Objective To enhance the reliability of medical equipment, this study aims to develop a failure cause diagnosis model and provide rational suggestions for efficient equipment use.

Methods Combine fault tree analysis (FTA) to identify basic events causing equipment failure and calculate their prior probabilities. Obtain conditional probability tables for each node through expert assessment. Integrate triangular fuzzy number theory with Bayesian networks (BN) to construct a fuzzy Bayesian network (FBN) for posterior probability inference and sensitivity analysis.

Results Using endoscopes as the subject, the analysis shows that the model accurately calculates the endoscope failure probability at 0.385%, and identifies the key causes: improper cleaning (X5, posterior probability 0.36064), untimely fault detection (X8, posterior probability 0.23571), irregular transportation (X6, posterior probability 0.11344), and natural aging (X10, posterior probability 0.11377). Sensitivity analysis also confirms their influence weights (mutual information values are 0.00749, 0.00591, 0.00202, 0.00174 ).

Conclusion The model can accurately perform quantitative analysis and rapid fault location of medical equipment failures, enabling effective preventive measures.