Fault diagnosis of Photovoltaic arrays becomes an interesting topic for authors due to the difficulty distinguish between faults. Many techniques have been applied for the diagnosis and classification of faults based on datasets samples like Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM). However, to assure the best accuracy of diagnosis model must extract and prepare important data using a dimensionality reduction technique namely, Principal Component Analysis (PCA), and Independent Component Analysis (ICA). Therefore, this paper aims to build a diagnosis model using Support Vector Machine based on radial basis kernel function through prepared data using t-Distributed Stochastic Neighbor Embedding (T-SNE). The proposed model is compared with other methods for preparing data with SVM classifiers which are PCA and ICA. The simulation of faults, like partial shading, degradation, short circuit, and open circuit and diagnosis models studied are investigated and its results are reported.

AbstractPermanent Magnet Synchronous Machine (PMSM) is widely utilised in numerous industrial applications due to its precise control capabilities. However, these motors frequently encounter operational faults, potentially leading to severe safety and performance issues. Consequently, effective health monitoring techniques for early fault detection are essential to maintain optimal performance and extend the lifespan of these systems. This study presents a qualification‐based methodology for diagnosing faults in three‐phase PMSMs through vibration–current data fusion analysis. The stator faults, specifically inter‐turn short circuits (ITSC) induced via bypassing resistances, were investigated using experimental data from a custom‐built test rig. The collected current and vibration signals were transformed into statistical features. Various operating scenarios were diagnosed utilising a deep regulated neural network (RegNet), an improved convolutional neural network based on an enhanced residual architecture. The proposed approach was assessed through various metrics including training efficiency, precision, recall, f1‐score, and accuracy, and compared against several neural network methods. The findings reveal that the proposed RegNet model achieves perfect accuracy, attaining 100%. This research highlights the efficacy of data fusion analysis and deep learning in fault diagnosis, facilitating proactive maintenance strategies and improving the reliability of PMSMs in diverse industrial applications and renewable energy systems.

Effective fault identification and diagnosis in photovoltaic (PV) arrays is vital for improving the effectiveness, and safety of solar energy systems. While various artificial intelligence methods have successfully established fault detection and diagnosis models, introducing inefficiencies and potentially overlooking useful features. Moreover, these methods often employ neural networks with limited performance capabilities. In response to these challenges, this paper introduces an innovative intelligent model that integrates a combination of a gated residual neural network (GRN) and a multi-head self-attention mechanism (MHSA). To evaluate the proposed fault diagnosis model, the small-scale PV grid system is implemented, and fault simulation experiments, including arc faults, maximum power tracking failures, line-to-line, open circuit, degradation, and partial shading with normal conditions, are conducted to acquire simulation datasets. Additionally, widely used neural network models, including artificial neural networks, recurrent neural networks, convolutional neural networks, and the proposed model without an attention mechanism, are employed for comparison. Furthermore, common machine learning approaches found in the literature for diagnosing faults of PV arrays, optimized by Bayesian technique are implemented and compared. Simulation results highlight that the proposed approach attains superior performance across key metrics, including accuracy, precision, recall, f1-score, and training efficiency. Notably, the proposed model achieves an impressive testing accuracy of 99.71%, surpassing alternative methods. This highlights its effectiveness as a robust and efficient solution for fault diagnosis in PV arrays.

In this research paper, a maximum power point tracking (MPPT) has been achieved using controllers based on artificial intelligence techniques, such as fuzzy logic (FLC), and artificial neural networks (ANN) controllers, since PI and PID classical controllers cannot give good performances in many applications that include strong nonlinearity caused by wind turbines aerodynamics, power converters of the conversion system, and the nature of wind flow. For this reason, we have proposed to use three MPPT control strategies; classical PI controller, fuzzy logic controller (FLC), and artificial neural network (ANN) controller. To avoid wind turbine catastrophes in high winds, the technique of pitch control has been investigated in parallel. Using MATLAB/Simulink, the proposed technique has been validated on a variable speed wind turbine with five-phase permanents magnets synchronous generator (PMSG) connected to a grid. The simulation results show the effectiveness of the proposed FLC and ANN controllers to achieve high tracking performance in the variable speed wind energy conversion systems (WECS).

Photovoltaic water pumping application is important field of interest for sustainable development. The maximum power point (MPP) at which PV system is to be operated is tracked by peak tracker to utilize solar power. Performance of any MPPT can be evaluated based on tracking speed, accuracy and stability. This paper deals with the application of the incremental conductance and fuzzy logic controller to extract the maximum power point in a PV water system with field oriented control of a permanent magnet synchronous motor (PMSM). The proposed MPPT techniques were developed and tested successfully on the PV water pumping system. A comparative study between the proposed methods under similar operating conditions is presented. The performances in terms of voltage and power ripples show the effectiveness of the fuzzy logic MPPT technique.

Stator winding short-circuit faults arising from winding insulation faults are among the most frequent faults in permanent magnet synchronous motors (PMSMs). If left undetected, such fault may be rapidly propagated, resulting in phase-to-phase or phase-to-ground faults, even the breakdown of the whole motor. A powerful fault diagnosis method requires the computation of a fault sensitive quantity and an appropriate method to get a diagnostic index and a threshold which present the edge between faulty and healthy conditions. This is particularly critical for stator short-circuit faults, especially in PMSMs which can cause catastrophic damage to the machine in a very short time. This paper proposes a new detection fault approach based on pattern recognition analysis for detecting the stator inter-turn fault in two phases. Firstly, an image of αβ stator currents in healthy and faulty conditions is composed in the 2D plane. Then, the extracted parameters according to the obtained image as areas and angles of rectangle shapes are used to detect the stator winding faults. Finally, a fault severity index (FSI) gives a slight or a serious degree of faults in PMSM. The experimental results are presented in this paper to show the usefulness of the proposed approach.

