse complicated problems (Chen et al., 2020; Goh et al., 2020; flame optimisation (MFO)-SVM, and found notable results.
Zhang and Goh, 2013, 2016), including predictions of the perfor- Armaghani et al. (2017) also compared the performance of PSO-
mance of TBMs (Goh et al., 2017, 2018; Xiang et al., 2018). In the ANN and ICA-ANN models with that of the conventional ANN,
recent past, several soft computing algorithms, such as neural and reported that the hybrid intelligent models are superior to the
network (NN), artificial NN (ANN), adaptive neuro-fuzzy inference simple ANN method. On the other hand, Zeng et al. (2021)
system (ANFIS), support vector regression (SVR), support vector concluded that the hybridisation of ELM and PSO results in
machine (SVM), gene expression programming (GEP), relevance higher accuracy than the single ELM model, and Zhou et al. (2021)
vector regression (RVR), relevance vector machine (RVM), deep NN showed that the hybrid SVM model (i.e. MFO-SVM) is more
(DNN), long-short-term memory (LSTM), classification and powerful than standard SVM in addressing TBM’s performance
regression trees (CART), k-nearest neighbour (KNN), and chi- with a high accuracy level. A thorough examination of these studies
squared automatic interaction detection (CHAID) (Grima et al., reveals that most of the authors consider single CSC models and
2000; Benardos and Kaliampakos, 2004; Mobarra et al., 2013; hybrid models in predicting the performance of TBM. However, the
Ghasemi et al., 2014; Mahdevari et al., 2014; Salimi et al., 2016; performance enhancement of the CSC models through ensemble
Armaghani et al., 2018; Koopialipoor et al., 2019; Xu et al., 2019; modelling was not addressed in earlier studies.
Gao et al., 2020; Zhang et al., 2020a; Li et al., 2021), have been used Recently, some researchers have focused on ensemble machine
successfully for predicting the ROP of TBMs. Successful application learning models for predicting the desired outputs in different
of these methods can also be found in the literature. Besides, many engineering disciplines (Basaran et al., 2019; Cai et al., 2020; Wang
other conventional soft computing (CSC) models, such as minimax et al., 2020; Asteris et al., 2021; Kardani et al., 2021b, c; Zhang et al.,
probability machine regression (MPMR), functional network (FN), 2021a, b). It is pertinent to say that ensemble models work on an
Gaussian process regression, and extreme learning machine (ELM), advanced level to augment the performance of “unstable” models
have been used successfully in different engineering disciplines for (Breiman, 1999; Qiu et al., 2014; Chatterjee et al., 2015). It must be
predicting the desired output(s) (Rajasekaran, 2004; Liu et al., 2015; noted that an ensemble model constructed with two or more in-
Jagan et al., 2019; Kumar and Samui, 2019; Samui, 2019; Ahmed dividual soft computing models exhibits better performance
et al., 2020; Mahmoud et al., 2020; Raja and Shukla, 2020, 2021a; compared to a single model (Qiu et al., 2014; Chatterjee et al., 2015;
Kumar et al., 2021a, b). Cai et al., 2020). Hence, taking these points as a reference, this study
For estimating the performance of TBM, several CSC models aims to implement a recently proposed approach, named hybrid
have been used, including ANN/NN (Benardos and Kaliampakos, ensemble technique (Asteris et al., 2021), for estimating the ROP of
2004; Yagiz et al., 2009; Javad and Narges, 2010; Mobarra et al., TBM. To this end, four common CSC techniques, i.e. MPMR, RVM,
A. Bardhan et al. / Journal of Rock Mechanics and Geotechnical Engineering xxx (xxxx) xxx 3
ELM, and FN, are used, analysed, and discussed. Among them, the Based on kernel formulation, the MPMR model is depicted
former two models are categorised as regression-based models, below, which shows the relationship between the independent
while ELM and FN are NN-based models. However, the working variable (x) and response variable (y):
principles of ELM and FN are different. As stated above, these CSC
algorithms have also been successfully utilised in many engineer- X
n
y ¼ f ðxÞ ¼ bi Kðxi ; xÞ þ b (2)
ing disciplines. Nonetheless, the application of MPMR, ELM, and FN
i¼1
in estimating TBM’s performance is relatively scarce.
In the subsequent step, a hybrid ensemble model (HENSM) was where Kðxi ; xÞ represents a kernel function, b and bi are the out-
used for aggregating the outputs of the aforementioned CSC models puts, and n is the total number of observations of the input variable.
via an ANN model. In particular, the ANN was utilised to combine In general, the radial basis function (RBF), i.e. Kðxi ;xÞ ¼ exp½ ðxi ;
the CSC model outputs, while the HENSM was formulated to pre- xÞðxi ; xÞT =ð2s2 Þ, is used, where s is the width of the RBF. To use the
dict the ROP of the TBM. The prediction performance of the HENSM above MPMR formulation for regression, original data with d inputs
and CSC models was investigated with respect to a number of are used to create two classes of points (gi ; hi Þ as follows:
performance indices followed by uncertainty analysis and statisti-
cal testing. The empirical results confirmed the applicability and gi ¼ ðyi þ ε; xi1 ; xi2 ; .:: ; xid Þ; hi ¼ ðyi ε; xi1 ; xi2 ; .:: ; xid Þ
benefits of the introduced HENSM in TBM performance estimation (3)
in a rock environment.
The remainder of this study is organised into the following The minimum probability machine classification boundary be-
sections, including the introduction section presented above. Sec- tween points gi and hi is shown below:
tion 2 presents the theoretical details of the utilised models,
including the approach of HENSM, while Section 3 explains the X
2n
gi K c ðzi ; zÞ þ bc ¼ 0 (4)
details of the collected dataset, descriptive statistics, statistical i¼1
analysis, and performance parameters. This is followed by a
detailed discussion on the performance of the employed models in The above classification boundary between gi and hi corre-
Section 4. Finally, in Section 5, the concluding remarks are sponds to a regression surface, termed as MPMR model. Eq. (4) can
provided. formulate using any binary classification algorithm, and it is not
limited to MPMCA. Precisely, if a binary classifier derived from Eq.
(1) has the above form where c ¼ 1 for the first class and c ¼ 1 for
2. Theoretical background of the employed models
the second class, then a crossing point needs to be found first. For
the crossing point, the classifier separates these classes for a certain
This section discusses the theoretical background of the
input (X ¼ ðx1 ; x2 ; .:: ; xd ÞÞ which is equivalent to finding the
employed models in predicting the ROP of TBM. It begins with
output of the regression model for a given input combination. For
presenting the details of CSC models, i.e. MPMR, RVM, ELM, and FN
detailed methodology, the work of Strohmann and Grudic (2003)
employed. Finally, the details of the ANN and the methodological
can be referred to.
development of the proposed HENSM are presented.
2.2. Relevance vector machine (RVM)
2.1. Minimax probability machine regression (MPMR)
RVM, introduced by Tipping (1999), is a supervised machine
MPMR is a regression framework (Strohmann and Grudic, learning technique that uses Bayesian interpretation to find
2003), which is established based on the minimax probability regression solutions and probabilistic classification. It has the same
machine classification algorithm (MPMCA). A regression model can functional formulation as SVM, but provides probabilistic inter-
be formulated as maximising the minimum probability of predicted pretation. In supervised machine learning, inputs (x1, x2, ., xn)
values where the prediction of the output lies within some bound come allied with their corresponding outputs ðt1 ; t2 ; .::; tn Þ. The
of the true function. The regression formulation closely shadows outputs might be real values for regression and class labels for
the classification formulation (Marshall and Olkin, 1960; Huang classifications. For a given training dataset, machine learns a model
et al., 2006), which can be given as based on input and output values. SVM is also a supervised machine
X n o learning technique that makes predictions based on a function
1
supEðzÞ ¼ zCovðzÞ ¼ Pr aT z b ¼ u2 given by
z 1 þ u2
¼ infaT z bðz zÞT S1 T X
N
z ðz zÞ (1) y ¼ f ðxÞ ¼ wn Kðx ; xn Þ þ w0 (5)
n¼1
where a and b are two constants, z is a random vector, and
supremum (sup) is taken over the distribution having mean z and where wn is the model weight. RVM uses training data for building
covariance matrix Sz . The above hypothesis assumes linear regression model in the form of
boundaries, but its nonlinear version can be obtained by using
Mercer kernels (Strohmann and Grudic, 2003). The expression ti ¼ yðxi Þ þ εi (6)
given in Eq. (1) is used to construct a nonlinear regression model,
which maximises the minimum probability that the future pre- where εi is the noise element of the predicted vector with the mean
dictions will lies within ε to the true regression function of 0 and variance of s2 , which is denoted as Nð0; s2 Þ. In the case of a
(Strohmann and Grudic, 2003). Implementation of MRMR by con- linear model, the prediction function is a linear combination of
structing a nonlinear classifier which divides two sets of points, basis functions ai ðxÞ and depicted below:
obtained by transferring the regression data (between þε and eε)
along the response variable axis. The classification boundary be- X
M
yðxÞ ¼ wi ai ðxÞ (7)
tween the two sets is categorised as a regression surface, and it is
i¼1
termed as MPMR model.
The above equation can be rewritten in the form of y ¼Fw þ ε,

