当前位置: X-MOL 学术Adv. Manuf. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Thermal error modeling based on BiLSTM deep learning for CNC machine tool
Advances in Manufacturing ( IF 5.2 ) Pub Date : 2021-02-21 , DOI: 10.1007/s40436-020-00342-x
Pu-Ling Liu , Zheng-Chun Du , Hui-Min Li , Ming Deng , Xiao-Bing Feng , Jian-Guo Yang

The machining accuracy of computer numerical control machine tools has always been a focus of the manufacturing industry. Among all errors, thermal error affects the machining accuracy considerably. Because of the significant impact of Industry 4.0 on machine tools, existing thermal error modeling methods have encountered unprecedented challenges in terms of model complexity and capability of dealing with a large number of time series data. A thermal error modeling method is proposed based on bidirectional long short-term memory (BiLSTM) deep learning, which has good learning ability and a strong capability to handle a large group of dynamic data. A four-layer model framework that includes BiLSTM, a feedforward neural network, and the max pooling is constructed. An elaborately designed algorithm is proposed for better and faster model training. The window length of the input sequence is selected based on the phase space reconstruction of the time series. The model prediction accuracy and model robustness were verified experimentally by three validation tests in which thermal errors predicted by the proposed model were compensated for real workpiece cutting. The average depth variation of the workpiece was reduced from approximately 50 µm to less than 2 µm after compensation. The reduction in maximum depth variation was more than 85%. The proposed model was proved to be feasible and effective for improving machining accuracy significantly.



中文翻译:

基于BiLSTM深度学习的数控机床热误差建模

计算机数控机床的加工精度一直是制造业关注的焦点。在所有误差中,热误差会极大地影响加工精度。由于工业4.0对机床的重大影响,现有的热误差建模方法在模型复杂性和处理大量时间序列数据的能力方面遇到了前所未有的挑战。提出了一种基于双向长短期记忆(BiLSTM)深度学习的热误差建模方法,该方法具有良好的学习能力和强大的处理大量动态数据的能力。构建了一个四层模型框架,其中包括BiLSTM,前馈神经网络和最大池。提出了一种精心设计的算法,可以更好,更快地进行模型训练。根据时间序列的相空间重构,选择输入序列的窗口长度。通过三个验证测试对模型预测的准确性和模型的鲁棒性进行了实验验证,其中对所提出的模型预测的热误差进行了补偿,以进行实际的工件切割。补偿后,工件的平均深度变化从大约50 µm减小到小于2 µm。最大深度变化的减少超过85%。所提出的模型被证明是可行和有效的,以显着提高加工精度。通过三个验证测试对模型预测的准确性和模型的鲁棒性进行了实验验证,其中对所提出的模型预测的热误差进行了补偿,以进行实际的工件切割。补偿后,工件的平均深度变化从大约50 µm减小到小于2 µm。最大深度变化的减少超过85%。所提出的模型被证明是可行和有效的,以显着提高加工精度。通过三个验证测试对模型预测的准确性和模型的鲁棒性进行了实验验证,其中,针对实际工件的切削,对所提出的模型预测的热误差进行了补偿。补偿后,工件的平均深度变化从大约50 µm减小到小于2 µm。最大深度变化的减少超过85%。实践证明,该模型对提高加工精度是可行和有效的。

更新日期:2021-02-21
down
wechat
bug