基于模糊模型的发动机部件级故障隔离方法研究

Research of fault component isolation algorithms for LRE base on fuzzy model

发动机故障诊断与故障隔离是发动机健康监控领域的一大难题,但对发动机故障定位、预防灾难性事故发生及发动机维修意义重大。为了准确地确定故障发生的部位,本文针对某型液体火箭发动机,提出一种基于模糊模型的部件级故障隔离方法。首先对发动机系统进行部件的划分,然后建立各个部件的模糊模型并进行训练,最后按照设定的故障检测与隔离策略对故障进行诊断。利用两组发动机故障仿真数据对基于模糊模型部件级故障隔离方法进行验证,结果表明:本方法可以实现单一或多个部件故障隔离。

Fault detection and diagnosis is a difficult problem in liquid-propellant rocket engines （LRE） healthy monitoring, but it has important significance for locating an engine fault, preventing tragedy accident from occurring, and maintaining engines. So a fault isolation method in components level based on fuzzy model was proposed to confirm the position of the fault for certain Liquid-propellant rocket engines. Firstly, it divided the engine into several components ; secondly the fuzzy model for each component was established and trained; finally the method performed fault diagnosis according to established strategy. The fault isolation algorithm based on fuzzy model was validated by two sets of simulation data. The results indicate that fault isolation algorithm can isolate single fault or multi-fauh components effectively.