Computational modeling, simulation, and optimization of manufacturing processes and materials systems have been a persistent endeavor of the engineering research community at large. The two primary factors that achieved significant progress in this field are exponential increases in computing power and the incorporation of data-driven modeling methods. Process and systems modeling often involve expensive and time-intensive simulations and experiments, but incorporation of machine learning (ML) models as efficient surrogate models could potentially enhance the understanding and reduce the optimization cost of the concerned processes and systems.
However, there is a rising need to go beyond the conventional data-driven techniques to address challenges, such as the presence of noise in data, limited budget, data sparsity, and lack of interpretability of ML models. Tackling these issues will enable more comprehensive modeling of manufacturing processes and discovery of novel material systems. From this, the new paradigm of Scientific Machine Learning is emerging, seeking to incorporate domain-awareness, interpretability, and robustness into the models and modeling techniques.
- Physics-informed ML for process/materials design and optimization
- Physics-informed ML for diagnostics, prognostics, and process control
- Uncertainty quantification in scientific machine learning
- Leveraging high-throughput framework for modeling and optimization
- Efficient modeling through adaptive and active learning algorithms
- Explainable AI and causal inference augmented predictive modeling
- Exploring state-of-the-art ML algorithms in modeling and optimization
- Understanding of systems through knowledge representation and reasoning
- Leveraging data-fusion and multi-fidelity techniques in modeling
Paper submission deadline: July 30, 2023
Initial review completed: September 30, 2023
Publication date: August 2024
Papers should be submitted electronically to the journal through the ASME Journal Tool. If you already have an account, log in as an author and select Submit Paper. If you do not have an account, you can create your one here.
Once at the Paper Submittal page, select ASME Journal of Computing and Information Science in Engineering, and then select the Special Issue on Scientific Machine Learning for Manufacturing Processes and Material Systems.
Papers received after the deadline or papers not selected for the Special Issue may be accepted for publication in a regular issue.
Dr. Anindya Bhaduri, GE Research, USA
Prof. Francisco Chinesta, ENSAM Institute of Technology, France
Prof. Elias Cueto, University of Zaragoza, Spain
Prof. Dehao Liu, Binghamton University, USA
Dr. John G. Michopoulos, Naval Research Laboratory, USA
Dr. Sandipp Krishnan Ravi, GE Research, USA
Prof. Jian-Xun Wang, University of Notre Dame, USA