The integration of photovoltaic (PV) systems into the global energy landscape has been boosted in recent years, driven by environmental concerns and research into renewable energy sources. The accurate prediction of temperature and solar irradiance is essential for optimizing the performance and grid integration of PV systems. Machine learning (ML) has become an effective tool for improving the accuracy of these predictions. This comprehensive review explores the pioneer techniques and methodologies employed in the field of ML-based forecasting of temperature and solar irradiance for PV systems. This article presents a comparative study between various algorithms and techniques commonly used for temperature and solar radiation forecasting. These include regression models such as decision trees, random forest, XGBoost, and support vector machines (SVM). The beginning of this article highlights the importance of accurate weather forecasts for the operation of PV systems and the challenges associated with traditional meteorological models. Next, fundamental concepts of machine learning are explored, highlighting the benefits of improved accuracy in estimating the PV power generation for grid integration.

Anomaly detection is the process of detecting unusual or unforeseen patterns or events in data. Many factors, such as malfunctioning hardware, malevolent activities, or modifications to the data’s underlying distribution, might cause anomalies. One of the key factors in anomaly detection is balancing the trade-off between sensitivity and specificity. Balancing these trade-offs requires careful tuning of the anomaly detection algorithm and consideration of the specific domain and application. Deep learning techniques’ applications, such as LSTMs (long short-term memory algorithms), which are autoencoders for detecting an anomaly, have garnered increasing attention in recent years. The main goal of this work was to develop an anomaly detection solution for an electrical machine using an LSTM-autoencoder deep learning model. The work focused on detecting anomalies in an electrical motor’s variation vibrations in three axes: axial (X), radial (Y), and tangential (Z), which are indicative of potential faults or failures. The presented model is a combination of the two architectures; LSTM layers were added to the autoencoder in order to leverage the LSTM capacity for handling large amounts of temporal data. To prove the LSTM efficiency, we will create a regular autoencoder model using the Python programming language and the TensorFlow machine learning framework, and compare its performance with our main LSTM-based autoencoder model. The two models will be trained on the same database, and evaluated on three primary points: training time, loss function, and MSE anomalies. Based on the obtained results, it is clear that the LSTM-autoencoder shows significantly smaller loss values and MSE anomalies compared to the regular autoencoder. On the other hand, the regular autoencoder performs better than the LSTM, comparing the training time. It appears then, that the LSTM-autoencoder presents a superior performance although it was slower than the standard autoencoder due to the complexity of the added LSTM layers.

With the progressive adoption of silicon carbide (SiC) power devices in modern power converters, exploiting their superior efficiency, faster switching speed, and higher power density, an understanding of the factors influencing these properties becomes vital. One such critical factor is switching losses, which can drastically affect overall system performance. This study develops and presents a new analytical model for predicting the turn-on switching losses in SiC MOSFETs with Kelvin pin. The proposed model, derived from a carefully constructed set of nonlinear differential equations, accounts for the nonlinearity of the transconductance by incorporating a novel transfer characteristic model. The model also incorporates the nonlinear junction capacitances effects. The developed analytical model allows for the prediction and optimization of turn-on switching losses in SiC MOSFETs, thus enabling improved energy efficiency and reliability. The accuracy of the proposed model is verified through comparison with experimental results obtained using the double pulse test board that was designed and constructed, demonstrating its applicability for the investigation of SiC MOSFET power losses.

Drilling operations can encounter considerable challenges posed by strong, coupled vibrations that exert a complex influence on rotary drilling system performance. These vibrations are classified into three distinct types based on their propagation direction: axial, lateral, and torsional. Previous research efforts have predominantly focused on examining each vibration type in isolation. However, the effectiveness and resilience of developed controllers are profoundly affected by the often overlooked coupling effects arising from other types of vibrations. In this study, we propose the implementation of a Proportional-Integral-Derivative (PID) controller for the coupled Axial-Torsional vibration system. The research presented herein is dedicated to investigate the performance of the controller under strongly coupled vibrations. To address the dynamic vibrations encountered during drilling, it is imperative to understand the intricate behavior of the drill bit in response to these vibrations before designing controllers to mitigate their impact. Numerous models have been proposed in the existing literature to elucidate the behavior of the drill string under axial-torsional vibrations. The objective of this research is to develop a comprehensive model of the drilling system and investigate the robustness of the PID controller to mitigate the adverse effects of coupled Axial-Torsional vibrations. By effectively analysing the obtained results, this study has contributed to the optimization and improvement of drilling operations under sever coupled vibrations.

The aim of this paper is to present an evaluation of the performancerate of four different photovoltaic techniques in the Saharan environment. The purpose of this study is to investigate, analyse, discuss and illustrate the most effective of the different photovoltaic cell technologies (monocrystalline , amorphous silicon , poly-crystalline silicon and cadmium telluridethin film ) installed in Ghardaia which is located in southern of Algeria’s Sahara desert. In order to choose the most suitable technology in the Saharan climate conditions, the energy values produced by the plant were compared to those found by the PVSYST sizing software. The results show that thin-film and amorphous silicon panels produce low illumination, so they are the best choice for the Saharan environment.

This paper focuses on regulation of the parallel active power filter (APF) Dc Voltage bus by judicious choice of rule bases and intervals for each selected fuzzy variable of suitable fuzzy logic controller. In addition, an algorithm describes the main steps for designing an FLC that has any number of rules with direct application to the APF capacitor voltage regulation. Where their simulation, by MATLAB, applied to PV conversion chain network will be represented in the booths cases, constant and variable non-linear loads after modeling, to show the effectiveness of this kind of regulators on electrical power quality and improve the reliability of the APF on PV system. The delivered voltage of PV plant has been regulated and controlled with MPPT using P&O technique and FLC regulator after modeling of each part of the conversion chain. PV plant supplies a nonlinear load from the rectifier installed on the output of the conversion chain via a controlled power inverter. A 3 × 3 rules fuzzy regulator is implanted in the control part of the APF to examine the influence of the FLC on the produced electrical power quality. Simulation results are represented and analyzed.