摘要
针对自动焊接智能化程度相对较低的问题,提出一种基于在线视觉反馈的卡尔曼滤波-高斯过程回归(kalman filter gaussian process regression, KF-GPR)的建模方法,分析了建模方法的理论可行性,建立了熔池关键动态特征与焊接参数的最优预测模型.相比于传统统计方法,KF-GRP可以更准确的估计动态焊接过程的分布形式与参数,具有高度的鲁棒性和容错性,并能得到更加合理的模型.设计了304不锈钢不填丝TIG焊试验,利用试验取得的8 423组试验数据进行建模并验证.结果表明,KF-GPR能有效地抑制信号噪声,对熔池特征进行快速、高精度建模,为后续焊接动态控制奠定基础.
To help an automatic welding machine on reasoning dynamic welding process,a Kalman Filter Gaussian Process Regression(KF-GPR)model was proposed,and its theoretical basis was annualized.A prediction model was established later.Compared to conventional statistic method,the KF-GRP method can better estimate the distributed form and parameters for a dynamic welding process,which had higher robustness and fault tolerance.TIG welding experiment of the304stainless steel was carried out to verify the method.Totally8423pairs of experiment data were collected and used for the model.The modeling results showed the proposed KFGPR can suppress noises and provide fast and accurate model,which is essential for future online control experiment.
作者
董航
丛明
Zhang Yuming
陈和平
DONG Hang;CONG Ming;ZHANG Yuming;CHEN Heping(School of Mechanical Engineering, Dalian University of Technology, Dalian 116024,China;Department of Electrical and Computer Engineering and Institute for Sustainable Manufacturing, Lexington 40506;Shenzhen Academy of Robotics, Shenzhen 518000, China)
出处
《焊接学报》
EI
CAS
CSCD
北大核心
2018年第12期49-52,131,共5页
Transactions of The China Welding Institution
基金
辽宁省科技创新重大专项(2015106011).
