Lei Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lei Yuan has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Huijun Li
University of Wollongong
10 shared publications - Zengxi Pan
University of Wollongong
10 shared publications Donghong Ding
7 shared publications- Fengyang He
University of Wollongong
6 shared publications Zengxi Pan
6 shared publications- Donghong Ding
School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing, China
5 shared publications
Latest Publications
- Open Access
- 20 November 2026
- Published by IOP Publishing in International Journal of Extreme Manufacturing
- Vol. 9 (2) , 022003
Geometry control in wire arc additive manufacturing: challenges, strategies, and future perspectives
The deployment of autonomous artificial intelligence (AI) within complex physical systems remains a grand challenge. While intelligent manufacturing aims to address this by infusing industrial processes with real-time adaptation, the prevailing approach often involves applying machine learning (ML) to isolated, well-defined sub-problems. This component-wise strategy, however, proves insufficient for processes like wire arc additive manufacturing (WAAM), where geometric fidelity is governed by deeply coupled, multi-scale thermo-fluid dynamics that defy simple predictive modelling. Here, using WAAM as a foundational case study of a complex cyber-physical system, we provide a systematic review of the intelligent strategies required for end-to-end geometry control. We deconstruct this challenge into a unified framework spanning the full process chain—pre-deposition, in-process, and post-deposition—and map the corresponding control methods onto the critical physical scales of the bead, layer, and part. Our synthesis reveals that the primary limitations are not a lack of algorithmic novelty but rather fundamental issues of model generalisation from sparse, high-cost data and the integration of heterogeneous physical priors. This analysis points towards a necessary paradigm shift: moving from static, data-driven prediction towards dynamic, autonomous control architectures. We argue that realising the next generation of intelligent manufacturing requires a focus on integrated systems, such as physics-informed digital twins and multi-sensor fusion platforms, that can holistically manage process complexity in real time.
- 20 November 2026
- Published by IOP Publishing in International Journal of Extreme Manufacturing
- Vol. 9 (2) , 022003
Open AccessGeometry control in wire arc additive manufacturing: challenges, strategies, and future perspectives
The deployment of autonomous artificial intelligence (AI) within complex physical systems remains a grand challenge. While intelligent manufacturing aims to address this by infusing industrial processes with real-time adaptation, the prevailing approach often involves applying machine learning (ML) to isolated, well-defined sub-problems. This component-wise strategy, however, proves insufficient for processes like wire arc additive manufacturing (WAAM), where geometric fidelity is governed by deeply coupled, multi-scale thermo-fluid dynamics that defy simple predictive modelling. Here, using WAAM as a foundational case study of a complex cyber-physical system, we provide a systematic review of the intelligent strategies required for end-to-end geometry control. We deconstruct this challenge into a unified framework spanning the full process chain—pre-deposition, in-process, and post-deposition—and map the corresponding control methods onto the critical physical scales of the bead, layer, and part. Our synthesis reveals that the primary limitations are not a lack of algorithmic novelty but rather fundamental issues of model generalisation from sparse, high-cost data and the integration of heterogeneous physical priors. This analysis points towards a necessary paradigm shift: moving from static, data-driven prediction towards dynamic, autonomous control architectures. We argue that realising the next generation of intelligent manufacturing requires a focus on integrated systems, such as physics-informed digital twins and multi-sensor fusion platforms, that can holistically manage process complexity in real time.
- Open Access
- 1 July 2026
- Published by Elsevier in Progress in Materials Science
- Vol. 163
Process innovations in wire arc additive manufacturing systems: progress, challenges and future opportunities
- 1 July 2026
- Published by Elsevier in Progress in Materials Science
- Vol. 163
Open AccessProcess innovations in wire arc additive manufacturing systems: progress, challenges and future opportunities
- Open Access
- 12 March 2026
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 250
Physics-guided generative data augmentation for vision-based signal processing under class-imbalanced conditions in directed energy deposition monitoring system
- 12 March 2026
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 250
Open AccessPhysics-guided generative data augmentation for vision-based signal processing under class-imbalanced conditions in directed energy deposition monitoring system
- Open Access
- 26 November 2025
- Published by Elsevier in Journal of Materials Processing Technology
- Vol. 347
Investigation of the mechanisms of structure-induced acoustic modulation in WA-DED metal additive manufacturing with an adaptive modelling approach
- 26 November 2025
- Published by Elsevier in Journal of Materials Processing Technology
- Vol. 347
Open AccessInvestigation of the mechanisms of structure-induced acoustic modulation in WA-DED metal additive manufacturing with an adaptive modelling approach
- Open Access
- 11 April 2025
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 232
A recurrent neural network-based monitoring system using time-sequential molten pool images in wire arc directed energy deposition
- 11 April 2025
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 232
Open AccessA recurrent neural network-based monitoring system using time-sequential molten pool images in wire arc directed energy deposition
- Top Cited PapersOpen Access
- 13 January 2025
- Published by IOP Publishing in International Journal of Extreme Manufacturing
- Vol. 7 (2) , 022016
A comprehensive review and future perspectives of simulation approaches in wire arc additive manufacturing (WAAM)
Wire arc additive manufacturing (WAAM) has emerged as a promising technique for producing large-scale metal components, favoured by high deposition rates, flexibility and low cost. Despite its potential, the complexity of WAAM processes, which involves intricate thermal dynamics, phase transitions, and metallurgical, mechanical, and chemical interactions, presents considerable challenges in final product qualities. Simulation technologies in WAAM have proven invaluable, providing accurate predictions in key areas such as material properties, defect identification, deposit morphology, and residual stress. These predictions play a critical role in optimising manufacturing strategies for the final product. This paper provides a comprehensive review of the simulation techniques applied in WAAM, tracing developments from 2013 to 2023. Initially, it analyses the current challenges faced by simulation methods in three main areas. Subsequently, the review explores the current modelling approaches and the applications of these simulations. Following this, the paper discusses the present state of WAAM simulation, identifying specific issues inherent to WAAM simulation itself. Finally, through a thorough review of existing literature and related analysis, the paper offers future perspectives on potential advancements in WAAM simulation strategies.
