Periodic Reporting for period 1 - EnerMan (ENERgy-efficient manufacturing system MANagement)
Okres sprawozdawczy: 2021-01-01 do 2022-06-30
Industrial production in Europe uses large amounts of energy. To reduce it we need to apply control automation closed loops also on energy consumption optimization as part of a holistic energy sustainability approach. A KPI in the factory production management integrating the energy sustainability and energy consumption is necessary.
The typical approach of in manufacturing management measures and accesses energy consumption on the base of few static measuring points in the line rather than holistically. This hinders accurate metrics on the consumed energy and provides a false view of the factory’s energy consumption and associated cost. The problem increases with higher complexity when the “hidden” information amount on energy consumptionis is considerable. Environmental physical parameter variations and also, machine degradation may impact energy consumption. To extract hidden information from data, a holistic data processing approach based on big data analytics and/or artificial intelligence is needed.
The industrial sector uses more energy than any other end-use sector, (~54% of the world’s total delivered energy). Geo and socio-political situations have a strong impact on the cost of, and amount of energy required. The cost of energy has also an indirect impact on productivity and cost to the market of the produced goods. In Europe the industrial sector creates 15% of the overall GDP with a value of sold production in 2021, in the EU amounted to €5209 billion. Hindering the productivity of the manufacturing process in this situation would heavily hinder the European economy and its associated workplaces.
Furthermore the amount of energy used in the industrial sector generates heavy environmental impact and its reduction would contribute significantly to a drop in harmful emissions of pollutants and greenhouse gases
The achievement of energy consumption reduction will require new competences, professions, and job-places in the future, with is a potential up to 152,191 jobs (high-end estimate) to be created in the industrial sector within 2030 because of energy consumption savings, assuming no productivity improvements in the energy saving activity.
By reducing industrialcosts, EnerMan will have a significant impact on the creation of more high-added value jobs in the fields of data science, AI, software engineering, digital twin technology and will shape professions for the factories of the future and a profound impact on the quality of life of citizens, both directly involved in manufacturing settings and on the wider societal community.
EnerMan overall objectives are:
Obj. 1: Design an Intelligent, autonomous, flexible and reconfigurable energy sustainability manufacturing closed control loop Manager to constantly adapt the manufacturing process, product line, equipment functionality in order to always comply with operator determined energy sustainability indicators.
Obj. 2: Provide intelligent, holistic, secure and trusted sensor data collection and analysis mechanism that processes energy data from heterogeneous Factory actors to extract accurate energy sustainability metrics
Obj. 3: Structure a FOF Digital twin to simulate the factory operations and predicts holistically, based on historical and real collected data, a factory energy sustainability fingerprint. The Digital Twin considers the energy impact of human operator behaviour
Obj. 4: Consider, in the EnerMan lifecycle, users and operators to provide Extended Reality solutions that increase their situational awareness on energy sustainability well practices for the industrial process
Obj. 5: Integrate the EnerMan various tools into a unified solution and realize industrial manufacturing opportunities in energy consuming environments by validating tools and techniques in real-world settings
Obj. 6: Specify a standardized regulation framework for energy sustainability optimization achievement in multiple industry manufacturing environments. Also, specify a certification strategy for industrial manufacturing energy sustainability
Obj. 7: Define evidence-based business and financing models along with a business plan for the post project sustainable exploitation of the EnerMan framework.
stproject sustainable exploitation of the EnerMan framework.
The typical approach of in manufacturing management measures and accesses energy consumption on the base of few static measuring points in the line rather than holistically. This hinders accurate metrics on the consumed energy and provides a false view of the factory’s energy consumption and associated cost. The problem increases with higher complexity when the “hidden” information amount on energy consumptionis is considerable. Environmental physical parameter variations and also, machine degradation may impact energy consumption. To extract hidden information from data, a holistic data processing approach based on big data analytics and/or artificial intelligence is needed.
The industrial sector uses more energy than any other end-use sector, (~54% of the world’s total delivered energy). Geo and socio-political situations have a strong impact on the cost of, and amount of energy required. The cost of energy has also an indirect impact on productivity and cost to the market of the produced goods. In Europe the industrial sector creates 15% of the overall GDP with a value of sold production in 2021, in the EU amounted to €5209 billion. Hindering the productivity of the manufacturing process in this situation would heavily hinder the European economy and its associated workplaces.
Furthermore the amount of energy used in the industrial sector generates heavy environmental impact and its reduction would contribute significantly to a drop in harmful emissions of pollutants and greenhouse gases
The achievement of energy consumption reduction will require new competences, professions, and job-places in the future, with is a potential up to 152,191 jobs (high-end estimate) to be created in the industrial sector within 2030 because of energy consumption savings, assuming no productivity improvements in the energy saving activity.
By reducing industrialcosts, EnerMan will have a significant impact on the creation of more high-added value jobs in the fields of data science, AI, software engineering, digital twin technology and will shape professions for the factories of the future and a profound impact on the quality of life of citizens, both directly involved in manufacturing settings and on the wider societal community.
EnerMan overall objectives are:
Obj. 1: Design an Intelligent, autonomous, flexible and reconfigurable energy sustainability manufacturing closed control loop Manager to constantly adapt the manufacturing process, product line, equipment functionality in order to always comply with operator determined energy sustainability indicators.
