在随机模糊系统的故障诊断中,信息的不确定性常常会引起系统输出的不确定。针对此问题,本文结合模糊推理及可能性理论提出了一种新的融合故障诊断方法。首先对可能性合成规则进行分析,利用随机模糊变量对传感器信息的不确定性进行表示,利用模糊推理和可能性合成规则对多源不确定性信息进行融合处理,用融合结果进行故障判决,最后以电梯故障诊断为例,对所提方法的有效性进行了验证。 In the stochastic fuzzy system fault diagnosis, the uncertainty of the information often leads to the uncertainty of the system output. To solve this problem, this paper presents a new fusion fault diagnosis method based on fuzzy reasoning and possibility theory. Firstly, the rule of probability synthesis is analyzed, the uncertainty of sensor information is expressed by using random fuzzy variables, the fuzzy uncertainty reasoning and possibility synthesis rules are used to fuse the multi-source uncertainty information, and the fusion result is used to make fault decision. Finally, Taking elevator fault diagnosis as an example, the validity of the proposed method is verified.