where F is a matrix of N M dimensions. Its ith column is formed
with the values of the basis function ai ðxÞ at all training points. The
noise vector is ε ¼½ε1 ; ε2 ; .::; εN . For a given dataset of indepen-
dent and dependent pairs fxn ; yn gN i¼1 , standard formulation is
normally followed and assumes that pðyjxÞ is the multivariate
Gaussian distribution NðyyðxÞ; s2 Þ. As defined in Eq. (6), the mean
of this distribution is modelled by y(x) for a given x. The likelihood
of the dataset can be given by
N=2
1 0
p t w; s2 ¼ 2ps2 exp jt F wjj 2
(8)
2ps2
where t ¼ ðt1 ; t2 ; .::; tN Þ, w ¼ ðw0 ; w1 ; .::; wN Þ; and F0 is a

design matrix of N (N þ 1) dimensions with F0nm ¼ Kðxn ; xm1 Þ
and Fn1 0 ¼ 1. Maximum likelihood estimation of w and s2 often
results in overfitting. As suggested by Tipping (1999), the imposi-
tion of some prior constraints on w by adding a ‘complexity’ pen-
alty term to the likelihood or error function can overcome the
overfitting. This adjusts the simplification ability of the learning
process. Generally, new parameters (high level) are used to compel
an unambiguous zero-mean Gaussian prior probability distribution
over the weights. Using Bayes’ rule, the posterior distribution of
weights is given by Fig. 1. A typical network of an extreme learning machine.
pt w; s2 pwa

p wt; a; s ¼
2 (9)
p t a ; s 2
oi ðtÞ ¼ mTi hðtÞ (12)
where a is a vector of N þ 1 hyperparameters.
The resulting posterior distribution over the weights is the where mi ˛ Rq ð i˛f1; 2; .; og Þ is the weight vector, and it con-
multivariable Gaussian distribution: nects the hidden neurons to the ith output neuron; and hðtÞ˛ Rq is
the output vector of hidden neurons, which is given by
X T 1
h i
p wt; a; s2 ¼ N s2 F t ; s2 FT F þ A (10)
hðtÞ ¼ f wT1 xðtÞ þ b1 ; f wT2 xðtÞ þ b2 ; .; f wTq xðtÞ þ bq
(13)
A ¼ diagða0 ; a1 ; .::; aN Þ. For uniform hyperpriors, the term
where
pðt a; s2 Þ is required to maximise:
where bk ðk ¼ 1; 2; /; q) is the bias of kth hidden neuron, wk ˛Rp
Z is the weight vector of kth hidden neuron, and f ð ,Þ denotes the

p t a; s2 ¼ p t w; s2 pðwjaÞdw activation function (sigmoidal function). It is worth noting that the
(11) bias (bk ) and weight (wk Þ vectors are produced in a random manner
ð2pÞN=2 1
¼ qffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi exp yT s2 þ FA1 FT 1 y from which the hidden layer output matrix (H) can be formed. The
2
js2 þ FA1 FT j weight matrix is then calculated using the ‘MooreePenrose pseudo
inverse’ method, which is given by
Maximisation of pðt a; s2 Þ is called as the Type II maximum
likelihood method. Hyperparameter estimation is carried out using 1
M ¼ H HT H DT (14)
gradient descent on the objective function. The non-zero weights of
w will be considered as relevant vectors.
where D ¼ ½dð1Þ; dð2Þ; .::; dðnÞ represents a matrix of o n di-
mensions, and its tth column is the real largest vector dðtÞ˛Ro. The
2.3. Extreme learning machine (ELM) class label for the new input parameters can be calculated as
Y ¼ arg maxfOi g ði ¼ 1; 2; .; OÞ (15)

ELM, introduced by Huang et al. (2006), is a single hidden layer
feed-forward NN used for solving regression, clustering, and
where Y is the predicted class label. Detailed working principle of
feature learning problems. During the course of the training and
ELM can be referred to the literature (Zeng et al., 2021).
predicting stages, weights and bias are assigned randomly between
inputs and hidden nodes which remain constant throughout the
operation. On the other hand, weights between the hidden and 2.4. Functional network (FN)
output layers can be learned quickly. In addition, the computational
cost of ELM is on the lower side compared to another back- FN, introduced by Castillo et al. (2000), is an extension of NNs.
propagation algorithm network. A typical structure of an ELM is The main benefit of NNs is to learn from records with the help of
shown in Fig. 1. various learning methods such as parametric and structural
For the construction of a classification model from a set of data learning methods. In NN, the error function is minimised for the
(X ¼ xt ˛Rp ðt ¼ 1; 2; . ; nÞ) having n samples and p input learning process. The main disadvantage is that the solution ob-
parameters, the output of an ELM network with p inputs, q hidden tained from NN cannot be guaranteed as the best one due to the
neurons, and o output neurons can be written in the form of limited ability to develop the theory and uncertainties involved in
the problem. While solving a complicated problem, such limita-

tions can be overcome by using FN. FN is a more comprehensive
version of NNs, and it combines domain knowledge and data. FN
uses structural learning and parametric learning to develop a
model. In structural learning, functional equations are used for
simplification, whereas in parametric learning, neuron functions
are estimated based on the combination of shape functions.
Note that FN is a combination of storing units, layers of the Fig. 3. Flowchart showing the working steps of functional network.
computing unit, and a set of links. Storing unit consists of input
storing units, intermediate layer units, and output units. Neurons of
the computing unit assess the set of input values approaching from
the following layer. Functions that are not arbitrary but can be
determined by the network structure are termed as links. Besides
data, other informational and functional properties such as
invariance, commutativity, and associativity are also considered
during the construction of networks. In FN, weights of the functions
are merged and learned. In some cases, the learning method leads
to a global minimum quite easily. A graphical representation of an
FN is shown in Fig. 2. In addition, the steps of FN working are Fig. 4. Associativity of functional network.
depicted in Fig. 3.
The learning method of FN comprises neural functions obtained
from a set of dependent and independent variables, and the
X
4
learning process is based on minimising the Euclidean norm of the f4 ðx4 Þ ¼ a4i q4i (19)
error function (Rajasekaran, 2004): i¼1
From the input function, the below function can be constructed

1X n
as
E¼ ðO FðiÞÞ2 (16)
2 i¼1 i
b
f 4 ðx4 Þ ¼ f1 ðx1 Þ þ f2 ðx2 Þ þ f3 ðx3 Þ (20)
and the approximate neural function can be organised as
and the error in the jth datum is given by

X
m ej ¼ f1 x1j þ f2 x2j þ f3 x3j f4 x4j (21)
fi ðxÞ ¼ aij qij ðXÞ (17)
j¼1 The above equation can also be rewritten or reproduced in the
form of
where q is the shape function, and it can be associated with
different functions such as algebraic expressions, trigonometric ~g
ej ¼ bj fa (22)
functions, and exponential functions. These associative optimisa-
The sum of squares of the error for all data can be given by
tion functions lead the formulation to a system of linear or
nonlinear equations. For a system with three inputs ðx1 ; x2 ; x3 Þ and X
n
one output ðx4 Þ, the association of the FN can be constructed, as E ¼ ak ¼ aki qki ðxk0 Þ (23)
shown in Fig. 4, the mathematical formulation of which is given by i¼1
where xk0 is the initial value. For the uniqueness of the above so-
X
ms
lution, the following equation must be satisfied:
fs ðxs Þ ¼ asi qsi ðs ¼ 1; 2; .Þ (18)
i¼1
0 1
X
mk X
n
fk ðxk0 Þ ¼ ~ i@
eTj ej ¼ ha bj bj A fa
~ g ¼ ha
~i½Afa
~g (24)
where ms can be of any order; and qsi can be polynomial of any
i¼1 j¼1
degree, trigonometric, trigonometric polynomial, exponential, or
any other mathematical functions, termed as shape functions. For a To achieve more generalised functions, it is required to guar-
polynomial expression, the function can be expressed as antee the individuality of the illustration of the network. Some-
times different neuron functions lead to a same output for a similar
input which leads to an ill-conditioned estimation. To solve these
problems, a generalised method is used for all types of FNs (Castillo
and Gutiérrez, 1998).
2.5. Artificial neural network (ANN)
ANNs, inspired by the biological neural system, consist of many

