A Predictive Model of Dimensional Deviation Based on Regeneration PSO-SVR with Cutting Feature Weight in Milling

Abstract

Abstract Support vector regression (SVR) optimized by particle swarm optimization (PSO) has low predictive accuracy and premature convergence in milling. To solve this problem, A PSO-SVR model combined with the cutting feature weight was proposed in this paper. Firstly, basing on the SVR, the feature weight was integrated with the kernel function, and added the premature judging to the PSO to improve the global searching ability. Secondly, the mathematical model composed of the cutting force, temperature and cutting vibration was built based on the datasets obtained by experiment. The covariance was calculated to get the characteristic weights of process parameters, which promoted the incremental data in turn. Finally, the predictive model of the dimensional deviation was established based on the promoted PSO-SVR and the result was compared with the general PSO-SVR. The accuracy of the predictive model reached 97.5%. And compared with the predictive model of the general PSO-SVR without feature weighting, the dimensional deviation predictive accuracy and generalization ability of the regeneration PSO-SVR predictive model with feature weighting was improved by 37.75% and 24.5%.