在316L不锈钢的激光焊接过程中，其焊接工艺参数直接影响焊缝的形貌，建立焊接工艺参数与焊缝几何形状之间的关系对于优化焊接工艺参数，降低焊接成本非常重要. 根据316L不锈钢焊缝二维不光滑轮廓形貌特点，采用分段函数思想，分别使用Hermite插值和最小二乘拟合的方法描述焊缝轮廓，构建广义回归神经网络焊缝二维形貌预测模型. 结果表明，采用Hermite插值的方法能够获得更准确的焊缝形貌，其平均相对误差为−3.49%. 该模型为316L不锈钢激光焊焊缝预测提供一种有效方法.
In the laser welding process of 316L stainless steel, the welding process parameters directly affect the appearance of the weld. Establishing the relationship between welding process parameters and weld geometry is very important for optimizing welding process parameters and reducing welding costs. According to the characteristics of the two-dimensional rough contours of 316L stainless steel welds, the idea of piecewise function is used to describe the contours of the welds using Hermite interpolation and least square fitting respectively, and a generalized regression neural network two-dimensional weld topography prediction model is constructed.The experimental results show that the Hermite interpolation method can obtain a more accurate weld profile, with an average relative error of −3.49%. The proposed model provides an effective method for welding seam prediction of 316L stainless steel welding process.
[1] Cui Bing, Yan Peipei, Du Quanbin, et al. The welding application of high strength steels used in engineering machinery[J]. China Welding, 2021, 30(1): 57 ? 64.
[2] Shanmugam N S, Buvanashekaran G, Sankaranarayanasamy K. Some studies on weld bead geometries for laser spot welding process using finite element analysis[J]. Materials & Design, 2012, 34: 412 ? 426
[3] 吴向阳, 宿浩, 孙岩, 等. 激光 + GMAW复合热源焊接过程热-力耦合数值分析[J]. 焊接学报, 2021, 42(1): 91 ? 96
Wu Xiangyang, Su Hao, Sun Yan, et al. Thermal-mechanical coupled numerical analysis of laser + GMAW hybrid heat source welding process[J]. Transactions of the China Welding Institution, 2021, 42(1): 91 ? 96
[4] 夏佩云. 面向焊缝形貌预测的光纤激光深熔焊温度场及应力场数值模拟 [D]. 武汉: 华中科技大学, 2012.
Xia Peiyun. Numerical simulation of temperature andstress field in fibre laser keyhole welding orienting prediction of weld shape[D]. Wuhan: Huazhong University of Science and Technology, 2012.
[5] Luo M, Shin Y C. Estimation of keyhole geometry and prediction of welding defects during laser welding based on a vision system and a radial basis function neural network [J]. The International Journal of Advanced Manufacturing Technology, 2015, 81(1−4): 263−276.
[6] Wang X, Zhang C, Li P, et al. Modeling and optimization of joint quality for laser transmission joint of thermoplastic using an artificial neural network and a genetic algorithm[J]. Optics and Lasers in Engineering, 2012, 50(11): 1522 ? 1532.
[7] Yang Y, Cao L, Zhou Q, et al. Multi-objective process parameters optimization of laser-magnetic hybrid welding combining Kriging and NSGA-II[J]. Robotics and Computer Integrated Manufacturing, 2018, 49: 253 ? 262.
[8] Wang H, Zhang Z, Liu L. Prediction and fitting of weld morphology of Al alloy-CFRP welding-rivet hybrid bonding joint based on GA-BP neural network[J]. Journal of Manufacturing Processes, 2020(5): 109 ? 120
[9] 张志亮, 郝泳涛. 基于神经网络的焊缝形状预测模型[J]. 电脑知识与技术, 2013, 9(31): 7096 ? 7099
Zhang Zhiliang, Hao Yongtao. Orienting prediction of weld shape[J]. Computer Knowledge and Technology, 2013, 9(31): 7096 ? 7099
[10] 张建勋, 王军, 裴怡, 等. CO2气保焊焊缝形状的神经网络预测模型[J]. 焊接技术, 2002(3): 11 ? 12
Zhang Jianxun, Wang Jun, Pei Yi, et al. Neural network prediction model for weld shape of CO2 gas shielded welding[J]. Welding Technology, 2002(3): 11 ? 12
[11] Specht D F. A general regression neural network[J]. Neural Network, IEEE Transaction, 1991, 2(6): 568 ? 576.
[12] Qiao L, Wang Z, Zhu J. Application of improved GRNN model to predict interlamellar spacing and mechanical properties of hypereutectoid steel[J]. Materials Science and Engineering:A, 2020, 792: 139845.
[13] Zhu S, Lian X, Wei L, et al. PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors[J]. Atmospheric Environment, 2018, 183: 20 ? 32.
[14] Land W H, Ma X, Barnes E, et al. PNN/GRNN ensemble processor design for early screening of breast cancer[J]. Procedia Computer Science, 2012, 12: 438 ? 443.
[15] Ding Hua, Wang Zongcheng, Guo Yicheng. Multi-objective optimization of fiber laser cutting based on generalized regression neural network and non-dominated sorting genetic algorithm[J]. Infrared Physics & Technology, 2020, 108: 103337.
[16] Wan X, Li Y, Xia C. A T-wave alternans assessment method based on least squares curve fitting technique[J]. Measurement, 2016, 86: 93 ? 100.
[17] Wan X K, Yan K H, Li A. Improved modified moving average analysis of T-wave alternans using least squares-based curve fitting method[J]. International Journal of Biomathematics, 2014, 7(4): 1450044
