Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63

Journal of Mechatronics, Electrical Power,

and Vehicular Technology
e-ISSN: 2088-6985
p-ISSN: 2087-3379
www.mevjournal.com

Smart guided missile using accelerometer and gyroscope

based on backpropagation neural network method
for optimal control output feedback
Kamil Faqih a, Sujito b, *, Siti Sendari a, Faiz Syaikhoni Aziz a
a
Electrical Engineering Postgraduate, Electrical Engineering Department, Universitas Negeri Malang
Jl. Semarang No. 5 Sumbersari, Lowokwaru, Malang, East Java, 65145, Indonesia
b
Intelligent Power and Advance Energy System, Electrical Engineering Department, Universitas Negeri Malang
Jl. Semarang No. 5 Sumbersari, Lowokwaru, Malang, East Java, 65145, Indonesia

Received 25 July 2020; Accepted 12 October 2020; Published online 22 December 2020

Abstract
As a maritime country with a large area, besides the need to defend itself with the military, it also needs to protect itself
with aerospace technology that can be controlled automatically. This research aims to develop an air defense system that can
control guided missiles automatically with high accuracy. The right method can provide a high level of accuracy in controlling
missiles to the targeted object. With the backpropagation neural network method for optimal control output feedback, it can
process information data from the radar to control missile’s movement with a high degree of accuracy. The controller uses
optimal control output feedback, which is equipped with a lock system and utilizes an accelerometer that can detect the slope
of the missile and a gyroscope that can detect the slope between the target direction of the missile to follow the target, control
the position, and direction of the missile. The target speed of movement can be easily identified and followed by the missile
through the lock system. Sampling data comes from signals generated by radars located in defense areas and from missiles.
Each part’s data processing speed is calculated using a fast algorithm that is reliable and has a level of accuracy and fast
processing. Data processing impacts on the accuracy of missile movements on any change in the position and motion of targets
and target speed. Improved maneuvering accuracy in the first training system can detect 1000 files with a load of 273, while in
the last training, the system can detect 1000 files without a load period. So the missile can be guided to hit the target without
obstacles when maneuvering.
©2020 Research Centre for Electrical Power and Mechatronics - Indonesian Institute of Sciences. This is an open access article
under the CC BY-NC-SA license (https://creativecommons.org/licenses/by-nc-sa/4.0/).
Keywords: smart missile; backpropagation; neural network; optimal control; output feedback; lock system.

I. Introduction the development of technology in air attack systems.

The air defense, which has the most potential in
Air attacks become a severe problem in the counteracting airstrikes is missiles with a high level
military world. Air attacks can come in the form of of maneuvering accuracy accompanied by an auto-
cruise rockets, short-range rockets, warplanes, pilot system that can guide missiles to hit targets in
drones, and others. The observatory results by the air. Eloy Garcia et al. describe the effectiveness of
Anthony D'Amato in his research entitled air defense, with the theme of the cooperative
retrospective measures of Israeli air attack against missile guide to active defense of air vehicles [2].
the Osiraq reactor [1] which explains that Israeli About active countermeasures against missile
airstrikes are considered understandable and attacks that lead to the aircraft as a target, with the
legitimate defenses. So that in warfare, airstrikes can aim of airstrikes can be anticipated to the maximum
be categorized as a method of self-defense that can and can avoid casualties and material damage.
be allowed even if it has an enermous impact and a One of the most needed air defense systems is a
large number of victims. Technological advances in missile that can be launched and controlled
the field of air defense must be developed along with automatically. Missile targeting system by knowing
the target location of the guidance system such as
inertial navigation system (INS), and terrain contour
* Corresponding Author. Tel: +62-851-32014085 matching (TERCOM) or global positioning system
E-mail address: sujito.ft@um.ac.id

doi: https://dx.doi.org/10.14203/j.mev.2020.v11.55-63
2088-6985 / 2087-3379 ©2020 Research Centre for Electrical Power and Mechatronics - Indonesian Institute of Sciences (RCEPM LIPI).
This is an open access article under the CC BY-NC-SA license (https://creativecommons.org/licenses/by-nc-sa/4.0/).
MEV is Sinta 2 Journal (https://sinta.ristekbrin.go.id/journals/detail?id=814) accredited by Ministry of Research & Technology, Republic Indonesia.
56 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63

