https://www.mdu.se/

mdu.sePublications
Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 46) Show all publications
Zhou, Y., Aslanidou, I., Karlsson, M. & Kyprianidis, K. (2024). An explainable AI model for power plant NOx emission control. Energy and AI, 15, Article ID 100326.
Open this publication in new window or tab >>An explainable AI model for power plant NOx emission control
2024 (English)In: Energy and AI, ISSN 2666-5468, Vol. 15, article id 100326Article in journal (Refereed) Published
Abstract [en]

In recent years, developing Artificial Intelligence (AI) models for complex system has become a popular research area. There have been several successful AI models for predicting the Selective Non-Catalytic Reduction (SNCR) system in power plants and large boilers. However, all these models are in essence black box models and lack of explainability, which are not able to give new knowledge. In this study, a novel explainable AI (XAI) model that combines the polynomial kernel method with Sparse Identification of Nonlinear Dynamics (SINDy) model is proposed to find the governing equation of SNCR system based on 5-year operation data from a power plant. This proposed model identifies the system's governing equation in a simple polynomial format with polynomial order of 1 and only 1 independent variable among original 68 input variables. In addition, the explainable AI model achieves a considerable accuracy with less than 21 % deviation from base-line models of partial least squares model and artificial neural network model.

National Category
Engineering and Technology Energy Engineering Chemical Process Engineering
Identifiers
urn:nbn:se:mdh:diva-65124 (URN)10.1016/j.egyai.2023.100326 (DOI)001132419000001 ()2-s2.0-85178644436 (Scopus ID)
Available from: 2023-12-20 Created: 2023-12-20 Last updated: 2024-01-17Bibliographically approved
Soibam, J., Aslanidou, I., Kyprianidis, K. & Bel Fdhila, R. (2024). Inverse flow prediction using ensemble PINNs and uncertainty quantification. International Journal of Heat and Mass Transfer, 226
Open this publication in new window or tab >>Inverse flow prediction using ensemble PINNs and uncertainty quantification
2024 (English)In: International Journal of Heat and Mass Transfer, ISSN 0017-9310, E-ISSN 1879-2189, Vol. 226Article in journal (Refereed) Published
Abstract [en]

The thermal boundary conditions in a numerical simulation for heat transfer are often imprecise. This leads to poorly defined boundary conditions for the energy equation. The lack of accurate thermal boundary conditions in real-world applications makes it impossible to effectively solve the problem, regardless of the advancement of conventional numerical methods. 

This study utilises a physics-informed neural network to tackle ill-posed problems for unknown thermal boundaries with limited sensor data. The network approximates velocity and temperature fields while complying with the Navier-Stokes and energy equations, thereby revealing unknown thermal boundaries and reconstructing the flow field around a square cylinder. The method relies on optimal sensor placement determined by the QR pivoting technique, which ensures the effective capture of the dynamics, leading to enhanced model accuracy. In an effort to increase the robustness and generalisability, an ensemble physics-informed neural network is implemented. This approach mitigates the risks of overfitting and underfitting while providing a measure of model confidence. As a result, the ensemble model can identify regions of reliable prediction and potential inaccuracies. Therefore, broadening its applicability in tackling complex heat transfer problems with unknown boundary conditions.

Keywords
Heat transfer, mixed convection, physics informed neural network, optimal sensor placement, transient simulation, inverse method
National Category
Engineering and Technology Computational Mathematics
Research subject
Energy- and Environmental Engineering
Identifiers
urn:nbn:se:mdh:diva-64897 (URN)10.1016/j.ijheatmasstransfer.2024.125480 (DOI)001226062100001 ()2-s2.0-85189514108 (Scopus ID)
Available from: 2023-11-29 Created: 2023-11-29 Last updated: 2024-05-29Bibliographically approved
Sanchez de Ocaña, A., Bruch, J. & Aslanidou, I. (2024). Sources of Complexity in the Development of Digital Twins in Manufacturing. In: Sustainable Production Through Advanced Manufacturing, Intelligent Automation And Work Integrated Learning, Sps 2024: . Paper presented at 11th Swedish Production Symposium, SPS2024, Trollhattan, 23 April 2024 through 26 April 2024 (pp. 299-310). IOS PRESSNIEUWE HEMWEG 6B, 1013 BG AMSTERDAM, NETHERLANDS
Open this publication in new window or tab >>Sources of Complexity in the Development of Digital Twins in Manufacturing
2024 (English)In: Sustainable Production Through Advanced Manufacturing, Intelligent Automation And Work Integrated Learning, Sps 2024, IOS PRESSNIEUWE HEMWEG 6B, 1013 BG AMSTERDAM, NETHERLANDS , 2024, p. 299-310Conference paper, Published paper (Refereed)
Abstract [en]

