Application of BN in the Fault Diagnosis of Brake Failure System
Jian Hui Liu, Jing Lin Zhang, Ming Di Jin · Applied Mechanics and Materials · 2014
To solve the problems caused by the complex failure mechanisms in hydraulic brake failure systems and the uncertain linkages between fault type and fault symptoms, a method of Bayesian network (BN) is offered for failure diagnosis. A statistical strategy is adopted there in this algorithm on the rule base provided by many experts to discard the weak causal relationship rules while keep the relatively strong ones during the BN structure learning, and a BN-based model of layered architecture is established for fault diagnosis of hydraulic braking failure systems. Experimental data analysis shows that the Bayesian network fault diagnosis model has higher accuracy than fuzzy logic diagnosis method, effectively solving the uncertainties in fault diagnosis.