摘要
对缸盖振动信号进行二进小波分解 ,从分解后的尺度 1信号中提取诊断特征参数 ,利用这些诊断参数及改型的ART网络对气阀机构进行故障诊断与识别 ,取得了较好的效果。
Vibration signal measured on cylinder head was analyzed and processed with wavelet decomposition algorithm. The energy and energy percentages of different segments in time domain on scale 1 signal were worked out. These parameters and the ART network were used to carry out the clustering of different valve train states. The results show that it can carry out the diagnosing for valve train effectively and concisely.
出处
《机械》
2001年第6期17-19,共3页
Machinery
关键词
振动
故障诊断
内燃机
ART网络
神经网络
vibration
fault diagnosis
internal combustion engines
Adaptive Resonance Theory (ART)
