机器学习在弯曲模中的应用尝试

Application of Machine Learning in Bending Dies

利用人工神经网络技术,把在线测量数据作为神经网络的训练样本,建立输入工艺参数、输出行程的神经网络模型,并通过在线监测检验相关模型的准确性,在公差取值范围内,采用神经网络模型代替传统有限元数学模型,对工艺参数进行实时反馈及优化,最终实现可自我学习的智能弯曲成型系统的开发。该系统可自动试模,自动调整参数,并实现稳定全自动生产。

In this paper,using artificial neural network technology,the on-line measurement data are taken as training samples of neural network,and the neural network model of input process parameters and output stroke is established.The accuracy of relevant models is tested by on-line monitoring.In the range of tolerance,the neural network model is used instead of the traditional finite element model.Learning model,realtime feedback and optimization of process parameters,and finally realize the development of self-learning intelligent bending forming system.The system can automatically test the mold,adjust the parameters automatically,and achieve stable and full automatic production.