高压断路器振声联合故障诊断方法

Vibration and Acoustic Joint Mechanical Fault Diagnosis Method of High Voltage Circuit Breakers

针对现有的高压断路器机械故障诊断方法存在的不足,本文提出了一种新的高压断路器振声联合诊断机械故障的方法。此方法首先利用快速核独立分量分析(fast KICA)对采集到的声波信号进行盲源分离处理,并对处理后的声波信号和采集到的振动信号进行改进集合经验模式分解(EEMD)。其次,对分解后的每一个固有模态函数(IMF)求其二维谱熵,并以此二维谱熵矩阵的变换矩阵作为支持向量机的输入特征向量对断路器机械状态进行识别。最后实验表明,振声联合复合分析方法有效提高了高压断路器机械故障诊断的正确性和实用性。

Based on the existing shortcomings of mechanical fault diagnosis of high voltage circuit breakers, this paper proposes a new method of high voltage circuit breaker mechanical fault diagnosis which based on the joint of vibration signal and acoustic signal. This method first uses fast kernel independent component analysis(fast KICA) to make blind source separation processing for acoustic signals collected, and processed acoustic signals and collected vibration signals should be decomposed by improving the ensemble empirical mode decomposition(EEMD) decomposition. Next is calculated the two-dimensional spectral entropy of the decomposed intrinsic mode function(IMF), and the two-dimensional spectrum entropy matrix transformation matrix is made as input feature vector of the support vector machine to identify mechanical condition of the circuit breaker. The last, the experiments show that vibration signals and acoustic signals joint complex analysis effectively improve diagnostic accuracy and practicality of high voltage circuit breaker mechanical fault diagnosis.