(GPS). The use of the INS method mathematically TERCOM, so Missile maneuvers are less accurate in
developed by Castro Toscano M, J, et al., the theme is chasing target because missiles have difficulty
methodological use of inertial navigation systems for detecting targets when missiles and targets are at a
the task of strapdown navigation [3], which presents certain height. Automatic control by utilizing sensors
mathematical descriptions for inertial navigation has been developed by Faqih. K et al. with the theme
systems and integration of device implementations. of smart grid photovoltaic system pilot scale using
The virtual sensor can detect the weight of changes sunlight intensity and state of charge (SoC) battery
in the object (target), calculate variables such as based on Mamdani fuzzy logic control [12], about
speed, position, and attitude on the mobile body of control systems that utilize sensors for automatic
the navigation system. So this system can guide the control performance on power sources.
missile by knowing the missile position and target Significant progress has been achieved in the
position, then calculate the distance and position of design of optimal control output feedback using the
both. As for the TERCOM radar (on missile bodies) RL algorithm by Modares et al [13]. Optimal control
use a height gauge algorithm. Research on the is applied to develop the control system. Meanwhile,
TERCOM radar was developed by Zhang Hua and Hu frequency domain analysis in classical control theory
Xiulin with the theme of a height gauge algorithm is also used to verify system frequency performance,
applied to the TERCOM radar altimeter [4] which including crossover frequencies, phase margins, and
serves to measure the distance of the object. So that profit margins, bringing restrictions on performance
it can provide feedback on missile maneuver values. The controller obtained is the optimal output
performance. One method of locking the missile feedback controller for a simplified model with
system in TERCOM is using infrared. As developed by certain durability. Optimal control theory and
Ab-Rahman and Mazen R., the locking system using frequency domain analysis are combined to get fast
the infrared method utilizes a detector that can tracking performance, small error conditions, and
detect high temperatures at the target to respond to certain durability [14]. Optimal control for missile
missile defenses [5]. Missile design with an infrared guidance systems has been developed by Jingliang
system was used in France during World War I [6]. Sun et al with the theme "robust optimal control for
Missile's responsibility for targets has been missile-target guidance systems via adaptive
developed by Kerem G et al. with the theme dynamic programming", focusing on the
response surface-based performance analysis of an effectiveness of a strong optimal control method for
air-defense missile system which aims to reduce the intercepting maneuvers with feedback using the
computational burden in each detection process adaptive dynamic programming (ADP)
when missiles are maneuvered [7]. technique [15].
The missile test launch system has been To reduce the error rate in determining the
developed by Baoquan Li et al. about the meeting point between missiles and targets, the
measurement system and automatic testing of smart missile system utilizes the Kalman filter in
several surface-to-air autopilot missiles, which focus estimating state variables from a linear discrete
on the use of computer control and multimedia dynamic system that minimizes the estimated error
technology, to increase the speed and accuracy of covariance [16]. Another estimate is the extension of
measurement and testing to the maximum and the Kalman filter called the ensemble Kalman filter
reduce the training work time [8]. Research that (EnKF). In the EnKF method, the algorithm is
discusses defense missile architecture has been executed by producing many specific ensembles to
discussed by Ender. T et al. with the theme of calculate the average and error covariance of state
system-of-systems analysis the effectiveness of variables [17]. In using the EnKF method, some
ballistic missile defense architecture through schemes can be implemented in the EnKF method,
substitute modeling and simulation [9], using which is the square root scheme that can be
modeling and simulation that supports architecture- implemented in EnKF. This scheme can affect the
level analysis on defense missiles including the estimation results, both in terms of accuracy and
sensitivity of operational-level metrics to the computational time [18], so it can be applied to
formation (overview) tracking integration and estimate the missile position and simulated with
making the right decisions. The launching path for Matlab software.
surface-to-air missiles has been developed by Guo- The autopilot design on air defense missiles has
Min and Hui Gu on simulating the availability of been developed by Delin Luo et al. [19]. Target
surface-to-air missile weapons systems that focus on identification is carried out to test the performance
estimating target points [10]. of the missile autopilot, but it is still unable to detect
The smart system on missile control provides the direction of the target which changed drastically,
innovation in determining the direction of missile so the need for a more accurate maneuvering system
movement towards a target by utilizing an on missiles equipped with intelligent algorithms.
accelerometer sensor that functions to control the There is also a missile control study with a bank to
tilt of the rocket and the gyroscope sensor to detect turn (BTT) system that can detect changes in the
the tilt of the target to the missile. The lock system is target direction, this study is represented by Mehta
obtained from the data sent from INS and TERCOM. S.S with the theme of adaptive vision-based missile
Research on missiles utilizing INS radar has been guidance in the presence of avoiding target
developed by Xinqi Fu and Meirong Chen [11] about maneuvers [20]. With a focus on minimizing
missile allocation based on SAR bistatic-borne maneuvering errors with targets whose speed is
missiles, which utilize INS without relying on unknown and can change. The BTT system still
 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63 57

