Tommi A. Karhela
Research Subjects
Tommi A. Karhela has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Jouni Savolainen
Semantum Ltd, Espoo, Finland
2 shared publicationsAntti Aikala
VTT Technical Research Centre of Finland Ltd, Espoo, Finland
1 shared publication- Gerardo Santillan Martinez
Aalto University, Helsinki, Finland
1 shared publication Hannu Niemistö
Semantum Ltd, Espoo, Finland
1 shared publicationKalle Kondelin
VTT Technical Research Centre of Finland Ltd, Espoo, Finland
1 shared publication- Miro Eklund
Åbo Akademi University
1 shared publication
Latest Publications
- Open Access
- 9 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 24185-24202
Using a Digital Twin as the Objective Function for Evolutionary Algorithm Applications in Large Scale Industrial Processes
In this paper, we describe how the up-to-date state of a digital twin, and its corresponding simulation model, can be used as a fitness function of an evolutionary algorithm for optimizing a large-scale industrial process. An ICT architecture is presented for solving the computational challenges that arise when the fitness function evaluation takes considerable amount of time. Parallel computation of the fitness function in a cloud computing environment is proposed and the evolutionary algorithm is connected to the computational environment using the Function-as-a-Service approach. A case-study was conducted on the district heating network of Espoo, the second largest city in Finland. The study shows that the architecture is suited for optimizing the operating costs of the large district heating network, with over 800 km of water pipes and over 14 heat producers, reaching a cost-saving of an average of 2%, and up-to 4%, over the current industrial state-of-the-art method in use at the city of Espoo.
- 9 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 24185-24202
Open AccessUsing a Digital Twin as the Objective Function for Evolutionary Algorithm Applications in Large Scale Industrial Processes
In this paper, we describe how the up-to-date state of a digital twin, and its corresponding simulation model, can be used as a fitness function of an evolutionary algorithm for optimizing a large-scale industrial process. An ICT architecture is presented for solving the computational challenges that arise when the fitness function evaluation takes considerable amount of time. Parallel computation of the fitness function in a cloud computing environment is proposed and the evolutionary algorithm is connected to the computational environment using the Function-as-a-Service approach. A case-study was conducted on the district heating network of Espoo, the second largest city in Finland. The study shows that the architecture is suited for optimizing the operating costs of the large district heating network, with over 800 km of water pipes and over 14 heat producers, reaching a cost-saving of an average of 2%, and up-to 4%, over the current industrial state-of-the-art method in use at the city of Espoo.
- 1 July 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 726-729
Parameters selection in predictive online simulation
Industrial applications with reliable predictive features are becoming increasingly important. A tracking simulator is an example of an online simulation system with great capabilities that fills the gap left by other predictive applications. In a tracking simulator, a simulation model is run in parallel with a physical process controlled by the process' control system. At the same time, a tracking mechanism is used to keep the state of the simulation model as close as possible to the real process by continually adjusting parameters of the model. The selection of these parameters impacts directly on the quality of the tracking simulation results and it is a complex task in processes with a big number of variables. This paper presents two case studies of tracking simulation where the controlled parameters are selected using different techniques. The first case study deals with a laboratory-scale hot water generation process where the parameters' selection is performed manually. The second case study deals with a combined heat and power production process with major uncertainties in the process structure. In this case, we focus on the variance decomposition method used to determine the most suitable controlled parameters. Conclusions and future work are finally presented.
- 1 July 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 726-729
Parameters selection in predictive online simulation
Industrial applications with reliable predictive features are becoming increasingly important. A tracking simulator is an example of an online simulation system with great capabilities that fills the gap left by other predictive applications. In a tracking simulator, a simulation model is run in parallel with a physical process controlled by the process' control system. At the same time, a tracking mechanism is used to keep the state of the simulation model as close as possible to the real process by continually adjusting parameters of the model. The selection of these parameters impacts directly on the quality of the tracking simulation results and it is a complex task in processes with a big number of variables. This paper presents two case studies of tracking simulation where the controlled parameters are selected using different techniques. The first case study deals with a laboratory-scale hot water generation process where the parameters' selection is performed manually. The second case study deals with a combined heat and power production process with major uncertainties in the process structure. In this case, we focus on the variance decomposition method used to determine the most suitable controlled parameters. Conclusions and future work are finally presented.