Digital twins have emerged as a critical technology to enable smart production. Digital twins can enhance the current production system by optimizing the current setup and facilitating decision-making based on facts rather than gut feeling. Despite the numerous benefits explored, digital twins have faced many challenges in developing and implementing production systems. Their complexity is causing a lack of digital twin implementations in the production system. This complexity can be traced back to physical and virtual entities and the digital twin development process. By conducting a case study in a global manufacturing company, this publication explores the sources of complexity when developing digital twins. The findings are organized around the digital twin development steps and their corresponding complexity. The number of different types of entities being modeled, the choice of the modeling approach, modeling low-frequency events, emergent phenomena, and the unpredictability and variability of the manufacturing process are all examples of structural and dynamic complexity that have been found to impede success in digital twin applications. This research has implications for managers who are involved in the development of digital twins in their organizations. It can help with methodological guidance when dealing with an undefined and complicated process of digital twin development.

Place, publisher, year, edition, pages
IOS PRESSNIEUWE HEMWEG 6B, 1013 BG AMSTERDAM, NETHERLANDS, 2024
Keywords
Complexity, Digital Twin Modeling, Simulation, Smart Production, Virtual Models, 'current, Critical technologies, Current production, Decisions makings, Production system, Decision making
National Category
Mechanical Engineering
Identifiers
urn:nbn:se:mdh:diva-66583 (URN)10.3233/ATDE240174 (DOI)2-s2.0-85191348483 (Scopus ID)9781643685106 (ISBN)
Conference
11th Swedish Production Symposium, SPS2024, Trollhattan, 23 April 2024 through 26 April 2024
Available from: 2024-05-08 Created: 2024-05-08 Last updated: 2024-07-03Bibliographically approved
Soibam, J., Scheiff, V., Aslanidou, I., Kyprianidis, K. & Bel Fdhila, R. (2023). Application of deep learning for segmentation of bubble dynamics in subcooled boiling. International Journal of Multiphase Flow, 169, Article ID 104589.
Open this publication in new window or tab >>Application of deep learning for segmentation of bubble dynamics in subcooled boiling
Show others...
2023 (English)In: International Journal of Multiphase Flow, ISSN 0301-9322, E-ISSN 1879-3533, Vol. 169, article id 104589Article in journal (Refereed) Published
Abstract [en]

The present work focuses on designing a robust deep-learning model to track bubble dynamics in a vertical rectangular mini-channel. The rectangular mini-channel is heated from one side with a constant heat flux, resulting in the creation of bubbles. Images of the bubbles are recorded using a high-speed camera, which serve as the input data for the deep learning model. The raw image data acquired from the high-speed camera is inherently noisy due to the presence of shadows, reflections, background noise, and chaotic bubbles. The objective is to extract the mask of the bubble given all these challenging factors. Transfer learning is adopted to eliminate the need for a large dataset to train the deep learning model and also to reduce computational costs. The trained model is then validated against the validation datasets, demonstrating an accuracy of 98% while detecting the bubbles. The model is then evaluated on different experimental conditions, such as lighting, background, and blurry images with noise. The model demonstrates high robustness to different conditions and is able to detect the edges of the bubbles and classify them accurately. Moreover, the model achieves an average intersection over union of 85%, indicating a high level of accuracy in predicting the masks of the bubbles. The method enables accurate recognition and tracking of individual bubble dynamics, capturing their coalescence, oscillation, and collisions to estimate local parameters by proving the bubble masks. This allows for a comprehensive understanding of their spatial-temporal behaviour, including the estimation of local Reynolds numbers.

