In this paper, a monitoring method for DC-DC converters in photovoltaic applications is presented. The primary goal is to prevent catastrophic failures by detecting malfunctioning conditions during the operation of the electrical system. The proposed prognostic procedure is based on machine learning techniques and focuses on the variations of passive components with respect to their nominal range. A theoretical study is proposed to choose the best measurements for the prognostic analysis and adapt the monitoring method to a photovoltaic system. In order to facilitate this study, a graphical assessment of testability is presented, and the effects of the variable solar irradiance on the selected measurements are also considered from a graphical point of view. The main technique presented in this paper to identify the malfunction conditions is based on a Multilayer neural network with Multi-Valued Neurons. The performances of this classifier applied on a Zeta converter are compared to those of a Support Vector Machine algorithm. The simulations carried out in the Simulink environment show a classification rate higher than 90%, and this means that the monitoring method allows the identification of problems in the initial phases, thus guaranteeing the possibility to change the work set-up and organize maintenance operations for DC-DC converters.

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.

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 corresponding variation in the frequency response. The proposed system is based on the use of a complex neural network with feedforward architecture. It processes the frequency response, allowing the classification of the cable conditions with an accuracy higher than 90%.

This paper presents a detailed analysis of a convolutional neural network based on multi-valued neurons (CNNMVN) and a fully connected multilayer neural network based on multi-valued neurons (MLMVN), employed here as a convolutional neural network in the frequency domain. We begin by providing an overview of the fundamental concepts underlying CNNMVN, focusing on the organization of convolutional layers and the CNNMVN learning algorithm. The error backpropagation rule for this network is justified and presented in detail. Subsequently, we consider how MLMVN can be used as a convolutional neural network in the frequency domain. It is shown that each neuron in the first hidden layer of MLMVN may work as a frequency-domain convolutional kernel, utilizing the Convolution Theorem. Essentially, these neurons create Fourier transforms of the feature maps that would have resulted from the convolutions in the spatial domain performed in regular convolutional neural networks. Furthermore, we discuss optimization techniques for both networks and compare the resulting convolutions to explore which features they extract from images. Finally, we present experimental results showing that both approaches can achieve high accuracy in image recognition.

This chapter contains sections titled: Brain–Computer Interface (BCI) BCI Based on Steady-State Visual Evoked Potentials EEG Signal Preprocessing Decoding Based on MLMVN for Phase-Coded SSVEP BCI System Validation Discussion