基于深度学习的无人驾驶汽车导航传感器异常诊断方法

doi:10.3901/JME.2021.24.268

机械工程学报 ›› 2021, Vol. 57 ›› Issue (24): 268-278.doi: 10.3901/JME.2021.24.268

扫码分享

基于深度学习的无人驾驶汽车导航传感器异常诊断方法

宫文峰^1,2, 王元哲², 陈辉¹, WANG Danwei²

1. 武汉理工大学高性能舰船技术教育部重点实验室武汉 430063;
2. 南洋理工大学电机与电子工程学院新加坡 639798 新加坡

收稿日期:2021-05-21 修回日期:2021-10-25 出版日期:2021-12-20 发布日期:2022-02-28
作者简介:宫文峰,男,1987年出生,讲师/工程师,武汉理工大学与新加坡南洋理工大学联合培养博士研究生。主要研究方向为复杂装备故障诊断与寿命预测、深度学习与人工智能、机械振动与CAE技术等。E-mail:wfgongcn@163.com;王元哲,男,1990年出生,博士,新加坡南洋理工大学研究员。主要研究方向为机器人学,控制工程,网络安全。E-mail:wang0951@e.ntu.edu.sg;陈辉,男,1962年出生,博士,博士研究生导师,国家二级教授。主要研究方向为船舶电力推进系统和智能装备控制。E-mail:hchen@whut.edu.cn;WANG Danwei,男,1957年出生,博士,博士研究生导师,新加坡南洋理工大学终身教授、新加坡工程院院士,IEEE Fellow。主要研究方向为机器人学,控制工程,故障诊断。E-mail:edwwang@ntu.edu.sg
基金资助:
国家重点研发计划（2019YFE0104600）、工信部“绿色智能内河船舶创新专项”、国家自然科学基金（51579200，U1709215）、广西自然科学基金（2020GXNSFBA159058）、中央高校基本科研业务费专项武汉理工大学优秀博士学位论文培育（2019-YB-023）和中国国家留学基金委博士联合培养（CSC201906950020）资助项目。

Anomaly Diagnosis for Navigation Sensors of Unmanned Autonomous Vehicles Based on Deep Learning

GONG Wenfeng^1,2, WANG Yuanzhe², CHEN Hui¹, WANG Danwei²

1. Key Laboratory of High Performance Ship Technology of Ministry of Education in China, Wuhan University of Technology, Wuhan 430063;
2. School of Electrical and Electronic Engineering, Nanyang Technological University, Singaprore 639798, Singapore

Received:2021-05-21 Revised:2021-10-25 Online:2021-12-20 Published:2022-02-28

摘要/Abstract

摘要： 近年来，无人驾驶汽车（Unmanned autonomous vehicle，UAV）作为未来智能交通系统（Intelligent transportation system，ITS）的重点发展方向已成为业内研究的热点。作为一种新兴智能交通工具，无人汽车的行驶完全依赖于导航传感器提供的精确位置和路径数据。GPS传感器因计算机黑客的恶意网络攻击或物理故障而造成导航位置数据异常或篡改给无人车的安全行驶带来了巨大的威胁和挑战。针对无人汽车GPS传感器易受攻击的现实问题，提出一种基于深度学习的无人车GPS传感器异常检测新方法。该方法通过改进传统一维卷积神经网络（1D Convolutional neural network，1D-CNN）的拓扑结构，设计出1DGAP-CNN算法框架，使其满足快速实时性的诊断要求。首先，原始的多传感器位置数据直接输入到提出的算法中进行数据融合和预处理；其次，提出的算法自动的进行特征提取、降维减参和模式辨识；最后，模型直接输出诊断结果，整个诊断过程由模型自主完成。结果表明，提出的方法相比于主流的智能诊断算法具有更高的诊断准确率和更快的检测速度。

关键词: 无人驾驶汽车, 深度学习, 异常诊断, 导航传感器, 网络攻击

Abstract: As a key technology of future intelligent transportation systems(ITS), unmanned autonomous vehicles(UAVs) have become a research hotspot in recent years. As an emerging intelligent transportation tool, unmanned vehicles rely on the precise location observations provided by navigation sensors. Once compromised, navigation sensors may generate abnormal observations deviating away from the ground truth, which as a result will cause severe consequences or even fatal accidents. To enhance the security of UAVs, a new deep learning based anomaly diagnosis method is proposed in this paper for the detection and identification of sensor anomalies in UAVs. The proposed method improves the topological structure of the traditional 1D Convolutional neural network (1D-CNN) and designs a 1DGAP-CNN algorithm framework to achieve a real-time rapid diagnosis. First, the original pose measurements from multiple sensors are directly input into the proposed algorithm for data fusion and preprocessing. Secondly, the proposed algorithm automatically performs feature extraction, dimension transformation, parameter reduction, and anomaly identification. Finally, the diagnosis results are automatically generated. Evaluation results show that the proposed method has higher diagnostic accuracy and faster detection speed than the state-of-the-art intelligent diagnostic algorithms.

Key words: unmanned autonomous vehicles, deep learning, anomaly diagnosis, navigation sensor, cyber attacks

中图分类号:

宫文峰, 王元哲, 陈辉, WANG Danwei. 基于深度学习的无人驾驶汽车导航传感器异常诊断方法[J]. 机械工程学报, 2021, 57(24): 268-278.

GONG Wenfeng, WANG Yuanzhe, CHEN Hui, WANG Danwei. Anomaly Diagnosis for Navigation Sensors of Unmanned Autonomous Vehicles Based on Deep Learning[J]. Journal of Mechanical Engineering, 2021, 57(24): 268-278.

参考文献

[1] NING Z,ZHANG K,WANG X,et al. Joint computing and caching in 5G-envisioned Internet of vehicles:A deep reinforcement learning-based traffic control system[J]. IEEE Transactions on Intelligent Transportation Systems,2020.1-12.
[2] BAGLOEE S A,TAVANA M,ASADI M,et al. Autonomous vehicles:challenges,opportunities,and future implications for transportation policies[J]. Journal of Modern Transportation,2016,24(4):284-303.
[3] RASHEED I,HU F,ZHANG L. Deep reinforcement learning approach for autonomous vehicle systems for maintaining security and safety using LSTM-GAN[J]. Vehicular Communications,2020,26:100266.
[4] DETHE S N,SHEVATKAR V S,BIJWE R P. Google driverless car[J]. International Journal of Scientific Research in Science,Engineering and Technology,2011,2(2):133-137.
[5] FERDOWSI A,CHALLITA U,SAAD W,et al. Robust deep reinforcement learning for security and safety in autonomous vehicle systems[C]//21st International Conference on Intelligent Transportation Systems (ITSC). IEEE,2018,2018:1-8.
[6] SHI X,WONG Y D,CHAI C,et al. An automated machine learning (AutoML) method of risk prediction for decision-making of autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems,2020:1-10.
[7] 赵治国,周良杰,朱强. 无人驾驶车辆路径跟踪控制预瞄距离自适应优化[J]. 机械工程学报,2018,54(24):166-173. ZHAO Zhiguo,ZHOU Liangjie,ZHU Qiang. Preview distance adaptive optimization for the path tracking control of unmanned vehicle[J]. Journal of Mechanical Engineering,2018,54(24):166-173.
[8] LIU Q,MO Y,MO X,et al. Secure pose estimation for autonomous vehicles under cyber attacks[C]//2019 IEEE Intelligent Vehicles Symposium (IV). IEEE,2019:1583-1588.
[9] WANG Y,MASOUD N,KHOJANDI A. Real-Time sensor anomaly detection and recovery in connected automated vehicle sensors[J]. IEEE Transactions on Intelligent Transportation Systems,2020:1-11.
[10] CURTIS S. Hacker remotely crashes Jeep from 10 miles away[J]. The Telegraph,2015.
[11] SOLON O. Team of hackers take remote control of Tesla Model S from 12 miles away[J]. The Guardian,2016.
[12] FRANCO V,WANG Y,KHOJANDI A,et al. Real-time sensor anomaly detection and identification in automated vehicles[J]. IEEE Transactions on Intelligent Transportation Systems,2019,21(3):1264-1276.
[13] MO Y,SINOPOLI B. On the performance degradation of cyber-physical systems under stealthy integrity attacks[J]. IEEE Transactions on Automatic Control. 2016,61(9):2618-2624.
[14] LI Y,ZHU L. A Bayesian game based defense scheme for CBTC systems under man-in-the-middle attacks[C]//2019 IEEE Intelligent Transportation Systems Conference,IEEE,2019:2172-2176.
[15] ULLAH F,NAEEM H,JABBAR S,et al. Cyber security threats detection in internet of things using deep learning approach[J]. IEEE Access. 2019,7(99):124379-124389.
[16] GONG W,CHEN H,ZHANG Z,et al. A data-driven-based fault diagnosis approach for electrical power DC-DC inverter by using modified convolutional neural network with global average pooling and 2-D feature image[J]. IEEE Access,2020,8:73677-73697.
[17] LECUN Y,BOSER B,DENKER J S,et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation,1989,1(4):541-551.
[18] GOODFELLOW I,BENGIO Y,COURVILLE A. Deep learning[M]. The MIT Press,2016.
[19] 宫文峰,陈辉,张美玲,等. 基于深度学习的电机轴承微小故障智能诊断方法[J]. 仪器仪表学报,2020,41(01):195-205. GONG Wenfeng,CHEN Hui,ZHANG Meiling,et al. Intelligent diagnosis method for incipient fault of motor bearing based on deep learning[J]. Chinese Journal of Scientific Instrument,2020,41(01):195-205.
[20] XIA M,LI T,XU L,et al. Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks[J]. IEEE/ASME Transactions on Mechatronics,2018,23(1):101-110.
[21] 姜洪权,贺帅,高建民,等. 一种改进卷积神经网络模型的焊缝缺陷识别方法[J]. 机械工程学报,2020,56(8):235-242. JIANG Hongquan,HE Shuai,GAO Jianmin,et al. An improved convolutional neural network for weld defect recognition[J]. Journal of Mechanical Engineering,2020,56(8):235-242.
[22] LIN M,CHEN Q,YAN S C. Network in network[C]//International Conference on Learning Representations,2014:1-10.
[23] 曲建岭,余路,袁涛,等. 基于一维卷积神经网络的滚动轴承自适应故障诊断算法[J]. 仪器仪表学报,2018,39(7):134-143. QU Jianling,YU Lu,YUAN Tao,et al. Adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural network[J]. Chinese Journal of Scientific Instrument,2018,39(7):134-143.
[24] 宫文峰,陈辉,WANG Danwei,等. 基于改进CNN-GAP-SVM的船舶电力变换器快速故障诊断方法[J/OL]. 计算机集成制造系统,2020:1-18. GONG Wenfeng,Chen Hui,Danwei WANG,et al. Fast fault diagnosis method of marine electrical converter based on improved CNN-GAP-SVM algorithm[J]. Computer Integrated Manufacturing Systems,2020:1-18.
[25] WEN L,LI X,GAO L,et al. A new convolutional ceural cetwork-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics,2018,65(7):5990-5998.
[26] SHAO H,JIANG H,ZHAO H,et al. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis[J]. Mechanical Systems and Signal Processing,2017,95:187-204.

基于深度学习的无人驾驶汽车导航传感器异常诊断方法

Anomaly Diagnosis for Navigation Sensors of Unmanned Autonomous Vehicles Based on Deep Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李春凯, 王嘉昕, 石玗, 代悦. GTAW熔池激光条纹动态行为与熔透预测方法研究[J]. 机械工程学报, 2024, 60(6): 236-244.
[2]	赵德望, 姜超, 赵延广, 杨文平, 樊俊铃. 铝锂合金疲劳性能及预测研究-基于试验和“浅层”+“深度”混合神经网络方法[J]. 机械工程学报, 2024, 60(16): 190-199.
[3]	付玲, 佘玲娟, 颜镀镭, 张鹏, 龙湘云. 基于内嵌物理信息与注意力机制BiLSTM神经网络的臂架系统疲劳损伤预测模型[J]. 机械工程学报, 2024, 60(13): 205-215.
[4]	陈钱, 陈康康, 董兴建, 皇甫一樊, 彭志科, 孟光. 一种面向机械设备故障诊断的可解释卷积神经网络[J]. 机械工程学报, 2024, 60(12): 65-76.
[5]	刘岳开, 王天杨, 褚福磊. 基于低延迟可解释性深度学习的复杂旋转机械关键部件知识嵌入与诊断方法研究[J]. 机械工程学报, 2024, 60(12): 107-115.
[6]	赖旭伟, 丁昆, 张楷, 黄锋飞, 郑庆, 李致萱, 丁国富. 基于可解释物理引导空间注意力改进的跨工艺参数立铣刀磨损辨识[J]. 机械工程学报, 2024, 60(12): 147-157.
[7]	林昕, 毛杨坤, 傅盈西, 朱锟鹏. 基于图像语义分割与图卷积的选区激光熔融成形过程羽流运动特征分析[J]. 机械工程学报, 2024, 60(12): 168-182.
[8]	邵海东, 肖一鸣, 邓乾旺, 任颖莹, 韩特. 基于不确定性感知网络的可信机械故障诊断[J]. 机械工程学报, 2024, 60(12): 194-206.
[9]	李玖法, 邹博文, 任玥. 考虑车-路交互作用的车辆轨迹预测算法研究[J]. 机械工程学报, 2024, 60(10): 76-85.
[10]	林晨, 魏洪乾, 荆威, 张幽彤. 汽车功能安全：面向敏感指令攻击场景的自主驾驶车辆路径规划风险缓解控制[J]. 机械工程学报, 2024, 60(10): 302-316.
[11]	刘聪, 刘辉, 韩立金, 聂士达. 基于学习型滑模预测控制的无人驾驶车辆非结构化环境轨迹跟踪及稳定性控制[J]. 机械工程学报, 2024, 60(10): 399-412.
[12]	许思远, 张卫东, 毛玉明, 牛斌. 数据驱动的指定变形非均质多胞结构优化设计[J]. 机械工程学报, 2024, 60(1): 85-95.
[13]	何赟泽, 李响, 王洪金, 侯岳骏, 张帆, 牟欣颖, 刘浩, 程豪, 李时华, 李杰. 基于可见光和热成像的风机叶片全周期无损检测综述[J]. 机械工程学报, 2023, 59(6): 32-45.
[14]	张言茹, 张珺玮, 王占国, 李劼峰, 张维戈. 基于历史数据的车载锂离子电池异常诊断[J]. 机械工程学报, 2023, 59(22): 89-99.
[15]	曾嵘, 李勇, 曹一家, 谢李为, 邵霞. 智能配用电系统的网络攻击检测与保护控制技术：发展与挑战^*[J]. 电气工程学报, 2023, 18(2): 125-141.