The Morse project (Model-based optimisation for efficient use of resources and energy) will improve the products, business operations and competitiveness, as well as the energy and raw material efficiency, of the European steel industry. Morse brought together software houses, researchers developing models and steel factories for developing software tools that will be used to reform, accelerate and manage heavy production processes.
Morse’s main objective was to develop more advanced tools to improve steel quality and the management of complex processes. New ways of managing the entire production chain, lowering the consumption of energy and raw materials in particular, and reducing yield losses are being sought for the industry. A special development target was model-based software tools, which are being tested in close cooperation with various steel mills in Europe.
The overall evaluation of results compared to set objectives targets showed that improvements related to energy consumption, raw material usage, CO2 emissions, and different process and quality figures were overall achieved. During the testing period, the developed Morse tools led to significant savings in terms of energy consumption and CO2 emissions, although the evaluation in some cases were rather difficult due to changes in processes. Considering the large number of use cases, the results show that the developed tools have good potential for improving the process efficiency. After further and wider adoption of the tools, the impacts for lowering the consumption of energy and raw materials, and reducing yield losses will further increase and become possible in wider scale and other industries.
Morse in a nutshell
Tweets by eu_morse
The vision of Morse was to develop and apply control software solutions for integrated optimisation of the entire chain of production processes, to minimise the use of resources for producing high quality products with maximum yield.
The mission of the Morse project was to develop model-based, predictive raw material and energy optimisation tools for the whole process route. This approach was demonstrated in steel industry, to increase yield and product quality in production of high-strength carbon steels, stainless steels and cast steels.
The Morse project aim was to further develop and to integrate a set of software tools that have partly already been validated in different process steps in steel industries. With the enhanced Morse tools companies of the process industry will be enabled to optimise the use of raw materials and energy by coordinated prediction and control of resource input and product quality along the entire process route from raw material and energy intake to customer delivery.
We divided our main objective into specific objectives as follows
The project is organised into seven work packages presented in figure below. Morse project started with a six-month requirement and specification phase (WP1), which acted as a preliminary work for implementation and use case preparations. The development and implementation was performed in three WPs which were divided into process specific model development (WP2), process route optimisation actions (WP3) and application development (WP4) that integrated and took care of practical implementation in the system level. In the verification phase (WP5), the developed technology was tested and validated in three different industrial environments to prove the suitability and transferability of the developed technology.
First months focused on defining the requirements for Morse tools including models and software, and furthermore identifying the bottlenecks in processes and defining the use cases with Key Performance Indicators (KPIs) for industrial demonstrations. Alltogether 15 use cases were defined in different steel sectors in order to demonstrate the benefits of Morse tools. In addition to specification work, this period resulted the release of initial and modified process models, which were used within applications for unit process monitoring and control as well as part of the plant-wide process simulation and optimisation.
After definition of requirements and initial model setups, the implementation and development work was carried out to integrate the developed models and optimisation solutions to unit and through-process applications. After initial versions of the solutions were demonstrated and tested off-line in controlled environments, they were improved and adopted for online use. Validation of the tools was done at the end of the project parallel with development work to provide results and experiences from the actual industrial environment use.
Results from the Morse project are software tools for unit and through process monitoring, optimisation and control that are aiming for improved process efficiency. Developed solutions for the unit processes include static energy and mass balance models, and dynamic process models for Electric Arc Furnaces (EAF), Argon Oxygen Decarburization (AOD), Blast Furnaces (BF), Basic Oxygen Furnaces (BOF), Composition Adjustment by Sealed argon bubbling – Oxygen Blowing (CAS-OB) and statistical models for slab management. On-line Nonlinear Model Predictive Control (NMPC) was utilized in some cases for implementing the applications. Through process applications targeted for overall coordination of production included four main tools. Production management system for melt shop production with functions related to data and material management, Operator Support System utilising Reinforced Learning (RL) to assess human operators in process control, Plant-wide cost-optimisation system for offline analysis of total costs of production process including all relevant material and energy flows, and online Quality Monitoring Tool for managing the product and process quality along different process steps.
To prepare cross-sectorial exploitation of Morse results, communication and dissemination activities have been running continuously in order to promote the exchange of information between the project and the related community. Exploitation plans have been updated throughout the project and finally the Key Results (KR) and Key Exploitable Results (KER) were documented with related business models and plans. During the implementation of the project, totally 23 Key Results and six Key Exploitable Results with different exploitation nature and IPR strategy were defined.
