自适应蝙蝠算法优化PF的风力机桨距系统故障诊断方法

FAULT DIAGNOSIS METHOD FOR PITCH SYSTEM OF WIND TURBINES BASED ON ADAPTIVE BAT ALGORITHM OPTIMIZED PF

针对粒子滤波(PF)在变桨距系统故障诊断中存在的样本贫化现象导致故障诊断精度低的问题,提出一种蝙蝠算法自适应优化粒子滤波的故障诊断方法。通过改进的蝙蝠算法优化粒子滤波的采样过程,并结合最新的观测值定义粒子适应度函数,引导粒子整体向高似然区域移动;同时引入一个动态自适应惯性权重来设计新的粒子全局搜索位置更新机制,自适应调整粒子的全局搜索与局部搜索能力的有效协调,改善粒子贫化及陷入局部极值的问题,以期提高粒子群对故障状态的估计性能。通过对风力机桨距系统执行器和传感器故障诊断的仿真分析,表明该方法可有效提高故障诊断的准确性。

Aiming at the problem of low accuracy for fault diagnosis due to the sample impoverishment phenomenon exist in traditional particle filter（ PF） in the fault diagnosis of the variable pitch system,a fault diagnosis method based on adaptive bat algorithm optimizing particle filter is proposed. Combined the sampling process of optimizing particle filter by the improved bat algorithm with the latest observation to define the fitness function to guide the particle to move to the high likelihood region. At the same time,the dynamic adaptive inertia weight design is introduced to design a new global search position update mechanism,the balance between global search and local search ability is adjusted adaptively. Alleviating the phenomenon of particle impoverishment and avoiding local extremal,and the estimation performance of particle swarm to fault state is improved. Through the simulation analysis of actuator and sensor fault diagnosis of wind turbine pitch system,it is shown that this method can effectively improve the accuracy of fault diagnosis.