A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems
Inverse heat transfer problems are important in numerous scientific research and engineering applications. This paper proposes a network-based method utilizing the nonlinear autoregressive with exogenous inputs (NARX) neural network, which can achieve real-time identification of thermal boundary con...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/23/7819 |
| _version_ | 1827592318174101504 |
|---|---|
| author | Changxu Chen Zhenhai Pan |
| author_facet | Changxu Chen Zhenhai Pan |
| author_sort | Changxu Chen |
| collection | DOAJ |
| description | Inverse heat transfer problems are important in numerous scientific research and engineering applications. This paper proposes a network-based method utilizing the nonlinear autoregressive with exogenous inputs (NARX) neural network, which can achieve real-time identification of thermal boundary conditions for nonlinear transient heat transfer processes. With the introduction of the NARX neural network, the proposed method offers two key advantages: (1) The proposed method can obtain inversion results using only surface temperature time series. (2) The heat flux can be estimated even when the state equation of the system is unknown. The NARX neural network is trained using the Bayesian regularization algorithm with a dataset comprising exact surface temperature and heat flux data. The neural network takes current and historical surface temperature measurements as inputs to calculate the heat flux at the current time. The capability of the NARX method has been verified through numerical simulation experiments. Experimental results demonstrate that the NARX method has high precision, strong noise resistance, and broad applicability. The composition of the input data, the surface temperature measurement noise, and the boundary heat flux shape have been studied in detail for their impact on the inversion results. The NARX method is a highly competitive solution to inverse heat transfer problems. |
| first_indexed | 2024-03-09T01:51:52Z |
| format | Article |
| id | doaj.art-6efec50129f34ce49f61946f37548acf |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T01:51:52Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-6efec50129f34ce49f61946f37548acf2023-12-08T15:14:55ZengMDPI AGEnergies1996-10732023-11-011623781910.3390/en16237819A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer ProblemsChangxu Chen0Zhenhai Pan1School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaSchool of Mechanical Engineering, Shanghai Institute of Technology, Shanghai 201418, ChinaInverse heat transfer problems are important in numerous scientific research and engineering applications. This paper proposes a network-based method utilizing the nonlinear autoregressive with exogenous inputs (NARX) neural network, which can achieve real-time identification of thermal boundary conditions for nonlinear transient heat transfer processes. With the introduction of the NARX neural network, the proposed method offers two key advantages: (1) The proposed method can obtain inversion results using only surface temperature time series. (2) The heat flux can be estimated even when the state equation of the system is unknown. The NARX neural network is trained using the Bayesian regularization algorithm with a dataset comprising exact surface temperature and heat flux data. The neural network takes current and historical surface temperature measurements as inputs to calculate the heat flux at the current time. The capability of the NARX method has been verified through numerical simulation experiments. Experimental results demonstrate that the NARX method has high precision, strong noise resistance, and broad applicability. The composition of the input data, the surface temperature measurement noise, and the boundary heat flux shape have been studied in detail for their impact on the inversion results. The NARX method is a highly competitive solution to inverse heat transfer problems.https://www.mdpi.com/1996-1073/16/23/7819nonlinear inverse heat conduction problemNARX neural networktransient heat flux |
| spellingShingle | Changxu Chen Zhenhai Pan A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems Energies nonlinear inverse heat conduction problem NARX neural network transient heat flux |
| title | A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems |
| title_full | A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems |
| title_fullStr | A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems |
| title_full_unstemmed | A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems |
| title_short | A Neural Network-Based Method for Real-Time Inversion of Nonlinear Heat Transfer Problems |
| title_sort | neural network based method for real time inversion of nonlinear heat transfer problems |
| topic | nonlinear inverse heat conduction problem NARX neural network transient heat flux |
| url | https://www.mdpi.com/1996-1073/16/23/7819 |
| work_keys_str_mv | AT changxuchen aneuralnetworkbasedmethodforrealtimeinversionofnonlinearheattransferproblems AT zhenhaipan aneuralnetworkbasedmethodforrealtimeinversionofnonlinearheattransferproblems AT changxuchen neuralnetworkbasedmethodforrealtimeinversionofnonlinearheattransferproblems AT zhenhaipan neuralnetworkbasedmethodforrealtimeinversionofnonlinearheattransferproblems |