Filip Jurić
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Filip Jurić has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Neven Duić
University of Zagreb
5 shared publications Milan Vujanović
4 shared publications- Milan Vujanović
Faculty of Mechanical Engineering and Naval Architecture, University of Zagreb, Zagreb, Croatia
3 shared publications - Anh Tuan Hoang
University of Transport Ho Chi Minh City
2 shared publications - Carsten Schmalhorst
AVL Deutschland GmbH, Munich, Germany
2 shared publications - Dominik Pečaver Šošić
Krško Nuclear Power Plant, Krško, Slovenia
2 shared publications
Latest Publications
- Open Access
- 25 August 2025
- Published by Pensoft Publishers in Scientific Annals of the Danube Delta Institute
- Vol. 30, 17-30
Logical framework analysis (LFA) TOOL for planning support system (PSS) in Danube LIGHTHOUSE charter of mission oceans and inland waters
Within the Mission Oceans and Inland Waters framework, the Danube LIGHTHOUSE charter aims to support climate adaptation and sustainable development in the Danube Basin. To improve spatial and temporal planning for ecosystem restoration and urban economies, the Logical Framework Analysis (LFA) tool is integrated into a Planning Support System (PSS). This study aims to develop a methodology for scenario-based modelling to support policy planning, assess climate change adaptation measures and guide restoration, revitalisation and regeneration actions. Using GIS tools and artificial intelligence techniques, the study integrated system dynamics, cellular automata (FLUS model) and agent-based models. The results showed that the proposed scenarios present strategic directions for reducing ecosystem degradation and improving resilience to climate change through the adoption of integrated policies and adaptive land use management. The absence of an integrated methodology for ecological connectivity and spatial planning in the Danube Basin leads to negative effects on biodiversity (habitat degradation, environmental pollution) and socio-economically (decrease in population income, isolation of communities). The causes are insufficiently coordinated policies, poor infrastructure, land use conflicts, lack of financial resources, property rights, deficiencies in education and access to public services, etc. This leads to labor migration, lack of investment and biodiversity decline. In this context, there is a need for improved coordination between local communities, the private sector and authorities, along with investments in education, support for environmentally friendly local economic initiatives, ecological infrastructure and integrated water resources management.
- 25 August 2025
- Published by Pensoft Publishers in Scientific Annals of the Danube Delta Institute
- Vol. 30, 17-30
Open AccessLogical framework analysis (LFA) TOOL for planning support system (PSS) in Danube LIGHTHOUSE charter of mission oceans and inland waters
Within the Mission Oceans and Inland Waters framework, the Danube LIGHTHOUSE charter aims to support climate adaptation and sustainable development in the Danube Basin. To improve spatial and temporal planning for ecosystem restoration and urban economies, the Logical Framework Analysis (LFA) tool is integrated into a Planning Support System (PSS). This study aims to develop a methodology for scenario-based modelling to support policy planning, assess climate change adaptation measures and guide restoration, revitalisation and regeneration actions. Using GIS tools and artificial intelligence techniques, the study integrated system dynamics, cellular automata (FLUS model) and agent-based models. The results showed that the proposed scenarios present strategic directions for reducing ecosystem degradation and improving resilience to climate change through the adoption of integrated policies and adaptive land use management. The absence of an integrated methodology for ecological connectivity and spatial planning in the Danube Basin leads to negative effects on biodiversity (habitat degradation, environmental pollution) and socio-economically (decrease in population income, isolation of communities). The causes are insufficiently coordinated policies, poor infrastructure, land use conflicts, lack of financial resources, property rights, deficiencies in education and access to public services, etc. This leads to labor migration, lack of investment and biodiversity decline. In this context, there is a need for improved coordination between local communities, the private sector and authorities, along with investments in education, support for environmentally friendly local economic initiatives, ecological infrastructure and integrated water resources management.
- Open Access
- 2 January 2024
- Published by Springer Nature in Clean Technologies and Environmental Policy
- Vol. 26 (1) , 169
Correction: Numerical assessment of polyoxymethylene dimethyl ether (OME3) injection timing in compression ignition engine
- 2 January 2024
- Published by Springer Nature in Clean Technologies and Environmental Policy
- Vol. 26 (1) , 169
Open AccessCorrection: Numerical assessment of polyoxymethylene dimethyl ether (OME3) injection timing in compression ignition engine
- 11 November 2023
- Published by Springer Nature in Clean Technologies and Environmental Policy
- Vol. 26 (1) , 149-167
Numerical assessment of polyoxymethylene dimethyl ether (OME3) injection timing in compression ignition engine
- 11 November 2023
- Published by Springer Nature in Clean Technologies and Environmental Policy
- Vol. 26 (1) , 149-167
Numerical assessment of polyoxymethylene dimethyl ether (OME3) injection timing in compression ignition engine
- 20 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Numerical Modelling of Radiative Heat Transfer in Heavy-Duty Engines for Improved Emission Predictions
Computer Fluid Dynamics (CFD) coupling with experimental research is widely utilised in improving internal combustion engines in terms of pollutant formation and energy efficiency. Recent studies showed that including radiative heat transfer in participating media for more accurate internal combustion emission predictions is necessary. Especially in heavy-duty engines due to their more significant dimensions than automotive engines. In this work, the discrete ordinates method (DOM) is employed with the finite volume method in AVL FIRE™ CFD software. The absorptivity and emissivity are described with Weighted Sum of Gray Gases Method (WSGGM), which calculates the overall absorption coefficient using carbon dioxide, water vapour, and soot absorption coefficient. This paper aims to evaluate the impact of radiative heat transfer on the thermal state of the media and the formation prediction of pollutants. The radiative heat transfer model is validated against mean pressure results inside an engine cylinder. Finally, pollutant formation curves are compared and analysed, where approximately 15% NO mass fraction is obtained for the calculations with included radiative heat transfer.
