Transformer fault diagnosis based on Improved Particle Swarm Optimization to support Vector Machine

Abstract

Power transformer fault diagnosis exerts a vital part in the safe operation of power system. The PSO-SVM based on transformer fault diagnosis still has some shortcomings, such as slow convergence speed and easy to fall into local optimization. This dissertation proposes a transformer diagnosis method based on Improve Particle Swarm Optimization to support Vector Machine (MPSO-SVM). Adding disturbance to Particle swarm optimization (PSO) to disturb the position of such precocious particles, so as to get rid of local optimum. The case analysis represents that the diagnostic accuracy of MPSO-SVM is higher than that of PSO-SVM and Generalized Regression Neural Network (GRNN), and MPSO-SVM can effectively promote the fault diagnosis performance of transformer.

Fault diagnosis of electric vehicle drive motor system based on BP neural network algorithm

“…BP neural network model is built in python environment [9][10], and 16 kinds of fault data after wavelet packet preprocessing are imported into the algorithm model. The simplest single-layer structure is selected for the hidden layer, and the number of nodes is set to 16 according to the empirical formula; The output layer is set to 16 according to the fault category; Set the learning rate to 0.001; Set the maximum number of workouts to 100.…”

Rolling Bearing Fault Diagnosis Based on WOA-VMD-MPE and MPSO-LSSVM

“…The particle swarm optimization (PSO) algorithm is a global optimization algorithm with an efficient search function. However, it is easy to fall into the local optimum, the accuracy decreases in the late iteration, and the convergence speed is slow when searching for the best [ 39 ], so this paper proposes the improved particle swarm optimization (MPSO) algorithm. MPSO adopts linear decreasing weights and time-varying learning factors to optimize PSO, which improves the search ability and convergence speed of the algorithm.…”

A Transformer Fault Diagnosis Based on Improved Squirrel Search Algorithm and Support Vector Machine

“…Yu et al used de and modified Sparrow Search Algorithm to optimize SVM, but it did not study the defects of DE, and the diagnosis performance of this model were not significantly improved [9]. Wu et al used the mutation perturbation formula to improve Particle Swarm Optimization to optimize SVM, but it only improved the position update formula of PSO, which cannot significantly reduce the speed of diagnosis [10]. DE is used to improve Imperialist Competitive Algorithm by Zhang et al to optimize SVM.…”