single units and weighted artificial neurons (Asteris and Mokos,
2020). An ANN is also recognised as a processing element (PE)
since it processes information. Each PE contains one or more
weighted inputs, an output, and a transfer function. Basically, a PE is
Fig. 2. Architecture of functional network. an equation that balances the inputs and output. An ANN is also
known as a connectionist model since the connection weights (1) The standalone machine learning models are trained via
stand for the system’s memory. input data X and output data Y.
An ANN involves three main sets of layers with neurons. The (2) The predicted values are generated.
first and last layers of an ANN are known as the input and output (3) The predicted values of the individual machine learning
layers, respectively. They contain many neurons as the input and models are amalgamated.
output variables. Also, hidden layers exist between these two (4) New input data Xnew are formed, and an ANN is trained using
layers. Signals are transmitted through the input layer. The hidden the real predicted values Y.
layers serve as the computation engine, and predictions are per- (5) An HENSM is constructed.
formed within the output layer. The weights and biases are crucial
parameters of an ANN. The weights represent the interconnections Fig. 5 shows the overall diagram of the proposed HENSM
between a layer’s neurons, while the biases determine the degree method used in this study for predicting the ROP of TBM.
of freedom. Each of the nodes, except for the input nodes, utilises a
nonlinear activation function to produce the output. The output is 3. Data description and computational analysis
then utilised as the input for the next node. This process continues
until a proper solution to a given problem is found. To calculate the 3.1. Descriptive details of the collected dataset
error by comparing the actual result (i.e. the objective of the
problem) to the prediction (i.e. the outcome of the network), back- A sum of 185 datasets was collected from the literature (Javad
propagation is utilised. Then, the error propagates to a layer back at and Narges, 2010) and was used for predicting the ROP of TBM.
a time throughout the ANN structure, changing the weights on the The collected dataset comprised 150 data of Queens water tunnel
basis of their error contributions. project of USA, 8 data of KarajeTehran tunnel project of Iran, and 27
data of Gilgel Gibe II hydroelectric project of Ethiopia. The main
dataset consists of three input parameters, i.e. uniaxial compressive
2.6. Implementation procedure of hybrid ensemble model (HENSM) strength (UCS), rock quality designation (RQD), and distance be-
tween planes of weakness (DPW). These three parameters were
Ensemble learning is defined as a machine learning process that used to predict the ROP (in m/h), i.e. the output variable. Table 1
is used to achieve superior results through the strategical combi- represents descriptive statistics of the collected dataset with the
nation of several learning algorithms (Qiu et al., 2014; Chatterjee minimum, the maximum, the mean, and so on, of each variable. In
et al., 2015), i.e. the principle of ensemble modelling. An addition, Figs. 6 and 7 plot the correlation matrix (based on Pearson
ensemble model merges several standalone/individual models to correlation coefficient) and frequency histograms, respectively. The
deliver better prediction accuracy (Dietterich, 2000). Specifically, frequency histograms are presented in the form of a comparative
ensemble models have three main advantages: (i) the ability to histogram between the input and predicted variables. This diagram
decrease the risk of choosing the worst-performance model by the is useful to compare the input variables against the output. How-
aggregation of multiple candidate models; (ii) efficiency in dealing ever, for a fair comparison, all the parameters were scaled in a pre-
with locally optimal solutions; and (iii) a representational advan- defined range between 0 and 1. From Table 1, it is noted that the
tage (in numerous cases, one model cannot represent a true func- UCS of rocks lies in the range of 30e199.7 MPa, RQD has the min-
tion by a single hypothesis or formulation) (Qiu et al., 2014). It is imum and maximum values of 40.6% and 99.88%, respectively,
worth noting that, for regression and time series forecasting while the DPW locates between 0.05 m and 2 m. The output vari-
problems, different machine learning models that use identical able, ROP, is distributed in the range of 1.27e14.43 m/h.
data produce different prediction results. Thus, all the outputs
created by several machine learning models may be combined, 3.2. Statistical analysis
providing a more robust prediction compared with those by
separate machine learning models. An analysis of the relation be- From the descriptive analysis presented above, it was under-
tween the actual and predicted outputs makes it promising to stood that the present database comprises a wide range of data, and
create a more effective model via different ensemble methods, such hence statistical analysis was performed to assess the linear asso-
as randomness injection, voting, boosting, stacking, and bagging ciation between the input parameters and ROP, the details of which
(Bar et al., 2013; Qiu et al., 2014). are furnished in Fig. 8aec. The ROP values were correlated with the
Nonetheless, the present study uses an approach proposed by UCS, RQD, and DPW and presented in terms of determination co-
Asteria et al. (2021) instead of standalone ensemble techniques efficient (R2) value. As can be seen, the values of R2 scatter in the
mentioned above. The presented HENSM is made up of four indi-
vidual machine learning models (i.e. MPMR, RVM, ELM, and FN)
and an ANN. In particular, the ANN was employed for aggregating Table 1
Descriptive statistics of UCS, RQD, DPW, and ROP.
the outputs of the four individual machine learning models to
formulate the HENSM. The process details are as follows: Parameters UCS (MPa) RQD (%) DPW (m) ROP (m/h)
Minimum 30 40.6 0.05 1.27

1st Quartile 129.2 90.98 0.3 1.85
Mean 143 91.05 0.87 2.33
3rd Quartile 160.3 99.81 1.6 1.43
Maximum 199.7 99.88 2 14.43
Trimmed 143.53 94.51 0.83 2.13
Standard error 2.05 1.13 0.05 0.1
Standard deviation 27.93 15.38 0.67 1.32
Variance 780.32 15.38 0.67 1.32
Skewness 0.4 1.76 0.41 6.18
Kurtosis 4.32 4.84 1.67 49.06
Geometric mean 139.72 89.37 0.55 2.18
Harmonic mean 135.23 87.19 0.29 2.1
Fig. 5. Schematic diagram of the proposed hybrid ensemble model.
3.3. Artificial intelligence-based analysis
In the soft computing field, data normalisation is a pre-

processing task, which is performed to cancel out the multi-
dimensional effects. Therefore, before the development of the
models, the main dataset was normalised in the range of 0e1.
Subsequently, the normalised dataset was partitioned into training
and testing subsets. For this purpose, 70% of the main dataset (i.e.
130 samples) was selected at random for the training subset, and
the left-over dataset, i.e. 30% of the main dataset (i.e. 55 samples),
was used as the testing subset. The entire steps of developing the
predictive models of ROP of TBM can be described as: (i) normal-
isation of the main dataset, (ii) selection of training and testing
subsets, (iii) construction of models using training subset, and (iv)
validation of the developed models using the testing subset.
Consequently, to evaluate the models’ performance, several
widely used statistical indices, i.e. determination coefficient (R2),
performance index (PI), variance account for (VAF), Willmott’s in-
dex of agreement (WI), mean absolute error (MAE), mean bias error
(MBE), root mean square error (RMSE), and weighted mean abso-
lute percentage error (WMAPE), were determined (Kardani et al.,
2020, 2021a, d; Bardhan et al., 2021a, b; Ghani et al., 2021a,b;
Fig. 6. Correlation matrix. Kumar et al., 2021c; Ray et al., 2021). The mathematical expressions
of the above-mentioned indices are given in the following
equations:
range of 0.0944e0.2133, which in turn indicates that the parame-
ters are marginally correlated with ROP. To visualise the nature of
Pn P
the input parameters, the collected dataset is presented in Fig. 8aec i¼1 ðyi ymean Þ2 ni¼1 ðyi b
y i Þ2
through scatter plots of each input parameter. R2 ¼ Pn 2
(25)
i¼1 ðyi ymean Þ
9 9 9
(a) UCS (b) RQD (c) DPW
8 ROP 8 ROP 8 ROP
7 7 7
6 6 6
Density
Density
5
Density
5 5
4 4 4
3 3 3
2 2 2
1 1 1
0 0 0
0.0 0.2 0.4 0.6 0.8 1.0 0.0 0.2 0.4 0.6 0.8 1.0 0.0 0.2 0.4 0.6 0.8 1.0
UCS and ROP RQD and ROP DPW and ROP
Fig. 7. Frequency histograms.
Fig. 8. Liner relationship between the inputs and ROP.
PI ¼ adj:R2 þ 0:01VAF RMSE (26)
varðyi byiÞ
VAF ¼ 1 100% (27)
varðyi Þ
Pn
i¼1 ðyi b
y i Þ2
WI ¼ 1 Pn (28)
b ymean j þ jyi ymean jÞ2
i¼1 ðj y i
1X n
MAE ¼ jb
y yi j (29)
n i¼1 i
Fig. 9. Illustration of RVM weights corresponding to the training dataset.