requires operators to control missile direction. So Neural network planting is one of the methods
the guiding process is still too manual, so a developed for air defense missile technology. As has
microcontroller is needed to automatically adjust been developed by Deyun. Z and Feng. Z with the
the missile body to the target. theme of data fusion control and surface-to-air
Smart missile maneuver system is divided into missile guidance under complex conditions based on
several types of clusters according to the target neural-net technology [24] using a group method for
direction, research on the missile direction cluster data-processing to increase the effectiveness of land-
has been developed by Jan Farlik [21]. The theme is a to-air missile weapons systems based on filter data
simulation of surface-to-air missile units. The cluster tracked with a looping system. The amount of data
system implemented by Jan Farlik is not yet trained is 500 so that it can be developed by adding
equipped with an intelligent algorithm, so the target the number of iterations at the training stage, as well
accuracy can be less stable in some circumstances. as a more optimal looping system.
Missile maneuver requires prediction of a meeting Research that has been developed by Delin and
point between missile and target, research on Mehta still utilizes BTT manual control on missile
missile maneuver prediction has been developed by maneuvers. So it can be more efficient if the missile
Lee S. et al. with the theme of missile guidance based maneuver control system is equipped with sensors
on tracking the predicted target path [22] focusing and microcontrollers that are sufficient to guide the
only on determining missile maneuvers. So there is missile to the target automatically. While research
still no solution available if the missile is interrupted has been developed by Jan Farlik and Lee. S, the
when maneuvering. Intelligent algorithms can be a cluster system, and its prediction maneuver are still
solution to minimize interference on missile not equipped with an intelligent algorithm to handle
maneuvers. files on missile maneuvers. Embedding intelligent
Backpropagation is an effective method for algorithms on missiles can be a solution to minimize
learning neural networks and has been widely used vibration (fail) when missiles maneuver.
in various applications. The accuracy of the learning This research aims to develop a system for air
result, despite other facts, is highly affected by the defense missiles that can maneuver chasing targets
volume of high-quality data used for learning [23]. automatically with optimal feedback control that
utilizes accelerometer sensor readings for automatic
control. This system can minimize vibrations by
START utilizing the backpropagation neural network
algorithm on the sensor detector which can control
regular missile maneuvers based on the sensor value
cluster. So that the missile maneuver can be better
Initial Target without the need for manual control.
Condition
No
II. Materials and Methods
Launch Auto Pilot A. Missile architecture
Missile Stand By
The missile performance architecture has been
Yes
prepared about device specifications not damage the
missile launcher and body before and during the
Axis Sensor
Detector missile maneuver. The smart missile system has an
operating flow as shown in the flowchart of Figure 1.
The operation flow starts when the radar gets the
target info until the missile can reach the targeted
Train
Neural object.
Network
Data maneuvering is processed using MATLAB
software, which is equipped with neural network
tools to conduct training from data generated by
Feedback
Controll sensors, with backpropagation neural network
Manuver
training methods. The training results become a
reference for automatic control on the nozzle. With
the embedded sensor in the automatic control on
Initial Missile
Condition the smart algorithm for nozzle activation control, the
smart missile maneuver process is more organized
and accurate in chasing targets.
Miss
Hit target B. Backpropagation neural network missile
target
algorithm
Neural network systems can help accurate
maneuverability of automatic control of smart
End
missiles. Because the neural network can recognize
an object non-linearly. Neural network control
Figure 1. Smart missile architecture flowchart learning provides feedback with many conditions,
58 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63

