The Reliability Analysis of Horizontal Vibration of Elevator Based on Multi-State Fuzzy Bayesian Network

Reliability analysis is one of the important constituent parts of elevator safety evaluation. In order to obtain the exact value of fault probability of components in elevator system, by combining fuzzy theory with Bayesian network approach, we proposed a reliability analysis method of multi-state system based on fuzzy Bayesian networks. By expanding the traditional two-state Bayesian network to multi-state system, multi-state Bayesian network model of horizontal vibration of elevator is established. The language variable of the root probability is transformed into triangular fuzzy numbers under different states. After equalization, defuzzification and normalization, the precision probabilities can be gotten and then introduced to the multi-state Bayesian network model. The posterior probability and the probability importance degree of various root nodes are calculated with multi-state Bayesian network algorithm. The result can provide quantitative evaluation for the reliability of multi-state horizontal vibration of the elevator. Compared with the fuzzy fault analysis method based on T-S, the method we proposed is valid.