1X n
MBE ¼ ðb
y yi Þ (30)
n i¼1 i
presented and discussed below. Note that the same training dataset
vffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi was used in all cases. However, before discussing the model’s per-
u n
u1 X formance, the parametric configurations of each model are pre-
RMSE ¼ t ðy b y i Þ2 (31) sented below.
n i¼1 i
In MPMR modelling, two hyper-parameters, i.e. s (width of the
RBF) and ε (noise component of the measurement) play an

Pn yi by i important role, and hence the values of these parameters were
i¼1 yi yi rigorously checked within a predefined range of 0.5e5 for s and
WMAPE ¼ Pn (32) 0.001e1 for ε, respectively. Following the trial-and-error approach,
i¼1 yi
the best performance was obtained when the values of s and ε were
where yi and b y i represent the actual and estimated ith values, set to 1.1 and 0.003, respectively, which are the designed values of s
respectively; n is the number of samples for the dataset under and ε for the developed MPMR model.
consideration; ymean is the mean of the actual values; and adj:R2 is For modelling the RVM, the widely used Gaussian kernel was
the adjusted R2. Note that for an ideal model, the values of these used (Samui et al., 2011) for the same training dataset. The value of
indices should be equal to their ideal values, as given in Table 2. s was selected through trial-and-error runs and the best perfor-
Furthermore, score analysis was conducted to evaluate the mance was obtained at s ¼ 0.4. Therefore, the denominator term
developed models’ overall performance (Zorlu et al., 2008). It may (2s2) of the RBF, i.e. exp½ ðxi ;xÞðxi ; xÞT =ð2s2 Þ, can be calculated as
be noted that score analysis is an easy and effective method for 2 0.42, i.e. 0.32. The details of the weight vector against the
comparing the models’ performances. In this technique, the model training dataset are shown in Fig. 9. The following equation rep-
with the least value for each performance parameter is assigned a resents the developed RVM model for calculating the ROP of TBM:
score of 1, and the model with the best value for the same perfor- " #
X
130
ðx xi Þðx xi ÞT
mance parameter is assigned a score of m (the total number of ROP ¼ wi exp (33)
considered models) for training and testing results separately. In i¼1
0:32
the present work, m ¼ 5, i.e. the considered models are MPMR,
RVM, ELM, FN, and HENSM. The subsequent step involves calcu- where xi is the training dataset of 130 observations, and x is the
lating the total score by adding up their separate scores. The ulti- input for which ROP is to be determined.
mate model score was computed by adding the total scores In contrast, to determine the ELM structure, the number of
belonging to the training and testing phases. hidden neurons varying from 2 to 30 was examined. In this study,
sigmoid activation function was used to select the best possible
ELM model. Through trial-and-error runs, the most appropriate
4. Results and discussion value of hidden neurons was obtained as 12.
The fourth CSC model, i.e. FN, was also constructed using the
4.1. Realisations of conventional soft computing models same training dataset as those used in MPMR, RVM, and ELM
modelling. A trade-off was made in the present study, and FN with
As stated earlier, a sum of 185 datasets was collected and par- degree 3 and polynomial basis function was adopted. The equation
titioned into training and testing subsets, of which the training for the prediction of the ROP of TBM was obtained as follows:
subset was employed to construct the models, while the testing
subset was utilised to validate the developed models. Subsequently, X
n X
m0
different indices were determined to measure the prediction ca- y ¼ aþ aij fi xj (34)
pabilities of the developed models, the details of which are i¼1 j¼1
where m0 is the degree of variable.

Table 2
Ideal values of performance indices.
4.2. Realisation of hybrid ensemble model (HENSM)
Index Ideal value Index Ideal value
R2 1 MAE 0 This sub-section discusses the realisation of the HENSM. Note

PI 2 MBE 0 that a model that achieves better accuracy in the testing phase is
VAF (%) 100 RMSE 0 usually considered to be a robust model and accepted with higher
WI 1 WMAPE 0
conviction. Therefore, one may create an even more robust model
Fig. 10. Utilisation of standalone models for the development of hybrid ensemble model. TRe Training; TS e Testing.
by improving the testing phase performance. With this consider- combined training dataset was utilised as the validation dataset to
ation, the superiority of the ensemble method was leveraged in the stop overfitting.
work to construct an HENSM. This will be more advantageous with
respect to the variational inaccuracies of the utilised models.
4.3. Performance indices and evaluation
It is worth mentioning that in many cases, computational
models produce different results with different accuracies when
A comprehensive assessment of the CSC and HENSM models
there are insufficient samples. Hence, ensemble techniques can
based on multiple performance indices is presented in this sub-
decrease the risk of choosing the less accurate model via the ag-
section, the details of which are listed in Tables 3 and 4 for the
gregation of multiple individual models. The present study at-
training and testing datasets, respectively. Furthermore, the scatter
tempts hybrid ensemble modelling via an HENSM combining four
plots between the actual and predicted outputs are presented in
CSC models that are used to estimate the ROP of TBM. As mentioned
Figs. 11 and 12. As can be seen, overall, all CSC models were able to
in Section 2.6, the ANN was used for constructing the HENSM. This
predict the ROP with significant accuracy that can be evident by
model combines the outputs from all four individual models as
high R2 value (ranging between 0.7214 for FN and 0.911 for ELM)
inputs and the real output, i.e. actual ROP of TBM. In Fig. 10, the
and low RMSE (ranging between 0.0286 for ELM and 0.0505 for FN)
process of implementing the HENSM is presented, from which the
in the training phase. For the testing dataset, the values of R2 were
amalgamation procedure of CSC models can be visualised. It must
obtained in the range of 0.7767 (for MPMR) to 0.8518 (for RVM),
be noted that a trial-and-error approach was followed to finalise
while the values of RMSE were obtained in the range of 0.0453 (for
the structure of ANN in HENSM modelling. In this case, the
RVM) to 0.0532 (for FN). Based on the score analysis, the best
Levenberg-Marquardt back-propagation function was selected as
standalone model is ELM (total score of 30) in the training phase
the training function. The ultimate ANN structure is composed of
and RVM (total score of 30) in the testing phase. Contrarily, the
three input neurons, two hidden neurons, and one output neuron.
constructed HENSM attained the most accurate prediction with the
The activation function used in input to hidden and output layers
highest R2 (0.9126 for training and 0.865 for testing dataset) and
are tan-sigmoid and purelin, respectively. Also, a total of 10% of the
lowest RMSE value (0.0283 for training and 0.0418 for testing
Table 3
Outcomes of the training dataset.
Index Particular R2 PI VAF WI MAE MBE RMSE WMAPE Total score
MPMR Value 0.8956 1.7578 89.5593% 0.972 0.0227 0 0.0309 0.2852

Score 2 2 2 2 2 5 2 2 19
RVM Value 0.9099 1.789 90.9938% 0.9761 0.0205 0.0007 0.0287 0.2575
Score 3 3 3 3 4 2 3 3 24
ELM Value 0.911 1.7913 91.0966% 0.9764 0.0205 0 0.0286 0.2574
Score 4 4 4 4 3 3 4 4 30
FN Value 0.7214 1.3856 72.1372% 0.9139 0.0332 0 0.0505 0.4198
Score 1 1 1 1 1 4 1 1 11
HENSM Value 0.9126 1.7947 91.2556% 0.9766 0.0204 0.001 0.0283 0.2554
Score 5 5 5 5 5 1 5 5 36
Table 4
Outcomes of the testing dataset.
Index R2 PI VAF WI MAE MBE RMSE WMAPE Total score
MPMR Value 0.7767 1.4872 77.5715% 0.9358 0.0344 0.0027 0.0521 0.3873
Score 1 1 2 2 2 4 2 2 16
RVM Value 0.8518 1.6289 83.1133% 0.959 0.03 0.0043 0.0453 0.3346
Score 4 4 4 4 4 2 4 4 30
ELM Value 0.8267 1.5909 82.1114% 0.9525 0.0301 0.0046 0.0467 0.3367
Score 3 3 3 3 3 1 3 3 22
FN Value 0.8039 1.505 76.5798% 0.9164 0.0363 0.0021 0.0532 0.4115
Score 2 2 1 1 1 5 1 1 14
HENSM Value 0.865 1.6715 85.6303% 0.9636 0.0282 0.0043 0.0418 0.3142
Score 5 5 5 5 5 3 5 5 38
15.00 15.00 15.00

