Liu Chao, He Yan, Wang Yulin, Li Yufeng, Wang Shilong, Wang Lexiang, Wang Yan
State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400030, China.
School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China.
ISA Trans. 2020 Jun;101:493-502. doi: 10.1016/j.isatra.2020.01.031. Epub 2020 Jan 25.
Temperature in the cutting zone during dry machining has a significant effect on the tool life and surface integrity of the workpiece. This paper describes a comprehensive research on the cutting temperature in dry machining of ball screw under whirling milling by using infrared imaging. The effects of tool parameter and geometric parameter of workpiece together with the cutting parameters on the maximum and average temperatures in the cutting zone were analyzed in full detail. The influencing degree of these parameters on the maximum and average temperatures was affected by the value ranges of the parameters. In addition, the regression model and back propagation (BP) neural network model were proposed for predicting the maximum and average temperatures in the cutting zone. The verification of the predictive models showed that compared to the regression model, BP neural network model could predict the cutting temperature with high precision. The R of BP neural network model for predicting the maximum and average cutting temperatures in the cutting zone was higher than 99.8%, and the mean relative error and root mean square error were less than 4% and 19%, respectively.
干式切削加工时切削区域的温度对刀具寿命和工件的表面完整性有显著影响。本文描述了一项通过红外成像对旋风铣削滚珠丝杠干式切削加工中的切削温度进行的全面研究。详细分析了刀具参数、工件几何参数以及切削参数对切削区域最高温度和平均温度的影响。这些参数对最高温度和平均温度的影响程度受参数取值范围的影响。此外，还提出了回归模型和反向传播（BP）神经网络模型来预测切削区域的最高温度和平均温度。预测模型的验证表明，与回归模型相比，BP神经网络模型能够高精度地预测切削温度。BP神经网络模型预测切削区域最高温度和平均切削温度的R值高于99.8%，平均相对误差和均方根误差分别小于4%和19%。
