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 fault components effectively. 