Papers by Antonio Luchetta
Advances in Science, Technology and Engineering Systems Journal
In this paper a classification system based on a complex-valued neural network is used to evaluat... more In this paper a classification system based on a complex-valued neural network is used to evaluate the health state of joints in high voltage overhead transmission lines. The aim of this method is to prevent breakages on the joints through the frequency response measurements obtained at the initial point of the network. The specific advantage of this kind of measure is to be non-intrusive and therefore safer than other approaches, also considering the high voltage nature of the lines. A feedforward multi-layer neural network with multi-valued neurons is used to achieve the goal. The results obtained for power lines characterized by three and four junction regions show that the system is able to identify the health state of each joint, with an accuracy level greater than 90%.
Electronics
In this paper, we present a new method designed to recognize single parametric faults in analog c... more In this paper, we present a new method designed to recognize single parametric faults in analog circuits. The technique follows a rigorous approach constituted by three sequential steps: calculating the testability and extracting the ambiguity groups of the circuit under test (CUT); localizing the failure and putting it in the correct fault class (FC) via multi-frequency measurements or simulations; and (optional) estimating the value of the faulty component. The fabrication tolerances of the healthy components are taken into account in every step of the procedure. The work combines machine learning techniques, used for classification and approximation, with testability analysis procedures for analog circuits.
Journal of Artificial Intelligence and Soft Computing Research
A procedure for the identification of lumped models of distributed parameter electromagnetic syst... more A procedure for the identification of lumped models of distributed parameter electromagnetic systems is presented in this paper. A Frequency Response Analysis (FRA) of the device to be modeled is performed, executing repeated measurements or intensive simulations. The method can be used to extract the values of the components. The fundamental brick of this architecture is a multi-valued neuron (MVN), used in a multilayer neural network (MLMVN); the neuron is modified in order to use arbitrary complex-valued inputs, which represent the frequency response of the device. It is shown that this modification requires just a slight change in the MLMVN learning algorithm. The method is tested over three completely different examples to clearly explain its generality.
Energies
A smart monitoring system capable of detecting and classifying the health conditions of MV (Mediu... more A smart monitoring system capable of detecting and classifying the health conditions of MV (Medium Voltage) underground cables is presented in this work. Using the analysis technique proposed here, it is possible to prevent the occurrence of catastrophic failures in medium voltage underground lines, for which it is generally difficult to realize maintenance operations and carry out punctual inspections. This prognostic method is based on Frequency Response Analysis (FRA) and can be used online during normal network operation, resulting in a minimally invasive tool. In order to obtain the good results shown in the simulation section, it is necessary to develop a lamped equivalent circuit of the network branch under consideration. The standard π-model is used in this paper to analyse sections of a medium voltage cable and the parameter variations with temperature are used to classify the state of health of the line. In fact, the variation of the electrical parameters produces a corres...
Applied Sciences
The use of electronic loads has improved many aspects of everyday life, permitting more efficient... more The use of electronic loads has improved many aspects of everyday life, permitting more efficient, precise and automated process. As a drawback, the nonlinear behavior of these systems entails the injection of electrical disturbances on the power grid that can cause distortion of voltage and current. In order to adopt countermeasures, it is important to detect and classify these disturbances. To do this, several Machine Learning Algorithms are currently exploited. Among them, for the present work, the Long Short Term Memory (LSTM), the Convolutional Neural Networks (CNN), the Convolutional Neural Networks Long Short Term Memory (CNN-LSTM) and the CNN-LSTM with adjusted hyperparameters are compared. As a preliminary stage of the research, the voltage and current time signals are simulated using MATLAB Simulink. Thanks to the simulation results, it is possible to acquire a current and voltage dataset with which the identification algorithms are trained, validated and tested. These dat...
Journal of Physics: Conference Series
In this paper a new method is developed and described, aimed at the modeling and diagnosis of the... more In this paper a new method is developed and described, aimed at the modeling and diagnosis of the joints connecting the ends of two cables on a high voltage electricity pylon. Identifying the anomalous joint behaviour through the line frequency response analysis is the first objective of the work. For this reason, it is necessary to model the whole overhead line with a lumped circuit and studying the joint electrical parameter variation. The problem is approached in multiple steps: modelling, testability analysis of the model, optimal frequency selection, identification of the possible failures. Some simulated cases are included in order to show the potentialities of the method.
