Innovative technological solutions, leveraging artificial intelligence (AI) techniques, are being adopted across various industrial sectors to enable the automation of complex tasks that have traditionally required human expertise. This transformation strongly relies on data generated from production lines via sensor networks, serving as a valuable resource for improving several aspects of production processes. Their optimization spans such tasks as detecting anomalies, ensuring adherence to high-quality standards, monitoring the transformation of products, and minimizing material wastage. Furthermore, the capabilities of AI extend beyond production processes to provide support in the forecasting of abrupt changes in the conditions of machines to prevent disruption to operational continuity.
As researchers proceed further into the quest for enhanced production processes and sustainable practices, interest is also growing in the exploration of cutting-edge methods based on deep learning to facilitate autonomous decision-making among industrial units through machine-to-machine communications. This paradigm heavily relies on Edge and Internet-of-Things (IoT) technologies, which enable enhanced scalability and energy efficiency, as well as minimized latency. Nevertheless, this evolution introduces additional challenges, as the deployment of frameworks and models on resource-constrained devices requires a trade-off between performance optimization and adherence to real-time constraints. Therefore, gaining insights into how these models and procedures can operate in challenging real-world scenarios is crucial. Besides, industries such as automation, robotics, manufacturing, and automated transportation all demand a shift towards more reliable and safe approaches, and the need to establish trustworthiness and confidence in end users.
Combined with modern sensors, communication and big data analytics platforms, deep learning methodologies will play a key role in assisting human operators and increasing overall productivity. In this scenario, designing intelligent systems capable of integrating sensors, controllers, and wireless communication technologies in an effective orchestration is essential for a sustainable production. Thus, AI researchers are focusing on methods to support smart factories by designing flexible, adaptable and modular production lines.
This Research Topic aims to gather articles and research papers centered around deep learning solutions for industrial applications with an emphasis on sustainable performance, and proposing novel theories, frameworks, and datasets to explore the power of artificial intelligence and push the boundaries of what is currently possible in the industrial landscape.
Manuscript submissions from both academic and industrial sectors are encouraged for all aspects of industrial applications, which may include, but are not limited to:
Smart Manufacturing
- Real-time sensing
- Intelligent control
- Anomaly detection
- Quality inspection
- Fault detection and predictive maintenance
- Energy/resources consumption forecasting
- Planning and scheduling
Explainable AI (XAI)
- Feature/example-based techniques
- Model-agnostic/specific methods
- Local/global approaches
- Trust and transparency metrics
Optimization Techniques
- Model compression
- Knowledge distillation
- Pruning techniques
- Neural architecture search (NAS)
Smart Industries
- Food and beverage
- Automotive
- Transportation
- Aerospace
- Energy
- Electronics
- Wood
- Oil and gas
Keywords:
artificial intelligence (AI), sustainable production, trustworthiness, automation, Internet of Things (IoT)
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.
Innovative technological solutions, leveraging artificial intelligence (AI) techniques, are being adopted across various industrial sectors to enable the automation of complex tasks that have traditionally required human expertise. This transformation strongly relies on data generated from production lines via sensor networks, serving as a valuable resource for improving several aspects of production processes. Their optimization spans such tasks as detecting anomalies, ensuring adherence to high-quality standards, monitoring the transformation of products, and minimizing material wastage. Furthermore, the capabilities of AI extend beyond production processes to provide support in the forecasting of abrupt changes in the conditions of machines to prevent disruption to operational continuity.
As researchers proceed further into the quest for enhanced production processes and sustainable practices, interest is also growing in the exploration of cutting-edge methods based on deep learning to facilitate autonomous decision-making among industrial units through machine-to-machine communications. This paradigm heavily relies on Edge and Internet-of-Things (IoT) technologies, which enable enhanced scalability and energy efficiency, as well as minimized latency. Nevertheless, this evolution introduces additional challenges, as the deployment of frameworks and models on resource-constrained devices requires a trade-off between performance optimization and adherence to real-time constraints. Therefore, gaining insights into how these models and procedures can operate in challenging real-world scenarios is crucial. Besides, industries such as automation, robotics, manufacturing, and automated transportation all demand a shift towards more reliable and safe approaches, and the need to establish trustworthiness and confidence in end users.
Combined with modern sensors, communication and big data analytics platforms, deep learning methodologies will play a key role in assisting human operators and increasing overall productivity. In this scenario, designing intelligent systems capable of integrating sensors, controllers, and wireless communication technologies in an effective orchestration is essential for a sustainable production. Thus, AI researchers are focusing on methods to support smart factories by designing flexible, adaptable and modular production lines.
This Research Topic aims to gather articles and research papers centered around deep learning solutions for industrial applications with an emphasis on sustainable performance, and proposing novel theories, frameworks, and datasets to explore the power of artificial intelligence and push the boundaries of what is currently possible in the industrial landscape.
Manuscript submissions from both academic and industrial sectors are encouraged for all aspects of industrial applications, which may include, but are not limited to:
Smart Manufacturing
- Real-time sensing
- Intelligent control
- Anomaly detection
- Quality inspection
- Fault detection and predictive maintenance
- Energy/resources consumption forecasting
- Planning and scheduling
Explainable AI (XAI)
- Feature/example-based techniques
- Model-agnostic/specific methods
- Local/global approaches
- Trust and transparency metrics
Optimization Techniques
- Model compression
- Knowledge distillation
- Pruning techniques
- Neural architecture search (NAS)
Smart Industries
- Food and beverage
- Automotive
- Transportation
- Aerospace
- Energy
- Electronics
- Wood
- Oil and gas
Keywords:
artificial intelligence (AI), sustainable production, trustworthiness, automation, Internet of Things (IoT)
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.