This paper presents a genetic algorithm-based maximum power point tracking (MPPT) technique for wind power systems. The proposed method aims to overcome the drawbacks of the well-known perturb and observe (P& O) algorithms, such as oscillation around the maximum power point (MPP) and overall system stability. Given the non-linear mathematical model of wind turbines, intelligent search algorithms (ISAs), such as genetic algorithms, are well-suited for MPPT applications. The proposed method is designed to be computationally efficient and has a simple structure for ease of implementation. Simulation results, obtained using the MATLAB/SIMULINK environment, are compared between the proposed genetic algorithm-based MPPT and the traditional P& O technique under a typical day of data measured on the Morne à Cabrit site (Region east of Port-au-Prince, Haiti). The results demonstrate that the proposed technique rapidly tracks the MPP while significantly reducing steady-state oscillation.
The article is dedicated to the problems that arise during the operation of individual heating points associated with the frequent failure of control valves. An individual heating point is a component of a district heating system that connects the main network with the building’s own heating system. At the initial stage, a mathematical model of an operating facility was developed and investigated, the temperature of the coolant of which is controlled using a control valve available at the facility. As an alternative option to increase the reliability of the object as a whole, it is proposed to use a frequency-controlled electric drive, instead of a control valve operating according to the developed optimal algorithm. The implementation of the proposed solution will not require a change in the layout of the room, since it is proposed to install a frequency converter on a pump already present in the structure of an individual heating point. The solution and study of the task was carried out by simulation modeling in the Matlab Simulink environment. The results obtained allow us to conclude that the proposed solution is appropriate.
Based on the increasing use of a Proton Exchange Membrane-Fuel Cell (PEM-FC) stack, and starting from a benchmark that has such a power generation structure including a battery, this article presents the global architecture of the proposed system and its main components, where the general objective is to keep the V DC voltage of the DC type circuit constant. Due to the long response time of the PEM-FC stack for internal thermodynamic reasons, in the proposed system, we present the improvement of the performance for the Proportional Integral (PI) controller of the DC-DC converter by using a Computational Intelligence-Ant Colony (CI-ACO) algorithm for obtaining the optimal values of the tuning parameters for the PI controller, but also by using a Reinforcement Learning -Twin-Delayed Deep Deterministic Policy Gradient (RL-TD3 agent), which through the correction signals provided contributes to obtaining superior control performance. The comparative verification of the performance for the proposed control systems was performed in the Matlab/Simulink programming environment.
Power quality issues can arise in an electrical grid due to various factors, and one of the most common issues is harmonic distortion. Harmonics are essentially sinusoidal signals at frequencies that are multiples of the fundamental frequency, and they can occur when nonlinear loads such as variable speed drives, electronic ballasts, and computer power supplies are connected to the grid. The integration of large-scale photovoltaic (PV) systems into the electrical grid has led to an increase in harmonic distortion, which can affect the stability and reliability of the grid. In this paper, we use ETAP software to analyze the impact of large-scale PV integration on the harmonic distortion in the grid. A model of the PV system is created in ETAP, and a harmonic analysis is performed to determine the harmonic content of the system. The results show that the large-scale PV system generates significant levels of harmonic distortion. To mitigate the impact of the harmonics generated by the PV system, various mitigation techniques are analyzed. Passive filters were sized, implemented in the electrical network, and tested using ETAP as well as capacitor banks to mitigate the resonance impact.
The growing interest in electric vehicles has led to an increased focus on the development of efficient and reliable electric motors. To ensure reliable operation, it is essential to incorporate on-board diagnostic and prognostic tools that can detect and predict potential failures. This paper proposes an approach to diagnose and predict the health condition of induction motors used in electric vehicle powertrain applications using machine learning techniques. The proposed approach utilizes vibration signals collected from accelerometers attached to the motor and employs decision forest and decision tree algorithms to classify the health condition of the motor. The study aims to identify the most significant features of the vibration signals and evaluate the effectiveness of the proposed approach in diagnosing and predicting the health of the motor. The models are trained on full extracted features and selected features using Principal Component Analysis (PCA) and Correlation Analysis (CA) to improve the classification performance. The experimental results demonstrate that the combination of selected features using PCA with the Decision Forest (DF) algorithm achieves the best classification performance for the simulated motor fault conditions. This suggests that machine learning techniques can be effective in diagnosing and predicting the health of induction motors used in electric vehicle powertrain applications.