Figure 2. Smart missile algorithm

making it easier to map the input to a result, able to in Figure 3. Each neuron is arranged by grouping
adapt to the recognition of an object, has tolerance several clusters based on the smart missile sensor’s
for an error in the recognition of an object, can be weight to guide the missile to the target. The neuron
implemented on hardware, and can be implemented continues to work until the detected target can be
in parallel [25]. hit by a smart missile.
Artificial neural networks are usually composed The data axis is grouped into 72 clusters as
of elements in layers that are connected and neurons, so the missile can detect and chase targets
weighted. This network modifies these weights coming from any direction. The neurons variables
based on a series of inputs given from outside the are paraded to focus on the movement of the missile
system, to produce consistent and similar output to tilt by minimizing the readout of the vibrations so
the given inputs. Usually, each element will process that nozzle activation is more regular. In addition to
based on mathematical operations that have been neurons, control maneuvers as hidden layers are also
given to each element [26]. Smart missile systems grouped (cluster) according to target and missile
use the backpropagation neural network method. conditions. Clusters in hidden layers are arranged in
Where backpropagation is a supervised learning nine clusters to control 24 nozzles as shown in
algorithm and is usually used by perceptron with Figure 4.
many layers to change the weights that are Nine hidden layers arranged to condition the
connected with neurons in the hidden layer [26]. The nozzle activation as follows;
implantation of the backpropagation neural network • Low maneuverability; if one nozzle is activated
algorithm in missiles has been developed by Da • Medium maneuver; when two (in a group)
Huang et al. Regarding activation controls on the nozzles are activated
missile tail to match the exact spectrum volume • Hard maneuvers; when three (in a group)
with strong resistance [27]. The backpropagation nozzles are activated
algorithm uses error output to change its value. To • Low & low maneuverability; when two (in two
get this error, neurons are activated by using an groups) nozzles are activated
activation function that can be differentiated. • Low & medium maneuvers; when three (in two
As shown in Figure 2, smart missile maneuvering groups) nozzles are activated
is weighted according to the target slope angle and • Low & hard maneuvers; if four (in two groups)
the missile tilt. The weight that can be achieved is nozzles are activated
2 2
recorded at -10 m/s to 10 m/s . The greater the • Medium & medium maneuvers; if four (in two
weight of the target slope, the nozzle performance groups) nozzles are activated
will be maximized with the shortest delay possible. • Medium & hard maneuvers; if five (in two
The weight value is obtained from the comparison of groups) nozzles are activated
the target lock system tilt periodically and the • Hard & hard maneuvers; if six (in two groups)
missile tilt periodically. The equation produced in nozzles are activated
the smart missile represents each neuron as shown
 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63 59

