Abstract: A method of intelligent fault diagnosis for a large turbo-pump fed liquid-propellant rocket engine (LRE) is proposed and developed, based on the hybrid knowledge model and hybrid reasoning strategy. The method focuses on difficult problems and techniques suan as unified treatment of LRE knowledge, integration and translation of qualitative and quantitative knowledge, and knowledge based intelligent fault diagnosis reasoning. Results verified by test-firing data and simulated fault samples show that, the method proposed can be available for reference in design and realization of practical LRE fault diagnosis systems.

Key words: Knowledge base;Intelligent fault diagnosis;Liquid-propellant rocket engine

摘要： 以某大型泵压式液体火箭发动机为研究对象,围绕着发动机知识的统一处理、定性定量知识的集成与转化以及基于知识的智能故障诊断推理等技术和难点,研究发展了发动机基于混合知识模型和混合推理策略的智能故障诊断方法,并结合实际热试车数据和故障仿真实例进行了验证。研究结果对设计和实现工程实用的液体火箭发动机故障诊断系统具有重要的参考价值。

关键词: 知识库;智能故障诊断;液体推进剂火箭发动机