基于优化算法的风机振动故障模拟与诊断

为解决直驱永磁同步风力发电机 (Direct Drive Permanent Magnet synchronous windpower Generator,DDPMG)振动故障数据匮乏和传统算法故障诊断准确率低的问题,根据传统同步发电机振动特性与 DDPMG 相似的特点,采用同步发电机对 DDPMG 进行振动故障模拟,获取DDPMG 模拟振动在不同运行工况下的数据;并利用遗传算法(Genetic Algorithm,GA)分层优化最小二乘支持向量机(Least square Support Vector Machine,LS-SVM)参数的算法进行故障诊断。与未优化的 LS-SVM 诊断对比结果表明:采用优化算法的故障诊断准确率更高,可为后续DDPMG 振动监测与故障诊断技术研究提供参考。

Simulation and diagnosis research on vibration fault of wind power generator based on the optimization algorithm

In order to solve the problems of the vibration fault data shortage and low accuracy offault diagnosis rate in traditional algorithm for direct drive permanent magnet synchronous windpower generator ( DDPMG) vibration fault,according to the trait of traditional synchronousgenerator vibration characteristic is similar to DDPMG,adopts synchronous generator to simulatethe vibration faults of DDPMG,acquires the vibration data of simulating DDPMG under thedifferent operation conditions, using genetic algorithm (GA) hierarchically to optimize theparameters of least square support vector machine (LS-SVM)makes fault diagnosis. Compare withthe no optimization LS -SVM method,the diagnosis result shows that:the accuracy of faultdiagnosis by the optimized algorithm is much higher,it can provide reference for later DDPMGvibration fault monitoring and diagnosis technology research.