In recent years, the manufacturing sector is transforming towards digitalization, networking, automation and intelligence. Deep integration of Cyber-Physical Systems through Smart Manufacturing and Digital Twins has tremendous potential to enhance the total performance of manufacturing systems. Digital Twins are a data-driven virtual representation of physical systems which uses real-time data analytics to visualize, analyze, and monitor the performance of a manufacturing system. Together with Smart Manufacturing, a Digital Twin is considered a highly innovative and futuristic concept enabled by IoT, multi-sensor-fusion, Augmented Reality/Virtual reality (AR/VR), cloud computing, Big Data, and Artificial Intelligence (AI). In such data-driven systems, computational intelligence and the efficiency of their built-in models are extremely critical since they affect the system's overall performance.
Though data-driven systems enhance manufacturing processes' overall productivity and efficiency, inefficient computational models can cause prediction latencies and inaccuracies, especially during real-time predictions. Since the data generated and acquired during manufacturing processes have increased exponentially after the introduction of multi-sensor systems, the relevant information extraction and real-time response prediction have been a real bottleneck.
In this scenario, there is a growing need to develop, investigate, and apply innovative computational models, techniques and algorithms in smart manufacturing systems. These computational techniques can be based on Machine Learning, swarm intelligence, evolutionary algorithms etc. Some common areas of application for such models are optimal feature selection, dimensionality reduction, process optimization, response prediction, condition monitoring and intelligent data handling.
The Research Topic aims to collect the latest scientific contributions on intelligent computing techniques in Smart Manufacturing systems towards better process efficiency and accuracy. The concepts, methodologies, and applications of computational intelligence related to Digital Twins, Digital Manufacturing, Computed Integrated Design and Manufacturing, Multi-Sensor Systems, Condition Monitoring, Process Control, Manufacturing Optimization or any other relevant topics will be covered in the collection.
The main research themes include but are not limited to:
• Innovative AI/ML computational techniques for increased computational efficiency and accuracy
• Recent developments in evolutionary algorithms
• Latest advancements and application of swarm-based intelligence in manufacturing applications
• Other advanced optimization techniques focusing on manufacturing applications and services
• Intelligent data handling in Digital Twins
• Real-time optimization for condition monitoring and process control
Keywords:
Digital twins, Smart Manufacturing, Optimization, Swarm Intelligence, Evolutionary Algorithm, AI, Machine learning, Digital 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.
In recent years, the manufacturing sector is transforming towards digitalization, networking, automation and intelligence. Deep integration of Cyber-Physical Systems through Smart Manufacturing and Digital Twins has tremendous potential to enhance the total performance of manufacturing systems. Digital Twins are a data-driven virtual representation of physical systems which uses real-time data analytics to visualize, analyze, and monitor the performance of a manufacturing system. Together with Smart Manufacturing, a Digital Twin is considered a highly innovative and futuristic concept enabled by IoT, multi-sensor-fusion, Augmented Reality/Virtual reality (AR/VR), cloud computing, Big Data, and Artificial Intelligence (AI). In such data-driven systems, computational intelligence and the efficiency of their built-in models are extremely critical since they affect the system's overall performance.
Though data-driven systems enhance manufacturing processes' overall productivity and efficiency, inefficient computational models can cause prediction latencies and inaccuracies, especially during real-time predictions. Since the data generated and acquired during manufacturing processes have increased exponentially after the introduction of multi-sensor systems, the relevant information extraction and real-time response prediction have been a real bottleneck.
In this scenario, there is a growing need to develop, investigate, and apply innovative computational models, techniques and algorithms in smart manufacturing systems. These computational techniques can be based on Machine Learning, swarm intelligence, evolutionary algorithms etc. Some common areas of application for such models are optimal feature selection, dimensionality reduction, process optimization, response prediction, condition monitoring and intelligent data handling.
The Research Topic aims to collect the latest scientific contributions on intelligent computing techniques in Smart Manufacturing systems towards better process efficiency and accuracy. The concepts, methodologies, and applications of computational intelligence related to Digital Twins, Digital Manufacturing, Computed Integrated Design and Manufacturing, Multi-Sensor Systems, Condition Monitoring, Process Control, Manufacturing Optimization or any other relevant topics will be covered in the collection.
The main research themes include but are not limited to:
• Innovative AI/ML computational techniques for increased computational efficiency and accuracy
• Recent developments in evolutionary algorithms
• Latest advancements and application of swarm-based intelligence in manufacturing applications
• Other advanced optimization techniques focusing on manufacturing applications and services
• Intelligent data handling in Digital Twins
• Real-time optimization for condition monitoring and process control
Keywords:
Digital twins, Smart Manufacturing, Optimization, Swarm Intelligence, Evolutionary Algorithm, AI, Machine learning, Digital 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.