PulseAugur
EN
LIVE 07:52:29

New AI algorithms predict welding penetration with less labeled data · 2 sources tracked

By PulseAugur Editorial · [4 sources] ·

Researchers have developed new algorithms for predicting welding penetration status, addressing limitations in traditional supervised deep learning methods. One approach utilizes unsupervised domain adaptation with a gradual source domain expansion strategy to improve model performance across different welding processes like TIG and laser welding. Another method employs self-supervised learning with physics-informed neural networks and few-shot learning to achieve high accuracy in laser welding penetration prediction using minimal labeled data. AI

IMPACT These methods could significantly reduce the need for extensive labeled data in industrial welding applications, paving the way for more efficient and automated quality control.

RANK_REASON Two arXiv papers detailing novel algorithms for welding penetration prediction.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 4 sources. How we write summaries →

New AI algorithms predict welding penetration with less labeled data · 2 sources tracked

COVERAGE [4]

  1. arXiv cs.AI TIER_1 English(EN) · Xinhua Tang ·

    A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding

    Supervised deep learning has been widely used for weld penetration state classification; however, its performance often degrades significantly under domain shift, such as when transferring models between welding processes with distinct physical mechanisms:for instance, from arc-d…

  2. arXiv cs.AI TIER_1 English(EN) · Haichao Cui ·

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

    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…

  3. arXiv cs.CV TIER_1 English(EN) · Sen Li, Xiaoying Liu, Xiaojian Xu, Chendong Shao, Yaqi Wang, Ling Lan, Xinhua Tang, Haichao Cui ·

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

    arXiv:2606.26059v1 Announce Type: new Abstract: 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 …

  4. arXiv cs.CV TIER_1 English(EN) · Sen Li, Haichao Cui, Chendong Shao, Yaqi Wang, Xinhua Tang ·

    A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding

    arXiv:2606.26078v1 Announce Type: new Abstract: Supervised deep learning has been widely used for weld penetration state classification; however, its performance often degrades significantly under domain shift, such as when transferring models between welding processes with disti…

RELATED ENTITIES

RELATED TOPICS