Periodic Reporting for period 3 - INEVITABLE (Optimization and performance improving in metal industry by digital technologies)
Reporting period: 2022-04-01 to 2023-03-31
The INEVITABLE project aimed to optimize and enhance processes in the steel and nonferrous sectors through digital upgrades, upgrading traditional process automation and control systems by integrating high-level decision support that improves process reasoning and response to fluctuations.
Problem/Issue being addressed:
The project focused on resource and energy-intensive sectors of the process industry, specifically the steel and nonferrous metals sector, which have a significant impact on energy and resource consumption. It aimed to address the challenges faced by these sectors in terms of equipment monitoring, process efficiency, environmental sustainability, and energy/material efficiency.
Importance for society:
The project is important for society as it improves energy efficiency, reduces environmental impact, and contributes to sustainability. The optimized production processes result in better product quality, reduced scrap, and increased efficiency, benefiting consumers and industries. The project's impact extends to other industries as well.
Overall objectives:
The INEVITABLE project aimed to enhance performance indicators in the steel and nonferrous sectors by retrofitting existing production sites with digital and innovative control technologies. Objectives included:
• Improve energy efficiency and reduce environmental impacts.
• Enhance product quality, reduce scrap and improve energy efficiency.
• Increase process repeatability.
• Optimize production by providing process models for testing the effects of process parameters.
• Develop soft sensors for estimating unmeasured process variables to enhance process control.
• Provide methods for process diagnostics and condition monitoring to detect and address errors before they become critical and cause interruptions.
Conclusions of the action:
The INEVITABLE project successfully developed and implemented digital technologies to optimize production processes in the steel and nonferrous metals sectors. Real operational demonstrations showed improvements in process performance, product quality, productivity, energy efficiency, yield, and equipment reliability. The project aligned with Europe's sustainability goals, reducing energy consumption and CO2 emissions while enhancing product quality and productivity. Six innovative solutions were identified for exploitation, including operator support tools and monitoring systems. Extensive dissemination activities raised awareness and engaged stakeholders through the project website, social media, and promotional materials. The project's achievements contribute to digital transformation and optimization in the steel and nonferrous metals sectors, providing valuable insights for other industries. INEVITABLE successfully met its objectives, promoting digitalization, efficiency, and sustainability.
Problem/Issue being addressed:
The project focused on resource and energy-intensive sectors of the process industry, specifically the steel and nonferrous metals sector, which have a significant impact on energy and resource consumption. It aimed to address the challenges faced by these sectors in terms of equipment monitoring, process efficiency, environmental sustainability, and energy/material efficiency.
Importance for society:
The project is important for society as it improves energy efficiency, reduces environmental impact, and contributes to sustainability. The optimized production processes result in better product quality, reduced scrap, and increased efficiency, benefiting consumers and industries. The project's impact extends to other industries as well.
Overall objectives:
The INEVITABLE project aimed to enhance performance indicators in the steel and nonferrous sectors by retrofitting existing production sites with digital and innovative control technologies. Objectives included:
• Improve energy efficiency and reduce environmental impacts.
• Enhance product quality, reduce scrap and improve energy efficiency.
• Increase process repeatability.
• Optimize production by providing process models for testing the effects of process parameters.
• Develop soft sensors for estimating unmeasured process variables to enhance process control.
• Provide methods for process diagnostics and condition monitoring to detect and address errors before they become critical and cause interruptions.
Conclusions of the action:
The INEVITABLE project successfully developed and implemented digital technologies to optimize production processes in the steel and nonferrous metals sectors. Real operational demonstrations showed improvements in process performance, product quality, productivity, energy efficiency, yield, and equipment reliability. The project aligned with Europe's sustainability goals, reducing energy consumption and CO2 emissions while enhancing product quality and productivity. Six innovative solutions were identified for exploitation, including operator support tools and monitoring systems. Extensive dissemination activities raised awareness and engaged stakeholders through the project website, social media, and promotional materials. The project's achievements contribute to digital transformation and optimization in the steel and nonferrous metals sectors, providing valuable insights for other industries. INEVITABLE successfully met its objectives, promoting digitalization, efficiency, and sustainability.
An overview of the work performed in the INEVITABLE project and the main results achieved during project duration is as follows:
In the 1st reporting period, requirements and specifications (Fig. 2) were set for all UCs, and preparatory activities were carried out, despite some delays caused by the COVID-19 crisis. The project development progressed as planned with a 6-month extension.
The 2nd period focused on finalizing requirements and specification, and completing basic digitization upgrades. Cognitive solutions were developed, involving various enabling technologies such as data collection and sensor technologies (Fig. 3), tools for data analysis, control, and optimization (Fig. 4), and digitalization infrastructure (Fig. 5)
In the last reporting period, technical solutions were deployed and validated in production environments (predefined UCs), achieving key accomplishments:
• Electric Arc Furnace (EAF) Steelmaking Process: Mathematical models and an optimization framework were developed, improving process efficiency and providing decision support for operators.
