A physics-informed and data-driven framework for robotic welding in manufacturing

Abstract The development of artificial intelligence (AI)-based industrial data-driven models is the driving force behind the digital transformation of manufacturing processes and the application of smart manufacturing. However, in real-world industrial applications, the intricate interplay among dat...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingbo Liu, Fan Jiang, Shinichi Tashiro, Shujun Chen, Manabu Tanaka
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-60164-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850268903379304448
author Jingbo Liu
Fan Jiang
Shinichi Tashiro
Shujun Chen
Manabu Tanaka
author_facet Jingbo Liu
Fan Jiang
Shinichi Tashiro
Shujun Chen
Manabu Tanaka
author_sort Jingbo Liu
collection DOAJ
description Abstract The development of artificial intelligence (AI)-based industrial data-driven models is the driving force behind the digital transformation of manufacturing processes and the application of smart manufacturing. However, in real-world industrial applications, the intricate interplay among data quality, model accuracy, and generalizability poses significant challenges, hindering the effective deployment and scalability of data-driven models in complex manufacturing environments. To address this challenge, this paper proposes a universal Physics-informed Hybrid Optimization framework for Efficient Neural Intelligence (PHOENIX) in manufacturing, demonstrating its applicability in robotic welding scenarios. This framework systematically integrates physical principles into its input, model structure, and dynamic optimization processes, enabling proactive, real-time detection and predictive of welding instability. It achieves an accuracy of up to 98% for predictions within the next 50 ms and maintains an accuracy of 86% even for forecasts up to 1 s in advance. Through physics-informed data-driven modeling, the framework significantly reduces the dependence on high-cost data while maintaining the performance of the original model. By leveraging cloud-based optimization modules that integrate new data with historical experience, the framework enables autonomous model parameter optimization, ensuring its continuous adaptation to the complex and dynamic demands of industrial scenarios.
format Article
id doaj-art-ce8f1b53422b4ff08304b78c70dab7ed
institution OA Journals
issn 2041-1723
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-ce8f1b53422b4ff08304b78c70dab7ed2025-08-20T01:53:19ZengNature PortfolioNature Communications2041-17232025-05-0116111810.1038/s41467-025-60164-yA physics-informed and data-driven framework for robotic welding in manufacturingJingbo Liu0Fan Jiang1Shinichi Tashiro2Shujun Chen3Manabu Tanaka4Engineering Research Center of Advanced Manufacturing Technology for Automotive Components Ministry of Education, College of Mechanical & Energy Engineering, Beijing University of TechnologyEngineering Research Center of Advanced Manufacturing Technology for Automotive Components Ministry of Education, College of Mechanical & Energy Engineering, Beijing University of TechnologyJoining and Welding Research Institute, Osaka UniversityEngineering Research Center of Advanced Manufacturing Technology for Automotive Components Ministry of Education, College of Mechanical & Energy Engineering, Beijing University of TechnologyJoining and Welding Research Institute, Osaka UniversityAbstract The development of artificial intelligence (AI)-based industrial data-driven models is the driving force behind the digital transformation of manufacturing processes and the application of smart manufacturing. However, in real-world industrial applications, the intricate interplay among data quality, model accuracy, and generalizability poses significant challenges, hindering the effective deployment and scalability of data-driven models in complex manufacturing environments. To address this challenge, this paper proposes a universal Physics-informed Hybrid Optimization framework for Efficient Neural Intelligence (PHOENIX) in manufacturing, demonstrating its applicability in robotic welding scenarios. This framework systematically integrates physical principles into its input, model structure, and dynamic optimization processes, enabling proactive, real-time detection and predictive of welding instability. It achieves an accuracy of up to 98% for predictions within the next 50 ms and maintains an accuracy of 86% even for forecasts up to 1 s in advance. Through physics-informed data-driven modeling, the framework significantly reduces the dependence on high-cost data while maintaining the performance of the original model. By leveraging cloud-based optimization modules that integrate new data with historical experience, the framework enables autonomous model parameter optimization, ensuring its continuous adaptation to the complex and dynamic demands of industrial scenarios.https://doi.org/10.1038/s41467-025-60164-y
spellingShingle Jingbo Liu
Fan Jiang
Shinichi Tashiro
Shujun Chen
Manabu Tanaka
A physics-informed and data-driven framework for robotic welding in manufacturing
Nature Communications
title A physics-informed and data-driven framework for robotic welding in manufacturing
title_full A physics-informed and data-driven framework for robotic welding in manufacturing
title_fullStr A physics-informed and data-driven framework for robotic welding in manufacturing
title_full_unstemmed A physics-informed and data-driven framework for robotic welding in manufacturing
title_short A physics-informed and data-driven framework for robotic welding in manufacturing
title_sort physics informed and data driven framework for robotic welding in manufacturing
url https://doi.org/10.1038/s41467-025-60164-y
work_keys_str_mv AT jingboliu aphysicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT fanjiang aphysicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT shinichitashiro aphysicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT shujunchen aphysicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT manabutanaka aphysicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT jingboliu physicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT fanjiang physicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT shinichitashiro physicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT shujunchen physicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing
AT manabutanaka physicsinformedanddatadrivenframeworkforroboticweldinginmanufacturing