Ax1 - Ax2 < 0 ≥ -3

Right or left
AX1 – AX2=...... Ax1 - Ax2 < -3 ≥ -6
Low Manuver
Ax1 - Ax2 < -6

Ax1 – Ax2 > 0 ≤ 3

medium Manuver
Ax1 – Ax2 > 3 ≤ 6

Ax1 – Ax2 > 6

Ay1 - Ay2 < 0 ≥ -3 Hard Manuver

Detector Ay1 - Ay2 < -3 ≥ -6

Sensor
Ay1 - Ay2 < -6
Low & Low
Accel (gyro) Manuver
Ay1 – Ay2 > 0 ≤ 3
X axis:.....
Y axis:..... Front or back Ay1 – Ay2 > 3 ≤ 6
Z axis:..... AY1 – AY2=...... TARGET
Ay1 – Ay2 > 6
Low & medium AX1 = AX2
Manuver &
Accel (missile)
X axis:..... AY1 = AY2
Y axis:.....
Z axis:..... Low & Hard
Manuver

Medium & medium

Manuver

Feedback
Medium & Hard
Manuver
Oblique
AXt : AYt=......

Hard & Hard

Manuver

Total 72 neuron

Figure 3. Backpropagation neural network – feedback missile system

There is an equation for the number of nozzles missile according to the neurons guidance, to
that are activated, namely medium & medium increase the accuracy of the missile during the
maneuver and low & hard maneuver, totaling four maneuver.
active nozzles. The difference is, if medium &
C. Missile maneuver guidance system
medium each group activates two nozzles, while for
low & hard, the first group activates one nozzle and The missile guidance system functions as a
the second group turns on three nozzles (or vice determinant of the direction of the missile towards
versa). The hidden layers on the smart missile act as the target by adjusting the slope of the missile to
a control nozzle that can change the direction of the match the target position. The scheme developed

Y
Front

- X; Y 3 X; Y
FL
FR
2
3

(example)
2

1 One group nozzle

1

Left Right
-X 3 2 1 0 1 2 3 X
1

1
2

2
3

BL BR

- X; - Y 3 X; - Y

Back
-Y
(example)
Two group nozzle
Figure 4. Nozzle position hidden layers
60 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63

Target

(Accelerometer)
n
DOF Gyroscope tio
i r ec )
t D pe
(Accelerometer) rge sco
Missile Ta gyro
(

Movement

Missile Detector
Controll System
Missile Direction

Sensor (auto-pilot)
Figure 5. Auto-pilot missile scheme

can control the missile direction against randomly The calculation between the dependent variable
coming targets by utilizing the neural network. The and the independent variable on a smart missile
missile uses the degree of freedom (DOF) system on sensor is the main target of this research. So that the
the gyroscope by calculating the axis data from the neural network training method using
accelerometer. backpropagation gives high accuracy results and
By using DOF dynamics as a variable calculation, minimal vibrations to maneuver smart missiles
the technology of the nozzle on the missile body towards the target.
allows the missile to maneuver perfectly towards The increase in maneuver accuracy can be proven
the locked target and can minimize disturbance from by looking at the results of the first training until the
air pressure. There are 24 nozzles attached to the last training recorded, in the first training the system
missile body as shown in Figure 4. The number of only took 9 seconds to detect 1000 failures, while in
nozzles that are activated depends on the data the last training the system took about 1 minute to
obtained by the sensor. Nozzle technology is very detect 1000 failures, this indicates that the system is
commonly used in missiles, both as the main booster getting worse. Often trained, the errors are minimal,
and control attitude body missile. The target so the system is difficult to find 1000 files in the last
direction and missile condition are processed by the training.
autopilot system as shown in Figure 5 which is
B. Neural network performance
embedded with an intelligent backpropagation
neural network algorithm to optimize missile The neural network performance on a smart
maneuvers’ accuracy. missile displays a train, validation, and test graph as
The autopilot system works after the missile shown in Figure 7. The neural network performance
leaves the launcher until it reaches the target, so graph displays several training stages with a
there is no friction between the missile body and the different performance at each stage. The validation
missile launcher. The auto-pilot system continues to graph uses the mean square error (MSE) method to
work even though the target changes direction hold the test graph so that performance is more
(outwit), and the data from the sensor is stable during training. MSE is obtained from the
continuously processed using the intelligent lowest point on the validation graph.
backpropagation neural network algorithm so the When minimizing vibration in missiles, it
maneuverability is much better and the missile's produces a very significant change from the
accuracy level is getting higher. beginning of the training to the end of the training.

