摘要
提出一种基于BP(反向传播)神经网络磨削误差的预报方法,针对轴承套圈磨削误差序列的非线性特点,使用BP神经网络对其进行建模预测,为磨削自动线的监控调整提供准确的预报值,从而可有效地修正磨削过程中温度、变形及其他复杂因素对工件加工精度的影响,提高加工精度,降低轴承套圈磨削的尺寸分散度。
Based on the nonlinear feature of the grinding error sequence of bearing rings, a method of predicting grinding error based on BP neural network is proposed. By means of BP neural network, it models and predicts the grinding process,provides precise predicting values for the supervision and adjustment of grinding automatic lines, thus weakening the influence of complex factors such as heat and distortion on manufacturing precision of work-piece , and decreasing size deviation.
出处
《河南科技大学学报（自然科学版）》
CAS
2006年第2期13-15,共3页
Journal of Henan University of Science And Technology:Natural Science
基金
河南科技大学科研基金项目(2003QN04)
关键词
BP神经网络
轴承套圈
磨削
误差预测
BP neural network
Bearing ring
Grinding
Error prediction
