中国机械工程

• 机械基础工程 • 上一篇    下一篇

一种基于主成分分析和支持向量机的发动机故障诊断方法

张宇飞1;么子云1;唐松林2;朱丽娜1;张进杰1   

  1. 1.北京化工大学高端机械装备健康监控与自愈化北京市重点实验室,北京,100029
    2.中石油云南石化有限公司,昆明,650011
  • 出版日期:2016-12-25 发布日期:2016-12-28
  • 基金资助:
    国家重点基础研究发展计划(973计划)资助项目(2012CB026005);国家高技术研究发展计划(863计划)资助项目(2014AA041806);中央高校基本科研业务费专项资金资助项目(JD1506) 

An Engine Fault Diagnosis Method Based on PCL and SVM

Zhang Yufei1;Yao Ziyun1;Tang Songlin2;Zhu Lina1;Zhang Jinjie1   

  1. 1. Beijing Key Laboratory of Health Monitoring Control and Fault Self-recovery for High-end Machinery,Beijing University of Chemical Technology,Beijing,100029
    2.Petro China Yunnan Petrochemical Company Limited,Kunming,650011
  • Online:2016-12-25 Published:2016-12-28
  • Supported by:
     

摘要: 提出一种新型的基于主成分分析(PCA)和支持向量机(SVM)的故障诊断方法。首先提取振动信号的多项时域指标,并利用小波包分解提取频域特征;再利用PCA从提取的时域、频域特征中选取敏感特征,实现降维处理,减小数据处理复杂度;最后利用SVM进行特征子集的训练和测试,实现故障分离。该方法在柴油机的失火、撞缸、小头瓦磨损等典型实际故障中的诊断准确率高达98%,证实了该方法的有效性。

关键词: 发动机, 故障诊断, 特征提取, 小波包分解, 主成分分析, 支持向量机

Abstract: A new method was proposed based on PCA and SVM. First of all, the fault characteristics of vibration signals in time domain and frequency features were extracted by wavelet packet decomposition. Then the sensitive characteristics were selected with PCA to achieve dimensionality reduction and to decrease the complexity of data processing. Finally, SVM was used for training and testing of the feature subsets, and realizing the fault separation. Appling this method to typical faults of diesel engine such as misfire, cylinder collision and small head tile wear, the diagnosis accuracy rate is up to 98%, which confirmed the validity of this method.

Key words: engine, fault diagnosis, feature extraction, wavelet packet decomposition, principal component analysis(PCA), support vector machine (SVM)

中图分类号: