A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity
In the context of autonomous driving, sensing systems play a crucial role, and their accuracy and reliability can significantly impact the overall safety of autonomous vehicles. Despite this, fault diagnosis for sensing systems has not received widespread attention, and existing research has limitat...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-01-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/13/2/354 |
_version_ | 1797344233544220672 |
---|---|
author | Tianshi Jin Chenxi Zhang Yikang Zhang Mingliang Yang Weiping Ding |
author_facet | Tianshi Jin Chenxi Zhang Yikang Zhang Mingliang Yang Weiping Ding |
author_sort | Tianshi Jin |
collection | DOAJ |
description | In the context of autonomous driving, sensing systems play a crucial role, and their accuracy and reliability can significantly impact the overall safety of autonomous vehicles. Despite this, fault diagnosis for sensing systems has not received widespread attention, and existing research has limitations. This paper focuses on the unique characteristics of autonomous driving sensing systems and proposes a fault diagnosis method that combines hardware redundancy and analytical redundancy. Firstly, to ensure the authenticity of the study, we define 12 common real-world faults and inject them into the nuScenes dataset, creating an extended dataset. Then, employing heterogeneous hardware redundancy, we fuse MMW radar, LiDAR, and camera data, projecting them into pixel space. We utilize the “ground truth” obtained from the MMW radar to detect faults on the LiDAR and camera data. Finally, we use multidimensional temporal entropy to assess the information complexity fluctuations of LiDAR and the camera during faults. Simultaneously, we construct a CNN-based time-series data multi-classification model to identify fault types. Through experiments, our proposed method achieves 95.33% accuracy in detecting faults and 82.89% accuracy in fault diagnosis on real vehicles. The average response times for fault detection and diagnosis are 0.87 s and 1.36 s, respectively. The results demonstrate that the proposed method can effectively detect and diagnose faults in sensing systems and respond rapidly, providing enhanced reliability for autonomous driving systems. |
first_indexed | 2024-03-08T10:59:24Z |
format | Article |
id | doaj.art-a63f4f7b9b5648a1aca6e9094c230ead |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-08T10:59:24Z |
publishDate | 2024-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-a63f4f7b9b5648a1aca6e9094c230ead2024-01-26T16:14:06ZengMDPI AGElectronics2079-92922024-01-0113235410.3390/electronics13020354A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information ComplexityTianshi Jin0Chenxi Zhang1Yikang Zhang2Mingliang Yang3Weiping Ding4School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, ChinaIn the context of autonomous driving, sensing systems play a crucial role, and their accuracy and reliability can significantly impact the overall safety of autonomous vehicles. Despite this, fault diagnosis for sensing systems has not received widespread attention, and existing research has limitations. This paper focuses on the unique characteristics of autonomous driving sensing systems and proposes a fault diagnosis method that combines hardware redundancy and analytical redundancy. Firstly, to ensure the authenticity of the study, we define 12 common real-world faults and inject them into the nuScenes dataset, creating an extended dataset. Then, employing heterogeneous hardware redundancy, we fuse MMW radar, LiDAR, and camera data, projecting them into pixel space. We utilize the “ground truth” obtained from the MMW radar to detect faults on the LiDAR and camera data. Finally, we use multidimensional temporal entropy to assess the information complexity fluctuations of LiDAR and the camera during faults. Simultaneously, we construct a CNN-based time-series data multi-classification model to identify fault types. Through experiments, our proposed method achieves 95.33% accuracy in detecting faults and 82.89% accuracy in fault diagnosis on real vehicles. The average response times for fault detection and diagnosis are 0.87 s and 1.36 s, respectively. The results demonstrate that the proposed method can effectively detect and diagnose faults in sensing systems and respond rapidly, providing enhanced reliability for autonomous driving systems.https://www.mdpi.com/2079-9292/13/2/354autonomous drivingfault diagnosisinformation complexitymultidimensional entropy |
spellingShingle | Tianshi Jin Chenxi Zhang Yikang Zhang Mingliang Yang Weiping Ding A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity Electronics autonomous driving fault diagnosis information complexity multidimensional entropy |
title | A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity |
title_full | A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity |
title_fullStr | A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity |
title_full_unstemmed | A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity |
title_short | A Hybrid Fault Diagnosis Method for Autonomous Driving Sensing Systems Based on Information Complexity |
title_sort | hybrid fault diagnosis method for autonomous driving sensing systems based on information complexity |
topic | autonomous driving fault diagnosis information complexity multidimensional entropy |
url | https://www.mdpi.com/2079-9292/13/2/354 |
work_keys_str_mv | AT tianshijin ahybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT chenxizhang ahybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT yikangzhang ahybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT mingliangyang ahybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT weipingding ahybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT tianshijin hybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT chenxizhang hybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT yikangzhang hybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT mingliangyang hybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity AT weipingding hybridfaultdiagnosismethodforautonomousdrivingsensingsystemsbasedoninformationcomplexity |