Abstract—With the increased use of permanent magnet synchronous motors (PMSMs), efficient online condition monitoring and accurate fault diagnosis for these machines are very important. In order to reduce downtime and avoid unsafe operating conditions, it is essential to establish a methodology capable to detect incipient turn faults. This paper analyzed the consequences of turn-to-turn circuit faults between two phases in a PM synchronous motor. Thus, a simple method based on rotor speed ripples is proposed for detecting stator winding faults. Also, a fault index allows quantifying the severity of the fault. This latter seems to be well adapted for PM motors health monitoring and interturn fault diagnosis. Experimental results are included to show the ability of the proposed strategy to detect incipient faults.

Stator turn faults in permanent magnet synchronous motors (PMSMs) are more dangerous than those in induction motors (IMs) because of the presence of spinning rotor magnets that can be turned off at will.Condition monitoring and fault detection and diagnosis of the PMSM have been receiving a growing amount of attention among scientists and engineers in the past few years.The aim of this study is to propose a new detection technique of stator winding faults in a three-phase PMSM.This technique is based on the image analysis and recognition of the stator current Concordia patterns, and will allow the identification of turn faults in the stator winding as well as its correspondent fault index severity.A test bench of a vector controlled PMSM motor behaviors under short circuited turn in two phases stator windings has been built.Some experimental results of the phase to phase short circuits have been performed for diagnosis purpose.

Direct torque control (DTC) is a powerful control method for interior permanent magnet synchronous motor (IPMSM), it provides a systematic solution in improving the operation characteristics of not only the motor but also the voltage source inverter(VSI). Stator winding faults due to short circuited turns are one of the most electrical faults in DTC-IPMSM drive system. The main problem with fault is connected with their destructive character and a tendency to a rapid transition. In early stage of this failure, the motor may still operate. This paper presents a direct torque control for IPMSM motor under stator winding faults, in order to ensure system service continuity. As a very fast diagnosis could terminate the damage range in the stator winding, a proposed method based on the current space pattern recognition will be investigated. Comparisons between simulation and experimental results will be performed to evaluate the effectiveness of the proposed approach.

Time moments have been introduced in automatic control because of the analogy between the impulse response of a linear system and a probability function. Pasek described a testing procedure for determining the DC parameters from the current response to a step in the armature voltage motor. In this paper, two identification algorithms developed based on the moments and Pasek’s methods are introduced and applied to the parameter identification of a DC motor. The simulation and experimental results are presented and compared, showing that the moments method makes the model closer to reality, especially in a transient regime.

In order to develop an effective detection method and tolerant strategy, a simulation model which can describe accurately the behavior of a PMSM drive with stator turn faults, is absolutely required. In this paper a dynamic model for permanent magnet synchronous motor with a stator inter-turn winding fault is derived in abc-variables. The model is used in vector control for a PMSM drive for both healthy and faulty conditions. As any method should be fully confirmed with a simulation model before being applied to a real system, the stator turn fault vector control strategy for PMSM drive is implemented in MATLAB/SIMULINK. Simulation results show the limit of validity of the proposed strategy and allow proposing a strategy for diagnosis but also for fault tolerant control development.

Identification is considered to be among the main applications of inverse theory and its objective for a given physical system is to use data which is easily observable, to infer some of the geometric parameters which are not directly observable. In this paper, a parameter identification method using inverse problem methodology is proposed. The minimisation of the objective function with respect to the desired vector of design parameters is the most important procedure in solving the inverse problem. The conjugate gradient method is used to determine the unknown parameters, and Tikhonov's regularization method is then used to replace the original ill-posed problem with a well-posed problem. The simulation and experimental results are presented and compared.

The identification process consists of estimating the unknown parameters of system dynamics. Consequently, determination of the assumed system structure is of great importance in the process of system identification. Time moments have been introduced in automatic control because of the analogy between the impulse response of a linear system and a probability function. This basic idea has generated applications in identification, model order reduction and controller design. In this paper, a newly developed identification algorithm, called moments method, is introduced and applied to the parameter identification of a dc motor. The simulation and experimental results are presented and compared.

In this paper, a parameter identification using inverse problem methodology is proposed The magnetic permeability, which depends on the magnetic field and temperature, is a physical parameter which has to be taken into account in any electro thermal physical problem simulation. In order to shou, the validity of the proposed approach, the problem is usually treated as an optimization problem, where the conjugate gradient method is combined with the finite element analysis, to identify the relative magnetic permeability of the permanent magnets (PM) of a synchronous motor. Tikhonov's regularization method is then used to replace the original ill-posed or ill-conditioned problem with a well-posed or well-conditioned problem, able to provide a close approximation of the PM relative magnetic permeability. Copyright C 2007 Praise Worthy Prize S. r. l. - All rights reserved.

The estimation of d- and q-axis parameters is highly desirable, because they are fundamental parameters to many vector control algorithms in the d-q reference frame for fast and accurate responses. Using the flnite element method (FEM) for the determination of the interior permanent magnet synchronous motor (IPM) reactance provides an accurate means of determining the fleld distribution. However, this method might be time consuming. The magnetic circuit modelling approach has been successfully used to model a variety of electrical machine such as IPM motors. This paper deals with the inverse problem methodology for the identiflcation of d- and q-axis synchronous reactance of an IPM motor. The proposed method uses a measured electromotive force (EMF) to compute the objective function. The machine parameters identifled by the proposed approach are compared to experimental results.