Periodic Reporting for period 2 - IMOCO4.E (Intelligent Motion Control under Industry 4.E)
Okres sprawozdawczy: 2022-09-01 do 2023-08-31
The IMOCO4.E target is to provide vertically distributed edge-to-cloud intelligence for machines, robots and other human-in-the-loop cyber-physical systems having actively controlled moving elements. They face ever-growing requirements on long-term energy efficiency, size, motion speed, precision, adaptability, self-diagnostic, secure connectivity or new human-cognitive features.
IMOCO4.E strives to perceive and understand complex machines and/or robots. The two main pillars of this project are digital twins and AI principles (machine learning/deep learning). These pillars extend the I-MECH reference framework and methodology, by adding new functionality to Layer 3 and/or Layer 4 to deliver intelligible orchestration of (initially) a virtual and (later) physical implementation of the system. The virtual world (digital twin) facilitates a simulation environment where AI supports the optimization of individual system features and/or performance of a system of systems that interact.
State-of-the-art chip technology enables high computer power on the Edge layers (Layer 1) of the motion control systems, including high-speed drives and smart sensors. This ‘edge intelligence’ is expected to bring fast interpretation of massive data streams (like camera output) as input of higher control layers (Layer 2 & 3) to analyze and process the system performance and to perform real-time corrections.
In short, IMOCO4.E strives to deliver a reference platform consisting of AI and digital twin toolchains and a set of mating building blocks for resilient manufacturing applications. The optimal energy efficient performance and easy (re)configurability, traceability and cyber-security are crucial. The IMOCO4.E reference platform benefits will be directly verified in applications for semiconductors, packaging, industrial robotics and healthcare. Additionally, the project demonstrates the results in other generic “motion-control-centered” domains.
IMOCO4.E strives to perceive and understand complex machines and/or robots. The two main pillars of this project are digital twins and AI principles (machine learning/deep learning). These pillars extend the I-MECH reference framework and methodology, by adding new functionality to Layer 3 and/or Layer 4 to deliver intelligible orchestration of (initially) a virtual and (later) physical implementation of the system. The virtual world (digital twin) facilitates a simulation environment where AI supports the optimization of individual system features and/or performance of a system of systems that interact.
State-of-the-art chip technology enables high computer power on the Edge layers (Layer 1) of the motion control systems, including high-speed drives and smart sensors. This ‘edge intelligence’ is expected to bring fast interpretation of massive data streams (like camera output) as input of higher control layers (Layer 2 & 3) to analyze and process the system performance and to perform real-time corrections.
In short, IMOCO4.E strives to deliver a reference platform consisting of AI and digital twin toolchains and a set of mating building blocks for resilient manufacturing applications. The optimal energy efficient performance and easy (re)configurability, traceability and cyber-security are crucial. The IMOCO4.E reference platform benefits will be directly verified in applications for semiconductors, packaging, industrial robotics and healthcare. Additionally, the project demonstrates the results in other generic “motion-control-centered” domains.
Year 1:
IMOCO4.E project was successfully kicked-off on 8-10th September 2021 as a remote meeting (because of COVID-19 restrictions). The consortium assessed the demands placed on future smart manufacturing in Europe from a mechatronics and service-oriented point of view and established the current state of the art of IMOCO4.E relevant technologies as well as identified the latest promising emerging trends in smart motion control and smart manufacturing. We have also identified the shortcomings of existing solutions in meeting European manufacturing and production challenges in the future. In Work Package 2 an architecture was defined to meet the objectives. This architecture mainly serves effective technical communication within the consortium. E.g. building block owners can denote context and interfaces. Pilot, Demonstrator and Use Case owners can explain ‘at what layer’ IMOCO4.E will bring what type of improvements. A more detailed ‘requirement specification’ of Pilots, Demonstrators and Use Cases has been defined. Parallel to previous ‘definition’, deepening development of high-precision motion control, digital twin concept and demonstration and validation has started in several Work Packages. Furthermore, initial project dissemination and exploitation activities have been planned and started. The project consortium has also been able to present the very first results at several international conferences. Finally, after many remote meetings at M12 (Sep 2022) the consortium was able to physically meet in Riga, Latvia.
Year 2:
Elaborating on the generic requirements and the detailed requirements for each layer, a workshop has been organized that defines the generic IMOCO4.E framework, including different refinements to dedicated architectures for each Pilot, Demonstrator and Use Case. The generic reference framework has been published in the ETFA 2023 conference.
