• CN:11-2187/TH
  • ISSN:0577-6686

›› 2002, Vol. 38 ›› Issue (4): 88-90.

• 论文 • 上一篇    下一篇

扫码分享

基于ART——人工免疫网络的多级压缩机故障诊断

杜海峰;王孙安   

  1. 西安交通大学机械工程学院
  • 发布日期:2002-04-15

FAULT DIAGNOSE OF THE RECIPROCATING COMPRESSOR BASED ON ART—ARTIFICIAL IMMUNE NETWORK

Du Haifeng;Wang Sun’an   

  1. Xi’an Jiaotong University
  • Published:2002-04-15

摘要: 为解决多级往复式压缩机故障诊断这一复杂问题,提出了一种基于智能互补融合的智能诊断策。该策略整合了自适应共振网络(ART)和人工免疫网络各自的优点,对数据样本进行浓缩,建立从故障状态空间至解释空间的映射,从而达到故障诊断的目的。另外,还提出新的数据浓缩度量指标——数据蒸发率。对一个四级压缩机的故障诊断结果表明,提出的方法具有诊断率和数据蒸发率高等优点。

关键词: ART, 故障诊断, 人工免疫网络, 往复式压缩机

Abstract: Fault diagnosis of the multilevel reciprocating compressor is very complex. Based on the point view of complementary strategies, a new fault diagnosis’s method which integrates the ART and the artificial immune network is put forward. It can be used to enrich the data. Then the mapping of the causation between the reason and the result can be created, so the diagnosing is accomplished. The step of the new method is discussed detailedly. Additionally, a criterion about the data enriching are put forward. The correctness and the effectiveness of the method are proved by the experiment.

Key words: Artificial immune networ, ART, Fault diagnosis, Reciprocating compressor

中图分类号: