About this Research Topic
Chemical engineering is a branch of engineering that uses principles of chemistry, physics, mathematics to investigate the general rules of energy, material and momentum transformation, and reaction, so as to utilize energy and material more efficiently, profitably and safely in chemical industry. At present, chemical industries are faced with several challenging problems such as short in raw material, high energy consumption, strict safety and environment policy, which forces the industry and research institute to develop new technology, catalyst, material. Meanwhile, a big step has been made in artificial intelligence (AI) technology development, such as “Alpha Go”, robot, driverless car, Unmanned Aerial Vehicle and so on. Some of the AI technology has been applied in process industry. For example, deep learning, a very popular AI technique, has been shown to be effective in recognition of operation modes, fault detection and risk analysis in the refining process. Other recent advances in AI, such as reinforcement learning, statistical machine learning, and evolutionary computation, are promising in dealing with oil characterization, process modelling and optimization, decision-making, environmental perception, and autonomous intelligent control in various problems in chemical industry. Therefore, it is timely and of paramount importance to deeply integrate AI technology with chemical industry to achieve high-performance catalyst, accurate control, optimum planning and operation scheme with the help of ubiquitous sensing, proactive understanding, big data and automated learning.
This special issue will feature the most recent developments and the state-of-the-art of AI for chemical process industry. The targeted audience includes both academic researchers and industrial practitioners. It aims to provide a springboard to facilitate interdisciplinary research and share most recent developments in various related fields.
Topics of interest for the special issue include but are not limited to the following areas:
• Integration of deep learning methods in modelling and diagnosis
• Hybrid modelling integrating first principles and data
• Process reconstruction
• Mode optimization for unit operation
• Multiple-objective optimization in plant-wide optimization
• Distributed optimization and control in plant-wide optimization
• Automated machine learning in decision-making
• Human-Computer Interaction in integration of planning and scheduling
• Imbalanced learning in modelling and monitoring
• Data-driven modelling for oil rapid characterization
• Generative adversarial learning in modelling and monitoring
• Autonomous intelligent and cooperative control
• Computational intelligence in plant operation and troubleshooting
• Big data in safety monitoring, risk assessment and environmental protection
• Visualization, interpretation, and virtual manufacturing
Keywords: process modeling, material transformation, artificial intelligence, data science, machine learning, process manufacturing
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.