- 13 January 2025
- Published by IOP Publishing in International Journal of Extreme Manufacturing
- Vol. 7 (2) , 022016
Top Cited PapersOpen AccessA comprehensive review and future perspectives of simulation approaches in wire arc additive manufacturing (WAAM)
Wire arc additive manufacturing (WAAM) has emerged as a promising technique for producing large-scale metal components, favoured by high deposition rates, flexibility and low cost. Despite its potential, the complexity of WAAM processes, which involves intricate thermal dynamics, phase transitions, and metallurgical, mechanical, and chemical interactions, presents considerable challenges in final product qualities. Simulation technologies in WAAM have proven invaluable, providing accurate predictions in key areas such as material properties, defect identification, deposit morphology, and residual stress. These predictions play a critical role in optimising manufacturing strategies for the final product. This paper provides a comprehensive review of the simulation techniques applied in WAAM, tracing developments from 2013 to 2023. Initially, it analyses the current challenges faced by simulation methods in three main areas. Subsequently, the review explores the current modelling approaches and the applications of these simulations. Following this, the paper discusses the present state of WAAM simulation, identifying specific issues inherent to WAAM simulation itself. Finally, through a thorough review of existing literature and related analysis, the paper offers future perspectives on potential advancements in WAAM simulation strategies.
- 19 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (3) , 2630-2639
High-Frequency Real-Time Bead Geometry Measurement in Wire Arc Additive Manufacturing Based on Welding Signals
To support the increasing demand for smart manufacturing in wire arc additive manufacturing, such as digital twins, high-frequency real-time bead measurement is a long-standing challenge due to the protracted processing time of laser scans and vision-based approaches. This article introduces a pioneering approach for high-frequency, real-time bead geometry measurements. Utilizing high-frequency electric signal sensors, welding current, and voltage are captured. Time and frequency features are subsequently extracted and channeled into multilayer perceptron regressors to predict bead height and width. The model is trained using ground truth data derived from a laser profilometer. Furthermore, a feature dimension reduction algorithm coupled with an incremental learning framework is incorporated to optimize time efficiency and adaptability. Comprehensive practical experiments and a comparative analysis have been conducted. The results demonstrate that the proposed measurement system offers faster measuring speeds than vision-based methods while maintaining accuracy comparable to laser scanning techniques.
- 19 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (3) , 2630-2639
High-Frequency Real-Time Bead Geometry Measurement in Wire Arc Additive Manufacturing Based on Welding Signals
To support the increasing demand for smart manufacturing in wire arc additive manufacturing, such as digital twins, high-frequency real-time bead measurement is a long-standing challenge due to the protracted processing time of laser scans and vision-based approaches. This article introduces a pioneering approach for high-frequency, real-time bead geometry measurements. Utilizing high-frequency electric signal sensors, welding current, and voltage are captured. Time and frequency features are subsequently extracted and channeled into multilayer perceptron regressors to predict bead height and width. The model is trained using ground truth data derived from a laser profilometer. Furthermore, a feature dimension reduction algorithm coupled with an incremental learning framework is incorporated to optimize time efficiency and adaptability. Comprehensive practical experiments and a comparative analysis have been conducted. The results demonstrate that the proposed measurement system offers faster measuring speeds than vision-based methods while maintaining accuracy comparable to laser scanning techniques.
- Top Cited Papers
- 12 January 2023
- Published by Elsevier in Robotics and Computer-Integrated Manufacturing
- Vol. 82
Research and application of artificial intelligence techniques for wire arc additive manufacturing: a state-of-the-art review
- 12 January 2023
- Published by Elsevier in Robotics and Computer-Integrated Manufacturing
- Vol. 82
Top Cited PapersResearch and application of artificial intelligence techniques for wire arc additive manufacturing: a state-of-the-art review
- 14 December 2022
- Published by Elsevier in Journal of Manufacturing Processes
- Vol. 85, 683-694
Corner path optimization strategy for wire arc additive manufacturing of gap-free shapes
- 14 December 2022
- Published by Elsevier in Journal of Manufacturing Processes
- Vol. 85, 683-694
Corner path optimization strategy for wire arc additive manufacturing of gap-free shapes
- 1 March 2021
- Published by Elsevier in Journal of Manufacturing Processes
- Vol. 63, 24-34
Fabrication of metallic parts with overhanging structures using the robotic wire arc additive manufacturing
- 1 March 2021
- Published by Elsevier in Journal of Manufacturing Processes
- Vol. 63, 24-34
Fabrication of metallic parts with overhanging structures using the robotic wire arc additive manufacturing