MPMR (TR) RVM (TR) ELM (TR)
10.00 10.00 10.00

Predicted
Predicted
Predicted
5.00 5.00 5.00
0.00 0.00 0.00

0.00 5.00 10.00 15.00 0.00 5.00 10.00 15.00 0.00 5.00 10.00 15.00
Actual Actual Actual
(a) (b) (c)
15.00 15.00
FN (TR) HENSM (TR)
10.00 10.00
Predicted
Predicted
5.00 5.00
0.00 0.00
0.00 5.00 10.00 15.00 0.00 5.00 10.00 15.00
Actual Actual
(d) (e)
Fig. 11. Scatter plots between actual and estimated ROP values for the training (TR) dataset.
dataset) in both cases. The outcomes of score analysis also show attained the most desired prediction with the lowest OBJ value, and
that the constructed HENSM outperformed the best performing hence the proposed hybrid model is most accurate from this
CSC model and attained a final score of 36 and 38 in the training viewpoint.
and testing phases, respectively. The results of score analysis are To better demonstrate the values of performance indices, a
presented in Fig. 13 (for training results) and Fig. 14 (for testing recently proposed heat map-shaped graphical assessment, called
results) in the form of stacked bar plots. The comparisons of score accuracy matrix, is tested to visualise the model efficiency (Kardani
analyses presented in Table 5 indicate that RVM and ELM are the et al., 2021a). This matrix displays multiple statistical parameters to
top two standalone models (attained overall scores of 54 and 52, measure the model’s predictive performance for the training and
respectively); however, when the outputs of each model are com- testing datasets. Fig. 15 displays the accuracy matrix for the per-
bined with the ANN, they exhibit better performance than the best formance indices determined in this study. It indicates the accuracy
standalone model in predicting the ROP of TBM. of the performance parameters (in percentage) by comparing them
In addition, the objective function (OBJ) criterion was used to with their corresponding ideal values. For example, the ideal value
assess the predictive performance of all the employed models. The of MAE is 0 and, in the present work, the value of MAE for the
details of this parameter can be found in the literature (Gandomi training subset was determined as 0.0227 for the MPMR model (see
et al., 2013; Samadi et al., 2020; Raja et al., 2021; Raja and Shukla, Table 3). Thus, it can be estimated that the MPMR model attained
2021b). However, the expression presented by Samadi et al. 97.73% ((1e0.0227) 100%) accuracy in terms of MAE. On the other
(2020) was used. It should be noted that the best model has a hand, the values of R2 and PI were obtained as 0.865 and 1.6715 in
minimum OBJ value (ideal value ¼ 0). The values of OBJ for MPMR, the testing phase, respectively, for the HENSM (see Table 4), which
RVM, ELM, FN, and HENSM were calculated as 0.0366, 0.03, 0.0307, shows that HENSM attained 86.5% (0.865/1 100%) and 83.575%
0.0455, and 0.0284, respectively. These results indicate that HENSM (1.6715/2 100%) accuracy in terms of R2 and PI, respectively.
15.00 15.00 15.00

MPMR (TS) RVM (TS) ELM (TS)
10.00 10.00 10.00
Predicted
Predicted
Predicted
5.00 5.00 5.00
0.00 0.00 0.00

0.00 5.00 10.00 15.00 0.00 5.00 10.00 15.00 0.00 5.00 10.00 15.00
Actual Actual Actual
(a) (b) (c)
15.00 15.00
FN (TS) HENSM (TS)
10.00 10.00
Predicted
Predicted
5.00 5.00
0.00 0.00
0.00 5.00 10.00 15.00 0.00 5.00 10.00 15.00
Actual Actual
(d) (e)
Fig. 12. Scatter plots between actual and estimated ROP values for the testing (TS) dataset.
Similar procedure was followed for the other parameters as well. 95% confidence interval. The standard error (SE), lower and upper
However, it may be noted that the parameters such as VAF, which bounds (LB and UB) were calculated as follows:
are determined in percentage terms, should be converted in their
decimal form before implementing the above procedure. The su-
premacy of the developed HENSM based on uncertainty analysis
(UA) and statistical testing is presented in the following sub- SD
SE ¼ pffiffiffiffiffiffiffiffiffiffiffiffiffi; LB ¼ MOE ME; UB ¼ MOE þ ME; WCB
section. N1
¼ UB LB (38)
Note that in UA, WCB is an error range where about 95% of the
4.4. Uncertainty analysis and statistical testing entire data are located. Table 6 provides UA details, including the
MOE, SD, SE, ME, LB, UB, and WCB. These indices help to assess the
This sub-section presents the quantitative evaluation of the efficiency of the models. The smaller the value of WCB, the better
developed models through UA in the prediction of the ROP of TBM. the model certainty, meaning that the model will suffer from less
For this purpose, the testing dataset, which contains 55 real-time error, and it will predict more precise expected output. Based on
observational data points, was used. Thus, it can be useful to logi- the values of WCB, all the five models were ranked. It is seen that
cally compare predictive outputs for evaluating the reliability of the the proposed HENSM attained the lowest WCB value and secured
predictive models (Gholami et al., 2019). To carry out the UA, the the first rank, rendering it the most reliable predictive model. The
absolute error (εi) between observational (yi ) and predicted ( b yi) RVM model scored the second rank, which is the top performing
values, mean of absolute error (MOE), and standard deviation (SD) model among the CSC models, followed by ELM, FN, and MPMR.
of error were determined using the following expressions: However, the MPMR model exhibits the highest WCB value and the
lowest uncertainty. Fig. 16aec provides UA graphical representation
εi ¼ jyi b
yij (35) as a bar chart displaying MOE, WCB, and ME values for a better
comparison.
PN
Furthermore, a one-tailed t-test was executed to estimate the
i¼1 εi
MOE ¼ (36) significant difference of the proposed HENSM’s performance to the
N
CSC models in predicting the ROP of TBM in a rock environment.
sffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi This statistical test was executed on the MAE values with the
PN 2
i¼1 ðεi MOEÞ hypothesised mean difference HMD ¼ 0. At HMD ¼ 0 and confi-
SD ¼ (37)
N1 dence interval of 95% (i.e. a ¼ 0.05), the hypotheses of one-tailed t-
test are H0: MAEHENSM e MAECSC models ¼ 0 and HA: MAEHENSM e
where N is the number of observations (here N ¼ 55). Initially, MOE MAECSC-models < 0, where H0 and HA represent null hypothesis and
and SD were determined for the testing datasets using the above alternate hypothesis, respectively. The outcomes are presented in
equations. Subsequently, the width of confidence bound (WCB) Table 7. Note that the rejection (failed to accept) of H0 (i.e. t-stat < t-
value was determined by calculating the margin of error (ME) at a critical) shows that the proposed HENSM considerably
variable to the nth dependent variable; and n is the number of

dependent variables. In this study, m ¼ 3, n ¼ 1, and k ¼ 185. The
strength of relation between the ROP and the input parameters, i.e.
UCS, RQD, and DPW, is shown in Fig. 17. For actual and employed
models, the strength of relation of each variable is presented in the
figure itself. As can be seen, the UCS is the most influential
parameter on the ROP, followed by RQD and DPW, in call cases. It is
also worth noting that the employed models, especially HENSM
and RVM, almost modelled the actual output in predicting the ROP
of TBM.
4.6. Discussion
From the experimental results presented in the above sub-

