基于PSO-BP的超越离合器磨损预测算法OA

In order to improve the evaluation accuracy of the wear state of the key components of the overrunning clutch,an overrunning clutch wear prediction algorithm based on particle swarm optimization-back propagation(PSO-BP)was proposed.Firstly,a wear finite element model was established based on the ABAQUS finite element simulation platform by combining the Archard wear criterion and introducing the user subroutine UMESHMOTION.By mapping the wear amount to the displacement of the grid nodes,the geometric boundary evolution of the material removal effect and the dynamic update of the wear depth were realized,and the accuracy of the model was verified by experiments.Secondly,on this basis,the key parameters such as cumulative slip distance,instantaneous slip distance,and contact stress were further extracted as inputs,and the wear depth was used as output to construct a PSO-BP prediction model,realizing high-precision prediction of the wear depth of the contact area between the wedge and the inner ring.Comparative analysis shows that,compared with the traditional BP neural network and the GA-BP neural network,the PSO-BP model achieves a fitting accuracy of 99.838％,and its prediction error is more concentrated in the zero error region,reflecting a higher accuracy.