基于IEM-FA优化LSSVM的风机主轴轴承故障诊断研究

Research on Wind Turbine Main Shaft Bearing Fault Diagnosis Based on IEM-FA Optimized LSSVM

针对基本萤火虫算法(FA)易陷于局部最优值和搜索速度慢的问题,文章提出了一种改进的萤火虫算法(IEM-FA)。在种群迭代过程中加入振荡因子更新固定步长和细化扰动项,并利用IEMFA算法优化最小二乘支持向量机(LSSVM)的参数。测试结果表明,IEM-FA算法优化LSSVM的诊断模型模型可以准确、高效地对风机主轴轴承进行故障诊断。

According to the problem that the firefly algorithm(FA)is prone to local optimal value,and the slow speed of searching,an improved firefly algorithm(IEM-FA)is proposed.In the process of population iteration,oscillation factor was added to update the fixed step size and refine the disturbance term,and the parameters of the Least Squares Support Vector Machine(LSSVM)were optimized using the IEMFA algorithm.The test results show that the diagnosis model of LSSVM optimized by IEM-FA algorithm can diagnose the failure of the wind turbine main shaft bearing accurately and effectively.