Fig. 13. Bar plot of score analysis (training results). sections, it is observed that RVM and ELM are the top two con-
ventional models. However, detailed scrutiny reveals that RVM
attained the most accurate prediction in the testing phase only.
Although overall analysis shows that RVM outperformed other CSC
models with R2 ¼ 0.8518 and RMSE ¼ 0.0453, a lower performance
in the testing phase (R2 ¼ 0.9099 and RMSE ¼ 0.0287) against the
performance of ELM (R2 ¼ 0.911 and RMSE ¼ 0.0286) encourages
the authors to analyse the prediction capability in another way.
Therefore, a hybrid ensemble method was implemented to
augment the CSC models’ performance, especially for the testing
dataset. The performance of the proposed HENSM was then
assessed and compared for predicting the ROP of TBM in a rock
environment. Overall, the proposed HENSM attained the maximum
final score of 74 (36 (training) þ 38 (testing)) by far, followed by
RVM (54), ELM (52), MPMR (35), and FN (25). These results indicate
that RVM and ELM are the top two models among the 4 conven-
tional models (i.e. MPMR, RVM, ELM, and FN) employed in this
Fig. 14. Bar plot of score analysis (testing results).
study. However, the FN is the worst performing model with the
lowest final score of 25.
Analogous to CSC models, the proposed HENSM was developed
Table 5 utilising the outputs of the CSC models in a MATLAB (2015a
Overall score analysis for the developed models. version) environment. The computation costs were recorded as
Phase MPMR RVM ELM FN HENSM 0.311139 s for MPMR, 0.823362 s for RVM, 0.325061 s for ELM,
7.864904 s for FN, and 8.1252 s for HENSM. All the programmes run
Training 19 24 30 11 36
Testing 16 30 22 14 38 in MATLAB with i3-8130U CPU @ 2.20 GHz, 12 GB RAM, which in-
Final score 35 54 52 25 74 dicates that the constructed HENSM attained higher prediction
accuracy with very low computing cost. This is one of the main
advantages of the proposed approach due to the fact that this
outperformed all four CSC models in reducing the MAE value in approach can be implemented quickly. Also, the present technique
both phases. can reduce the risk of picking the least performing model by
combining individual models.
4.5. Sensitivity analysis 5. Concluding remarks
To evaluate the relative influence of the input variables on the Based on the data mining from the literature, 185 data records of
output, sensitivity analysis was performed. Note that the most ROP of TBM were collected, which cover three rock properties, i.e.
widely used method, i.e. the cosine amplitude method, was used in UCS, RQD, and DPW. These parameters were used as the input
this study (Asteris and Mokos, 2020; Kardani et al., 2021d). To parameters to predict the ROP of TBM in a rock environment. The
perform the sensitivity analysis, the strength of relation (Ryn ;m ) of collected dataset was used to rigorously train and validate the
input parameters (UCS, RQD, and DPW) in predicting the ROP of employed models to enable accurate predictions of ROP of TBM.
TBM was determined for the actual data and employed models Four standalone models, i.e. MPMR, RVM, ELM, and FN, and an
using the following expression: HENSM were employed in this study. The accuracies of these
Pk models in predicting the ROP of TBM were analysed and compared
i¼1 xm;i yn;i from different aspects. Subsequently, score analysis was performed
Ryn ;m ¼ rffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi (39)
Pk Pk to select the best-performing model. The UA and statistical testing
2 2
i¼1 xm;i i¼1 yn;i were also performed to estimate the reliability of the proposed
HENSM in predicting the ROP of TBM. The experimental results
where xm;i represents the ith value of mth independent variable; k reveal that the constructed HENSM attained higher performance
and m are the number of total observations and independent var- compared to the standalone models and can be used effectively to
iables, respectively; yn;i denotes the ith value of nth dependent estimate the ROP of TBM in the design phase of engineering
variable; Ryn ;m denotes the strength of relation of mth independent projects.
Fig. 15. Accuracy matrix. TR e Training; TE e Testing.
Table 6 Table 7
Results of uncertainty analysis. Results of one tailed t-test.
Model MOE SD SE ME LB UB WCB Rank Phase Model Sample HMD Degree of freedom t-stat t- H0
number (dof) critical
MPMR 0.0344 0.0391 0.0053 0.0106 0.0239 0.045 0.0211 5
RVM 0.03 0.034 0.0046 0.0092 0.0208 0.0391 0.0184 2 Training MPMR 130 0 129 2.1526 1.6568 Reject
ELM 0.0301 0.0357 0.0048 0.0096 0.0204 0.0397 0.0193 3 RVM 130 0 129 0.1596 1.6568 Reject
FN 0.0363 0.0388 0.0052 0.0105 0.0258 0.0468 0.021 4 ELM 130 0 129 0.2053 1.6568 Reject
HENSM 0.0282 0.0309 0.0042 0.0084 0.0198 0.0365 0.0167 1 FN 130 0 129 4.3162 1.6568 Reject
Testing MPMR 55 0 54 2.5739 1.6736 Reject
RVM 55 0 54 1.3706 1.6736 Reject
ELM 55 0 54 1.6799 1.6736 Reject
To sum up, a hybrid ensemble approach is successfully applied FN 55 0 54 1.4713 1.6736 Reject
in this study to predict the ROP of TBM in a rock environment. It
appears to be an accurate yet computationally efficient method due
to the following reasons: (i) easy implementation procedure; (ii) produced greater performance compared to CSC models, and (v)
higher prediction accuracy; (iii) very low computational cost; (iv) being representational. Experimental results exhibit that the
Fig. 16. Bar plots of UA showing: (a) MOE, (b) WCB, and (c) ME values.
Fig. 17. Bar plots of sensitivity analysis for the employed models.
HENSM outperformed other models at all levels (in terms of per- artificial neural network based on particle swarm optimization. Arab. J. Geosci.
7, 5383e5396.
formance indices, score analysis, UA, and statistical testing), which
Armaghani, D.J., Mohamad, E.T., Narayanasamy, M.S., Narita, N., Yagiz, S., 2017.
in turn indicates that the proposed model has high generalisation Development of hybrid intelligent models for predicting TBM penetration rate
capability in handling overfitting related issues of CSC techniques. in hard rock condition. Tunn. Undergr. Space Technol. 63, 29e43.
Despite these advantages, the proposed hybrid ensemble technique Asteris, P.G., Mokos, V.G., 2020. Concrete compressive strength using artificial
neural networks. Neural Comput. Appl. 32, 11807e11826.
can be improved in the future as follows: (i) incorporation of large Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P., Pilakoutas, K., 2021. Cement and
datasets to predict the desired output(s) more accurately; (ii) a concrete research predicting concrete compressive strength using hybrid
detailed assessment of results of the testing dataset through cross- ensembling of surrogate machine learning models. Cement Concr. Res. 145,
106449.
validation of different conventional machine learning models; (iii) Bar, A., Rokach, L., Shani, G., Shapira, B., Schclar, A., 2013. Improving Simple
adding expert endorsed data to cover much broader diversities; (iv) Collaborative Filtering Models Using Ensemble Methods. In: Zhou, Z.H., Roli, F.,
extending the application of the proposed approach in different Kittler, J. (Eds.), Multiple Classifier Systems: International Workshop on Mul-
tiple Classifier Systems (MCS 2013), vol. 7872. Springer, Berlin, Heidelberg,
fields; and (v) amalgamation of meta-heuristic optimisation algo- Germany. https://doi.org/10.1007/978-3-642-38067-9_1.
rithms and in-depth assessment of the proposed model over the Bardhan, A., Gokceoglu, C., Burman, A., Samui, P., Asteris, P.G., 2021a. Efficient
hybrid ANN and meta-heuristics models. Besides, more input pa- computational techniques for predicting the California bearing ratio of soil in
soaked conditions. Eng. Geol. 291, 106239.
rameters should be considered to predict the ROP of TBM more Bardhan, A., Samui, P., Ghosh, K., Gandomi, A.H., Bhattacharyya, S., 2021b. ELM-
accurately, particularly in a rock environment. However, this study based adaptive neuro swarm intelligence techniques for predicting the Cali-
presents the application of hybrid ensemble techniques for pre- fornia bearing ratio of soils in soaked conditions. Appl. Soft Comput. 110,
107595.
dicting the ROP of TBM in a rock environment for the first time.
Basaran, K., Özçift, A., Kılınç, D., 2019. A new approach for prediction of solar ra-
diation with using ensemble learning algorithm. Arabian J. Sci. Eng. 44, 7159e
7171.
Author’s contributions
Benardos, A.G., Kaliampakos, D.C., 2004. Modelling TBM performance with artificial
neural networks. Tunn. Undergr. Space Technol. 19 (6), 597e605.
A. Bardhan: Main author, conceptualisation, development of AI Breiman, L., 1999. Prediction games and arcing algorithms. Neural Comput. 11 (6),
models, statistical analysis, detailing, overall analysis, and manu- 1493e1517.
Bui, D.T., Nhu, V.H., Hoang, N.D., 2018. Prediction of soil compression coefficient for
script finalisation; N. Kardani: Methodological development of AI urban housing project using novel integration machine learning approach of
models, detailing, review and editing; A. GuhaRay: Introduction swarm intelligence and multi-layer perceptron neural network. Adv. Eng. Inf.
and literature review; A. Burman: Editing; P. Samui: Overall re- 38, 593e604.
Cai, R., Han, T., Liao, W., Huang, J., Li, D., Kumar, A., Ma, H., 2020. Prediction of
view; Y. Zhang: Overall review and editing. surface chloride concentration of marine concrete using ensemble machine
learning. Cement Concr. Res. 136, 106164.
Cassinelli, F., Cina, S., Innaurato, N., Mancini, R., Sampaolo, A., 1982. Power Con-
Declaration of competing interest sumption and Metal Wear in Tunnel-Boring Machines: Analysis of Tunnel-
Boring Operation in Hard Rock. In: Tunnelling ’82. Institution of Mining and
The authors declare that they have no known competing Metallurgy, London, UK, pp. 73e81.
Castillo, E., Cobo, A., Gutiérrez, J.M., Pruneda, E., 2000. Functional networks: a new
financial interests or personal relationships that could have network-based methodology. Comput. Aided Civ. Infrastruct. Eng. 15 (2), 90e
appeared to influence the work reported in this paper. 106.
Castillo, E., Gutiérrez, J.M., 1998. Nonlinear time series modeling and prediction
using functional networks. Extracting information masked by chaos. Phys. Lett.
References 244 (1e3), 71e84.
Chatterjee, S., Dash, A., Bandopadhyay, S., 2015. Ensemble support vector machine
Ahmed, A., Elkatatny, S., Ali, A., Abdulraheem, A., 2020. Prediction of Lost Circula- algorithm for reliability estimation of a mining machine. Qual. Reliab. Eng. Int.
tion Zones Using Artificial Neural Network and Functional Network. In: Abu 31 (8), 1503e1516.
Dhabi International Petroleum Exhibition & Conference. UAE, Abu Dhabi. Chen, L., Zhang, W., Gao, X., Wang, L., Li, Z., Böhlke, T., Perego, U., 2020. Design
https://doi.org/10.2118/203268-MS. charts for reliability assessment of rock bedding slopes stability against bi-
Alavi, A.H., Gandomi, A.H., 2011. A robust data mining approach for formulation of planar sliding: SRLEM and BPNN approaches. Georisk. https://doi.org/10.1080/
geotechnical engineering systems. Eng. Comput. Int. J. Comput.-Aided Eng. 28, 17499518.2020.1815215.
242e274. Dietterich, T.G., 2000. Ensemble Methods in Machine Learning. In: Zhou, Z.H.,
Armaghani, D.J., Faradonbeh, R.S., Momeni, E., Fahimifar, A., Tahir, M.M., 2018. Roli, F., Kittler, J. (Eds.), Multiple Classifier Systems: International Workshop on
Performance prediction of tunnel boring machine through developing a gene Multiple Classifier Systems (MCS 2013), vol. 7872, pp. 1e15. Springer, Berlin,
expression programming equation. Eng. Comput. 34, 129e141. Heidelberg, Germany.
Armaghani, D.J., Hajihassani, M., Mohamad, E.T., Marto, A., Noorani, S.A., 2014. Farmer, I.W., Glossop, N.H., 1980. Mechanics of disc cutter penetration. Tunn. Tunn.
Blasting-induced flyrock and ground vibration prediction through an expert 12 (6), 22e25.
Fattahi, H., 2019. Tunnel boring machine penetration rate. Int. J. Optim. Civil Eng. 9 Martins, F.F., Miranda, T.F.S., 2013. Prediction of Hard Rock TBM Penetration Rate
