Aims and scope
Industrial Artificial Intelligence (IAI) focuses research on AI applications in virtually all industrial processes. Concentrating on problem-solving from industrial perspectives, including the replacement of human interaction by intelligent machines, productivity improvements through embedding AI concepts into engineering systems, and insight discovery with machine learning and data mining techniques. IAI aims to establish effective communications between AI researchers and the industrial community, drive real-world applications of intelligent machines in industries, and provide effective and efficient solutions for problem-solving emerging Industry 4.0 challenges.
IAI will accept submission of research articles and encourage discussions centered around the utilization of Artificial Intelligence techniques, both established and cutting edge developments, to optimize or beneficially disrupt modern industrial practices. The journal will be among the first to provide a concentrated scientific, peer reviewed approach to systematically theorize and apply novel synergies of AI/Machine Learning to virtually every facet of industrial chains.
Specific topics to be covered include but are not limited to:
IAI will accept submission of research articles and encourage discussions centered around the utilization of Artificial Intelligence techniques, both established and cutting edge developments, to optimize or beneficially disrupt modern industrial practices. The journal will be among the first to provide a concentrated scientific, peer reviewed approach to systematically theorize and apply novel synergies of AI/Machine Learning to virtually every facet of industrial chains.
Specific topics to be covered include but are not limited to:
- Advanced machine learning techniques for industrial process intelligent sensing and industrial data modelling, such as edge computing, stochastic configuration networks and its variants, deep reservoir computing, federation learning, randomized fuzzy inference systems, and evolutionary computation.
- AI-driven data mining and industrial big data analytics, including causality analysis, feature extraction and knowledge acquisition, fast feature selection, robust fuzzy rule extraction, industrial data representation and visualization.
- AI-driven cooperative autonomous control, including new intelligent system theory and methods, such as cooperative control, autonomous control, operation optimization control, learning-based model predictive control, deep enhanced learning control, multi-agent collaborative sensing and control.
- AI-driven industrial process operational optimization decision-making, including intelligent decision system architecture and methods, such as non-convex optimization, dynamic intelligent optimization, intelligent decision-making based on incomplete information, data and model-enabled operational optimization, reinforcement learning for real-time optimization.
- AI-driven abnormal situation monitoring, image-based product quality surveillance, industrial internet-based remote monitoring and fault diagnosis, dynamic performance assessment, control performance monitoring and assessment, and predictive maintenance.
- Applications including digital twin and virtual manufacturing, smart grid, non-ferrous, petrochemical, sewage treatment, automating robots, drones, aircraft, submersibles, unmanned vehicles and other sports systems, and AI related applications in perception, cognition, decision making, control, and interaction.