车身镀锌钢板点焊性能预测人工神经网络模型优化
首发时间:2005-11-14
摘要:本文针对汽车车身镀锌钢板的点焊性能预测问题进行了研究:引入人工神经网络模型,来描述点焊规范参数空间同焊点接头质量空间的映射关系;在对普通BP网络存在的缺陷问题进行深入分析的基础上,结合大量实验综合考虑,对网络模型进行了优化改进;然后将实验得到的大量点焊规范参数与相应点焊接头质量的试验数据提供给神经网络学习。结果表明,学习后的优化BP神经网络能够准确有效地预测焊接电流对点焊熔核直径、压痕深度以及拉剪强度比的影响规律,且预测精度和准确率较高,符合工程需要,具有一定实用价值。
For information in English, please click here
Model Optimization of Artificial Neural Networks for Performance Predicting in Spot Welding of the Body Zinc-Coated Steel Sheets
Abstract:This paper focuses the performance predicting problems in the spot welding of the body zinc-coated steel sheets. Artificial neural networks(ANN)are used to describe the mapping relationship between welding parameters and welding quality. After analyzing the limitation existed in standard BP networks, the original model is optimized based on lots of experiments. Lots of experimental data about welding parameters and corresponding spot weld quality are provided to the ANN for study. The results show that the improved BP model can predict the influence of welding currents on nugget diameters, weld indentation or the shear loads ratio of spot welds. The forecasting precision is so high that can satisfy the practical need of engineering and have some application value.
Keywords: Body zinc-coated steel sheet Spot welding Artificial neural networks (ANN) Optimization
论文图表:
引用
No.3633317141131942****
同行评议
共计0人参与
勘误表
车身镀锌钢板点焊性能预测人工神经网络模型优化
评论
全部评论0/1000