基于QGA-SVR的工件表面粗糙度预测和分析

在自动化生产中建立难加工材料的表面质量预测模型,是实现可持续制造的基础。提出一种结合量子遗传算法和支持向量回归(Quantum genetic algorithm-Support vector regression,QGA-SVR)的已加工表面粗糙度预测模型,改进了现有寻优方法在搜索支持向量回归的模型参数易陷入局部最优解的问题。在量子门更新的过程中加入交叉和变异的操作,保证了模型全局搜索能力,为了提高支持向量回归的泛化能力,在参数优化过程结合了K-折叠交叉验证。结合干车削304不锈钢的切削试验以及现有的铣削实验数据,对比分析了基于量子遗传算法和遗传算法的支持向量回归模型。结果表明:QGA-SVR具有收敛速度快、预测精度高的优点,基于建立的QGA-SVR模型分析了切削参数对车削表面粗糙度的影响规律。

Prediction and Analysis of Workpiece Surface Roughness Based on QGA-SVR

Establishing a surface quality prediction model for difficult-to-machine materials in automated production is the basis for sustainable manufacturing. A prediction model for processed surface roughness was proposed combining quantum genetic algorithmand support vector regression (QGA-SVR), by which the problem was improved that the existing optimization method was easy to fall into local optimal solution when the model parameters of the search support vector regression were searched. The intersection and mutation operations were added in the process of quantum gate updating to ensure the global search ability of the model. In order to improve the generalization ability of support vector regression, the K-folding cross validation was combined in the parameter optimization process. The support vector regression models based on quantum genetic algorithm (QGA) and genetic algorithm (GA)were compared and analyzed by combining the dry turning 304 stainless steel test data and the existing milling experiment data.The results show that QGA-SVR has the advantages of fast convergence and high prediction accuracy. Based on the established QGA-SVR model, the influence law of cutting parameters on the turning surface roughness was analyzed