National Category
Energy Engineering
Identifiers
urn:nbn:se:mdh:diva-64495 (URN)10.1016/j.ijmultiphaseflow.2023.104589 (DOI)001070346100001 ()2-s2.0-85172483742 (Scopus ID)
Available from: 2023-10-11 Created: 2023-10-11 Last updated: 2023-11-29Bibliographically approved
Elvin, M., Bruch, J. & Aslanidou, I. (2023). Circular Production Equipment – Futuristic Thought or the Necessity of Tomorrow?. In: Alfnes, E., Romsdal, A.; Strandhagen, J.O.; von Cieminski, G.; Romero, D. (Ed.), Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures.: Proceedings, Part IV. Paper presented at IFIP WG 5.7 International Conference, APMS 2023, Trondheim, Norway, 17-21 September, 2023 (pp. 159-173).
Open this publication in new window or tab >>Circular Production Equipment – Futuristic Thought or the Necessity of Tomorrow?
2023 (English)In: Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures.: Proceedings, Part IV / [ed] Alfnes, E., Romsdal, A.; Strandhagen, J.O.; von Cieminski, G.; Romero, D., 2023, p. 159-173Conference paper, Published paper (Other academic)
Abstract [en]

With a growing population and increased use of resources, there is an urgent need to transform towards sustainable production in order to stay competitive. Prior studies suggest that circular thinking positively impacts the environmental impact of products. However, few studies have investigated the implications of applying circular thinking to the design of production equipment. We address this research gap by looking at what circularity is and how it can be perceived in the context of production equipment. Our research reveals that different circularity requirements need to be implemented in different phases of the life cycle of the production equipment. However, to succeed the requirements need to be considered already early in the design phase of the production equipment. Further, since the development of production equipment is a co-creation between the equipment with the manufacturing company, i.e. users of the production equipment. The circularity thinking between the two partners needs to be aligned and coordinated. Our findings emphasise the need for a holistic approach with system thinking implemented early in the life cycle of production equipment. 

Series
IFIP Advances in Information and Communication Technology ; 692
Keywords
green design, production development, manufacturing technology, sustainability
National Category
Other Engineering and Technologies
Identifiers
urn:nbn:se:mdh:diva-64454 (URN)10.1007/978-3-031-43688-8_12 (DOI)2-s2.0-85174448247 (Scopus ID)978-3-031-43687-1 (ISBN)978-3-031-43688-8 (ISBN)
Conference
IFIP WG 5.7 International Conference, APMS 2023, Trondheim, Norway, 17-21 September, 2023
Available from: 2023-10-04 Created: 2023-10-04 Last updated: 2023-10-30Bibliographically approved
Zhou, J., Aslanidou, I. & Kyprianidis, K. (2023). Effect of spray operation conditions on Nox emission control in a power station. Chemical engineering research & design, 191, 214-225
Open this publication in new window or tab >>Effect of spray operation conditions on Nox emission control in a power station
2023 (English)In: Chemical engineering research & design, ISSN 0263-8762, E-ISSN 1744-3563, Vol. 191, p. 214-225Article in journal (Refereed) Published
Abstract [en]

Adequately mixing of reactants is an important factor for efficient deNOx process in power station NOx emission control system. In this study, an experimental validated CFD simulation is conducted to investigate the effect of spray operation conditions on the mixing uniformity of reactant ammonia vapor in deNOx process occurring in a power station's furnace. According to the CFD simulation results, it is found that spray momentum ratio, initial droplet size and initial ammonia concentration all affect the mixing uniformity of ammonia vapor. Overall, a larger spray momentum ratio, larger initial droplet size and lower ammonia concentration contributes positively to the mixing uniformity. By comparing the same spray momentum ratio but different nozzle inlet velocity and furnace inlet velocity, it is found that the impact of spray momentum ratio mainly comes from furnace inlet velocity not nozzle inlet velocity. In addition, gravity should not be neglected. In the end, the method described in this study could provide a systematic way to study the effects of nozzle operation conditions on deNOx process.

Place, publisher, year, edition, pages
Institution of Chemical Engineers, 2023
Keywords
Ammonia, CFD, NOx emission, Power station, Spray, Drops, Emission control, Furnaces, Inlet flow, Mixing, Momentum, Spray nozzles, Ammonia vapors, CFD simulations, Inlet velocity, Mixing uniformities, Momentum ratio, NOx emissions, Operation conditions, Spray momentum
National Category
Energy Engineering
Identifiers
urn:nbn:se:mdh:diva-61797 (URN)10.1016/j.cherd.2023.01.013 (DOI)000926870700001 ()2-s2.0-85146913261 (Scopus ID)
Available from: 2023-02-08 Created: 2023-02-08 Last updated: 2023-03-01Bibliographically approved
Scheiff, V., Aslanidou, I., Kyprianidis, K. & Bel Fdhila, R. (2023). Experimental Study Of Nucleate Boiling Dynamics In A Rectangular Mini-Channel Set-Up. In: 8th Thermal and Fluids Engineering Conference (TFEC); March, 2023 Partially Online Virtual and at University of Maryland, MD Conference: . Paper presented at 8th Thermal and Fluids Engineering Conference (TFEC) (pp. 1199-1208). Begell House
Open this publication in new window or tab >>Experimental Study Of Nucleate Boiling Dynamics In A Rectangular Mini-Channel Set-Up
2023 (English)In: 8th Thermal and Fluids Engineering Conference (TFEC); March, 2023 Partially Online Virtual and at University of Maryland, MD Conference, Begell House, 2023, p. 1199-1208Conference paper, Published paper (Refereed)
Abstract [en]