VTT Technical Research Centre of Finland Ltd (VTT), is a state owned and controlled non-profit limited liability company established by law. As an impartial non-profit Research and Technology Organisation (RTO) and with the national mandate and mission to support economic competitiveness, societal development and innovation, VTT carries out research and innovation activities for the needs of industry and knowledge-based society.
SSAB is a highly specialized, global steel company. The company is a leading producer on the global market for Advanced High Strength Steels (AHSS) and Quenched & Tempered Steels (Q&T), strip, plate and tubular products, as well as construction solutions.
Outokumpu is a global leader in stainless steel. Stainless steel is an ideal material to create lasting solutions in demanding applications from cutlery to bridges, energy to medical equipment. Stainless steel as material is 100% recyclable, corrosion-resistant, maintenance-free, durable and hygienic. Outokumpu has been instrumental in developing the stainless steel industry into what it is today.
Maschinenfabrik Liezen und Gießerei GmbH (MFL) manufactures steel castings for rail traffic industry, environmental technology, construction industry and automotive industry. Numerous certifications, approvals as well as manufacturer-related product qualifications are their trademark. In their electric arc furnaces MFL produces the melts for low-alloyed steel castings, cryogenic steel castings, quenched and tempered steel castings, heat resistant castings and wear resistant castings.
BFI, VDEh-Betriebsforschungsinstitut GmbH, is one of Europe's leading private-sector institutes for applied research and development in the field of steel technology and connected branches. BFI is a non-profit, limited liability company for which Steel Institute VDEh is the only shareholder. The main object of institute’s work is the cross-process optimisation of steel production under resource efficiency, product quality, economic and environmental aspects.
Pinja is your partner in digitalization and industrial innovation. Our customers are industrial enterprises wanting to benefit from technology and new business models faster and more efficiently than their competitors. Pinja was born when a significant group of digitalisation top companies, namely Protacon, ARROW, SWD, Descal, Netwell, Vision Systems, and Powen, joined forces and adopted a common name. Pinja employs some 500 people in Finland, serving leading Finnish industrial and business clients and international organizations in more than 30 countries.
CYBERNETICA AS is a research intensive SME located in Trondheim, Norway. Cybernetica develops, implements and maintains specialized solutions for model-based control, supervision and optimization of selected industrial processes. Cybernetica’s main products are systems for model-based control and optimization of industrial processes.
GRIPS Industrial IT Solutions GmbH is an SME and develops innovative solutions for process automation and optimization for the steel, foundry and automotive industries using latest technologies in software development. The company was founded 1998 as subsidiary of GRIPS Software.
IDENER is a private research SME located in La Rinconada (Seville, Spain). The company develops computational science tools aimed to the optimal design and operation of complex systems in the areas of chemical and biochemical processing, integrated logistics, business intelligence, manufacturing, defense and aerospace. Specifically, the company is specialised in the development and implementation of mathematical optimisation engines, which are integrated in deployable tools in combination with the other units of the company (mathematical modelling, software development and advanced control) and also jointly with other project partners.
Detailed results from each use case are described in deliverable D5.5 Evaluation and reporting of achieved process improvements.
