Search

Abstract This paper explores artificial intelligent training schemes based on multilayer perceptron, considering back propagation and genetic algorithm (GA). The hybrid scheme is compared with the traditional support vector machine approach in the literature to analyze both fault and normal scenarios of a centrifugal pump. A comparative analysis of the performance of the variables was carried out using both schemes. The study used features extracted for three decomposition levels based on wavelet packet transform. In order to investigate the effectiveness of the extracted features, two mother wavelets were investigated. The salient part of this work is the optimization of the hidden layers numbers using GA. Furthermore, this optimization process was extended to the multilayer perceptron neurons. The evaluation of the model system performance used for the study shows better response of the extracted features, and hidden layers variables including the selected neurons. Moreover, the applied training algorithm used in the work was able to enhance the classifications obtained considering the hybrid artificial intelligent scheme been proposed. This work has achieved a number of contributions like GA‐based selection of hidden layers and neuron, applied in neural network of centrifugal pump condition classification. Furthermore, a hybrid training method combining GA and back propagation (BP) algorithms has been applied for condition classification of a centrifugal pump. The obtained results have shown the good ability of the proposed methods and algorithms.

This study investigates the transient performance of two variable speed wind turbines (VSWTs), namely doubly fed induction generator (DFIG) and the permanent magnet synchronous generator (PMSG), that are widely employed in wind energy conversion, considering their machine parameters. The machine parameters of both wind turbines were changed considering different scenarios, while keeping other parameters constant, to study the behavior of the wind generators. This study was carried out using the same operating conditions of rated wind speed, based on the characteristics of both wind turbine technologies. The wind turbines were subjected to a severe three phase to ground bolted fault to test the robustness of their controllers during grid fault conditions. Efforts were made to carry out an extensive comparative study to investigate the machine parameters that have more influence on the stability of the different wind turbines considered in this study. Simulations were carried out using power system computer-aided design and electromagnetic transient including DC (PSCAD/EMTDC). Effective machine parameter selection could help solve fault ride-through (FRT) problems cost-effectively for both VSWTs, without considering the external circuitry of and changing the original architecture of the wind turbines.