权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Intelligent Adaptive Control for Weld Penetration by Monitoring Shape and Oscillation of Molten Pool

通过监测熔池形状和振动实现焊缝熔深智能自适应控制

基本信息

批准号：
11650748
负责人：
SUGA Yasuo
金额：
$ 2.24万
依托单位：
Keio University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
1999
资助国家：
日本
起止时间：
1999 至 2000
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-11650748/
关键词：
Welding Welding robot Visual sensing Shape of molten pool Oscillation of molten pool Penetration control In-process monitoring Adaptive control

项目摘要

In welding of steel plates, the welding parameters including groove shape, plate thickness, welding speed and so on change with elapse time. Accordingly, it is very important to select the optimum welding conditions by controlling them according to change of welding parameters. In order to realize the adaptive control of welding conditions, new control systems were constructed.The first system used a CCD camera which was fixed at back side of welding torch, and it monitored the condition of the molten pool. In particular, the shape and dimension of the molten pool were measured during welding, and in-process control was performed to keep the shape and dimension. When the dimension of molten pool, such as pool width, increased, the control system decreased the welding current and keep the dimension of molten pool constant. In order to construct a robust control system, artificial neural network was applied to it. Furthermore, the system was applied to welding of fixed pipes, and effectiveness of the system was confirmed.The second system has a monitoring system of oscillation of molten pool. Already, it is well known that the oscillation frequency of the molten pool changes with penetration. In this research, new oscillating processes including assist gas oscillating method, pulse shielding gas oscillating method and pulse back assist gas oscillating method were proposed, and characteristics of these oscillating methods were investigated. As a result, it is confirmed that the gas oscillating method can oscillate a molten pool with relatively small size. which is difficult to be oscillated by the conventional pulse current oscillating method. Furthermore, welding control experiments were performed using the system constructed in this study, and the effectiveness of the system in penetration control was verified.

在钢板焊接过程中，坡口形状、板厚、焊接速度等焊接参数随时间的推移而变化。因此，根据焊接参数的变化对焊接条件进行控制，选择最佳的焊接条件就显得尤为重要。为了实现焊接工况的自适应控制，构建了新的控制系统。第一个系统采用安装在焊枪背面的CCD摄像机对熔池状态进行监测。特别是在焊接过程中对熔池的形状和尺寸进行了测量，并进行了过程控制以保持熔池的形状和尺寸。当熔池宽度等尺寸增大时，控制系统减小焊接电流，保持熔池尺寸不变。为了构建鲁棒控制系统，将人工神经网络应用到控制系统中。并将该系统应用于固定管道的焊接，验证了系统的有效性。第二系统设有熔池振荡监测系统。众所周知，熔池的振荡频率随熔深的变化而变化。提出了辅助气体振荡法、脉冲保护气体振荡法和脉冲反辅助气体振荡法等新型振荡方法，并分析了这些振荡方法的特点。结果表明，气体振荡法可以振荡较小尺寸的熔池。传统的脉冲电流振荡方法难以实现振荡。利用所构建的系统进行了焊接控制实验，验证了该系统在熔透控制中的有效性。