(2), 343e353. Based on Data Mining Techniques. In: Proceedings of the 18th International
Gandomi, A.H., Yun, G.J., Alavi, A.H., 2013. An evolutionary approach for modeling of Conference on Soil Mechanics and Geotechnical Engineering. Presses des Ponts,
shear strength of RC deep beams. Mater. Struct. 46, 2109e2119. Paris, France, pp. 1751e1754.
Gao, B., Wang, R., Lin, C., Guo, X., Liu, B., Zhang, W., 2020. TBM penetration rate Mobarra, Y., Hajian, A., Rahgozar, M., 2013. Application of Artificial Neural Networks
prediction based on the long short-term memory neural network. Undergr. to the Prediction of TBM Penetration Rate in TBM-Driven Golab Water Transfer
Space. https://doi.org/10.1016/j.undsp.2020.01.003 (in press). Tunnel. In: International Conference on Civil Engineering Architecture & Urban
Ghani, S., Kumari, S., 2021. Liquefaction study of fine-grained soil using computa- Sustainable Development. Tabriz, Iran.
tional model. Innov. Infrastruct. Solut. 6, 58. Mohammadzadeh, S.D., Bolouri Bazaz, J., Alavi, A.H., 2014. An evolutionary
Ghani, S., Kumari, S., Bardhan, A., 2021a. A novel liquefaction study for fine-grained computational approach for formulation of compression index of fine-grained
soil using PCA-based hybrid soft computing models. S adhan
a 46, 113. soils. Eng. Appl. Artif. Intell. 33, 58e68.
Ghani, S., Kumari, S., Choudhary, A.K., Jha, J.N., 2021b. Experimental and compu- Qiu, X., Zhang, L., Ren, Y., Suganthan, P.N., Amaratunga, G., 2014. Ensemble Deep
tational response of strip footing resting on prestressed geotextile-reinforced Learning for Regression and Time Series Forecasting. In: 2014 IEEE Symposium
industrial waste. Innov. Infrastruct. Solut. 6, 98. on Computational Intelligence in Ensemble Learning (CIEL). IEEE, New York,
Ghasemi, E., Yagiz, S., Ataei, M., 2014. Predicting penetration rate of hard rock USA. https://doi.org/10.1109/CIEL.2014.7015739.
tunnel boring machine using fuzzy logic. Bull. Eng. Geol. Environ. 73, 23e35. Raja, M.N.A., Shukla, S.K., 2021a. Multivariate adaptive regression splines model for
Gholami, A., Bonakdari, H., Samui, P., Mohammadian, M., Gharabaghi, B., 2019. reinforced soil foundations. Geosynth. Int. 28 (4), 368e390.
Predicting stable alluvial channel profiles using emotional artificial neural Raja, M.N.A., Shukla, S.K., 2021b. Predicting the settlement of geosynthetic-
networks. Appl. Soft Comput. 78, 420e437. reinforced soil foundations using evolutionary artificial intelligence technique.
Goh, A.T.C., Zhang, R.H., Wang, W., Wang, L., Liu, H.L., Zhang, W.G., 2020. Numerical Geotext. Geomembranes 49 (5), 1280e1293.
study of the effects of groundwater drawdown on ground settlement for Raja, M.N.A., Shukla, S.K., 2020. An extreme learning machine model for
excavation in residual soils. Acta Geotech 15, 1259e1272. geosynthetic-reinforced sandy soil foundations. Proc. Inst. Civil Eng. e Geotech.
Goh, A.T.C., Zhang, W., Zhang, Y., Xiao, Y., Xiang, Y., 2018. Determination of earth Eng. https://doi.org/10.1680/jgeen.19.00297.
pressure balance tunnel-related maximum surface settlement: a multivariate Raja, M.N.A., Shukla, S.K., Khan, M.U.A., 2021. An intelligent approach for predicting
adaptive regression splines approach. Bull. Eng. Geol. Environ. 77, 489e500. the strength of geosynthetic-reinforced subgrade soil. Int. J. Pavement Eng.
Goh, A.T.C., Zhang, Y., Zhang, R., Zhang, W., Xiao, Y., 2017. Evaluating stability of https://doi.org/10.1080/10298436.2021.1904237.
underground entry-type excavations using multivariate adaptive regression Rajasekaran, S., 2004. Functional networks in structural engineering. J. Comput. Civ.
splines and logistic regression. Tunn. Undergr. Space Technol. 70, 148e154. Eng. 18 (2), 172e181.
Graham, P.C., 1976. Rock Exploration for Machine Manufacturers. In: Exploration for Ray, R., Kumar, D., Samui, P., Roy, L.B., Goh, A.T.C., Zhang, W., 2021. Application of
Rock Engineering: Proceedings of the Symposium on Exploration for Rock soft computing techniques for shallow foundation reliability in geotechnical
Engineering, vol. 1. A. A. Balkema, Cape Town, South Africa, pp. 173e180. engineering. Geosci. Front. 12 (1), 375e383.
Grima, M.A., Bruines, P.A., Verhoef, P.N.W., 2000. Modeling tunnel boring machine Roy, B., Singh, M.P., 2020. An empirical-based rainfall-runoff modelling using
performance by neuro-fuzzy methods. Tunn. Undergr. Space Technol. 15 (3), optimization technique. Int. J. River Basin Manag. 18 (1), 49e67.
259e269. Salimi, A., Rostami, J., Moormann, C., Delisio, A., 2016. Application of non-linear
Huang, G.B., Zhu, Q.Y., Siew, C.K., 2006. Extreme learning machine: theory and regression analysis and artificial intelligence algorithms for performance pre-
applications. Neurocomputing 70 (1e3), 489e501. diction of hard rock TBMs. Tunn. Undergr. Space Technol. 58, 236e246.
Jagan, J., Samui, P., Kim, D., 2019. Reliability analysis of simply supported beam Samadi, M., Sarkardeh, H., Jabbari, E., 2020. Explicit data-driven models for pre-
using GRNN, ELM and GPR. Struct. Eng. Mech. 71 (6), 739e749. diction of pressure fluctuations occur during turbulent flows on sloping chan-
Javad, G., Narges, T., 2010. Application of artificial neural networks to the prediction nels. Stoch. Environ. Res. Risk Assess. 34, 691e707.
of tunnel boring machine penetration rate. Min. Sci. Technol. 20 (5), 727e733. Samui, P., 2019. Determination of friction capacity of driven pile in clay using
Kardani, N., Bardhan, A., Kim, D., Samui, P., Zhou, A., 2021a. Modelling the energy Gaussian process regression (GPR), and minimax probability machine regres-
performance of residential buildings using advanced computational frame- sion (MPMR). Geotech. Geol. Eng. 37, 4643e4647.
works based on RVM, GMDH, ANFIS-BBO and ANFIS-IPSO. J. Build. Eng. 35, Samui, P., Lansivaara, T., Kim, D., 2011. Utilization relevance vector machine for
102105. slope reliability analysis. Appl. Soft Comput. 11 (5), 4036e4040.
Kardani, N., Bardhan, A., Samui, P., Nazem, M., Zhou, A., Armaghani, D.J., 2021d. Shahrour, I., Zhang, W., 2021. Use of soft computing techniques for tunneling
A novel technique based on the improved firefly algorithm coupled with optimization of tunnel boring machines. Undergr. Space 6 (3), 233e239.
extreme learning machine (ELM-IFF) for predicting the thermal conductivity of Strohmann, T., Grudic, G.Z., 2003. A Formulation for Minimax Probability Machine
soil. Eng. Comput. https://doi.org/10.1007/s00366-021-01329-3. Regression. In: Dietterich, T.G., Becker, S., Ghahramani, Z. (Eds.), Advances in
Kardani, N., Zhou, A., Nazem, M., Lin, X., 2021b. Modelling of municipal solid waste Neural Information Processing Systems 14: Proceedings of the 2001 Conference.
gasification using an optimised ensemble soft computing model. Fuel 289, MIT Press, Cambridge, USA.
119903. Tipping, M.E., 1999. The Relevance Vector Machine. In: Solla, S.A., Leen, T.K.,
Kardani, N., Zhou, A., Nazem, M., Shen, S.L., 2021c. Improved prediction of slope Müller, K. (Eds.), NIPS’99: Proceedings of the 12th International Conference on
stability using a hybrid stacking ensemble method based on finite element Neural Information Processing Systems. MIT Press, Cambridge, USA, pp. 652e
analysis and field data. J. Rock Mech. Geotech. Eng. 13 (1), 188e201. 658.
Kardani, N., Zhou, A., Nazem, M., Shen, S.L., 2020. Estimation of bearing capacity of Wang, L., Wu, C., Tang, L., Zhang, W., Lacasse, S., Liu, H., Gao, L., 2020. Efficient
piles in cohesionless soil using optimised machine learning approaches. Geo- reliability analysis of earth dam slope stability using extreme gradient boosting
tech. Geol. Eng. 38, 2271e2291. method. Acta Geotech 15, 3135e3150.
Koopialipoor, M., Tootoonchi, H., Armaghani, D.J., Mohamad, E.T., Hedayat, A., 2019. Xiang, Y., Liu, H., Zhang, W., Chu, J., Zhou, D., Xiao, Y., 2018. Application of trans-
Application of deep neural networks in predicting the penetration rate of parent soil model test and DEM simulation in study of tunnel failure mecha-
tunnel boring machines. Bull. Eng. Geol. Environ. 78, 6347e6360. nism. Tunn. Undergr. Space Technol. 74, 178e184.
Kumar, M., Bardhan, A., Samui, P., Hu, J.W., Kaloop, R.M., 2021c. Reliability analysis Xu, H., Zhou, J., Asteris, P.G., Armaghani, D.J., Tahir, M.M., 2019. Supervised machine
of pile foundation using soft computing techniques: a comparative study. learning techniques to the prediction of tunnel boring machine penetration
Processes 9 (3), 486. rate. Appl. Sci. 9 (18), 3715.
Kumar, M., Samui, P., 2019. Reliability analysis of pile foundation using ELM and Yagiz, S., Gokceoglu, C., Sezer, E., Iplikci, S., 2009. Application of two non-linear
MARS. Geotech. Geol. Eng. 37, 3447e3457. prediction tools to the estimation of tunnel boring machine performance.
Kumar, R., Samui, P., Kumari, S., Dalkilic, Y.H., 2021a. Reliability analysis of circular Eng. Appl. Artif. Intell. 22 (4e5), 808e814.
footing by using GP and MPMR. Int. J. Appl. Metaheuristic Comput. (IJAMC) 12, Yagiz, S., Karahan, H., 2011. Prediction of hard rock TBM penetration rate using
1e19. particle swarm optimization. Int. J. Rock Mech. Min. Sci. 48 (3), 427e433.
Kumar, R., Samui, P., Kumari, S., Roy, S.S., 2021b. Determination of reliability index of Zeng, J., Roy, B., Kumar, D., Mohammed, A.S., Armaghani, D.J., Zhou, J.,
cantilever retaining wall by RVM, MPMR and MARS. Int. J. Adv. Intell. Paradigms Mohamad, E.T., 2021. Proposing several hybrid PSO-extreme learning machine
18 (3), 316e336. techniques to predict TBM performance. Eng. Comput. https://doi.org/10.1007/
Li, J., Li, P., Guo, D., Li, X., Chen, Z., 2021. Advanced prediction of tunnel boring s00366-020-01225-2.
machine performance based on big data. Geosci. Front. 12 (1), 331e338. Zhang, R., Wu, C., Goh, A.T.C., Böhlke, T., Zhang, W., 2021a. Estimation of diaphragm
Liu, Z., Shao, J., Xu, W., Wu, Q., 2015. Indirect estimation of unconfined compressive wall deflections for deep braced excavation in anisotropic clays using ensemble
strength of carbonate rocks using extreme learning machine. Acta Geotech 10, learning. Geosci. Front. 12 (1), 365e373.
651e663. Zhang, W., Goh, A.T.C., 2016. Multivariate adaptive regression splines and neural
Mahdevari, S., Shahriar, K., Yagiz, S., Shirazi, M.A., 2014. A support vector regression network models for prediction of pile drivability. Geosci. Front. 7 (1), 45e52.
model for predicting tunnel boring machine penetration rates. Int. J. Rock Mech. Zhang, W., Li, Y., Wu, C., Li, H., Goh, A.T.C., Liu, H., 2020b. Prediction of lining
Min. Sci. 72, 214e229. response for twin tunnels constructed in anisotropic clay using machine
Mahmoud, A.A., Elkatatny, S., Ali, A., Abdulraheem, A., Abouelresh, M., 2020. Esti- learning techniques. Undergr. Space. https://doi.org/10.1016/j.undsp.2020.02.
mation of the total organic carbon using functional neural networks and sup- 007.
port vector machine. In: International Petroleum Technology Conference, Zhang, W., Wu, C., Zhong, H., Li, Y., Wang, L., 2021b. Prediction of undrained shear
Dhahran, Kingdom of Saudi Arabia. https://doi.org/10.2523/IPTC-19659-MS. strength using extreme gradient boosting and random forest based on Bayesian
Marshall, A.W., Olkin, I., 1960. Multivariate Chebyshev inequalities. Ann. Math. Stat. optimization. Geosci. Front. 12 (1), 469e477.
31 (4), 1001e1014.
Zhang, W.G., Goh, A.T.C., 2013. Multivariate adaptive regression splines for analysis Zhou, J., Qiu, Y., Zhu, S., Armaghani, D.J., Li, C., Nguyen, H., Yagiz, S., 2021. Optimi-
of geotechnical engineering systems. Comput. Geotech. 48, 82e95. zation of support vector machine through the use of metaheuristic algorithms
Zhang, Y., Wei, M., Su, G., Li, Y., Zeng, J., Deng, X., 2020a. A novel intelligent method in forecasting TBM advance rate. Eng. Appl. Artif. Intell. 97, 104015.
for predicting the penetration rate of the tunnel boring machine in rocks. Math. Zorlu, K., Gokceoglu, C., Ocakoglu, F., Nefeslioglu, H.A., Acikalin, S., 2008. Prediction
Probl Eng. 2020, 3268694. of uniaxial compressive strength of sandstones using petrography-based
models. Eng. Geol. 96 (3e4), 141e158.

