Prediction of drill flank wear using ensemble of co-evolutionary particle swarm optimization based-selective neural network ensembles

Abstract

Flank wear prediction plays an important role in achieving improved productivity and better quality of the product. This study presents an effective co-evolutionary particle swarm optimization-based selective neural network ensembles (E-CPSOSEN) enabled tool wear prediction model for flank wear prediction in drilling operations. The E-CPSOSEN algorithm utilized two populations of particle swarm optimizations (PSOs) that are co-evolved simultaneously, one discrete particle swarm optimizations for evolving the binary selection vector, and the other continuous particle swarm optimizations for evolving the real weight vector. The two PSOs interact with each other through the fitness evaluation. The E-CPSOSEN algorithm is first tested on four benchmark problems taken from the literature. Upon achieving good results for test cases, the E-CPSOSEN enabled tool wear prediction model was employed to three illustrative case studies of flank wear prediction in drilling operations. Significant improvement is also obtained in comparison to the results already reported in literatures, which further reveals that the E-CPSOSEN enabled tool wear prediction model has more wonderful prediction performance than conventional single ANN-based models in predicting the flank wear in drilling operations. Moreover, an investigation was also conducted to identity the effects of the major parameters of the E-CPSOSEN algorithm upon its prediction performance. From the given results, the proposed enabled tool wear prediction model may be a promising tool for the accurate and automatic prediction of flank wear in drilling operations.