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。 Engine fault diagnosis and fault isolation are one of the major problems in the field of engine health monitoring. However, it is of great significance to engine fault location, prevention of catastrophic accidents and engine maintenance. In order to accurately determine the location of the fault, this paper presents a method of component-level fault isolation based on the fuzzy model for a certain type of liquid propellant rocket engine. Firstly, the engine system is divided into parts, and then the fuzzy model of each part is established and trained. Finally, the fault is diagnosed according to the set fault detection and isolation strategy. Two groups of engine fault simulation data are used to verify the fault isolation method based on the fuzzy model component level. The results show that this method can achieve single or multiple fault isolation.