Meanwhile, many novel IMOCO4.E technologies have been developed by the consortium. These developments have been organized in 10 abstract building blocks that are eventually embodied in a total of 85 different solutions. These solutions are systematically verified and validated with the formation of hardware, software and integration catalogs. In this way, the 1st iteration of the IMOCO4.E W-model framework development has been executed and reported, up to and including the Pilot, Demonstrator and Use Case integrations.
Particular attention was given to the many different forms and usages of digital twins and AI-based modelling solutions. The IMOCO4.E initial guidelines have been reported. These are currently being explored and evaluated by all project partners, where also the various XiL approaches and toolchains are taken into consideration. A dedicated workshop on model management has been held, in which the consistency between models, data and experiments has been addressed for digital twins during the operational lifecycle phase.
Project dissemination and exploitation activities have been continued, resulting in contents for the IMOCO4.E website, blogposts, social media, promotional material, publications, participation in events, networking with other projects, training courses and the regular IMOCO4.E newsletters.
In addition to many online meetings in different compositions, the consortium was able to physically meet in Bilbao, Brno and Eindhoven/Nijmegen to report and share the project results amongst themselves.
IMOCO4.E project was successfully kicked-off on 8-10th September 2021 as a remote meeting (because of COVID-19 restrictions). The consortium assessed the demands placed on future smart manufacturing in Europe from a mechatronics and service-oriented point of view and established the current state of the art of IMOCO4.E relevant technologies as well as identified the latest promising emerging trends in smart motion control and smart manufacturing. We have also identified the shortcomings of existing solutions in meeting European manufacturing and production challenges in the future. In Work Package 2 an architecture was defined to meet the objectives. This architecture mainly serves effective technical communication within the consortium. E.g. building block owners can denote context and interfaces. Pilot, Demonstrator and Use Case owners can explain ‘at what layer’ IMOCO4.E will bring what type of improvements. A more detailed ‘requirement specification’ of Pilots, Demonstrators and Use Cases has been defined. Parallel to previous ‘definition’, deepening development of high-precision motion control, digital twin concept and demonstration and validation has started in several Work Packages. Furthermore, initial project dissemination and exploitation activities have been planned and started. The project consortium has also been able to present the very first results at several international conferences. Finally, after many remote meetings at M12 (Sep 2022) the consortium was able to physically meet in Riga, Latvia.
Year 2:
Elaborating on the generic requirements and the detailed requirements for each layer, a workshop has been organized that defines the generic IMOCO4.E framework, including different refinements to dedicated architectures for each Pilot, Demonstrator and Use Case. The generic reference framework has been published in the ETFA 2023 conference.
Meanwhile, many novel IMOCO4.E technologies have been developed by the consortium. These developments have been organized in 10 abstract building blocks that are eventually embodied in a total of 85 different solutions. These solutions are systematically verified and validated with the formation of hardware, software and integration catalogs. In this way, the 1st iteration of the IMOCO4.E W-model framework development has been executed and reported, up to and including the Pilot, Demonstrator and Use Case integrations.
Particular attention was given to the many different forms and usages of digital twins and AI-based modelling solutions. The IMOCO4.E initial guidelines have been reported. These are currently being explored and evaluated by all project partners, where also the various XiL approaches and toolchains are taken into consideration. A dedicated workshop on model management has been held, in which the consistency between models, data and experiments has been addressed for digital twins during the operational lifecycle phase.
Project dissemination and exploitation activities have been continued, resulting in contents for the IMOCO4.E website, blogposts, social media, promotional material, publications, participation in events, networking with other projects, training courses and the regular IMOCO4.E newsletters.
In addition to many online meetings in different compositions, the consortium was able to physically meet in Bilbao, Brno and Eindhoven/Nijmegen to report and share the project results amongst themselves.
The project outputs will affect the entire value chain of the production automation and application markets. The joint approach to define a unifying architecture to meet commonly recognized challenges brings better comprehension and lifts Europe's competence level in this domain. Through the further evolved I-MECH methodology, it creates a sustainable proposition, such as “digital twins as a service” or “(generative) machine design as a service”, for the ongoing smartification of industries. It should allow also small and medium enterprises to be integral part of rapid development cycle based on digital twinning.