About this Research Topic
In the context of Circular Economy, Closed-Loop PLM extends the meaning of PLM in order to close the loop of the information among the different lifecycle phases of a product.
The degradation of functional components of engineering assets represents the main need for predictive maintenance. Degradation is also a major source of product defects. The Industrial Internet of Things (IIoT) and associated AI, Cloud and Edge Technologies allow for an efficient Data Driven approach – that takes also into account physics-based models and human expertise - to optimize the lifecycle of engineering assets and get most out of their value. There are two main technological approaches to do it: Predictive Maintenance and Zero Defect Manufacturing.
In this direction, emerging Artificial Intelligence and IIoT technologies will make machines “intelligent” by enhancing their ability to “think”, monitor their own use, enabling them to collaborate in new ways with digitally assisted workers to take appropriate actions avoiding sub-optimal operation conditions and, when necessary, notify authorized parties about various aspects of their “life”, in other words about possible imminent defects and needs for maintenance.
Intelligent Machines are meant to be used in the context of Industry 4.0 and IIoT, which may be defined as a global network infrastructure where physical and digital twin or digital shadow objects with unique ID are discovered and integrated seamlessly (taking into account security and privacy issues). They are able to offer and receive services, which are elements of business processes defined in the environment they become active.
Moreover, Intelligent Machines will be part of connected production systems, which should be able to dynamically create design, manufacturing and machine component experience contexts across their lifecycle. The ability of such intelligent machines to trustfully contribute to and exploit such digital threads and digital industrial contexts built through common and federated industrial data sharing spaces is a key enabler for the operation of smart AI services able to anticipate undesired manufacturing conditions and optimization of multi-stage zero defect control loops.
Together with that, ontologies and associated semantic technologies such as Knowledge Graphs are rapidly becoming popular in various domains and applications to deal with the tremendous increase of available data captured all along the lifecycle of a product and allow to go beyond “Big Data” and discover and explore their real meaning.
All of the above is making manufacturing develop more and more “cognitive” characteristics and so facilitating and enabling the augmentation of human-machine collaboration.
In this Research Topic, papers will address relevant questions such as:
• What are the main characteristics of Intelligent Machines?
• What processes are required to enable machines to “think”?
• What data is required to support the development and ongoing maintenance of Intelligent Machines?
• What if a machine could tell you what to do next with itself?
• How do we identify and manage the risks associated with Intelligent Machines making their own decisions?
• What code and software capabilities are needed to “drive” an Intelligent Machine?
• What are the roles and capabilities required for humans operating in an environment including Intelligent Machines?
• What are the business expectations for Intelligent Machines and what are the risks to realizing these results?
• What technologies would enable/facilitate the transition from research to real products
Note: Manuscripts submission is possible to Frontiers in Computer Science, Frontiers in Mechanical Engineering, Frontiers in Artificial Intelligence. In any author is interested in participating with a manuscript in scope with Frontiers in Big Data, please contact computerscience@frontiersin.org.
The degradation of functional components of engineering assets represents the main need for predictive maintenance. Degradation is also a major source of product defects. The Industrial Internet of Things (IIoT) and associated AI, Cloud and Edge Technologies allow for an efficient Data Driven approach – that takes also into account physics-based models and human expertise - to optimize the lifecycle of engineering assets and get most out of their value. There are two main technological approaches to do it: Predictive Maintenance and Zero Defect Manufacturing.
In this direction, emerging Artificial Intelligence and IIoT technologies will make machines “intelligent” by enhancing their ability to “think”, monitor their own use, enabling them to collaborate in new ways with digitally assisted workers to take appropriate actions avoiding sub-optimal operation conditions and, when necessary, notify authorized parties about various aspects of their “life”, in other words about possible imminent defects and needs for maintenance.
Intelligent Machines are meant to be used in the context of Industry 4.0 and IIoT, which may be defined as a global network infrastructure where physical and digital twin or digital shadow objects with unique ID are discovered and integrated seamlessly (taking into account security and privacy issues). They are able to offer and receive services, which are elements of business processes defined in the environment they become active.
Moreover, Intelligent Machines will be part of connected production systems, which should be able to dynamically create design, manufacturing and machine component experience contexts across their lifecycle. The ability of such intelligent machines to trustfully contribute to and exploit such digital threads and digital industrial contexts built through common and federated industrial data sharing spaces is a key enabler for the operation of smart AI services able to anticipate undesired manufacturing conditions and optimization of multi-stage zero defect control loops.
Together with that, ontologies and associated semantic technologies such as Knowledge Graphs are rapidly becoming popular in various domains and applications to deal with the tremendous increase of available data captured all along the lifecycle of a product and allow to go beyond “Big Data” and discover and explore their real meaning.
All of the above is making manufacturing develop more and more “cognitive” characteristics and so facilitating and enabling the augmentation of human-machine collaboration.
In this Research Topic, papers will address relevant questions such as:
• What are the main characteristics of Intelligent Machines?
• What processes are required to enable machines to “think”?
• What data is required to support the development and ongoing maintenance of Intelligent Machines?
• What if a machine could tell you what to do next with itself?
• How do we identify and manage the risks associated with Intelligent Machines making their own decisions?
• What code and software capabilities are needed to “drive” an Intelligent Machine?
• What are the roles and capabilities required for humans operating in an environment including Intelligent Machines?
• What are the business expectations for Intelligent Machines and what are the risks to realizing these results?
• What technologies would enable/facilitate the transition from research to real products
Note: Manuscripts submission is possible to Frontiers in Computer Science, Frontiers in Mechanical Engineering, Frontiers in Artificial Intelligence. In any author is interested in participating with a manuscript in scope with Frontiers in Big Data, please contact computerscience@frontiersin.org.
Keywords: Zero Defect Manufacturing, Predictive Maintenance, Data Driven Manufacturing, Industrial Internet of Things, Big Industrial Data, Industrial AI, Industry 4.0, PHM (Prognostics and Health Management), Intelligent Maintenance Systems
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.