• Cold Rolling Mill: A system for supervision, optimization, and condition monitoring was implemented at Acroni. DSS tool assists the operators in adapting recipes, leading to improved process control and product quality.
• Ultraclean Steel Manufacturing: Model-based surveillance systems were deployed at SID and VAS sites, to optimize stirring efficiency and homogenization in LF and RH plants, enhancing overall steel quality.
• Non-Ferrous Industrial Case: A digital cognitive architecture and AI-supported tools were implemented at EIPC to reduce scrap rate, improve efficiency, and enhance material properties.
Furthermore, various training materials were developed to disseminate the knowledge gained to different target groups. These materials aimed to share the expertise and methodologies developed throughout the project. In terms of exploitation and dissemination, the project consortium actively promoted the project results and outcomes. Communication channels such as the project website, social media accounts (Twitter, ResearchGate, LinkedIn), and promotional video were utilized to keep stakeholders and the public informed about the progress and results of the project. Flyers were developed and distributed at various events to promote the achievements of the project. Dissemination efforts played a key role in raising awareness, fostering engagement with relevant stakeholders.
In the 1st reporting period, requirements and specifications (Fig. 2) were set for all UCs, and preparatory activities were carried out, despite some delays caused by the COVID-19 crisis. The project development progressed as planned with a 6-month extension.
The 2nd period focused on finalizing requirements and specification, and completing basic digitization upgrades. Cognitive solutions were developed, involving various enabling technologies such as data collection and sensor technologies (Fig. 3), tools for data analysis, control, and optimization (Fig. 4), and digitalization infrastructure (Fig. 5)
In the last reporting period, technical solutions were deployed and validated in production environments (predefined UCs), achieving key accomplishments:
• Electric Arc Furnace (EAF) Steelmaking Process: Mathematical models and an optimization framework were developed, improving process efficiency and providing decision support for operators.
• Cold Rolling Mill: A system for supervision, optimization, and condition monitoring was implemented at Acroni. DSS tool assists the operators in adapting recipes, leading to improved process control and product quality.
• Ultraclean Steel Manufacturing: Model-based surveillance systems were deployed at SID and VAS sites, to optimize stirring efficiency and homogenization in LF and RH plants, enhancing overall steel quality.
• Non-Ferrous Industrial Case: A digital cognitive architecture and AI-supported tools were implemented at EIPC to reduce scrap rate, improve efficiency, and enhance material properties.
Furthermore, various training materials were developed to disseminate the knowledge gained to different target groups. These materials aimed to share the expertise and methodologies developed throughout the project. In terms of exploitation and dissemination, the project consortium actively promoted the project results and outcomes. Communication channels such as the project website, social media accounts (Twitter, ResearchGate, LinkedIn), and promotional video were utilized to keep stakeholders and the public informed about the progress and results of the project. Flyers were developed and distributed at various events to promote the achievements of the project. Dissemination efforts played a key role in raising awareness, fostering engagement with relevant stakeholders.
The overall ambition of the proposed project is to go beyond the state-of-the-art regarding functionality of traditional process automation and control systems with the goal to improve performance indicators of selected metal production processes. The proposed project should provide the following innovative high-level functionality:
• Process optimization and monitoring by understanding the relation between process parameters and performance indicators (quality, efficiency, energy consumption, etc.),
• Decision support for setting the process parameters to achieve performance indicators,
• Estimation of unmeasured process variables (soft sensors),
• Diagnostics and condition monitoring,
• Prediction of product properties as a function of process parameters, input material, etc.
The mentioned functionalities are a subject of academic research for many years, but practical implementation does not follow the theoretical results from several reasons. Exemplarily, advanced algorithms are demanding in terms of computational power (optimization, identification, machine learning) and data storage capacity (big amounts of data to be stored and processed). By increasing the computational power of industrial controllers and by the possibility of computing on decentralized platforms (e.g. cloud platforms, edge processing units), one of the obstacles for implementation of advanced control systems is significantly reduced.
• Process optimization and monitoring by understanding the relation between process parameters and performance indicators (quality, efficiency, energy consumption, etc.),
• Decision support for setting the process parameters to achieve performance indicators,
• Estimation of unmeasured process variables (soft sensors),
• Diagnostics and condition monitoring,
• Prediction of product properties as a function of process parameters, input material, etc.
The mentioned functionalities are a subject of academic research for many years, but practical implementation does not follow the theoretical results from several reasons. Exemplarily, advanced algorithms are demanding in terms of computational power (optimization, identification, machine learning) and data storage capacity (big amounts of data to be stored and processed). By increasing the computational power of industrial controllers and by the possibility of computing on decentralized platforms (e.g. cloud platforms, edge processing units), one of the obstacles for implementation of advanced control systems is significantly reduced.