Darwish Amena, Persson Manfred, Ericson Stefan, Ghasemi Rohollah, Salomonsson Kent
Virtual Manufacturing Processes, School of Engineering Sciences, University of Skövde, Kaplansgatan 11, SE-541 34 Skövde, Sweden.
Sensors (Basel). 2025 Aug 18;25(16):5120. doi: 10.3390/s25165120.
Laser beam welding (LBW) involves complex and rapid interactions between the laser and material, often resulting in defects such as pore formation. Emissions collected during the process offer valuable insight but are difficult to interpret directly for defect detection. In this study, we propose a data-driven framework to interpret electromagnetic emissions in LBW using both supervised and unsupervised learning. Our framework is implemented in the post-process monitoring stage and can be used as a real-time framework. The supervised approach uses labeled data corresponding to predefined defects (in this work, pore formation is an example of a defined defect). Meanwhile, the unsupervised method is used to identify anomalies without using predefined labels. Supervised and unsupervised learning aims to find reference values in the emissions data to determine the values of signals that lead to defects in welding (enabling quantitative monitoring). A total of 81 welding experiments were conducted, recording real-time emission data across 42 spectral channels. From these signals, statistical, temporal, and shape-based features were extracted, and dimensionality was reduced using Principal Component Analysis (PCA). The LSTM model achieved an average mean squared error (MSE) of 0.0029 and mean absolute error (MAE) of 0.0288 on the testing set across five folds. The Isolation Forest achieved 80% accuracy and 85.7% precision in detecting anomalous welds on a subset with validated defect labels. The proposed framework enhances the interpretability of 4D photonic data and enables both post-process analysis and potential real-time monitoring. It provides a scalable, data-driven approach to weld quality assessment for industrial applications.
激光束焊接（LBW）涉及激光与材料之间复杂且快速的相互作用，常常会产生诸如气孔形成等缺陷。在该过程中收集的发射信号提供了有价值的见解，但对于缺陷检测而言，直接解读这些信号却很困难。在本研究中，我们提出了一个数据驱动的框架，利用监督学习和无监督学习来解读激光束焊接中的电磁发射信号。我们的框架是在焊后监测阶段实现的，并且可以用作实时框架。监督方法使用与预定义缺陷相对应的标记数据（在本研究中，气孔形成是一个已定义缺陷的示例）。同时，无监督方法用于在不使用预定义标签的情况下识别异常情况。监督学习和无监督学习旨在在发射数据中找到参考值，以确定导致焊接缺陷的信号值（从而实现定量监测）。总共进行了81次焊接实验，记录了42个光谱通道的实时发射数据。从这些信号中提取了基于统计、时间和形状的特征，并使用主成分分析（PCA）进行了降维。长短期记忆（LSTM）模型在五折测试集上的平均均方误差（MSE）为0.0029，平均绝对误差（MAE）为0.0288。隔离森林算法在具有已验证缺陷标签的子集中检测异常焊缝时，准确率达到80%，精确率达到85.7%。所提出的框架增强了四维光子数据的可解释性，并实现了焊后分析和潜在的实时监测。它为工业应用中的焊接质量评估提供了一种可扩展的数据驱动方法。
