AUTHOR=Xu Feifei , Liu Yang , Wang Lei 

TITLE=An improved ELM-WOA–based fault diagnosis for electric power

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1135741

DOI=10.3389/fenrg.2023.1135741

ISSN=2296-598X

ABSTRACT=Due to the fast learning speed, the extreme learning machine (ELM) plays a very important role in the real-time monitoring of electric power. However, the ELM initial weights and thresholds are randomly selected, the network performance is difficult to achieve the optimal, in addition, there is lack of distance selection when detecting faults using artificial intelligent algorithm. To solve above problem, we presented a fault diagnosis method for microgrid based on whale algorithm optimization extreme learning machine (WOA-ELM). Firstly, the wavelet packet decomposition is used to analyze the three-phase fault voltage, and the energy entropy of the wavelet packet is calculated to form the eigenvector as the data sample; then, we used original ELM model coupled with theory of distance selection to locate fault, and compared it with SVM method; finally, the whale algorithm is used to optimize the input weight and hidden layer neuron threshold of ELM, i.e., WOA-ELM model, which solves the problem that the random initialization of the input weight and hidden layer neuron threshold easily affects the network performance, further improves the learning speed and generalization ability of the network, and is conducive to the overall optimization. Results show that (i) the accuracy of selecting data according to the fault distance is twice that of without selecting; (ii) compared with BP neural network, RBF neural network and ELM, the fault diagnosis model based on WOA-ELM has faster learning speed, stronger generalization ability and higher recognition accuracy; (iii) after optimization of WOA, WOA-ELM can improve 22.5% accuracy in fault detection compared to traditional ELM method. Our results are of great significance for improving the security of smart grid.