- 20 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Numerical Modelling of Radiative Heat Transfer in Heavy-Duty Engines for Improved Emission Predictions
Computer Fluid Dynamics (CFD) coupling with experimental research is widely utilised in improving internal combustion engines in terms of pollutant formation and energy efficiency. Recent studies showed that including radiative heat transfer in participating media for more accurate internal combustion emission predictions is necessary. Especially in heavy-duty engines due to their more significant dimensions than automotive engines. In this work, the discrete ordinates method (DOM) is employed with the finite volume method in AVL FIRE™ CFD software. The absorptivity and emissivity are described with Weighted Sum of Gray Gases Method (WSGGM), which calculates the overall absorption coefficient using carbon dioxide, water vapour, and soot absorption coefficient. This paper aims to evaluate the impact of radiative heat transfer on the thermal state of the media and the formation prediction of pollutants. The radiative heat transfer model is validated against mean pressure results inside an engine cylinder. Finally, pollutant formation curves are compared and analysed, where approximately 15% NO mass fraction is obtained for the calculations with included radiative heat transfer.
- Open Access
- 10 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 208-213
Deep Learning-Based Cone Angle Estimation Using Spray Sequence Images
Engine efficiency, combustion process, and gas emissions are greatly affected by spray strategies. Spray strategies are utilized in engines with internal combustion. Spray strategies are determined by parameters such as nozzle diameter, injection pressure, chamber pressure, cylinder type, and others. These parameters determine spray shape. Spray shape is established by three main spray macroscopic parameters which are cone angle, penetration length, and spray area. Spray cone angle, with other spray macroscopic parameters, is often used to describe the parameters of numerical simulations. In this paper, we propose two new methods for the estimation of spray cone angle which affects the air engulfing and mixing process. Spray images gathered during a single spray injection are highly correlated. To use this fact to our advantage we proposed two deep learning-based methods that use image sequence as input. StackNet is a regression neural network that stacks images and uses them as input. It also uses a feature extractor and a fully connected layer. CNN-LSTM is another regression neural network with a feature extractor, but it utilizes Long Short-Term Memory (LSTM) cells before a fully connected layer. Both of the methods were trained, validated, and tested on preprocessed sequence images. To achieve better generalization and more data diversity, data augmentation was used. Three state-of-the-art feature extractors were tested, VGG16, MobileNetV3, and EfficientNetB0. The proposed methods were compared with the baseline approach which uses a single image as an input. Experimental validation showed that StackNet with VGG as a feature extractor achieved the best result. The proposed method estimated cone angle with a mean absolute error of 0.505 degrees, which is more than two times more accurate than the best baseline approach.
- 10 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 208-213
Open AccessDeep Learning-Based Cone Angle Estimation Using Spray Sequence Images
Engine efficiency, combustion process, and gas emissions are greatly affected by spray strategies. Spray strategies are utilized in engines with internal combustion. Spray strategies are determined by parameters such as nozzle diameter, injection pressure, chamber pressure, cylinder type, and others. These parameters determine spray shape. Spray shape is established by three main spray macroscopic parameters which are cone angle, penetration length, and spray area. Spray cone angle, with other spray macroscopic parameters, is often used to describe the parameters of numerical simulations. In this paper, we propose two new methods for the estimation of spray cone angle which affects the air engulfing and mixing process. Spray images gathered during a single spray injection are highly correlated. To use this fact to our advantage we proposed two deep learning-based methods that use image sequence as input. StackNet is a regression neural network that stacks images and uses them as input. It also uses a feature extractor and a fully connected layer. CNN-LSTM is another regression neural network with a feature extractor, but it utilizes Long Short-Term Memory (LSTM) cells before a fully connected layer. Both of the methods were trained, validated, and tested on preprocessed sequence images. To achieve better generalization and more data diversity, data augmentation was used. Three state-of-the-art feature extractors were tested, VGG16, MobileNetV3, and EfficientNetB0. The proposed methods were compared with the baseline approach which uses a single image as an input. Experimental validation showed that StackNet with VGG as a feature extractor achieved the best result. The proposed method estimated cone angle with a mean absolute error of 0.505 degrees, which is more than two times more accurate than the best baseline approach.
- 29 December 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (13) , 9535-9548
Deep Learning-based Image Analysis Method for Estimation of Macroscopic Spray Parameters
- 29 December 2022
- Published by Springer Nature in Neural Computing and Applications
- Vol. 35 (13) , 9535-9548
Deep Learning-based Image Analysis Method for Estimation of Macroscopic Spray Parameters
- 3 June 2022
- Published by Wiley in International Journal of Energy Research
- Vol. 46 (14) , 20265-20278
Implementation of the spectral line‐based weighted‐sum‐of‐gray‐gases model in the finite volume method for radiation modeling in internal combustion engines
- 3 June 2022
- Published by Wiley in International Journal of Energy Research
- Vol. 46 (14) , 20265-20278
Implementation of the spectral line‐based weighted‐sum‐of‐gray‐gases model in the finite volume method for radiation modeling in internal combustion engines