摘要
本文首先根据小波包分解原理和应用经验总结出小波包特征量与汽机故障对照表,将其与模糊综合评判和BP网络有机结合在一起,建立了基于小波包特征提取的模糊BP诊断网络模型.采用模糊综合评判技术,使该网络可在少量典型故障样本监督下训练成功,对于缺少机组运行故障知识库的厂家具有推广应用前景.最后举例说明,该网络在汽机诊断中是一种有效的智能分类器.
According to the principle of wavelet packets and its application experience, a correspondent table which embodies the relation between the turbogenerator faults and the features of wavelet packets is established and a new approach based on the table in tandem with fuzzy BP neural network is presented. Owing to employing fuzzy comprehension judgement, the network may be trained successfully with a few standard fault samples and applied in electrical power in-dustry which is short of standard fault samples. It is adopted to process and classify vibration signal of a turbogenerator and the results indicate that it is a useful and effective intelligential classification.
出处
《振动与冲击》
EI
CSCD
1997年第3期30-34,共5页
Journal of Vibration and Shock
基金
国家自然科学基金资助项目.
关键词
机械设备
小波包
模糊综合评判
故障诊断
wavelet packets, fuzzy comprehension judgement, neural network, fault diagnosis, vibration signal
