About this Research Topic
With the continuous development of information technology and sensor technology, the accumulation of data in industry has reached an unprecedented level. In the era of big data, data-driven artificial intelligence (AI) models have been more widely used and developed in industrial production processes due to their flexibility and versatility, compared with mechanism and knowledge-driven models. For example, some key quality variables in industry cannot be collected by sensors in real time, but have to be analyzed through expensive instruments. For the purpose of obtaining these critical quality variables to control industrial processes, plenty of AI-based soft sensing models have been proposed. Furthermore, industrial security is a significant topic. AI-based process monitoring and fault diagnosis models will provide an alarm and diagnosis mechanism to reduce risks in industry.
Industrial production processes involve complex system engineering, which includes production equipment, information technology, a control system and other units. This Research Topic is dedicated to solving traditional industrial problems and improving existing industrial intelligence systems in the production process through AI technology. Examples include using deep learning to develop accurate soft sensors, utilizing AI technology to improve the performance of fault diagnosis systems, and implementing fault-tolerant control with advanced models. Progress in such areas faces significant challenges due to process characteristics and data problems, such as multimodality, nonlinearity, dynamics, etc. In addition, the rise of the industrial internet has increased the security risk of industrial intelligent systems. Therefore, issues such as industrial AI security and data privacy require further attention and research.
This Research Topic will focus on AI-driven industrial intelligence systems and related issues. Areas of interest include, but are not limited to:
- AI-based process monitoring and fault diagnosis technologies
- Data-driven soft sensing methods and their applications
- Advanced model-based fault-tolerant control
- Prognostics and health management (PHM) based on machine learning
- Industrial AI security
- AI-driven risk mitigation for supply chain management.
Industrial production processes involve complex system engineering, which includes production equipment, information technology, a control system and other units. This Research Topic is dedicated to solving traditional industrial problems and improving existing industrial intelligence systems in the production process through AI technology. Examples include using deep learning to develop accurate soft sensors, utilizing AI technology to improve the performance of fault diagnosis systems, and implementing fault-tolerant control with advanced models. Progress in such areas faces significant challenges due to process characteristics and data problems, such as multimodality, nonlinearity, dynamics, etc. In addition, the rise of the industrial internet has increased the security risk of industrial intelligent systems. Therefore, issues such as industrial AI security and data privacy require further attention and research.
This Research Topic will focus on AI-driven industrial intelligence systems and related issues. Areas of interest include, but are not limited to:
- AI-based process monitoring and fault diagnosis technologies
- Data-driven soft sensing methods and their applications
- Advanced model-based fault-tolerant control
- Prognostics and health management (PHM) based on machine learning
- Industrial AI security
- AI-driven risk mitigation for supply chain management.
Keywords: fault diagnosis, soft sensor, process monitoring, prognostics and health management, optimal control, industrial AI security
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.