(a)
III. Results and Discussions
The weight produced by the X-axis and Y-axis of
the missile and target accelerometer is calculated by
calculating the ratio and difference of each axis. The
training data results show the performance, training
state, and gradients of the smart missile system.
A. Training data results (b)
The accelerometer data calculation is trained
with the backpropagation neural network algorithm.
The algorithm is assembled with 72 neurons of
equation neurons connected to nine hidden layers,
as well as two types of target data axes (X-axis and
Y-axis). As in Figure 6, the network is trained by
entering 1000 max files at each stage. Figure 6. Train progress: (a) First train; (b) End train
 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63 61

(a) (b)

Figure 7. Perform neural network: (a) First train; (b) End train

This can be proven at the initial training with a mass graphs in the training state also display changes in
load of 273 to 0. shape at each stage, in the initial stages of a
In the final training, and the best point of discontinuous graph form with a validated period of
0.57
validation performance was 3,715 (around 10 ) in 727 out of 1000, then at the final stage of the
-0.46
the initial training, to 0.3423 (about 10 ) in the training state, the shape of the failure graph is not
final training. Besides that, the initial training chart interrupted (continued) with a period of validated by
shows fluctuating shapes, while the final training 1000 out of 1000. this indicates that the training
graph shows a constant form. This can indicate that stage of the smart missile can guide the missile so
the system can minimize vibration waves on smart that it can maneuver with minimal vibration, so that
missile systems. maneuvers (fail) can be minimized or overcome.
C. Training state neural network D. Neural network regression
The neural network training state on the smart Neural network regression in the smart missile to
missile displays a gradient graph and a check the target displays a single line of perception of
validation graph as shown in Figure 8. The neural training line intercept, validation line intercept, test
network training graph displays several training line intercept, and all line intercept. As shown in
stages with different statistics at each stage. Figure 9, each training stage displays the different
Gradient graphs and fail graphs that experience conditions of each line intercept.
changes at every stage of the training. The resulting Line intercept in neural network regression
changes indicate that the gradient value of 1000 shows changes in the independent variables that are
iterations is getting smaller and fluctuations are increasingly close to the dependent variable from
getting smaller too. Where the initial gradient value the data of the smart missile sensor results. The
of 7.88 becomes 0.00056, and in the end, the most significant change at each stage of the training
fluctuation disappears in the final training. Failure was shown by the line test, with the difference in

(a) (b)

Figure 8. State neural network training: (a) First train; (b) End train
62 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63

(a) (b)

