摘要
Abstract
Targeting the characteristics of mechanical vibration signals of high voltage circuit breaker , and there exists limitless for any signal fault feature to achieve the accurate diagnosis needs the whole diagnosis state area , a new method based on improved distance evaluation technique and multi-class support vector machine (MSVM) to diagnosis fault for high voltage circuit breaker is presented , and the method consists of three stages. Firstly, different features, including time-domain statistical characteristics, frequency-domain statistical characteristics, and empirical mode decomposition (EMD) energy entropies and wavelet packet transform (WPT) energy, are extracted to acquire more fault characteristic information. Second, an improved distance evaluation technique is proposed, and with it, the most superior features are selected from the original feature set. Finally , the most superior features are fed into MSVM with strategy of binary tree for estimating fault type. The experimentation shows that the method is effective to diagnose the faults of high voltage circuit breaker.关键词
高压断路器/能量熵/支持向量机/故障诊断Key words
high voltage circuit breaker/energy entropy/support vector machine/fault diagnosis
