Quality–efficiency coupling prediction and monitoring-based process optimization of thin plate parts with multi-machining feature

ABSTRACTQuality and efficiency prediction, as well as coupling optimization, is very important for improving product production. However, most of the researches are studying the quality and efficiency separately, which makes it difficult to improveproduction. Therefore, this paper proposes a quality–efficiency coupling prediction and monitoring-based process optimization method to effectively improve the quality and efficiency of thin plate parts with multi-machining features at the same time. And the best process parameters are recommended to better improve machining stability. Firstly, based on the generalized multi-layer residual network and deep neural network (MLResNet-DNN), the prediction models of quality and efficiency are constructed, respectively. Secondly, the quality–efficiency coupling index is constructed based on coupled permutation entropy (CPE) accordingly. Finally, the process optimization model based on the hybrid artificial bee colony–particle swarm optimization (HABC-PSO) algorithm is established to recommend the best process parameters according to the monitoring results of quality–efficiency CPE. The RMSE average value of the proposed quality and machining time prediction model has an average improvement of at least 10.8% and 25.9%, respectively, than other prediction model. The process parameters recommended by the proposed HABC-PSO method have improved the machining stability of quality and efficiency by at least 25.6%, and machining time is reduced by at least 25.7% compared with other optimization algorithms.KEYWORDS: Quality–efficiency couplingMLResNet-DNNcoupling permutation entropyT-square statisticscoupling monitorprocess optimization Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis work is financially supported in part by the project supported by the National Natural Science Foundation of China (52275507) and in part by the Major Science and Technology Special Project in Shannxi Province of China (2019zdzx01-01-02).