Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks

Source

arXiv

arxiv.org/abs/2606.26059v1

Read the source

Source

Plain-Language Brief

A new algorithm named SimPhysNet has been introduced to predict laser welding penetration with high accuracy using only a limited number of labelled images. The algorithm uses self-supervised learning and physics-informed neural networks, allowing it to work effectively in industrial applications where extensive, high-quality labelled data is not readily available. SimPhysNet achieved a classification accuracy of 96.06% with just 200 labelled images, which is comparable to the performance of traditional supervised learning algorithms using the entire labelled dataset.

What the Document Says

  • The paper introduces SimPhysNet, an algorithm for laser welding penetration prediction.
  • SimPhysNet uses self-supervised learning and a contrastive learning framework.
  • It incorporates a physics-informed neural network (PINN) to extract meaningful features from unlabelled data.
  • Three image augmentation tasks enhance its generalization capabilities.
  • A few-shot learning strategy based on prototypical networks enables robust classification using minimal labelled images.
  • SimPhysNet achieved 96.06% accuracy with 200 labelled images, compared to traditional methods with the entire dataset.

Key Concepts Mentioned

  • laser welding
  • penetration prediction
  • self-supervised learning
  • physics-informed neural networks
  • image augmentation
  • few-shot learning
  • prototypical networks

Claims Made by the Document

  • SimPhysNet achieves high classification accuracy in laser welding penetration prediction.
  • SimPhysNet overcomes limitations of supervised learning classification algorithms in industrial applications.

Evidence Used

  • Experimental results demonstrating 96.06% accuracy

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.