An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line System
During the operation of the vehicular power line system, the loads are randomly connected and subsequently disconnected. This can result in an impedance mismatch of the vehicular power line system, which in turn has a significant impact on the normal operation of the vehicular power line system. To...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10766592/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533451296047104 |
|---|---|
| author | Renfa Song Hanyan Li Yongtao Li |
| author_facet | Renfa Song Hanyan Li Yongtao Li |
| author_sort | Renfa Song |
| collection | DOAJ |
| description | During the operation of the vehicular power line system, the loads are randomly connected and subsequently disconnected. This can result in an impedance mismatch of the vehicular power line system, which in turn has a significant impact on the normal operation of the vehicular power line system. To tackle the issue of impedance matching that occurs while operating the vehicular power line system, a method utilizing an optimized BP neural network for impedance matching is proposed. The method initially examines the impedance matching of the vehicular power line system in accordance with circuit theory, subsequently constructing an impedance matching system. Then the impedance matching algorithm based on BP neural network is proposed, the optimal parameters of the BP neural network are selected through testing, and the structure of the hidden layer of the BP neural network is optimized using the PSO algorithm. Through simulation verification, the results indicate that this method can achieve impedance matching efficiently while meeting the required accuracy standards. A comparison with traditional impedance matching algorithms reveals that this method is 55.15% more efficient than the particle swarm optimization algorithm when executed under identical conditions. Following the dynamic matching test, the dynamic matching performance of this method is found to meet the requisite speed and accuracy standards. |
| format | Article |
| id | doaj-art-ede3850693aa477bb9bcd80843fc0364 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-ede3850693aa477bb9bcd80843fc03642025-01-16T00:01:53ZengIEEEIEEE Access2169-35362024-01-011217694917696010.1109/ACCESS.2024.350559310766592An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line SystemRenfa Song0https://orcid.org/0009-0004-7931-0198Hanyan Li1Yongtao Li2School of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Mechanical and Automotive Engineering, Guangxi University of Science and Technology, Liuzhou, ChinaDuring the operation of the vehicular power line system, the loads are randomly connected and subsequently disconnected. This can result in an impedance mismatch of the vehicular power line system, which in turn has a significant impact on the normal operation of the vehicular power line system. To tackle the issue of impedance matching that occurs while operating the vehicular power line system, a method utilizing an optimized BP neural network for impedance matching is proposed. The method initially examines the impedance matching of the vehicular power line system in accordance with circuit theory, subsequently constructing an impedance matching system. Then the impedance matching algorithm based on BP neural network is proposed, the optimal parameters of the BP neural network are selected through testing, and the structure of the hidden layer of the BP neural network is optimized using the PSO algorithm. Through simulation verification, the results indicate that this method can achieve impedance matching efficiently while meeting the required accuracy standards. A comparison with traditional impedance matching algorithms reveals that this method is 55.15% more efficient than the particle swarm optimization algorithm when executed under identical conditions. Following the dynamic matching test, the dynamic matching performance of this method is found to meet the requisite speed and accuracy standards.https://ieeexplore.ieee.org/document/10766592/Vehicular power line systemimpedance matchingBP neural networkparticle swarm optimization |
| spellingShingle | Renfa Song Hanyan Li Yongtao Li An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line System IEEE Access Vehicular power line system impedance matching BP neural network particle swarm optimization |
| title | An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line System |
| title_full | An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line System |
| title_fullStr | An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line System |
| title_full_unstemmed | An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line System |
| title_short | An Impedance Matching Method Based on Optimized BP Neural Network for Vehicular Power Line System |
| title_sort | impedance matching method based on optimized bp neural network for vehicular power line system |
| topic | Vehicular power line system impedance matching BP neural network particle swarm optimization |
| url | https://ieeexplore.ieee.org/document/10766592/ |
| work_keys_str_mv | AT renfasong animpedancematchingmethodbasedonoptimizedbpneuralnetworkforvehicularpowerlinesystem AT hanyanli animpedancematchingmethodbasedonoptimizedbpneuralnetworkforvehicularpowerlinesystem AT yongtaoli animpedancematchingmethodbasedonoptimizedbpneuralnetworkforvehicularpowerlinesystem AT renfasong impedancematchingmethodbasedonoptimizedbpneuralnetworkforvehicularpowerlinesystem AT hanyanli impedancematchingmethodbasedonoptimizedbpneuralnetworkforvehicularpowerlinesystem AT yongtaoli impedancematchingmethodbasedonoptimizedbpneuralnetworkforvehicularpowerlinesystem |