液体火箭发动机故障检测与诊断的反向选择算法  

Negative selection algorithm of fault detection and diagnosis for liquid-propellant rocket engine

作　　者：谢廷峰[1] 刘洪刚[1] 黄强[1] 吴建军[1] 

机构地区：[1]国防科技大学航天与材料工程学院,湖南长沙410073

出　　处：《推进技术》2009年第3期337-341,共5页Journal of Propulsion Technology

基　　金：教育部"新世纪优秀人才支持计划"(NCET-06-0927)

摘　　要：基于生物免疫系统中的反向选择原理,提出了液体火箭发动机地面试车故障检测与诊断的新方法,对检测器的产生、检测器数量的确定以及故障诊断的实现等几个问题进行了分析。基于发动机地面试车数据的验证结果表明,该方法能有效提高算法的训练效率、实时性能和诊断结果的准确性。A new fault detection and diagnosis method for liquid-propellant rocket engine was proposed,based on the negative selection mechanism of biologic immune system.The method was analyzed and improved from some aspects such as the generation of appropriate detectors and utilization in fault diagnosis.Verified results with real ground test data of engines show that the method proposed is effective.It can improve the training efficiency,real-time ability and veracity of fault detection and diagnosis effectively.

关 键 词：液体火箭发动机 反向选择算法+ 故障检测与诊断+ 

分 类 号：V434[航空宇航科学与技术—航空宇航推进理论与工程]