波动工况下点焊质量在线预测及模型解释  

Online prediction of resistance spot weld quality and model explanation under fluctuating conditions

作　　者：吕天乐 齐苗苗 闫德俊 黎书华 夏裕俊 李永兵[1,2] LV Tianle;QI Miaomiao;YAN Dejun;LI Shuhua;XIA Yujun;LI Yongbing(Shanghai Key Laboratory of Digital Manufacture of Complex Thin Plate Structures,Shanghai Jiao Tong University,Shanghai 200240;State Key Laboratory of Mechanical Systems and Vibration,Shanghai Jiao Tong University,Shanghai 200240;Shanghai Aerospace Equipment Manufacturing Plant Co.,LTD,Shanghai 200245;Guangdong Provincial Key Laboratory of Marine Advanced Welding Technology Enterprise,CSSC Huangpu Wenchong Shipbuilding Co.,LTD,Guangzhou 510715)

机构地区：[1]上海交通大学,上海市复杂薄板结构数字化制造重点实验室,上海200240 [2]上海交通大学,机械系统与振动国家重点实验室,上海200240 [3]上海航天设备制造总厂有限公司,上海200245 [4]中船黄埔文冲船舶有限公司,广东省舰船先进焊接技术企业重点实验室,广州510715

出　　处：《焊接学报》2022年第11期91-100,I0007,I0008,共12页Transactions of The China Welding Institution

基　　金：国家自然科学基金项目(52025058);国防基础科研项目(JCKY2021203B074);工信部高技术船舶项目(MC-201704-Z02)。

摘　　要：基于电阻点焊过程的多传感信号特征,面向多种板材组合建立焊点质量在线预测模型,研究了异常工况波动对四类机器学习回归模型的影响,分析了不同模型和输入变量对含异常工况试验数据集的适应性,并采用Shapley值、t-SNE等方法对波动工况下的模型性能进行解释.结果表明,高斯过程回归模型和电阻+力信号具有最佳的熔核直径预测性能,焊接电流、热输入能量和电极位移峰值特征对于波动工况具有良好普适性.此外,异常工况引起的信号特征分布差异会显著影响回归预测模型的泛化性能,应尽量减少训练集与数据集差异以提高焊点质量预测的准确性.Based on the features of multi-sensing signals in resistance spot welding process, online prediction models were established for the spot weld quality of different stack-ups in this paper. The influence of fluctuating welding conditions fluctuation on four machine learning regression models was studied, and the adaptability of different models and input variables on the database containing data of abnormal conditions was analyzed. Shapley value, and t-SNE methods were used to explain the model performance under fluctuating conditions.The results show that the Gaussian process regression model and resistance + force signal input had the best prediction performance of nugget diameter. Features of welding current, heat input and peak value of electrode displacement had good universality under fluctuating conditions. Besides, the difference of feature distribution caused by condition fluctuation could significantly influence the generalization performance of regression models. Thereby, the reduction of the difference between training set and test set could improve the prediction accuracy.

关 键 词：电阻点焊 波动工况 多传感器融合 质量在线检测 机器学习 

分 类 号：TG453.9[金属学及工艺—焊接]