MEAE 2025

Special Session 1

 

Causality Analysis and Digital Twin towards Aerospace Manufacturing Systems | 航空航天制造系统因果分析与数字孪生

Introducation:

Breakthroughs have been made in the development of complex aerospace products in China. For instance, C919 large aircraft is accelerating into a new stage of production capacity ramp-up. Aerospace manufacturing systems require large-scale intelligent equipment and efficient human collaboration, where even minor deviations in any process step can substantially affect overall performance. Additionally, the key quality characteristics, critical process parameters, and their interdependencies remain unclear, which severely restricts processing accuracy, manufacturing quality, and production efficiency. Traditional modeling and analysis methods for manufacturing systems often rely on data-driven or probabilistic models. While these methods have shown utility, challenges such as limited data reuse, low model interpretability, and insufficient practical application hinder their ability to accurately capture the underlying mechanisms of aerospace manufacturing systems.

Causal inference represents a more advanced data analysis approach. Its objective is to establish causal relationships and has been widely applied in various fields. From the perspective of causal science, in the absence of precise models for aerospace manufacturing systems, accurately identifying causal relationships among system variables from data to reflect the operational laws and evolution mechanisms of manufacturing processes is a fundamental scientific issue.

Moreover, smart manufacturing in aerospace focuses on evolving production processes to enhance efficiency and mitigate risks. Digital twins, by creating virtual replicas of physical systems, offer substantial benefits, including accelerated development, predictive failure diagnostics, and reduced maintenance costs. However, realizing these benefits at scale requires a structured, integrated approach that combines data, artificial intelligence, and digital twins to create closed-loop control systems.

Therefore, this special session focuses on causality analysis and digital twin towards aerospace manufacturing systems. The topics include, but will not be limited to the following:

1. High-fidelity digital twin modeling of aerospace manufacturing systems

2. Data-driven causal analysis for aerospace manufacturing systems

3. Process intelligent optimization for aerospace manufacturing systems

4. Quality consistency control of aerospace manufacturing systems

5. Human-machine collaboration in aerospace manufacturing systems

6. Artificial intelligence decision-making in aerospace manufacturing systems

我国在航空航天复杂产品研发方面已取得重大突破。以C919大型客机为例，其生产正加速进入产能爬升新阶段。航空航天制造系统需要大规模智能设备和高效人机协作，其中任何工序环节的微小偏差都可能对整体性能产生重大影响。此外，关键质量特性、核心工艺参数及其内在关联仍不明确，严重制约了加工精度、制造质量和生产效率的提升。

传统制造系统建模分析方法多基于数据驱动或概率模型。虽然这些方法具有一定实用性，但存在数据复用性差、模型可解释性低、工程应用不足等挑战，难以准确刻画航空航天制造系统的内在机理。因果推断作为更高级的分析方法，以建立因果关系为目标，已在多个领域得到广泛应用。从因果科学视角来看，在缺乏航空航天制造系统精确模型的条件下，如何从数据中准确识别系统变量间的因果关系以反映制造过程的运行规律和演化机理，是亟待解决的基础科学问题。
此外，航空航天智能制造聚焦于优化生产过程以提升效率和降低风险。数字孪生通过创建物理系统的虚拟映射，可带来显著效益，包括加速研发进程、实现故障预测诊断和降低维护成本等。但要实现这些效益的规模化应用，需要构建融合数据、人工智能和数字孪生的结构化集成方法，形成闭环控制系统。
因此，本专题聚焦航空航天制造系统的因果分析与数字孪生技术，涵盖（但不限于）以下主题：
● 航空航天制造系统高保真数字孪生建模
● 基于数据驱动的航空航天制造系统因果分析
● 航空航天制造系统工艺智能优化
● 航空航天制造系统质量一致性控制
● 航空航天制造系统人机协作
● 航空航天制造系统人工智能决策

 

Organizers:

	Lilan Liu, Shanghai University, China Lilan Liu is currently a professor in the School of Mechatronic Engineering and Automation of Shanghai University, and also serves as the director of the Shanghai Key Laboratory of Intelligent Manufacturing and Robotics. She has been recognized as a Leading talents and excellent academic/technical leader in Shanghai, with a main research interest in industrial big data and digital twins, especially in digital quality control for aerospace equipment.			Yan-Ning Sun, Shanghai University, China Yan-Ning Sun is currently a Lecturer at School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China. His current research interests include the fundamental study of artificial intelligence, complex network and industrial systems, and data-driven decision-making methods in complex industrial processes. He has been serving as a reviewer for many top-tier international journals and conferences in his research field.
	Changchun Liu, Nanjing University of Aeronautics and Astronautics, China Changchun Liu is currently an Assistant Researcher at College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China. His main research direction is human-robot collaborative manufacturing systems. He was invited to serve as a member of the Digital Manufacturing and Human-centric Automation Professional Committee of the Institute of Electrical and Electronics Engineers (IEEE), and concurrently served as a youth member of the Human-centric Intelligent Manufacturing Academic Conference.			Zenggui Gao, Shanghai University, China Zenggui Gao is currently an associate professor at the School of Automation, Shanghai University, deputy director of the Intelligent Manufacturing Industry Software Research Centre, deputy Secretary General of the Shanghai Mechanical Engineering Society Industrial Intelligent Manufacturing Technology Committee, and director of the journal Computer Integrated Manufacturing Systems. His research direction is human-computer interaction and collaboration, industrial digital twin.
	Qinge Xiao, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China Qinge Xiao is an Assistant Researcher at the Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences. Her research focuses on process planning for complex CNC machining, industrial applications of deep reinforcement learning, and human-machine collaborative manufacturing systems. She has published nearly 30 SCI/EI-indexed papers in top journals, covering topics like human-machine system modeling, manufacturing condition monitoring, and process optimization.			Wei Qin, Shanghai Jiao Tong University, China Wei Qin is currently an Associate Professor and the Associate Head of Department of Industrial Engineering at School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China. His current research interests include modeling, control and optimization He serves as the editor-in-chief and guest editor for several top international journals, including the Journal of Intelligent Manufacturing, International Journal of Computer Integrated Manufacturing, and Journal of Cleaner Production.

 

Submission Guideline:

Please submit your manuscript via Online Submission System: https://easychair.org/my/conference?conf=meae2025
Please choose Special Session: Causality Analysis and Digital Twin towards Aerospace Manufacturing Systems