A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks
作者: Sen Li, Xiaoying Liu, Xiaojian Xu, Chendong Shao, Yaqi Wang, Ling Lan, Xinhua Tang, Haichao Cui
分类: cs.CV, cs.AI
发布日期: 2026-06-24
DOI: 10.1016/j.jmapro.2026.01.035
💡 一句话要点
提出SimPhysNet以解决激光焊接渗透预测问题
🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱四：生成式动作 (Generative Motion)
关键词: 激光焊接 渗透预测 自监督学习 物理信息神经网络 少量学习
📋 核心要点
- 现有的监督学习方法在激光焊接渗透预测中依赖大量高质量标记数据，限制了其在工业应用中的有效性。
- 本文提出的SimPhysNet算法通过自监督学习结合物理先验，能够在仅有少量标记图像的情况下进行高效的渗透预测。
- 实验结果显示，SimPhysNet在使用200个标记图像时达到了96.06%的分类准确率，显著优于传统方法的性能。
📝 摘要（中文）
激光焊接的全渗透性对实现无缺陷焊接接头至关重要，因此准确预测渗透状态对于确保焊接质量至关重要。为此，本文提出了SimPhysNet，这是一种新颖的算法，能够仅使用有限数量的标记图像实现激光焊接渗透预测的高分类准确率。该方法有效克服了监督学习分类算法在工业应用中对大量高质量标记数据的依赖。SimPhysNet的核心是将物理先验嵌入对比学习框架中的独特自监督学习范式。通过结合物理信息神经网络（PINN），该模型能够从大量未标记数据中提取熔池和钥孔的物理特征，同时三个图像增强任务进一步提升其泛化能力。实验结果表明，SimPhysNet在仅使用200个标记图像的情况下，达到了96.06%的分类准确率，表现与使用整个标记数据集的传统监督学习算法相当。
🔬 方法详解
问题定义：本文旨在解决激光焊接过程中的渗透预测问题，现有方法因对大量标记数据的依赖而面临应用限制。
核心思路：SimPhysNet通过自监督学习与物理信息神经网络相结合，利用未标记数据提取物理特征，从而减少对标记数据的需求。
技术框架：该方法的整体架构包括自监督学习模块、物理信息神经网络和少量标记图像的原型网络，形成一个完整的预测流程。
关键创新：SimPhysNet的创新在于将物理先验嵌入对比学习框架，突破了传统监督学习对标记数据的依赖，实现了高效的渗透预测。
关键设计：模型设计中采用了特定的损失函数以优化物理特征提取，并通过图像增强技术提升模型的泛化能力。
📊 实验亮点
实验结果表明，SimPhysNet在仅使用200个标记图像的情况下，达到了96.06%的分类准确率，表现与使用整个标记数据集的传统监督学习算法相当，显示出其在数据稀缺情况下的优越性。
🎯 应用场景
该研究的潜在应用领域包括激光焊接自动化、智能制造和工业机器人等，能够显著提升焊接质量和效率。未来，SimPhysNet有望推动焊接过程的智能化和自动化，减少人工干预，提高生产效率。
📄 摘要（原文）
The laser welding full-penetration is of critical importance, as it constitutes one of the fundamental factors in achieving defect-free welded joints. Accurate prediction of the penetration state is therefore essential for ensuring weld quality. To this end, this paper introduces SimPhysNet, a novel algorithm that achieves high classification accuracy in laser welding penetration prediction using only a limited number of labelled images. This approach effectively overcomes the limitations of supervised learning classification algorithms, which are hindered in industrial applications by their dependence on extensive, high-quality labelled data. The core of SimPhysNet is a unique self-supervised learning paradigm that embeds physical priors into a contrastive learning framework. By incorporating a physics-informed neural network (PINN), the model is guided to extract physically meaningful features of the molten pool and keyhole from a large set of unlabelled data, while three image augmentation tasks further enhance its generalization capabilities. Subsequently, a few-shot learning strategy, based on prototypical networks, enables robust classification by constructing class representations from a minimal set of labelled images. Experimental results demonstrate that SimPhysNet achieves a classification accuracy of 96.06% using only 200 labelled images (approximately 5% of the total labelled dataset), which is comparable to the performance of conventional supervised learning algorithms that utilize the entire labelled dataset. This work presents a new, efficient, and highly accurate method, providing the way for the intelligent automation of laser welding.