About this Research Topic
Process systems engineering research heavily relies on computational modeling and simulation to aid optimization. While the discipline has seen significant advancements, thanks to increased computational resources and data-driven modeling, challenges remain. Accurate system identification and parameter determination are crucial, yet they often require resource-intensive simulations. Machine learning (ML) models offer potential as surrogate models, streamlining optimization and system identification processes. However, navigating issues like data noise, limited sensor configurations, and ML model interpretability continues to be a hurdle. The shift towards scientific machine learning and hybrid modeling in this field underscores the importance of domain knowledge, model clarity, and robust techniques. Emphasizing smart data acquisition and experimental design strategies further defines the evolving landscape of the process systems engineering research field.
We are seeking contributions that showcase the recent developments in computational modeling, simulation, and optimization within process systems engineering, with a particular emphasis on the integration of data-driven and machine learning techniques. One of the primary goals of this Research Topic is to highlight research that underscores the importance of accurate system identification, model selection, and parameter identification, especially when faced with resource limitations. We encourage discussion and solutions that address prevalent challenges in system identification of hybrid process models, such as data noise, limited sensor configurations, and the complexities inherent in interpreting ML models. Furthermore, we are looking to promote research emphasizing the significance of smart data strategies and efficient design of experiment concepts in this field. Ultimately, we aim to bridge the gap between traditional domain-specific knowledge and the cutting-edge techniques of scientific machine learning, process system engineering and design of experiments.
We welcome Original Research, Review, Mini-Review, and Perspective articles that include, but are not limited to, the following topics:
• Use of hybrid models in process systems engineering
• System identification strategies of hybrid models
• Uncertainty quantification and propagation
• Identifiability and systems theory aspects
• Scientific machine learning and physics-informed neural networks
• Modelling, numerical analysis and simulation
• Algorithms and software.
We are seeking contributions that showcase the recent developments in computational modeling, simulation, and optimization within process systems engineering, with a particular emphasis on the integration of data-driven and machine learning techniques. One of the primary goals of this Research Topic is to highlight research that underscores the importance of accurate system identification, model selection, and parameter identification, especially when faced with resource limitations. We encourage discussion and solutions that address prevalent challenges in system identification of hybrid process models, such as data noise, limited sensor configurations, and the complexities inherent in interpreting ML models. Furthermore, we are looking to promote research emphasizing the significance of smart data strategies and efficient design of experiment concepts in this field. Ultimately, we aim to bridge the gap between traditional domain-specific knowledge and the cutting-edge techniques of scientific machine learning, process system engineering and design of experiments.
We welcome Original Research, Review, Mini-Review, and Perspective articles that include, but are not limited to, the following topics:
• Use of hybrid models in process systems engineering
• System identification strategies of hybrid models
• Uncertainty quantification and propagation
• Identifiability and systems theory aspects
• Scientific machine learning and physics-informed neural networks
• Modelling, numerical analysis and simulation
• Algorithms and software.
Keywords: Process Systems Engineering, Scientific Machine Learning, System Identification, Smart Data Strategies, Design of Experiment
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
