薄壁件不一致刀齿铣削时铣削力系数构造与预测

发布时间：2018-07-28 09:32

【摘要】：针对薄壁件铣削过程中刀齿半径不一致现象引起的铣削力系数计算失真问题,提出构造刀齿半径不一致时的实际铣削力系数,并采用核偏最小二乘法对不同铣削用量时的实际铣削力系数进行预测。针对两齿螺旋铣刀铣削过程推导理论铣削力系数,根据刀齿半径不一致铣削过程引入名义铣削力,推导刀齿半径误差,构造实际铣削力系数;基于核分析方法突出的非线性分析及预测能力,提出采用核偏最小二乘法在高维空间建立实际铣削力系数关于铣削用量及其组合量的预测模型,分析该方法中核主元个数、高斯核函数核参数对预测模型精度的影响并确定其取值范围。最后分析考虑刀齿半径误差与不考虑时的铣削力系数,并比较核偏最小二乘预测方法与偏最小二乘预测方法,结果表明所提铣削力系数构造过程及预测方法具有较高的计算精度和预测能力。
[Abstract]:In view of the distortion of the calculation of milling force coefficient caused by the inconsistency of cutter tooth radius during thin-walled parts milling, the actual milling force coefficient is proposed when the cutter tooth radius is inconsistent. The kernel partial least square method is used to predict the actual milling force coefficient with different milling dosage. The theoretical milling force coefficient is deduced according to the milling process of two-tooth spiral milling cutter. The nominal milling force is introduced according to the inconsistent milling process of cutter tooth radius, and the error of cutter tooth radius is deduced, and the actual milling force coefficient is constructed. Based on the outstanding nonlinear analysis and prediction ability of kernel analysis method, the kernel partial least square method is used to establish the prediction model of actual milling force coefficient on milling amount and its combination quantity in high dimensional space, and the number of kernel principal components in this method is analyzed. The influence of the kernel parameters of Gao Si kernel function on the accuracy of the prediction model and the range of its values are determined. Finally, considering cutter radius error and milling force coefficient without consideration, the kernel partial least square prediction method and partial least square prediction method are compared. The results show that the proposed milling force coefficient construction process and prediction method have higher calculation accuracy and prediction ability.
【作者单位】：同济大学机械与能源工程学院;同济大学中德学院;
【基金】：国家科技重大专项(2011ZX04016-021);国家科技重大专项(2012ZX04005031)资助项目国家科技支撑计划(2012BAF 01B02)
【分类号】：TG54

【参考文献】