基于Choquet模糊积分的水电机组振动故障诊断

张彼德;田源;邹江平;刘秀峰;吴华丰;隆力

振动与冲击 ›› 2013, Vol. 32 ›› Issue (12) : 61-66.

PDF(874 KB)
PDF(874 KB)
振动与冲击 ›› 2013, Vol. 32 ›› Issue (12) : 61-66.
论文

基于Choquet模糊积分的水电机组振动故障诊断

  • 张彼德1,田源1,2,邹江平1,刘秀峰1,吴华丰2,隆力2
作者信息 +

Vibration Fault Diagnosis of Hydro- generating Unit Base on Choquet Integrate

  • ZHANG Bide1 TIAN Yuan1,2 Zou jiangping1 LIU Xiufeng1 Wu Huafeng2 Long Li2
Author information +
文章历史 +

摘要

为提高水电机组故障诊断的准确性,提出了基于Choquet模糊积分融合的多分类器组合故障诊断方法,对朴素贝叶斯分类器进行了基于属性相似度的加权改进,得到基于属性相似度的加权朴素贝叶斯分类器(Attribute Similarity Weighted Naive Bayes Classifier,简称SWNBC),并应用基于Mahalanobis距离的分类器(Mahalanobis Distance Classifier,简称MDC)与BP神经网络( BP neural network)组合成为SWNBC+MDC+BP的多分类器组合模型,以小波包提取的相关频带能量作为输入特征向量,应用组合模型对水电机组故障进行诊断,采用模糊积分法来决定最终的故障类型。实验结果表明该模型相对于单一的分类器,能有效提高识别故障的精度。

Abstract

A new method of Vibration hydro-generating Unit fault diagnosis was proposed base on Choquet Integrate combined classifier for improve fault diagnosis accuracy, improve Naive Bayes Classifier base on Attribute Similarity Weighted Naive Bayes Classifier(SWNBC),use Mahalanobis Distance Classifier(MDC) and BP neural network (BP) composed combined classifier SWNBC+MDC+BP, wavelet packet extraction of related band energy as input characteristic vector.Applicate combined classifier for fault diagnosis, fuzzy integral to make the final fault type. The simulation experiment shows that the model is better than the single classifier, can effectively identify fault.

关键词

水电机组 / 故障诊断 / 加权贝叶斯 / 模糊积分

Key words

Hydro-generating Unit / Fault diagnosis / Weighted Naive Bayes Classifier / Fuzzy integrate

引用本文

导出引用
张彼德;田源;邹江平;刘秀峰;吴华丰;隆力. 基于Choquet模糊积分的水电机组振动故障诊断[J]. 振动与冲击, 2013, 32(12): 61-66
ZHANG Bide TIAN Yuan; Zou jiangping LIU Xiufeng Wu Huafeng Long Li. Vibration Fault Diagnosis of Hydro- generating Unit Base on Choquet Integrate[J]. Journal of Vibration and Shock, 2013, 32(12): 61-66

PDF(874 KB)

855

Accesses

0

Citation

Detail

段落导航
相关文章

/