Since the company start-up in 2000, Cybernetica has systematically developed its technology, resulting in unique solutions for model-based control, supervision and optimization of industrial processes. Before that, in the 1990’s, research activities at SINTEF and the Norwegian University of Science and Technology (NTNU) led to the company spin-out.
Striving to stay in the forefront, the staff continuously improves the technology through research and development, in parallel with installation work. Cybernetica maintains a significant volume of R&D activities, and has an extensive network with national and international universities and other research organizations.
Involvement in research projects enables business expansion through the development of first-of-a-kind applications for new processes. At present, Cybernetica is engaged in several research programmes.
- Demonstrating a Refinery-Adapted Cluster-Integrated Strategy to Enable Full-Chain CCUS Implementation (REALISE CCUS) – a European research project on Carbon Capture, Utilization and Storage (CCUS). The project is focused on oil refineries and similar clusters of CO2 emitting processes, for which new technical solutions are developed to accelerate the introduction of full-scale carbon capture and sequestration. The tasks range from development and preparation of new amine solvents that outperform the current benchmark, to techno-economic assessment of full-scale integrated carbon capture at specific sites, including studies on the sociopolitical aspects and impacts of CCUS. Cybernetica works with development of process models for carbon capture processes and nonlinear model-predictive control (NMPC) applications for the case studies in the project, including campaigns with closed-loop NMPC control and full-scale assessment for the cluster-integrated, multi-absorber case study. Visit the REALISE project website for more information.
- Cognitive plants through proactive self-learning hybrid digital twins (COGNITWIN) – a European research project aiming to develop hybrid digital twins for industrial processes. The project combines the efforts of partners from different areas of the European process industry under the shared goal of using the latest advances in data-driven modelling and sensor technologies to create a new generation of robust, self-learning digital twins. Cybernetica is implementing new technology for improved fault detection in advanced process control and is also involved in developing hybrid digital twins for industrial cases for ferrosilicon refining and control of emissions from aluminium production. Read more at the COGNITWIN project website.
- Model-based optimisation for efficient use of resources and energy (MORSE) – a European research project with the objective to develop advanced digital tools for optimizing processes and enhance the overall performance of the European steel industry. The project brings together steel producers, researchers and software providers, developing advanced process models and software tools. The new software tools will be designed to optimize process yields and reduce losses, leading to improved steel quality, reduced energy and raw materials consumption. Cybernetica is responsible for developing nonlinear model-predictive control applications, for different steel refining process units. The applications will be demonstrated in cooperation with plant owning partners. Read more at the MORSE project website.
- Cross-sectorial real-time sensing, advanced control and optimisation of batch processes saving energy and raw materials (RECOBA) – a European research project with the objective to maximise the efficiency of batch processes (regarding quality, energy, raw materials, costs). In many aspects, batch processes are superior to continuous ones. RECOBA will therefore take advantage of recent progress in sensor technologies, modelling and control to develop a new paradigm for the design and operation of batch processes: Operation at maximum efficiency; Dynamic, quality driven process trajectories rather than fixed schedules; Detailed analysis and tracking of all relevant process and product variables. Read more at the RECOBA project website.
- Control and Real-Time Optimisation of Intensive Polymerisation Processes (COOPOL) – a European research project aiming at scientific breakthroughs in the area of advanced control and optimisation of polymerisation processes, allowing the COOPOL partners to achieve a significant increase in product quality of polymerisation reactions by employing the novel process control approach to intensified semi-batch and ‘smart-scale’ continuous polymerisation processes. Read more about COOPOL in the European Commission’s featured article “Process optimisation for streamlined polymerisation”.
Norwegian research initiatives:
- High Precision Extrusion Temperature Control through Digital Technology (ExtruTeC) – a research project to develop better temperature control for extrusion of high precision aluminium profiles through soft-sensing and nonlinear model-predictive control. The aluminium extrusion press is a high-temperature, high-pressure, fast-paced process where accurate temperature control will enable production of stronger and thinner extruded profiles. The project’s goals provide a direct benefit to customers by reducing material weight in end-use applications (e.g. car industry) and improving product quality capability. Cybernetica develops spatially distributed process models of the extrusion press and pre-heaters and integrate those in digital twins for soft-sensing applications. Cybernetica also develops a nonlinear model-predictive control solution for the extrusion press and co-operates with NTNU on development of a supervisory press cycle optimisation solution.
- Demonstration of Optimal Control of Post-Combustion Carbon Capture Processes (DOCPCC) – a research project with the objective to demonstrate reduced energy costs through use of advanced process control (NMPC) in amine-based CO2 capture processes. Read more.
- Accelerate learning through technology (ALTT) – a research project with the objective to enable process operators rapidly to master the art of controlling highly complex processes, such as the electrolysis of aluminium. The enabler for radically accelerated learning will is an environment using a dynamic process model in a combination of process simulation, gamification and gaming.
- Fault tolerant model predictive control (SAFE-MPC) – a research project with the objective to develop methodology, algorithms, software modules and work procedures facilitating the efficient development of applications for model predictive control and real time optimization which are tolerant to faults in instrumentation, process equipment and process operation; and to demonstrate this technology through pilot implementations on industrial processes.