Abstract

As a power element of the hydraulic system, the health state of the plunger pump affected the working condition of the system, and it is necessary to predict the health state. In this paper, the belief rule base (BRB) is used to fuse multi-source information and develop a health state prediction model of the plunger pump. Forecasting values of indicators are obtained by introducing Long Short-Term Memory (LSTM) to provide input information for BRB. The experts construct the indicator system and establish the BRB based on the system mechanism and knowledge. The projection covariance matrix adaption evolution strategy (P-CMA-ES) algorithm is used to optimize the model parameters and reduce the errors caused by the uncertainty of expert knowledge. The validity and superiority of the proposed model are verified by taking a certain type of plunger pump as an example.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call