| 引用本文: | 陈振款,何建萍,李芳,华学明,黄文荣.基于BP神经网络薄板P-PAW搭接的间隙自适应工艺参数优化[J].材料科学与工艺,2024,32(1):18-24.DOI:10.11951/j.issn.1005-0299.20220417. |
| CHEN zhenkuan,HE jianping,LI fang,HUA xueming,HUANG wenrong.Optimization of adaptive process parameters for P-PAW lap welding gap of sheet metal based on BP neural network[J].Materials Science and Technology,2024,32(1):18-24.DOI:10.11951/j.issn.1005-0299.20220417. |
|
| 摘要: |
| 对大型LNG燃料薄膜舱中1.2 mm厚SUS304L不锈钢板薄板的搭接焊,存在的搭接间隙会带来焊缝成形不良等严重影响船舱安全性的问题。本文通过激光传感器检测搭接间隙变化,设计了不同的峰值电流和焊接速度在不同间隙下的工艺实验,研究了间隙对焊缝成形质量的影响机制；基于BP神经网络建立不同间隙下的脉冲等离子弧焊(P-PAW)的工艺参数和间隙及焊缝成形尺寸之间的拓扑关系模型,通过工艺实验获取模型的训练样本,实现了基于BP神经网络的间隙自适应工艺参数优化系统。结果表明,该系统实现了不同搭接间隙下进行实时工艺参数优化的功能,并对搭接间隙在0~0.6 mm变化时所带来的空洞等缺陷起到了有效的抑制作用,实现了良好的焊接成形一致性控制,提高了在LNG薄膜舱中不锈钢板焊接的自适应能力。 |
| 关键词: 等离子弧焊 激光传感 焊接间隙 自适应焊接 BP神经网络 |
| DOI：10.11951/j.issn.1005-0299.20220417 |
| 分类号:TG401 |
| 文献标识码:A |
| 基金项目:国家自然科学基金资助项目(51775327)；工业和信息化部高技术船舶科研计划项目(2020313). |
|
| Optimization of adaptive process parameters for P-PAW lap welding gap of sheet metal based on BP neural network |
|
CHEN zhenkuan1, HE jianping1, LI fang2, HUA xueming2, HUANG wenrong3
|
|
(1.School of Materials Science and Engineering, Shanghai University of Engineering Science, Shanghai 201620, China; 2.Shanghai Key Laboratory of Materials Laser Processing and Modification (Shanghai Jiao Tong University), Shanghai 200240, China; 3.Hudong-Zhonghua Shipbuilding (Group) Co., Ltd., Shanghai 200129, China)
|
| Abstract: |
| For the lap welding of 1.2 mm thick SUS304L stainless steel plates and sheets in large LNG fuel film tanks, there are problems that the lap gap will lead to poor weld formation, which seriously affect the safety of the cabin. In this paper, the laser sensor is used to detect the change of the lap gap, welding process tests are designed for different peak currents and welding speeds under different gaps and the influence mechanism of gap on weld forming quality is studied. Based on BP neural network, the topological relationship model between the process parameters and the gap and the weld forming size under different gaps is established. The training samples of the model are obtained through process experiments of pulsed plasma arc welding; the gap adaptive process parameter optimization system based on BP neural network is realized. The test results show that the system realizes the function of real-time process parameter optimization under different lapping gaps, effectively suppresses the void and other defects caused by the change of lapping gap between 0 and 0.6 mm, achieving good welding forming consistency control, and improving the adaptive welding ability of stainless steel plates and sheets in large LNG fuel film tanks. |
| Key words: plasma arc welding laser sensor welding gap adaptive welding BP neural network |
