摘要
在汽车车身焊接过程中,电阻点焊的质量主要通过控制焊点能承受的拉剪力控制。但是检测焊点能承受的拉剪力需要进行破坏性实验,不仅效率低、成本高,且产品件上的焊点是无法进行此类破坏性的检验,只能用试片进行样本抽检或者通过超声波进行人工抽检。为能实现实时在线监测焊点质量,文章设计了多种点焊强度的预测模型,对比各模型在调整拟合优度(R~2)、平均绝对百分比误差(MAPE)等性能指标上的预测效果,最终选择了遗传算法优化反向传播神经网络模型。该模型的R~2、MAPE分别达到了0.9928、2.292%,效果良好,有助于汽车车身质量的整体提升。
In automotive body welding,the quality of resistance spot welding is primarily determ-ined by the shear strength that the weld nugget can withstand.However,measuring this shear strength requires destructive testing,which is not only inefficient and costly but also impractical for inspecting welds on actual production parts.Therefore,quality inspection is limited to sample testing using coupons or manual ultrasonic spot checks.To enable real-time online monitoring of weld quality,this paper designs multiple prediction models for spot welding strength.The predictive performance of these models is compared based on metrics such as the adjusted coefficient of determination(R2)and mean absolute percentage error(MAPE).The genetic algorithm-optimized backpropagation neural network model is ultimately selected.This model achieves an adjusted R2 of 0.9928 and a MAPE of 2.292%,demonstrating excellent performance and contributing to the overall improvement of automotive body quality.
作者
赖志永
林妍敏
万小梦
王煜奎
黄倚轩
LAI Zhiyong;LIN Yanmin;WAN Xiaomeng;WANG Yukui;HUANG Yixuan(China National Heavy Duty Truck Group Fujian Haixi Automobile Company Limited,Yong'an 366000,China;SDIC Intelligence(Xiamen)Information Company Limited,Xiamen 361000,China;Xiamen ITG Energy Company Limited,Xiamen 361000,China;Zijin International Trading Company Limited,Xiamen 361000,China)
出处
《汽车实用技术》
2025年第19期92-96,共5页
Automobile Applied Technology
关键词
电阻点焊
遗传算法优化神经网络
智能优化算法
焊点拉剪力预测
预测模型
resistance spot welding
genetic algorithm-optimized neural network
intelligent opti-mization algorithm
weld shear strength prediction
prediction model
