Search

This paper presents a new scheme for dynamical systems and time series modeling and identification. It is based on artificial neural networks (ANN) and metaheuristic algorithms. This scheme combines the strength of ANN with the dexterity of metaheuristic algorithms. This fusion is renowned for its ability to detect complex patterns, which considerably improves accuracy, computational efficiency, and robustness. The proposed scheme deals with the curve fitting and addresses ANN's local minima problem. This approach introduces the identification concept using a fresh novel identification element, referred to as the error model. The proposed framework encompasses a parallel interconnection of two models. The principal sub-model is the elementary model, characterized by standard specifications and a lower resolution, designed for the data being examined. In order to address the resolution limitation and achieve heightened precision, a second sub-model, named the error model, is introduced. This error model captures the disparities between the primary model and considered data. The parameters of the proposed scheme are adjusted using metaheuristic algorithms. This technique is tested across many benchmark data sets to determine its efficacy. A comparative study along with benchmark approaches will be provided. Extensive computer studies show that the suggested strategy considerably increases convergence and resolution. [ABSTRACT FROM AUTHOR]

Water quality control and monitoring is an important concern of countries over the world. We present in this work, the use the self-organizing feature maps of Kohonen (SOFM) as features selection technique and advanced classification techniques, such as: Long Short-Term Memory (LSTM) and Support Vector Machines (SVM). This study involved the advanced assessment of surface water quality from Tilesdit dam in Algeria. Typically, water quality status is determined by comparing collected data with water quality standards. LSTM and SVM have been applied with SOFM-based features selection for water quality classification. In this work, the training step is realized using the mentioned approaches to supervise the water quality from several physicochemical parameters. Eleven of them were collected in 4 seasons during the period (2016-2018) from study area. Experiments step using a mentioned dataset in terms of accuracy (training and test), running time and robustness, is carried out. The performance of our approach is optimized by regulating the parameter values using a SFOM based features selection method. The proposed approach outperforms current conventional methods, as this approach is a combination of strong feature selection and classification techniques. Optimal input features are selected directly from the original datasets, aiming to reduce the computational time and complexity. The impact of this result is significant both technically (lower learning time) and economically (reduced the number of sensors) and can improve obviously the performance of our monitoring system. The accuracy is more than 98% in training and testing steps with features selection process for the LSTM and SVM models. The best results of sensitivity, specificity, precision, and F-score of the two proposed models were ranged all between 96,99 % and 100%. In a nutshell, the two comparative machine learning methods provide very high classification accuracy and make a considerable solution for water quality control and monitoring. [ABSTRACT FROM AUTHOR]

This paper proposes a sliding mode control strategy for hybrid power system (HPS). The hybrid power system consists of four-leg voltage source Inverter Bridge. The HPS ensures full compensation for harmonic phase currents, neutral current, reactive power compensation and unbalanced nonlinear load currents. The Sliding Mode control strategy with a three dimensional space vector modulation deals with power quality enhancement in standalone power-supply systems with the key objective to compensate for AC side load and phase disturbances that result essentially from the presence of nonlinear and unbalanced loads. The four-leg voltage source inverters play an important role by providing both balanced and unbalanced loads with clean power and balanced output voltage. The simulation results show that the performance of the four-leg HPS with the proposed control algorithm. [ABSTRACT FROM AUTHOR]