Nowadays thermal management becomes a challenge as it implies high power density with high lossesconverted to large heat release. For low power levels, natural or forced single-phase convection could besufficient. For a much higher heat release nucleate boiling can be the alternative solution since it can dissipate the heat more efficiently, thanks to the latent heat effect present during the phase change. Its performance depends on many parameters that enable potential control and make system integration often very complex. The transition towards nucleate boiling, called Onset of Nucleate Boiling requires better estimation, and the mechanism still lacks understanding, especially in mini-channels. This study aims to characterize nucleate boiling in a rectangular mini-channel experimental set-up, built at Mälardalenuniversity, to better characterize the onset of nucleate boiling and the fully developed bubbly flow. The experiment allows full control of single-phase and two-phase regimes by varying the thermo-hydraulic and heat transfer conditions. With the use of a high-speed camera, bubble dynamics and their principal characteristics such as size, shape, propagation, and nucleation site location are determined with a digital image analysis technique developed within this work. The image processing has proved to be successful even on noisy images due to shadows or background changes. The reconstruction of segmented bubbles enabled flexible and automated bubble and path detection with a statistical approach, especially at the Onset of Nucleate Boiling. Local Reynolds numbers are then estimated to determine the drag coefficient in the flow during bubble growth, or their coalescence.

Place, publisher, year, edition, pages
Begell House, 2023
Keywords
Mini-channel experiment, bubble tracking, nucleate boiling, subcooled boiling, Flow visualization
National Category
Energy Engineering
Identifiers
urn:nbn:se:mdh:diva-62214 (URN)10.1615/TFEC2023.tbf.045945 (DOI)001191885700130 ()2-s2.0-85171268187 (Scopus ID)
Conference
8th Thermal and Fluids Engineering Conference (TFEC)
Available from: 2023-04-12 Created: 2023-04-12 Last updated: 2024-04-17Bibliographically approved
Soibam, J., Aslanidou, I., Kyprianidis, K. & Bel Fdhila, R. (2023). Inverse Flow Prediction Using Pinns In An Enclosure Containing Heat Sources. In: Proc. Thermal Fluids Eng. Summer Conf.: . Paper presented at Proceedings of the Thermal and Fluids Engineering Summer Conference (pp. 429-438). Begell House Inc.
Open this publication in new window or tab >>Inverse Flow Prediction Using Pinns In An Enclosure Containing Heat Sources
2023 (English)In: Proc. Thermal Fluids Eng. Summer Conf., Begell House Inc. , 2023, p. 429-438Conference paper, Published paper (Refereed)
Abstract [en]

While simulating heat transfer problems using a numerical method, the thermal boundary conditions are never known precisely, which leads to ill-posed boundary conditions for the energy equation. The lack of knowledge of accurate thermal boundary conditions in a practical application makes it impossible to solve this problem no matter how sophisticated the conventional numerical method is. Hence, the current work addresses this ill-posed problem using physics informed neural network by assuming that the thermal boundary near the source is unknown and only a few measurements of temperature are known in the domain. Physics-informed neural network is employed to represent the velocity and temperature fields, while simultaneously enforcing the Navier-Stokes and energy equations at random points in the domain. This work serves as an inverse problem since the goal here is to reproduce the global flow field and temperature profile in the domain with few measurement data points. Furthermore, the work focuses on using transfer learning for different parameters such as the position and size of the source term inside the enclosure domain. These parameters are of particular interest while designing a thermal system and being able to predict the flow and thermal behaviour instantly will allow for better design of the system. For this study, the sensors' data are extracted from numerical simulation results. The placement of the sensors in the domain plays a vital role in accuracy hence, sensors were optimized using the residual of the energy equation. The results obtained from this work demonstrate that the proposed method is in good agreement with the underlying physics represented by the numerical results.

