Convolutional Neural Network-Based Tire Pressure Monitoring System
Tire pressure has a significant influence on the driving safety of road vehicles; therefore, it is mandatory in many countries to equip all new road vehicles with a tire pressure monitoring system (TPMS). There are two types of TPMSs in use: the direct TPMS (dTPMS) and the indirect TPMS (iTPMS), bot...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10177918/ |
| _version_ | 1827893500418457600 |
|---|---|
| author | Zoltan Marton Istvan Szalay Denes Fodor |
| author_facet | Zoltan Marton Istvan Szalay Denes Fodor |
| author_sort | Zoltan Marton |
| collection | DOAJ |
| description | Tire pressure has a significant influence on the driving safety of road vehicles; therefore, it is mandatory in many countries to equip all new road vehicles with a tire pressure monitoring system (TPMS). There are two types of TPMSs in use: the direct TPMS (dTPMS) and the indirect TPMS (iTPMS), both of which have made significant improvement in the last decade. The most accurate iTPMS methods used in commercial vehicles apply the Fourier transform on wheel speed sensor (WSS) signals and extract the pressure-dependent eigenfrequency by utilizing center of gravity (CoG) or peak search (PS) methods, the research focus is shifting towards model-based and artificial intelligence-based methods. In this paper we propose a novel advanced iTPMS method based on modern signal processing and a convolutional neural network (CNN) for eigenfrequency detection. The proposed iTPMS method uses the hybrid wavelet-Fourier transform in combination with a CNN trained for pattern recognition-based eigenfrequency detection, and according to experimental results, it outperforms the commercially most frequently used Fourier transform and CoG method combination both in terms of computational requirement and accuracy. |
| first_indexed | 2024-03-12T21:54:39Z |
| format | Article |
| id | doaj.art-f1993d6a45084982a08d8f352a20869c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T21:54:39Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f1993d6a45084982a08d8f352a20869c2023-07-25T23:00:09ZengIEEEIEEE Access2169-35362023-01-0111703177033210.1109/ACCESS.2023.329440810177918Convolutional Neural Network-Based Tire Pressure Monitoring SystemZoltan Marton0https://orcid.org/0009-0005-0952-0525Istvan Szalay1Denes Fodor2Research Center for Engineering Sciences, Faculty of Engineering, University of Pannonia, Veszprém, HungaryDepartment of Power Electronics and Electric Drives, Audi Hungaria Faculty of Automotive Engineering, Széchenyi István University, Gyõr, HungaryDepartment of Power Electronics and Electric Drives, Audi Hungaria Faculty of Automotive Engineering, Széchenyi István University, Gyõr, HungaryTire pressure has a significant influence on the driving safety of road vehicles; therefore, it is mandatory in many countries to equip all new road vehicles with a tire pressure monitoring system (TPMS). There are two types of TPMSs in use: the direct TPMS (dTPMS) and the indirect TPMS (iTPMS), both of which have made significant improvement in the last decade. The most accurate iTPMS methods used in commercial vehicles apply the Fourier transform on wheel speed sensor (WSS) signals and extract the pressure-dependent eigenfrequency by utilizing center of gravity (CoG) or peak search (PS) methods, the research focus is shifting towards model-based and artificial intelligence-based methods. In this paper we propose a novel advanced iTPMS method based on modern signal processing and a convolutional neural network (CNN) for eigenfrequency detection. The proposed iTPMS method uses the hybrid wavelet-Fourier transform in combination with a CNN trained for pattern recognition-based eigenfrequency detection, and according to experimental results, it outperforms the commercially most frequently used Fourier transform and CoG method combination both in terms of computational requirement and accuracy.https://ieeexplore.ieee.org/document/10177918/Convolutional neural networkstire pressure monitoring system (TPMS)eigenfrequencyfourier transformcosine transformhybrid wavelet-Fourier transform |
| spellingShingle | Zoltan Marton Istvan Szalay Denes Fodor Convolutional Neural Network-Based Tire Pressure Monitoring System IEEE Access Convolutional neural networks tire pressure monitoring system (TPMS) eigenfrequency fourier transform cosine transform hybrid wavelet-Fourier transform |
| title | Convolutional Neural Network-Based Tire Pressure Monitoring System |
| title_full | Convolutional Neural Network-Based Tire Pressure Monitoring System |
| title_fullStr | Convolutional Neural Network-Based Tire Pressure Monitoring System |
| title_full_unstemmed | Convolutional Neural Network-Based Tire Pressure Monitoring System |
| title_short | Convolutional Neural Network-Based Tire Pressure Monitoring System |
| title_sort | convolutional neural network based tire pressure monitoring system |
| topic | Convolutional neural networks tire pressure monitoring system (TPMS) eigenfrequency fourier transform cosine transform hybrid wavelet-Fourier transform |
| url | https://ieeexplore.ieee.org/document/10177918/ |
| work_keys_str_mv | AT zoltanmarton convolutionalneuralnetworkbasedtirepressuremonitoringsystem AT istvanszalay convolutionalneuralnetworkbasedtirepressuremonitoringsystem AT denesfodor convolutionalneuralnetworkbasedtirepressuremonitoringsystem |