工程技术论坛Engineering Technology Forum

数控加工中心主轴热误差SFO-Bilstm预测建模
陈庚 刘龙 袁粼 蔡依琳 高文文*

新疆理工职业大学，新疆，844004；

摘要：在高精度加工过程中，数控机床主轴误差对加工精度的影响较为严重。其中，数控机床热误差占总误差比例高达40%~70%，是主要的误差源之一。为了提高热误差预测的精度，提出了一种使用旗鱼优化算法(SFO)优化双向时序预测网络(Bilstm)的数控机床主轴热误差预测建模方法。以机床主轴五点法获取的热误差数据和测量得到的温度数据作为输入，使用SFO对Bilstm的隐含层节点、全连接层节点、学习率、L2正则化常数进行优化，建立主轴热误差SFO-Bilstm预测模型。在VDL-600A型数控机床上进行实例验证，使用五点法进行测量辨识，同时测量主轴附近的温度。实验结果表明：所提出的旗鱼优化算法(SFO)优化双向时序预测网络(Bilstm)的鲁棒性和准确性更高。

关键词：数控机床；主轴热误差；热误差建模；SFO-Bilstm网络

参考文献

[1]Zhang H,Xiang S,Liu C,et al.Reverse identification of dynamic and static motion errors for five-axis machine based on specimen feature decomposition[J].ISA Transactions,2023,134:302-311.

[2]Feng W,Li Z,Gu Q,et al.Thermally induced positioning error modelling and compensation based on thermal characteristic analysis[J].International Journal of Machine Tools and Manufacture,2015,93:26-36.

[3]孙惠娟,殷国富,方辉,et al.五轴数控机床综合误差建模评价方法研究[J].四川大学学报(工程科学版),2012,44(6):197-202.

[4]Tanaka S,Kizaki T,Tomita K,et al.Robust thermal error estimation for machine tools based on in-process multi-point temperature measurement of a single axis actuated by a ball screw feed drive system[J].Journal of Manufacturing Processes,2023,85:262-271.

[5]Fu G,Zheng Y,Zhou L,et al.Look ahead prediction of spindle thermal errors with on machine measurement and the cubic ex-ponential smoothing unscented Kalman filter-ing-based temperature prediction model of the machine tools[J].Measurement,2023,210:112536.

[6]Fu G,Zhou L,Zheng Y,et al.Improved unscented Kalman filter algorithm-based rapid identification of thermal errors of machine tool spindle for shortening thermal equilibrium time[J].Measurement,2022,195:111121.

[7]马驰,赵亮,梅雪松,etal.基于粒子群算法与BP网络的机床主轴热误差建模[J].上海交通大学学报,2016,50(5):686-695.

[8]Pahk H,Lee S W.Thermal error measurement and real time com-pensation system for the CNC machine tools in-corporating the spindle thermal error and the feed axis thermal error[J].The International Journal of Advanced Manufacturing Technology,2002,20(7):487-494.

[9]Wenjie Cao,Haolin Li,Qiang Li.A method of thermal error prediction modeling for CNC machine tool spindle system based on linear correlation[J].The International Journal of Advanced Manufacturing Technology,2022,118:3079-3090.

[10]Jiacheng Sun,Zhenyu Liu,Chan Qiu,et al. An axial attention-BiLSTM-based method for predicting the migration of CNC machine tool spindle thermal error under varying working conditions[J].The International Journal of Advanced Manufacturing Technology,2024,130:1405-1419.