Research on a Fault Diagnosis Method of a Belt Conveyor
Aiming at the problems of fuzzy,incomplete and low precision of belt conveyor fault diagnosis information collection,a multi-information fusion belt conveyor fault diagnosis method is proposed.Adopt two means of sound signal and infrared image for information acquisition,use BP neural network for data processing,and fuse the whale algorithm to improve the correct rate of fault diagnosis;take 500 groups of belt conveyor feature vectors,300 groups of training data,150 groups of test data,the maximum number of iterations is 100,and the dimensionality is 3 data samples were respectively used for sound signal fault diagnosis and infrared image Fault diagnosis is experimented,and the results show that the BP neural network optimised by the whale algorithm has the smallest error and the highest accuracy rate,which meets the needs of belt conveyor fault diagnosis.
belt conveyorfault diagnosissoundinfraredBP neural networkwhale algorithm
NETL
NSTL
万方数据