Neural Processing Letters
IEEE Transactions on Instrumentation and Measurement
IEEE Transactions on Circuits and Systems I: Regular Papers
International Journal of Numerical Modelling: Electronic Networks, Devices and Fields
2016 AEIT International Annual Conference (AEIT), 2016
Proceedings of 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (MELECON 96), 2000
A new approach for testability measurement of analog networks is presented. It is based on the us... more A new approach for testability measurement of analog networks is presented. It is based on the use of symbolic techniques, that allow us to realize very simple testability evaluation algorithms. The new method presents noteworthy advantages from a computational point of view with respect to previous symbolic techniques of testability measurement developed by the authors in the past. In fact it does not require the computation of the sensitivities of the network functions, but it is based only on the study of the network function symbolic coefficients. A new theorem has been proved and the subsequent new algorithm permits to completely eliminate the roundoff errors and increase the computing speed. A brief introduction to the program which implements this new algorithm is also presented
Proceedings of Iscas 95 International Symposium on Circuits and Systems, 1995
A symbolic approach to the frequency domain characterization of dc-dc converters is presented. Th... more A symbolic approach to the frequency domain characterization of dc-dc converters is presented. The symbolic analysis is based on a sampled-data technique derived from a state variable approach, exploiting the numerical values of the state variable and output samples obtained by s-domain symbolic network functions of the circuit. A symbolic program developed by the authors is presented. It is shown that the computer synibolic analysis can be easily applied also to the averaged models of dc-dc converters. Possible developments to the frequency domain analysis of the whole dc-dc converter including the control system are also proposed.
2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC), 2015
ABSTRACT The paper considers an open loop-operation of a PWM DC DC Buck converter at a constant d... more ABSTRACT The paper considers an open loop-operation of a PWM DC DC Buck converter at a constant duty-cycle. Under these conditions, the converters compensate the effects of the parasitic resistances adjusting the diode duty-cycle D1. All four network functions describing the frequency-domain behavior of a discontinuous conduction mode (DCM) operated DC-DC buck converter power stage are derived considering D1 adjustments. These network functions are derived in a closed form both manually and by using a symbolic circuit simulator. Bode plots of the network functions are also given for the buck converter. These functions are derived by utilizing a small signal equivalent circuit of the switching-cell composed of controlled current sources and resistance. Experimental result confirm the accuracy of theoretical derivations.
2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC), 2015
ABSTRACT A comparison among several recently published techniques suitable for DC-DC converter sw... more ABSTRACT A comparison among several recently published techniques suitable for DC-DC converter switching cell modelling when the converter is operated in discontinuous conduction mode (DCM) is presented. All these techniques consider the effect of parasitic components due to actual components utilized in assembling converter circuits. The paper is also concentrated on two techniques resulting in an equivalent circuit of the switching cell. The first one provides a small-signal equivalent circuit of the switching cell suitable for straightforward frequency-domain analysis of DC-DC converters, which allows for a derivation in a closed form of the four canonical s-domain transfer functions describing the converter operation. The second one, more recent, provides a model suitable for predicting large-signal time-domain transients as well as small-signal frequency-domain characteristics. This comparison is new and is supported by experimental measurements.
2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC), 2015
2014 International Symposium on Fundamentals of Electrical Engineering (ISFEE), 2014
2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC), 2015
ABSTRACT Actually, several multilevel converter circuits have been studied in literature, but onl... more ABSTRACT Actually, several multilevel converter circuits have been studied in literature, but only a few of them have been experimentally tested. This paper shows an analysis of different multilevel inverter topologies along with their control techniques. The identification of the more suitable solutions for a given hybrid plant configuration has been made through computer simulations and the most promising circuit has been designed for experimental tests. The converter electrical parameters such as efficiency, output voltage THD and energy losses have been checked by means of accurate computer simulations.
Uploads
Papers by Antonio Luchetta