• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2023, Vol. 45 ›› Issue (02): 332-337.

• 人工智能与数据挖掘 • 上一篇    下一篇

基于BA-RVM算法的发动机故障诊断技术研究

陈财森1,胡海荣2,程志炜3,房璐璐1   

  1. (1.陆军装甲兵学院演训中心,北京 100072;
    2.陆军装甲兵学院信息通信系,北京 100072;3.32167部队,西藏 拉萨 850000)
  • 收稿日期:2021-01-05 修回日期:2021-05-20 接受日期:2023-02-25 出版日期:2023-02-25 发布日期:2023-02-16
  • 基金资助:
    国家自然科学基金(U1836101);军委科技委基础加强计划技术领域基金(2019-JCJQ-JJ-31)

Engine fault diagnosis technology based on BA-RVM algorithm

CHEN Cai-sen1,HU Hai-rong2,CHENG Zhi-wei3,FANG Lu-lu1   

  1. (1.Center of Exercise and Training,Army Academy of Armored Forces,Beijing 100072;
    2.Department of Information and Communication,Army Academy of Armored Forces,Beijing 100072;
    3.32167 Troop,Lhasa 850000,China)
  • Received:2021-01-05 Revised:2021-05-20 Accepted:2023-02-25 Online:2023-02-25 Published:2023-02-16

摘要: 发动机是装备动力系统的核心部件,针对传统检测技术在大量故障装备中难以准确快速诊断发动机故障,且诊断工作量大、效率低等问题,提出一种基于BA-RVM算法的发动机故障诊断模型。通过融合典型装甲装备发动机的各项指标,利用采集的参数指标与发动机的故障数据对模型进行训练,使得模型能够基于发动机的参数对故障类型进行预测。在模型训练时,采用蝙蝠算法BA对相关向量机算法RVM的核参数宽度进行优化,得到RVM最优参数的预测模型。最后,以12/200ZL型水冷废气涡轮增压柴油机为对象开展实验。实验结果表明,基于BA-RVM算法的故障诊断错误率比BP算法的降低了66.67%,比SVM算法的降低了62.5%。

关键词: 发动机故障, 蝙蝠算法, 相关向量机算法, 故障诊断

Abstract: Engine is the core component of the armored equipment's power system. Aiming at the problems that the traditional detection technology is difficult to accurately and quickly diagnose the engine fault in a large number of faulty equipment, the diagnosis workload is large, and the efficiency is low, an engine fault diagnosis technology based on the BA-RVM algorithm is proposed. By merging the various parameter index data of typical armored equipment engines, the model is trained by using the data of the acquisition parameter index and the engine fault, so that the model can predict the fault type based on the parameters of the engine. In the model training, the bat algorithm (BA) is proposed to adjust the kernel parameter width of the correlation vector machine algorithm (RVM), so as to obtain the prediction model of the RVM optimal parameters. Finally, the experimental verification of 12/200ZL water-cooled exhaust turbocharged diesel engine is carried out. The experimental results show that, compared with BP algorithm and SVM algorithm, BA-RVM algorithm reduces the error rate of fault diagnosis by 66.67% and 62.5%, respectively.

Key words: engine fault, bat algorithm, correlation vector machine algorithm, fault diagnosis