The rising popularity of intelligent manufacturing has brought numerous challenges to both industry and academia. Traditional cyber-physical systems have been transformed into human-cyber-physical systems, with more human factors involved. Thus, industrial systems have become increasingly complex with the interaction of many different components, and user-centered design and manufacturing are continuously replacing massive production in many domains.

In order to improve the efficiency of industrial systems to meet the requirements of users and consumers, systematic modeling and intelligent decision approaches are required for the automation of complex industrial systems. Advances in sensor and data storage technologies have allowed different types of sensors to be deployed in industrial systems. The data accumulated from various industrial sensors covers a wide range of data formats, such as time-series, images, video, and sound waves, among others. The data collected from industrial systems systematically reflects the operations of different system components and thus analyzing the data can offer a powerful way for complex system modeling and control. Recent successful applications of artificial Intelligence (AI) algorithms, especially deep learning algorithms, in various domains have proven their ability to solve complex data processing and analytics problems, such as non-linear regression, multi-label classification, and dynamic optimization. Since multiple types of data are employed to develop AI-based models, theories and applications of data-driven AI algorithms in complex industrial systems require more research. Data-driven decision making can therefore be performed based on both structured and unstructured data from industrial systems. With the algorithm-based modeling of complex industrial systems, the concept of digital twins can be facilitated, and better decisions can be made based on real-time simulation results.

The aim of this Special Issue is to collect research focusing on data-driven intelligence algorithms for systematic modeling, simulation, and optimization of complex industrial systems, such as manufacturing, power generation, or healthcare. We aim to provide an opportunity for us to gain a significantly better understanding of the current developments and the future direction of data-enabled intelligence in relation to complex industrial systems. We welcome both original research and review articles.

Potential topics include but are not limited to the following:

• Industrial applications of complex system theory
• Machine learning and deep learning for complex manufacturing system modeling
• Data-driven control of industrial systems
• Metaheuristic algorithms for system identification and optimization
• Multi-source data fusion for complex industrial systems
• Mobile computing and sensing for real-time system simulation
• System science and system engineering for industrial systems