Equipment Health Status Assessment Based on Belief Rule Base and Hidden Markov Mode

In order to solve the problems of high dimension and large scale of multi-sensor monitoring data and low-accuracy prediction in the remaining useful life (RUL) of nonlinear degradation equipment, a degradation index construction method based on Hidden Markov model (HMM) is proposed, and combined with the belief rule base (BRB) reasoning method to evaluate the health status and realize the RUL prediction. Firstly, the Gaussian HMM is established by taking a variety of performance parameters in the equipment life cycle as the observation vector, and then the equipment performance degradation process is simulated. Secondly, the degradation index is used as the label to train the BRB model, and then the automatic evaluation of equipment health state can be realized. Finally, the RUL is calculated by the BRB-HMM hybrid model. To validate the effectiveness and feasibility of the proposed approach, a case study is carredout on the NASA's commercial modular aero-propulsion system simulation datasets.