Hybrid machine learning-enabled adaptive welding speed control
Hybrid machine learning-enabled adaptive welding speed control
复制标题
DOI：
10.1016/j.jmapro.2021.09.023
复制
发表时间：
2021-11
影响因子：
6.2
通讯作者：
J. Kershaw;Rui Yu;Yuming Zhang;Peng Wang
中科院分区：
文献类型：
--
作者：
J. Kershaw;Rui Yu;Yuming Zhang;Peng Wang
工业机器人在自动化制造过程中变得更加多样化和普遍，例如焊接。然而，现有的机器人控制系统无法自适应地调整其操作以响应动态焊接环境，而熟练的人类焊工可以。复杂的自适应机器人控制依赖于感知数据的有效和高效处理，高动态系统的表征和预测，以及实时自适应机器人反应。本研究针对恒流GTAW焊接的实时焊接质量预测和自适应焊接速度调整进行了初步研究。为了收集训练混合机器学习模型所需的数据，使用两个摄像机来监控焊接过程，其中一个摄像机（在实际机器人焊接中可用）记录顶部焊接池的动态，另一个摄像机（在实际机器人焊接中不可用，但适用于训练目的）记录背面焊头的形成。给定这两个数据集，可以通过擅长图像表征的卷积神经网络（CNN）发现相关性。在主动焊接控制过程中，利用CNN对顶部焊池图像进行分析，预测背面焊头宽度。此外，监测过程已应用于多个不同速度的实验试验。这使得焊接速度对焊头宽度的影响可以通过多层感知器（MLP）进行建模。通过训练后的MLP，开发了一种计算效率高的梯度下降算法，以相应调整行进速度，以获得完全穿透材料的最佳头宽。由于梯度下降的性质，机器人在质量较远时改变速度较快，在接近目标时微调速度。实验研究表明，在实时预测磁珠宽度和自适应调速以实现理想磁珠宽度方面取得了良好的效果。
Industrial robots have become more diverse and common for automating manufacturing processes, such as welding. Existing robotic control, however, is incapable of adaptively adjusting its operation in response to a dynamic welding environment, whereas a skilled human welder can. Sophisticated and adaptive robotic control relies on the effective and efficient processing of perception data, characterization and prediction of highly dynamic systems, and real-time adaptative robotic reactions. This research presents a preliminary study on developing appropriate Machine Learning (ML) techniques for real-time welding quality prediction and adaptive welding speed adjustment for GTAW welding at a constant current. In order to collect the data needed to train the hybrid ML models, two cameras are applied to monitor the welding process, with one camera (available in practical robotic welding) recording the top-side weld pool dynamics and a second camera (unavailable in practical robotic welding, but applicable for training purpose) recording the back-side bead formation. Given these two data sets, correlations can be discovered through a convolutional neural network (CNN) that is good at image characterization. With the CNN, top-side weld pool images can be analyzed to predict the back-side bead width during active welding control. Furthermore, the monitoring process has been applied to multiple experimental trials with varying speeds. This allowed the effect of welding speed on bead width to be modeled through a Multi-Layer Perceptron (MLP). Through the trained MLP, a computationally efficient gradient descent algorithm has been developed to adjust the travel speed accordingly to achieve an optimal bead width with full material penetration. Because of the nature of gradient descent, the robot would change faster when the quality is further away and then fine-tune the speed when it was close to the goal. Experimental studies have shown promising results on real-time bead width prediction and adaptive speed adjustment to realize ideal bead width.