In order to solve the problem of fault diagnosis for asynchronous motor rotor and improve the accuracy and efficiency of the diagnosis,a fault diagnosis method based on the least squares SVM and improved particle swarm optimization(PSO) algorithm is proposed.Firstly,by studying the inertia weight strategy of PSO,a nonlinear decreasing inertia weight strategy is given.Then,the improved PSO algorithm is used to optimize the mixed kernel function based on LS-SVM.Finally,the proposed algorithm is used to diagnose the rotor fault.The results show that this algorithm can find the optimal parameters through fewer iterations,which overcomes the defects of local minimum,and improves the diagnostic efficiency and diagnostic accuracy.%针对异步电动机转子的故障诊断问题,为了提高诊断精度和诊断效率,提出基于混合核函数的最小二乘支持向量机与改进的粒子群算法相结合(IPSO-LS-SVM)的故障诊断方法.首先对PSO的惯性权值策略进行研究,给出一种非线性递减惯性权值策略,然后利用改进后的PSO优化基于混合核函数的LS-SVM,最后,应用改进算法完成转子的故障诊断.结果表明,改进算法通过较少的迭代次数即寻找到最优参数,克服了陷入局部极小值的缺陷,诊断效率和诊断精度都得到了提升.
展开▼