摘要
基于统计学习理论的支持向量机是专门研究少样本情况下的统计规律及学习方法,为故障诊断向智能化方向发展提供了途径。本文首先介绍了支持向量机的基本原理;其次提出了一种基于小波包和熵理论的振动信号特征提取方法,即利用小波包分解各节点重构信号的熵值反映信号与正常状态的偏移;最后详细介绍了这种新方法在断路器故障诊断中的具体应用,并与传统神经网络方法相比较。使用结果表明:无论在分类效果,还是学习速度方面,支持向量机都优于神经网络,更适合在断路器机械状态识别中的应用。
In fault diagnosis for HV circuit breakers, the lack of actual samples restricts the development of its diagnosis. Support Vector Machine (SVM), based on the statistical learning theory, can solve this problem. In this paper, the principle of SVM is introduced firstly. Secondly, a new method to process vibration signals is presented. The new method decomposes vibration signals with wavelet packet, and extracts entropy parameters from the restructured signals at the third level. Lastly, the new method and SVM are applied to the fault recognition of circuit breakers, and the usable process is introduced in detail In addition, SVM is compared with the artificial neural network, and the paper concludes that in terms of classification and learning speed, SVM is better than neural network clearly, and SVM is more applicable to fault recognition of circuit breakers.
出处
《电工技术学报》
EI
CSCD
北大核心
2006年第8期53-58,共6页
Transactions of China Electrotechnical Society
关键词
高压断路器
支持向量机
神经网络
故障诊断
HV circuit breaker, support vector machine, neural network, fault diagnosis