Place, publisher, year, edition, pages
Begell House Inc., 2023
Keywords
Convection, Heat Transfer, Machine learning, Physics informed neural network, Transfer Learning
National Category
Energy Engineering
Identifiers
urn:nbn:se:mdh:diva-64443 (URN)10.1615/TFEC2023.cmd.045937 (DOI)001191885700048 ()2-s2.0-85171300317 (Scopus ID)
Conference
Proceedings of the Thermal and Fluids Engineering Summer Conference
Available from: 2023-10-05 Created: 2023-10-05 Last updated: 2024-04-17Bibliographically approved
Sanchez de Ocana, A., Bruch, J. & Aslanidou, I. (2023). Model Simplification: Addressing Digital Twin Challenges and Requirements in Manufacturing. In: Alfnes, E., Romsdal, A., Strandhagen, J.O., von Cieminski, G., Romero, D (Ed.), Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures: . Paper presented at IFIP International Conference on Advances in Production Management Systems, APMS 2023 (pp. 287-301).
Open this publication in new window or tab >>Model Simplification: Addressing Digital Twin Challenges and Requirements in Manufacturing
2023 (English)In: Advances in Production Management Systems. Production Management Systems for Responsible Manufacturing, Service, and Logistics Futures / [ed] Alfnes, E., Romsdal, A., Strandhagen, J.O., von Cieminski, G., Romero, D, 2023, p. 287-301Conference paper, Published paper (Refereed)
Abstract [en]

Leveraging the potential of digital twins is of utmost importance to support smart production. Digital twin research has principally focused on defining digital twin concepts and applications and proposing various frameworks for their implementation. Less is known about using simplified models to overcome many challenges related to digital twin models. Based on a longitudinal case study at a multinational manufacturing company engaged in digital twins in manufacturing efforts, this paper identifies the main challenges encountered related to people, processes, and technology, as well as requirements placed on a digital twin. This study also presents the opportunities of applying simplified models for digital twins to overcome the identified challenges and fulfill the defined requirements. The present study provides theoretical and practical implications of the development of digital twins in manufacturing, focusing attention on the challenges and requirements that affect the outcome of the manufacturing company to drive digital twin efforts.

National Category
Production Engineering, Human Work Science and Ergonomics
Identifiers
urn:nbn:se:mdh:diva-64538 (URN)10.1007/978-3-031-43666-6_20 (DOI)2-s2.0-85174445280 (Scopus ID)978-3-031-43665-9 (ISBN)978-3-031-43666-6 (ISBN)
Conference
IFIP International Conference on Advances in Production Management Systems, APMS 2023
Available from: 2023-10-17 Created: 2023-10-17 Last updated: 2023-10-26Bibliographically approved
Iplik, E., Aslanidou, I. & Kyprianidis, K. (2022). A Feedforward Model Predictive Controller for Optimal Hydrocracker Operation. Processes, 10(12), 2583-2583
Open this publication in new window or tab >>A Feedforward Model Predictive Controller for Optimal Hydrocracker Operation
2022 (English)In: Processes, E-ISSN 2227-9717, Vol. 10, no 12, p. 2583-2583Article in journal (Refereed) Published
Abstract [en]

Hydrocracking is an energy-intensive process, and its control system aims at stable product specifications. When the main product is diesel, the quality measure is usually 95% of the true boiling point. Constant diesel quality is hard to achieve when the feed characteristics vary and feedback control has a long response time. This work suggests a feedforward model predictive control structure for an industrial hydrocracker. A state-space model, an autoregressive exogenous model, a support vector machine regression model, and a deep neural network model are tested in this structure. The resulting reactor temperature decisions and final diesel product quality values are compared against each other and against the actual measurements. The results show the importance of the feed character measurements. Significant improvements are shown in terms of product quality as well as energy savings through decreasing the heat duty of the preheating furnace. 

Keywords
hydrocracking, model predictive control, feedforward control, deep neural network
National Category
Control Engineering
Identifiers
urn:nbn:se:mdh:diva-61124 (URN)10.3390/pr10122583 (DOI)000903010900001 ()2-s2.0-85144843895 (Scopus ID)
Available from: 2022-12-06 Created: 2022-12-06 Last updated: 2023-01-25Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-2978-6217

Search in DiVA

Show all publications