基于径向基函数神经网络的脉冲激光薄板焊接变形预测

张健; 杨锐

doi:doi:10.3788/cjl201138.1103002

中国激光, 2011, 38 (11): 1103002, 网络出版: 2011-10-12

基于径向基函数神经网络的脉冲激光薄板焊接变形预测

Prediction of Pulsed Laser Welding of Thin Plate Based on Radial Basis Function Neural Network

论文大纲

张健 ^*杨锐

作者单位

天津职业技术师范大学，天津 300222

摘要

以轿车用低碳钢薄板为实验样品，分析了脉冲激光焊接产生的主要变形方式。利用径向基函数神经网络对薄板焊接产生的横向收缩变形和横向弯曲变形进行预测。采用响应面法对实验参数进行优化设计。将脉冲频率、脉宽、聚焦镜焦距、离焦量、工件移动速度、保护气体种类、工件温度波动和光功率波动作为神经网络输入，提高了焊接变形预测的准确度。通过对比6种神经网络对薄板焊接变形预测的结果得出了最佳的网络结构。实验证明该神经网络对薄板焊接产生的变形有较高的预测准确度。

Abstract

A set of mild steel thin plate specimens used for automotive industry are used as laboratory samples. Different types of distortions are analyzed. Radial basis function neural network (RBFN) models have been developed to predict transverse shrinkage and longitudinal bending distortion of welded plates. Response surface method is used to set up the experimental parameters matrix. Pulse frequency, pulse width, focal distance, defocus distance, moving speed of welded plates, shielded gas, workpiece temperature fluctuation and laser power fluctuation are used as input variables of these models to increase the prediction accuracy. Six different types of RBFN models have been developed to predict the distortion of welded plates. The best one is selected from them and resulted in better output prediction.

参考文献

[1] 汪洪峰, 黄铭敏, 田昕. 汽车铝合金薄板激光焊接数值模拟［J］. 现代零部件, 2009, 6(12): 30～32

Wang Hongfeng, Huang Mingmin, Tian Xin. Numerical simulation on automobile aluminium alloy thin plate laser welding［J］. Modern Components, 2009, 6(12): 30～32

[2] 王文先, 张亚楠, 崔泽琴等. 双面超薄不锈钢复合板激光焊接接头组织性能研究［J］. 中国激光, 2011, 38(5): 0503002

Wang Wenxian, Zhang Ya′nan, Cui Zeqin et al.. Study on microstructure and properties of double ultra-thin stainless steel clad plate by laser welding［J］. Chinese J. Lasers, 2011, 38(5): 0503002

[3] 钟如涛, 秦应雄, 唐霞辉. 激光功率的微观波动对加工质量的影响［J］. 中国激光, 2010, 37(10): 2638～2641

Zhong Rutao, Qin Yingxiong, Tang Xiahui. Influence of micro-fluctuation of laser power to processing quality［J］. Chinese J. Lasers, 2010, 37(10): 2638～2641

[4] 梅丽芳, 陈根余, 金湘中等. 车用铝合金光纤激光搭接焊的研究［J］. 中国激光, 2010, 37(8): 2091～2097

Mei Lifang, Chen Genyu, Jin Xiangzhong et al.. Study on fiber laser overlap-welding of automobile aluminum alloy［J］. Chinese J. Lasers, 2010, 37(8): 2091～2097

[5] 殷苏民, 齐善东. 基于神经网络的激光冲击金属板料变形量研究［J］. 中国激光, 2010, 37(1): 284～290

Yin Sumin, Qi Shandong. Study on sheet metal deformation under laser shock forming based on neural network［J］. Chinese J. Lasers, 2010, 37(1): 284～290

[6] 马广义, 吴东江, 王占宏等. 脉冲激光焊接对超薄Hastelloy C-276焊缝成形的影响［J］. 中国激光, 2011, 38(6): 0603014

Ma Guangyi, Wu Dongjiang, Wang Zhanhong et al.. Weld joint forming of thin hastelloy C-276 sheet of pulsed laser welding［J］. Chinese J. Lasers, 2011, 38(6): 0603014

[7] 龚伟怀, 陈玉华, 吕榛等. 0.2 mm厚GH4169薄片激光微焊接接头的组织性能［J］. 中国激光, 2011, 38(6): 0603008

Gong Weihuai, Chen Yuhua, Lü Zhen et al.. Microstructure and properties of 0.2 mm thick sheet GH4169 by laser microwelding［J］ . Chinese J. Lasers, 2011, 38(6): 0603008

[8] 刘会霞, 向宝珍, 许贞凯等. 基于田口方法的NdYAG脉冲激光焊接工艺参数优化［J］. 中国激光, 2010, 37(s1): 350～357

Liu Huixia, Xiang Baozhen, Xu Zhenkai et al.. Process parameters optimization of NdYAG pulsed laser welding based on taguchi method［J］. Chinese J. Lasers, 2010, 37(s1): 350～357

[9] Dean Deng, Wei Liang, Hidekazu Murakawa. Determination of welding deformation in fillet-welded joint by means of numerical simulation and comparison with experimental measurements［J］. Journal of Materials Processing Technology, 2007, 23(3): 219～225

[10] Mohammad Taghi, Vakil Baghmisheh, Nikola Pavesic. Training RBF networks with selective backpropagation［J］. Neurocomputing, 2004, 62: 39～64栏目编辑：宋梅梅

张健, 杨锐. 基于径向基函数神经网络的脉冲激光薄板焊接变形预测[J]. 中国激光, 2011, 38(11): 1103002. Zhang Jian, Yang Rui. Prediction of Pulsed Laser Welding of Thin Plate Based on Radial Basis Function Neural Network[J]. Chinese Journal of Lasers, 2011, 38(11): 1103002.

基于径向基函数神经网络的脉冲激光薄板焊接变形预测

关于本站 Cookie 的使用提示

全站搜索

基于径向基函数神经网络的脉冲激光薄板焊接变形预测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索