Figure 9. Neural network regression: (a) First train; (b) End train

variables of 4.2 at the initial stage of the training K. Faqih, Sujito, S. Sendari, and F. S. Aziz contributed
being 0.32 at the end of the training. This indicates equally as the main contributor to this paper. All authors
that the difference between the slope of the target as read and approved the final paper.
a fixed variable, and the missile as the independent Funding statement
variable, results in a comparison that approaches the
similarity of the axes. So the missile can be in the This research was funded by Sujito from a private
sector.
right maneuver to hit the target.
Conflict of interest
IV. Conclusion The authors declare no conflict of interest.
Smart guided missile system using the Additional information
accelerometer and gyroscope, can guide the missile
No additional information is available for this paper.
to the target with a highly accurate difference in
variables. The slope between the missile maneuver
against the target can be reduced by a difference of References
2
0.32 m/s . Backpropagation neural network with [1] Anthony D’Amato, “Israel’s Air Strike Against the Osiraq
optimal feedback control makes this system able to Reactor: A Retrospective,” Northwest. Univ. Sch. Law Sch.
2
minimize vibration up to 0.34 m/s , so that missile Commons, vol. 10 Temp. Int'l & Comp. L.J. 259-264, 2010.
[2] E. Garcia, D. W. Casbeer, Z. E. Fuchs, and M. Pachter,
maneuvers are much better with minimal zigzag
“Cooperative Missile Guidance for Active Defense of Air
movement. Fail that can be detected and validated as Vehicles,” IEEE Trans. Aerosp. Electron. Syst., vol. 54, no. 2, pp.
a whole, namely 1000 files out of 1000 times (epoch) 706–721, Apr. 2018.
so the autopilot system can be more regular in [3] M. J. Castro-Toscano et al., “A methodological use of inertial
adjusting the missile body when maneuvering navigation systems for strapdown navigation task,” in 2017
IEEE 26th International Symposium on Industrial Electronics
towards the target. (ISIE), Jun. 2017, pp. 1589–1595.
[4] Zhang Hua and Hu Xiulin, “A height-measuring algorithm
applied to TERCOM radar altimeter,” in 2010 3rd International
Acknowledgement Conference on Advanced Computer Theory and
Engineering(ICACTE), Aug. 2010, vol. 5, pp. V5-43-V5-46.
Thank you to Universitas Negeri Malang for
[5] M. S. Ab-Rahman and M. R. Hassan, “Lock-on range of infrared
support in the form of directives, facilities, and heat seeker missile,” in 2009 International Conference on
research facilities in the form of laboratories for the Electrical Engineering and Informatics, Aug. 2009, vol. 02, pp.
success and smoothness of this research. 472–477.
[6] I. F. Gibbons and J. J. Botha, “Tactical radar missile challenges,”
in 2015 IEEE Radar Conference, Oct. 2015, pp. 46–50.
Declarations [7] K. Günaydin, T. Çimen, and O. Tekinalp, “Response surface
based performance analysis of an Air-Defense Missile System,”
Author contribution in 2014 IEEE Aerospace Conference, Mar. 2014, pp. 1–10.
[8] B. Li, G. He, and J. Wu, “A Research of Automatic Measuring
The simulation of the research data was developed by K. and Test System of Some Surface-to-Air Missile Autopilot,” in
Faqih. Sujito founded the idea of the research and supervise 2009 IEEE Circuits and Systems International Conference on
the work. Improvement of the English language and Testing and Diagnosis, Apr. 2009, pp. 1–3.
structure of the paper was supervised by S. Sendari. Data [9] T. Ender et al., “Systems-of-Systems Analysis of Ballistic
collection and layout submission by F. S. Aziz. Missile Defense Architecture Effectiveness Through Surrogate
 K. Faqih et al. / Journal of Mechatronics, Electrical Power, and Vehicular Technology 11 (2020) 55-63 63

