基于AFSA优化级联随机共振的轴承故障诊断方法

Bearing Fault Diagnosis Method Based on Cascaded Stochastic Resonance Optimized by AFSA

针对航空发动机转子系统中轴承故障诊断困难的问题,提出基于人工鱼群算法(AFSA)优化的级联随机共振轴承故障诊断方法。建立1个2级级联随机共振系统对轴承微弱故障信号进行增强,以故障信号的输出信噪比为优化目标函数,采用AFSA算法同步优化双稳态随机共振系统的结构参数a和b,采用优化后的级联随机共振系统分别处理仿真信号和试验信号,提取故障特征频率验证算法的有效性。结果表明:所建立的故障诊断算法具有良好的滤波降噪特性,提取的滚动轴承故障特征频率与理论值的误差小于0.1%。

Aiming at the difficulty of bearing fault diagnosis in aeroengine rotor system,a bearing fault diagnosis method was proposed based on cascaded stochastic resonance optimized by Artificial Fish Swarm Algorithm(AFSA). A 2-stage cascade stochastic resonance system was established to enhance the weak fault signal of bearing. Taking the output Signal-to-Noise Ratio(SNR) of the fault signal as the optimization objective function,the structural parameter a and b of the bistable stochastic resonance system were optimized synchronously by AFSA algorithm. The simulation signal and the test signal were processed by the optimized cascade stochastic resonance system,and the validity of the algorithm was verified by extracting the fault characteristic frequency. The results show that the fault diagnosis algorithm has good characteristics of filtering and noise reduction,and the error between the calculated value and the theoretical value of fault characteristic frequency of the extracted rolling bearing is less than 0.1%.