Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management System
Vehicle integrated thermal management system (VTMS) is an important technology used for improving the energy efficiency of vehicles. Physics-based modeling is widely used to predict the energy flow in such systems. However, physics-based modeling requires several experimental approaches to get the r...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/20/5301 |
| _version_ | 1797551206754680832 |
|---|---|
| author | Duwon Choi Youngkuk An Nankyu Lee Jinil Park Jonghwa Lee |
| author_facet | Duwon Choi Youngkuk An Nankyu Lee Jinil Park Jonghwa Lee |
| author_sort | Duwon Choi |
| collection | DOAJ |
| description | Vehicle integrated thermal management system (VTMS) is an important technology used for improving the energy efficiency of vehicles. Physics-based modeling is widely used to predict the energy flow in such systems. However, physics-based modeling requires several experimental approaches to get the required parameters. The experimental approach to obtain these parameters is expensive and requires great effort to configure a separate experimental device and conduct the experiment. Therefore, in this study, a neural network (NN) approach is applied to reduce the cost and effort necessary to develop a VTMS. The physics-based modeling is also analyzed and compared with recent NN techniques, such as ConvLSTM and temporal convolutional network (TCN), to confirm the feasibility of the NN approach at EPA Federal Test Procedure (FTP-75), Highway Fuel Economy Test cycle (HWFET), Worldwide harmonized Light duty driving Test Cycle (WLTC) and actual on-road driving conditions. TCN performed the best among the tested models and was easier to build than physics-based modeling. For validating the two different approaches, the physical properties of a 1 L class passenger car with an electric control valve are measured. The NN model proved to be effective in predicting the characteristics of a vehicle cooling system. The proposed method will reduce research costs in the field of predictive control and VTMS design. |
| first_indexed | 2024-03-10T15:42:12Z |
| format | Article |
| id | doaj.art-3ddea025593b4156afad8c4d3bea7d10 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T15:42:12Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-3ddea025593b4156afad8c4d3bea7d102023-11-20T16:45:24ZengMDPI AGEnergies1996-10732020-10-011320530110.3390/en13205301Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management SystemDuwon Choi0Youngkuk An1Nankyu Lee2Jinil Park3Jonghwa Lee4Department of Mechanical Engineering, Ajou University, 206 World cup-ro, Yeongtong-gu, Suwon 16499, Gyeonggi, KoreaDepartment of Mechanical Engineering, Ajou University, 206 World cup-ro, Yeongtong-gu, Suwon 16499, Gyeonggi, KoreaVehicle Calibration Team, Tenergy, 145 Gwanggyo-ro, Yeongtong-gu, Suwon 16229, Gyeonggi, KoreaDepartment of Mechanical Engineering, Ajou University, 206 World cup-ro, Yeongtong-gu, Suwon 16499, Gyeonggi, KoreaDepartment of Mechanical Engineering, Ajou University, 206 World cup-ro, Yeongtong-gu, Suwon 16499, Gyeonggi, KoreaVehicle integrated thermal management system (VTMS) is an important technology used for improving the energy efficiency of vehicles. Physics-based modeling is widely used to predict the energy flow in such systems. However, physics-based modeling requires several experimental approaches to get the required parameters. The experimental approach to obtain these parameters is expensive and requires great effort to configure a separate experimental device and conduct the experiment. Therefore, in this study, a neural network (NN) approach is applied to reduce the cost and effort necessary to develop a VTMS. The physics-based modeling is also analyzed and compared with recent NN techniques, such as ConvLSTM and temporal convolutional network (TCN), to confirm the feasibility of the NN approach at EPA Federal Test Procedure (FTP-75), Highway Fuel Economy Test cycle (HWFET), Worldwide harmonized Light duty driving Test Cycle (WLTC) and actual on-road driving conditions. TCN performed the best among the tested models and was easier to build than physics-based modeling. For validating the two different approaches, the physical properties of a 1 L class passenger car with an electric control valve are measured. The NN model proved to be effective in predicting the characteristics of a vehicle cooling system. The proposed method will reduce research costs in the field of predictive control and VTMS design.https://www.mdpi.com/1996-1073/13/20/5301neural networkrecurrent neural networkconvolutional neural networktemporal convolutional networkdeep learningtime series forecasting |
| spellingShingle | Duwon Choi Youngkuk An Nankyu Lee Jinil Park Jonghwa Lee Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management System Energies neural network recurrent neural network convolutional neural network temporal convolutional network deep learning time series forecasting |
| title | Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management System |
| title_full | Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management System |
| title_fullStr | Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management System |
| title_full_unstemmed | Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management System |
| title_short | Comparative Study of Physics-Based Modeling and Neural Network Approach to Predict Cooling in Vehicle Integrated Thermal Management System |
| title_sort | comparative study of physics based modeling and neural network approach to predict cooling in vehicle integrated thermal management system |
| topic | neural network recurrent neural network convolutional neural network temporal convolutional network deep learning time series forecasting |
| url | https://www.mdpi.com/1996-1073/13/20/5301 |
| work_keys_str_mv | AT duwonchoi comparativestudyofphysicsbasedmodelingandneuralnetworkapproachtopredictcoolinginvehicleintegratedthermalmanagementsystem AT youngkukan comparativestudyofphysicsbasedmodelingandneuralnetworkapproachtopredictcoolinginvehicleintegratedthermalmanagementsystem AT nankyulee comparativestudyofphysicsbasedmodelingandneuralnetworkapproachtopredictcoolinginvehicleintegratedthermalmanagementsystem AT jinilpark comparativestudyofphysicsbasedmodelingandneuralnetworkapproachtopredictcoolinginvehicleintegratedthermalmanagementsystem AT jonghwalee comparativestudyofphysicsbasedmodelingandneuralnetworkapproachtopredictcoolinginvehicleintegratedthermalmanagementsystem |