基于相关性分析和SSA-BP神经网络的铝合金电阻点焊质量预测
Quality prediction of aluminum alloy resistance spot weld-ing based on correlation analysis and SSA-BP neural net-work
董建伟 1胡建明 1罗震1
作者信息
- 1. 天津大学,材料科学与工程学院,天津, 300350
- 折叠
摘要
基于电阻点焊过程中工艺信号特征,在不同间距、不同间隙和不同间距与间隙 3种条件下,引入相关性分析方法分析工艺信号与熔核直径之间的相关性,并建立基于麻雀搜索算法-BP神经网络(sparrow search algorithm-back propagation neural network,SSA-BP)的电阻点焊质量预测模型,将功率、焊接电流、焊接电压和动态电阻作为预测模型输入特征.结果表明,经麻雀搜索算法优化后的BP神经网络在测试集上的决定系数R2、均方误差(mean-square error,MSE)、均方根误差(root mean square error,RMSE)和平均绝对误差(mean absolute error,MAE)分别为0.95,1.55,1.24和 0.90,均优于BP模型.获得了功率、焊接电流、焊接电压和动态电阻与熔核直径的映射关系,可为焊接的工艺参数设计提供依据.
Abstract
Based on the characteristics of the process signals in the resistance spot welding process,three working condi-tions of different spacing,different gaps and different spacing and gaps are analyzed,and correlation analysis is introduced to extract the correlation between the process signals and the dia-meter of nugget.A resistance spot welding quality prediction model based on Sparrow Search Algorithm-Back Propagation Neural Network(SSA-BP)was established,and power,weld-ing current,welding voltage and dynamic resistance are used as input features of the prediction model.The results show that the BP neural network optimized by the sparrow search al-gorithm outperforms the BP model on the test set with R2,MSE,RMSE and MAE of 0.95,1.55,1.24 and 0.90,respect-ively.It is also determined that there exists a mapping relation-ship between power,welding current,welding voltage and dy-namic resistance and the diameter of the nugget,which provides a basis for the design of process parameters for weld-ing.
关键词
电阻点焊/熔核直径/麻雀搜索算法/BP神经网络/相关性分析Key words
resistance spot welding/nugget diameter/sparrow search algorithm/BP neural network/correlation analysis引用本文复制引用
基金项目
国家自然科学基金资助项目(52075378)
出版年
2024
NETL
NSTL
万方数据