Special Session VI
Data-driven Modeling and Optimization for Large-scale Systems in Intelligent Manufacturing
大规模智能制造系统数据驱动建模与优化
Introduction:
Data-driven modeling and optimization techniques play an important role in large-scale industrial systems central to intelligent manufacturing. By applying advanced analytics, machine learning algorithms, and artificial intelligence, manufacturers can predict system behaviors, optimize operational parameters, and achieve significant improvements in productivity and quality. This leads to smarter, more flexible, and sustainable manufacturing systems equipped to meet the challenges of the modern industrial landscape. However, there are several key challenges. First, the data collected from large-scale industrial systems exhibit dynamic, high-dimensional, and nonlinear characteristics, which pose significant difficulties for effective feature extraction using existing methods. Second, the complexity of neural networks results in a lack of interpretability in deep learning methods. Therefore, this special session calls for interpretable designs for data-driven modeling and intelligence optimization.
Any interpretable enhancement technique for large-scale industrial system modeling falls within this scope, including, but not limited to, deep learning methods, data-driven modeling, performance interpretability analysis, etc.
数据驱动建模与优化技术在作为智能制造核心的大规模工业系统中发挥着重要作用。通过应用先进的分析方法、机器学习算法以及人工智能，制造商能够预测系统行为、优化运行参数，并在生产率和质量方面实现显著提升。这将催生更智能、更灵活且更具可持续性的制造系统，使其有能力应对现代工业格局所带来的挑战。然而，也存在一些关键挑战。首先，从大规模工业系统中收集的数据呈现出动态、高维和非线性的特征，这给运用现有方法进行有效的特征提取带来了极大困难。其次，神经网络的复杂性导致深度学习方法缺乏可解释性。因此，本次专题研讨会征集数据驱动建模和智能优化方面具有可解释性的设计方案。任何针对大规模工业系统建模的可解释性增强技术均属于本专题的范畴，包括但不限于深度学习方法、数据驱动建模、性能可解释性分析等等。
Organizers:
|
Ling Li, Changsha University of Science & Technology, China Ling Li is the Associate Researcher, Master’s Supervisor, and Associate Dean of International College of Engineering, Deputy Department Head at the School of Electrical and Information Engineering, Changsha University of Science & Technology. With a long-standing focus on modelling and optimization of complex industrial processes, operating performance assessment, uncertain optimization, etc. She has presided over and participated in a number of research projects, including the projects funded by the National Natural Science Foundation of China (NSFC), the projects funded by the Natural Science Foundation of Hunan Province (NSFHNP), and the projects funded by the South China Grid (SCG) Science and Technology Project. In recent years, she has published more than ten high-quality papers in internationally recognized journals such as Information Sciences, Computers & Chemical Engineering, Neurocomputing, and IEEE Transactions on Industrial Informatics. |
|
Xiuli Zhu, University of Shanghai for Science and Technology, China Xiuli Zhu received the Ph.D. degree in control science and engineering from Donghua University, Shanghai. She was a Visiting Scholar with the Department of Chemical and Materials Engineering, University of Alberta, Edmonton, AB, Canada, from September 2019 to September 2021. She is currently a Lecturer at the University of Shanghai for Science and Technology, Shanghai, China. Her research interests include explainable artificial intelligence, fault diagnosis, data-driven modeling, and intelligence optimization. |
|
Meidi Sun, Changsha University of Science and Technology, China Meidi Sun received the B.S., M.S., and Ph.D. degrees in control engineering fromHunan University, Changsha, China, in 2010, 2014, and 2021, respectively. She is currently a Lecturer with the School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha. Her research interests include machine learning, health management, fault diagnosis, and intelligence optimization.
|
Submission Guideline:
Please submit your manuscript via Online Submission System: https://easychair.org/conferences/?conf=rcae2025
Please choose Special Session: Data-driven Modeling and Optimization for Large-scale Systems in Intelligent Manufacturing