A Nonlinear Flux Linkage Model for Bearingless Induction Motor Based on GWO-LSSVM

Abstract

The flux-linkage characteristics of bearingless induction motors (BIMs) are nonlinear, and the models established by the general analytical method cannot accurately reflect the actual characteristics of BIMs. Thus, a novel method for nonlinear modeling of BIM flux linkage is proposed in this paper. The main objective of this method is to improve the accuracy of the flux linkage model based on the least square support vector machine (LSSVM) technique by applying the gray wolf optimization (GWO) algorithm to determine the optimal kernel parameter and regularization parameter of the LSSVM automatically. In this method, all BIMs flux linkage data are obtained from the finite-element method. In this paper, the relationship between input and output of the nonlinear flux linkage model is studied, and the precision model of GWO-LSSVM flux linkage is obtained. The simulation results demonstrate that the GWO-LSSVM model has high prediction accuracy and strong prediction ability. In addition, the GWO-LSSVM model is compared with other models. From this simulation comparison, it can be concluded that GWO-LSSVM modeling has the characteristics of higher accuracy. INDEX TERMS Bearingless induction motor, gray wolf optimization, least squares support vector machine, nonlinear model, finite element analysis.

A Hybrid Model for Short-term PV Output Forecasting Based on PCA-GWO-GRNN

“…The GWO algorithm is a swarm intelligence algorithm proposed by [30] with good self-organizing learning ability, simple parameters, easy implementation, and good global searchability [31], [32]. And by comparing with other four famous meta-heuristic algorithms (PSO algorithm, gravity search algorithm, differential evolution algorithm and fast evolutionary programing algorithm) on 29 test functions, the simulation test proves its superiority.…”

Least square support vectors machines approach to diagnosis of stator winding short circuit fault in induction motor

“…LS-SVM is based on concepts of machinery learning. For that we establish the model on two steps:  training  test In the first step, we consider a given training set [15][16][17][18][19][20] as follows:…”

“…However, the more used kernel function is RBF, a simple Gaussian function. It is defined by (16).  sv 2 is the squared variance of the Gaussian function.…”

Heterogeneous wireless sensor network routing protocol for an adaptive gray wolf optimizer

“…As a typical cluster intelligent optimization algorithm, GWO [30] simulates the predation behavior of the grey wolf population, and compares the wolf group tracking process with the prey as the optimization process, so as to achieve the optimal solution. Applying GWO to the cluster head optimization problem of WSNs, the position of the wolf group represents the position of the sensor.…”