Obj. 2: Provide intelligent, holistic, secure and trusted sensor data collection and analysis mechanism that processes energy data from heterogeneous Factory actors to extract accurate energy sustainability metrics
Obj. 3: Structure a FOF Digital twin to simulate the factory operations and predicts holistically, based on historical and real collected data, a factory energy sustainability fingerprint. The Digital Twin considers the energy impact of human operator behaviour
Obj. 4: Consider, in the EnerMan lifecycle, users and operators to provide Extended Reality solutions that increase their situational awareness on energy sustainability well practices for the industrial process
Obj. 5: Integrate the EnerMan various tools into a unified solution and realize industrial manufacturing opportunities in energy consuming environments by validating tools and techniques in real-world settings
Obj. 6: Specify a standardized regulation framework for energy sustainability optimization achievement in multiple industry manufacturing environments. Also, specify a certification strategy for industrial manufacturing energy sustainability
Obj. 7: Define evidence-based business and financing models along with a business plan for the post project sustainable exploitation of the EnerMan framework.
stproject sustainable exploitation of the EnerMan framework.
• Definition of the end users’ needs and requirements
• SoA analysis of best practices and benchmark of existing solutions to achieve energy sustainability
• System architecture requirements elicitation
• EnerMan intelligent CPS end node hardware functionality created
• SW agents using holistic data processing and diverse sensing modalities created
• Design and Implementation of an edge IIoT level support mechanism
• Data Collection Mechanisms Security and Privacy Enhancement
• Design and Development of the Big Data Analytics Engine, of the EnerMan visualization platform, of the EnerMan intelligent Decision Support System and of a VR/xR environment to increase energy sustainability industry operators situational awareness
• Determination of Digital Twin parameters, energy related indicators
• Generation of energy-related flows and process consumption models for training and simulation purposes
• Developmen of the EnerMan prediction Engine
• Pilot and Real-conditions industrial settings specifications and launch of the assessment protocol
• SoA analysis of best practices and benchmark of existing solutions to achieve energy sustainability
• System architecture requirements elicitation
• EnerMan intelligent CPS end node hardware functionality created
• SW agents using holistic data processing and diverse sensing modalities created
• Design and Implementation of an edge IIoT level support mechanism
• Data Collection Mechanisms Security and Privacy Enhancement
• Design and Development of the Big Data Analytics Engine, of the EnerMan visualization platform, of the EnerMan intelligent Decision Support System and of a VR/xR environment to increase energy sustainability industry operators situational awareness
• Determination of Digital Twin parameters, energy related indicators
• Generation of energy-related flows and process consumption models for training and simulation purposes
• Developmen of the EnerMan prediction Engine
• Pilot and Real-conditions industrial settings specifications and launch of the assessment protocol
Expected Results
• create innovative CPS end nodes for the IIoT to use acceleration through reconfigurable hardware to considerable increase responsiveness of such devices
• use of virtual, computer-aided specific models in the form of an “Energy aware Digital Twin”
• provide a holistic optimization of production systems leading to energy-efficient systems, to pollutant reduction in operation
• consider new parameters of the virtual environment derived by ergonomic constraints, human tasks and human-machine interaction
• develop Data Assimilation methods to overpass the frontier between model simulations and experimental measurements
• use prediction algorithms for potential failure and estimate the Time-To-Failures. Take advantage of online monitoring to prevent potential degradation of any obvious signs of trouble
• A Cross reality (XR) framework will allow designers and researchers to verify different solutions provided for the working environment during participatory VDR sessions. Virtual models and 3D Geometrical data will be integrated with real inputs from workers and simulated machines to reduce as much as possible the need for physical prototypes. This could provide reviewers the possibility to evaluate different design solutions for enhanced manufacturing lines in real-time
• Virtual training performed on-line with CPS to drive operators in real time. Feedback on energy impact displayed with AR techniques. Usability of such a framework will be carefully considered
Potential Impacts:
• EnerMan will deploy, test and validate solutions that will reduce the energy consumption in production processes in real-life experiments at least 25%
• it will ensure the reduction of Lifecycle cost of at least 15% in real-life manufacturing environments
• it will improve the performance of Factories of the Future in terms of their environmental footprint
• it will deliver best practices for energy efficiency, driven by standardized procedures and relevant standardization bodies
• it will facilitate the application of energy efficient management procedures in real manufacturing environment
• create innovative CPS end nodes for the IIoT to use acceleration through reconfigurable hardware to considerable increase responsiveness of such devices
• use of virtual, computer-aided specific models in the form of an “Energy aware Digital Twin”
• provide a holistic optimization of production systems leading to energy-efficient systems, to pollutant reduction in operation
• consider new parameters of the virtual environment derived by ergonomic constraints, human tasks and human-machine interaction
• develop Data Assimilation methods to overpass the frontier between model simulations and experimental measurements
• use prediction algorithms for potential failure and estimate the Time-To-Failures. Take advantage of online monitoring to prevent potential degradation of any obvious signs of trouble
• A Cross reality (XR) framework will allow designers and researchers to verify different solutions provided for the working environment during participatory VDR sessions. Virtual models and 3D Geometrical data will be integrated with real inputs from workers and simulated machines to reduce as much as possible the need for physical prototypes. This could provide reviewers the possibility to evaluate different design solutions for enhanced manufacturing lines in real-time
• Virtual training performed on-line with CPS to drive operators in real time. Feedback on energy impact displayed with AR techniques. Usability of such a framework will be carefully considered
Potential Impacts:
• EnerMan will deploy, test and validate solutions that will reduce the energy consumption in production processes in real-life experiments at least 25%
• it will ensure the reduction of Lifecycle cost of at least 15% in real-life manufacturing environments
• it will improve the performance of Factories of the Future in terms of their environmental footprint
• it will deliver best practices for energy efficiency, driven by standardized procedures and relevant standardization bodies
• it will facilitate the application of energy efficient management procedures in real manufacturing environment