基于PSO-LSSVM算法的表面粗糙度预测模型与应用

为便于选取合适的切削参数,以满足期望的加工表面质量要求,提出一种最小二乘支持向量机(LSSVM)和粒子群优化(PSO)相结合的表面粗糙度预测模型。以预测精度和收敛速度为指标,对比PSO-LSSVM模型与支持向量机、人工神经网络和遗传算法优化BP神经网络模型的优劣。结果表明:PSO-LSSVM模型具有较高的预测精度和较快的收敛速度。基于MATLAB GUI搭建了表面粗糙度预测与参数优化应用系统。该系统具有较好的实用性,可实现简单、快速预测表面粗糙度,帮助决策人员灵活选取切削参数。

Surface Roughness Prediction Model and Application Based on PSO-LSSVM Algorithm

For the purpose of selecting appropriate cutting parameters to meet desired surface quality requirement, a surface roughness prediction model based on least square support vector machine (LSSVM) and particle swarm optimization (PSO) was proposed. The prediction accuracy and convergence speed were used as indicators, the PSO-LSSVM model was compared with support vector machine, artificial neural network and genetic algorithm based back-propagation neural network model. The results show that PSO-LSSVM model has a relatively higher prediction accuracy and faster convergence speed. A surface roughness prediction and parameter optimization application system was developed based on MATLAB GUI. The application system has good practicability, so simple and fast prediction of surface roughness can be realized and it helps decision makers to select cutting parameters flexibly.