基于多传感器振动信号融合的真空断路器故障诊断

根据真空断路器故障诊断特点,提出了小波包、RBF神经网络与D-S证据理论相结合的决策层信息融合诊断方法。首先,运用小波包—能量谱分析方法对振动信号进行分解处理,提取特征向量,并以此作为诊断的依据;其次,建立神经网络模型,以特征向量为RBF神经网络的输入,进行断路器初步故障诊断;然后将诊断结果作为对各种故障模式的基本概率分配值,利用D-S证据理论,实现对初步诊断结果的融合,从而得到最终的融合诊断结果。实验结果表明,该方法诊断真空断路器故障能取得良好的效果。

Fault Diagnosis of Vacuum Circuit Breaker Based on Multi-sensor for Vibration Signals of Fusion

According to the characteristics of fault diagnosis for vacuum circuit breaker,a decision level information fusion diagnosis method is presented by using wavelet packet,RBF neural network and D-S evidence theory.Firstly,according to the method of wavelet packet-energy spectrum,vibration signals are decomposed and extracted feature vector as a basis for diagnosis;Then,neural network model is established,and the initial diagnosis results are obtained through the RBF neural network;Finally,the diagnosis results are used as the basic probability distribution value to each fault mode,and the D-S evidence theory is applied,and the final fusion diagnosis results are obtained.The experiment shows that the proposed method is effective to diagnose the faults of vacuum circuit breakers.