Modeling and Simulation,” IEEE Syst. J., vol. 4, no. 2, pp. 156– [18] T. Herlambang, E. B. Djatmiko, and H. Nurhadi, “Ensemble
166, Jun. 2010. Kalman Filter with a Square Root Scheme (EnKF-SR) for
[10] Guo-Min Zheng and Hui Gu, “Research on availability Trajectory Estimation of AUV SEGOROGENI ITS,” Int. Rev.
simulation of Surface-to-Air missile weapon systems,” in 2010 Mech. Eng. IREME, vol. 9, no. 6, pp. 553-560–560, Nov. 2015.
International Conference On Computer Design and [19] D. Luo, J. Zhang, and Y. Liu, “Autopilot design for bank to turn
Applications, Jun. 2010, vol. 5, pp. V5-99-V5-103. missile,” in 2016 12th IEEE International Conference on
[11] X. Fu and M. Chen, “Missile Location Based on Missile-Borne Control and Automation (ICCA), Jun. 2016, pp. 401–406.
Bistatic SAR,” in 2014 Seventh International Symposium on [20] S. S. Mehta, W. MacKunis, and J. W. Curtis, “Adaptive Vision-
Computational Intelligence and Design, Dec. 2014, vol. 2, pp. based Missile Guidance in the Presence of Evasive Target
232–235. Maneuvers,” IFAC Proc. Vol., vol. 44, no. 1, pp. 5471–5476, Jan.
[12] K. Faqih et al., “Smart grid photovoltaic system pilot scale 2011.
using sunlight intensity and state of charge (SoC) battery based [21] J. Farlik, “Simulation of surface-to-air missile units: Cluster
on Mamdani fuzzy logic control,” J. Mechatron. Electr. Power design,” in International Conference on Military Technologies
Veh. Technol., vol. 10, no. 1, Art. no. 1, Dec. 2019. (ICMT) 2015, May 2015, pp. 1–6.
[13] H. Modares, F. L. Lewis, and Z.-P. Jiang, “Optimal Output- [22] S. Lee, N. Cho, and Y. Kim, “Missile Guidance Based on
Feedback Control of Unknown Continuous-Time Linear Tracking of Predicted Target Trajectory,” in 2018 26th
Systems Using Off-policy Reinforcement Learning,” IEEE Trans. Mediterranean Conference on Control and Automation (MED),
Cybern., vol. 46, no. 11, pp. 2401–2410, Nov. 2016. Jun. 2018, pp. 229–234.
[14] X. Lidan, Z. Ke’nan, C. Wanchun, and Y. Xingliang, “Optimal [23] D. E. Rumelhart, “Hinton and Williams, RJ (1986):‘Learning
Control and Output Feedback Considerations for Missile with internal representations by error propagation,’” Parallel
Blended Aero-fin and Lateral Impulsive Thrust,” Chin. J. Distrib. Process., vol. 1, 1986.
Aeronaut., vol. 23, no. 4, pp. 401–408, Aug. 2010. [24] Z. Deyun and Z. Feng, “Data fusion control and guidance of
[15] J. Sun, C. Liu, and J. Dai, “Robust optimal control for missile- surface-to-air missile under the complex circumstance based
target guidance systems via adaptive dynamic programming,” on neural-net technology,” J. Syst. Eng. Electron., vol. 19, no. 5,
in 2018 Chinese Automation Congress (CAC), Nov. 2018, pp. pp. 996–1002, Oct. 2008.
836–841. [25] Y.-J. Liu, J. Li, S. Tong, and C. L. P. Chen, “Neural Network
[16] F. L. Lewis, Optimal Estimation: With an Introduction to Control-Based Adaptive Learning Design for Nonlinear Systems
Stochastic Control Theory, 1 edition. New York: Wiley- With Full-State Constraints,” IEEE Trans. Neural Netw. Learn.
Interscience, 1986. Syst., vol. 27, no. 7, pp. 1562–1571, Jul. 2016.
[17] T. Herlambang, E. B. Djatmiko, and H. Nurhadi, “Navigation [26] V. Amrizal and Q. Aini, Kecerdasan Buatan. Halaman Moeka
and guidance control system of AUV with trajectory Publishing, 2013.
estimation of linear modelling,” in 2015 International [27] D. Huang, S. Huang, Y. Tang, W. Zhao, and W. Cao, “Matching
Conference on Advanced Mechatronics, Intelligent algorithm of missile tail flame based on back-propagation
Manufacture, and Industrial Automation (ICAMIMIA), Oct. neural network,” in Fourth Seminar on Novel Optoelectronic
2015, pp. 184–187. Detection Technology and Application, Feb. 2018, vol. 10697, p.
1069702.