Key public deliverables are:
D1.2 System requirements specification (SRS)
February 2018 (pdf - 1.87 MB)
D1.3 List of generic KPIs to assess the system functionality and benchmarks for system validation on use cases
March 2018 (pdf - 1.13 MB)
D2.1 Layout of process models
June 2018 (pdf - 2.78 MB)
D2.4 Validation of process models
June 2021 (pdf - 4.45MB)
D2.5 Guidelines for model set-up, validation and auto-calibration
June 2021 (pdf - 2.00MB)
D6.1 Project website
November 2017 (pdf - 1.03MB)
D6.2 Dissemination plan
January 2018 (pdf - 711 KB)
D6.3 Communication plan
March 2018 (pdf - 1.40 MB)
D5.5 Evaluation and reporting of achieved process improvements
November 2021 (pdf - 5.91 MB)
D6.4 Initial exploitation plan
March 2019 (pdf - 557 KB)
D6.5 Exploitation plan
February 2022 (pdf - 1640 KB)
D7.1 Setting up project content management system
November 2017 (pdf - 499 KB)
Publications within the project
Backman, J., Kyllönen, V., & Helaakoski, H. (2019). Methods and Tools of Improving Steel Manufacturing Processes: Current State and Future Methods. IFAC-PapersOnLine, 52(13), 1174-1179
Linnestad, K., Ollila, S., Wasbø, S. O., Bogdanoff, A., & Rotevatn, T. (2021). Adaptive First Principles Model for the CAS-OB Process for Real-Time Applications. Metals, 11(10), 1554. doi:10.3390/met11101554
Jawahery, S., Visuri, V.-V., Wasbø, S. O., Hammervold, A., Hyttinen, N., & Schlautmann, M. (2021). Thermophysical Model for Online Optimization and Control of the Electric Arc Furnace. Metals, 11(10), 1587. doi:10.3390/met11101587
Andreiana, D. S., Acevedo Galicia, L. E., Ollila, S., Leyva Guerrero, C., Ojeda Roldán, Á., Dorado Navas, F., & del Real Torres, A. (2022). Steelmaking Process Optimised through a Decision Support System Aided by Self-Learning Machine Learning. Processes, 10(3), 434. doi: 10.3390/pr10030434
Ojeda Roldán Á, Gassner G, Schlautmann M, Acevedo Galicia LE, Andreiana DS, Heiskanen M, Leyva Guerrero C, Dorado Navas F, del Real Torres A. Optimisation of Operator Support Systems through Artificial Intelligence for the Cast Steel Industry: A Case for Optimisation of the Oxygen Blowing Process Based on Machine Learning Algorithms. Journal of Manufacturing and Materials Processing. 2022; 6(2):34. doi: 10.3390/jmmp6020034
Takalo-Mattila, J., Heiskanen, M., Kyllönen, V., Määttä, L., & Bogdanoff, A. (2022). Explainable Steel Quality Prediction System Based on Gradient Boosting Decision Trees. IEEE Access. doi: 10.1109/ACCESS.2022.3185607
Helaakoski, H., Ollila, S., Wasbø, S. O., Rotevatn, T., Moreira, S., Schlautmann, M., & Backman, J. (2019). Model-Based Optimisation for Efficient Use of Resources and Energy. In METEC & 4th European Steel Technology and Application Days 2019.
Visuri, V. V., Jawahery, S., Hyttinen, N., Wasbø, S. O. & Schlautmann, M. (2021). Preliminary Experiences from the Application of Model Predictive Control for the EAF Process in Stainless Steelmaking”. In 4th European Academic Symposium on EAF Steelmaking (EASES) on June 18 2021 in Aachen, Germany.
Gassner, G., Fuchs, P., Schlautmann, M., Stubbe G., Jendryssek, U., Niehues, P., Leyva, C., Ojeda, A. (2021). Development and Application of Model-based Software Tools for Raw Material and Energy Optimisation at the Cast Steel Production Route – Results from MORSE project. In 5th ESTAD (European Steel Technology and Application Days) 2021 on August 30 to September 2 2021 in Stockholm, Sweden.
Visuri, V-V., Kupari, P., Hammervold, A., Wasbø, S. O., Schlautmann, M., Peiss, V. (2021). Model Predictive Control of the AOD Process for Material and Energy Optimisation. In 9th International Conference on Modeling and Simulation of Metallurgical Processes in Steelmaking (STEELSIM 2021) from October 4 to October 7 2021 in Vienna, Austria.
Other publications of the consortium related to the project
Kanninen, K., Lilja, J. Cost optimisation system for an integrated steel mill. Stahl und Eisen (2017). Issue no 6. Page 75-78
Tamminen S., Tiensuu H., Ferreira E., Helaakoski H., Kyllönen V., Jokisaari J. and Puukko E. (2018) From Measurements to Knowledge - Online Quality Monitoring and Smart Manufacturing. In: Perner P. (eds) Advances in Data Mining. Applications and Theoretical Aspects. ICDM 2018. Lecture Notes in Computer Science, vol 10933. Springer, Cham.
Tamminen, S., Ferreira, E., Tiensuu, H., Helaakoski, H., Kyllönen, V., Jokisaari, J., ... & Röning, J. (2019). An online quality monitoring tool for information acquisition and sharing in manufacturing: requirements and solutions for the steel industry. International Journal of Industrial and Systems Engineering, 33(3), 291-313.
Download the Morse project and leaflet to know more about the project:
MORSE Results Online Webinar
Dr. Heli Helaakoski
VTT Technical Research Centre of Finland Ltd (Finland)