›› 2012, Vol. 32 ›› Issue (5): 173-176.DOI: 10.3969/j.issn.1006-1335.2012.05.039

Previous Articles     Next Articles

Fault Diagnosis for Valve Train of Diesel Engines Based on Exhaust Noise

YIN Gang1,ZHANG Ying-tang1, LI Zhi-ning1,LI Jie-Ren2,ZHANG Guang1   

  1. ( 1. Department of Guns Engineering,  Ordnance Engineering College,  Shijiazhuang  050003,  China;2. Agent Room of Wuhan Army Force Nanyang District,  Nanyang  474678,  Henan  China )
  • Received:2011-11-14 Revised:2012-02-20 Online:2012-10-18 Published:2012-10-15

基于排气噪声的柴油机气阀故障诊断

尹 刚1张英堂1李志宁1李杰仁2张 光1   

  1. ( 1. 军械工程学院  火炮工程系,  石家庄  050003;  2. 武汉军代局  南阳军代室,  河南  南阳  474678 )
  • 通讯作者: 尹刚
  • 基金资助:

    军内科研项目;河北省自然科学基金资助项目(编号: E20007001048)

Abstract: The auto-regressive(AR) model of exhaust noise in diesel engine’s seven operating modes about the valve train was established. The auto-regressive parameters were regarded as the characteristic vectors to build the fault diagnosis model which was based on extreme learning machine. The proposed method was also compared with that of BP neural network, RBF neural network and support vector machine. Experimental results show that exhaust noise can be used for fault diagnosis in diesel engine’s value train. The classification accuracies of above four different intelligent methods are all higher than 95%. But the method of extreme learning machine has advantage apparently in training rate.

Key words: acoustics , exhaust noise , extreme learning machine , fault diagnosis , diesel engine , AR model

摘要: 通过对柴油机气阀机构七种状态下的排气噪声信号建立AR模型,以AR模型的自回归参数作为故障识别的特征向量,建立基于极限学习机的柴油机气阀故障诊断模型,并与反向传播神经网络算法、径向基网络算法和基于支持向量机的诊断模型相比较。试验结果表明,排气噪声信号可用于柴油机气阀故障的诊断,且基于极限学习机的诊断模型与其他三种算法的分类正确率均可达到95 %以上,但在学习速度上,极限学习机具有明显的优势。

关键词: 声学, 排气噪声, 极限学习机, 故障诊断, 柴油机, AR模型

CLC Number: