COMPLICATED MECHANICAL EQUIPMENT DIAGNOSIS BASED ON BAYESIAN NETWORKS

Chaoquan Chen, Xinrong Li, Xiaolan XIE

ABSTRACT: Mechanical equipment fault diagnosis is a complicated process. Due to the complex structure, the different operating environment, the different detection means and testing equipment, the difference between the operator and other factor, that well lead to many uncertainties. In order to solve these problems, this paper established a Bayesian Network-based mechanical equipment fault diagnosis model. The evaluation function and firefly algorithm are introduced to optimize the model. Introduce a priori knowledge to self-learning during model establishment, reduce the uncertainty caused by the test object information. Improve the reliability of mechanical equipment fault detection, finally verified by an example.

Keywords: Bayesian Network, Firefly algorithm, Mechanical fault, Fault diagnosis