Abidhan - JRMGE

Uploaded by

Copyright:

Available Formats

Abidhan - JRMGE

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Abidhan - JRMGE

Uploaded by

Copyright:

Available Formats

Journal of Rock Mechanics and Geotechnical Engineering xxx (xxxx) xxx

Contents lists available at ScienceDirect

Journal of Rock Mechanics and

Hybrid ensemble soft computing approach for predicting penetration rate

1. Introduction method is a well-developed technology, professionals are imple-

The above equation can be rewritten in the form of y ¼Fw þ ε,

where t ¼ ðt1 ; t2 ; .::; tN Þ, w ¼ ðw0 ; w1 ; .::; wN Þ; and F0 is a

pt w; s2  pwa

Y ¼ arg maxfOi g ði ¼ 1; 2; .; OÞ (15)

the problem. While solving a complicated problem, such limita-

From the input function, the below function can be constructed

2.5. Artiﬁcial neural network (ANN)

ANNs, inspired by the biological neural system, consist of many

Minimum 30 40.6 0.05 1.27

3.3. Artiﬁcial intelligence-based analysis

In the soft computing ﬁeld, data normalisation is a pre-

Fig. 7. Frequency histograms.

Fig. 8. Liner relationship between the inputs and ROP.

PI ¼ adj:R2 þ 0:01VAF RMSE (26)

Fig. 9. Illustration of RVM weights corresponding to the training dataset.

where m0 is the degree of variable.

R2 1 MAE 0 This sub-section discusses the realisation of the HENSM. Note

Index Particular R2 PI VAF WI MAE MBE RMSE WMAPE Total score

MPMR Value 0.8956 1.7578 89.5593% 0.972 0.0227 0 0.0309 0.2852

Index R2 PI VAF WI MAE MBE RMSE WMAPE Total score

15.00 15.00 15.00

10.00 10.00 10.00

5.00 5.00 5.00

0.00 0.00 0.00

15.00 15.00 15.00

10.00 10.00 10.00

5.00 5.00 5.00

0.00 0.00 0.00

variable to the nth dependent variable; and n is the number of

From the experimental results presented in the above sub-

4.5. Sensitivity analysis 5. Concluding remarks

Fig. 15. Accuracy matrix. TR e Training; TE e Testing.

You might also like

pt w; s2 pwa