您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (6): 30-40.doi: 10.6040/j.issn.1672-3961.0.2022.215

• 交通工程——智慧交通专题 • 上一篇    

基于双层混合集成的自动驾驶汽车故障检测

闵海根1,2,3,雷小平1,李杰4,童星4,吴霞1,3*,方煜坤1   

  1. 1.长安大学信息工程学院, 陕西 西安 710064;2.西部交通安全与智能协同控制省部共建协同创新中心, 陕西 西安 710021;3.长安大学“车联网”教育部-中国移动联合实验室, 陕西 西安 710021;4.山东高速信息集团有限公司, 山东 济南 250014
  • 发布日期:2022-12-23
  • 作者简介:闵海根(1990— ),男,陕西安康人,副教授,博士,主要研究方向为智慧交通、智能网联汽车故障诊断及车路协同管控. E-mail: hgmin@chd.edu.cn. *通信作者简介:吴霞(1992— ),女,山西孝义人,讲师,博士,主要研究方向为混合交通流主动控制方法. E-mail: wuxia@chd.edu.cn.
  • 基金资助:
    国家重点研发计划项目(2021YFB2501205);国家自然科学基金青年项目(61903046);陕西省自然科学青年基金(2022JQ-663)

Fault detection of autonomous vehicle based on bi-layer hybrid ensemble

MIN Haigen1,2,3, LEI Xiaoping1, LI Jie4, TONG Xing4, WU Xia1,3*, FANG Yukun1   

  1. 1. School of Information and Engineering, Chang'an University, Xi'an 710064, Shaanxi, China;
    2. Collaborative Innovation Center for Western China Traffic Safety and Intelligent Cooperative Control, Xi'an 710021, Shaanxi, China;
    3. The Joint Laboratory for Internet of Vehicles, Ministry of Education-China Mobile Communications Corporation, Chang'an University, Xi'an 710021, Shaanxi, China;
    4. Shandong Hi-Speed Information Group Co. Ltd., Jinan 250014, Shandong, China
  • Published:2022-12-23

PDF (PC)

102

摘要： 针对单一故障检测算法难以学习到数据样本全部特征的问题,提出基于双层混合集成的无监督自动驾驶汽车故障检测方法。使用非全连接的自动编码器作为基学习器构建第1层同质集成框架——集成自动编码器,分析和选择包含集成自动编码器、一类支持向量机、孤立森林和局部离群因子的基学习器构建第2层异质多模型集成框架,学习自动驾驶汽车正常传感器数据特征;提出基于自动编码器的投票集成方法,实现基学习器特征的降维和编码融合;通过sigmoid函数映射计算故障概率并对数据是否故障进行判断。试验结果表明,提出的双层混合集成故障检测方法性能优于基学习器算法,F1指标提高了9%~40%,G指标提高了2%~28%,该故障检测方法可有效实现自动驾驶汽车故障检测。

关键词: 自动驾驶汽车, 故障检测, 集成学习, 自动编码器, 无监督学习

中图分类号: 

  • TP391
[1] SCHRICK D V. Remarks on terminology in the field of supervision, fault detection and diagnosis[J]. IFAC Proceedings Volumes, 1997, 30(18): 959-964.
[2] ZHAO Ming, CHEN Jingchao. A review of methods for detecting point anomalies on numerical dataset[C] //2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference(ITNEC). Chong-qing, China: IEEE, 2020: 559-565.
[3] GAO Zhiwei, CECATI C, DING S X. A survey of fault diagnosis and fault-tolerant techniques: Part II: fault diagnosis with knowledge-based and hybrid/active approaches[J]. IEEE Transactions on Industrial Electronics, 2015, 62(6): 3768-3774.
[4] LUNZE J, RICHTER J H. Reconfigurable fault-tolerant control: a tutorial introduction[J]. European Journal of Control, 2008, 14(5): 359-386.
[5] SCHÖLKOPF B, WILLIAMSON R C, SMOLA A, et al. Support vector method for novelty detection[C] //Advances in Neural Information Processing Systems. Denver, USA: ACM, 1999: 582-588.
[6] ERFANI S M, RAJASEGARAR S, KARUNASEKERA S, et al. High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning[J]. Pattern Recognition, 2016: 121-134.
[7] MA J, PERKINS S. Time-series novelty detection using one-class support vector machines[C] //Proceedings of the International Joint Conference on Neural Networks. Portland, USA: IEEE, 2003: 1741-1745.
[8] BARBADO A, CORCHO Ó, BENJAMINS R. Rule extraction in unsupervised anomaly detection for model explainability: application to oneclass SVM[J]. Expert Systems with Applications, 2022, 189: 116100.
[9] 闵海根, 方煜坤, 吴霞, 等. 基于自动编码器和长短时记忆网络的智能汽车故障诊断方法研究[J]. 四川大学学报(自然科学版), 2021,58(5):79-87. MIN Haigen, FANG Yukun, WU Xia, et al. Fault diagnosis research for intelligent vehicles based on autoencoder and LSTM[J]. Journal of Sichuan University(Natural Science Edition), 2021, 58(5): 79-87.
[10] GONG Dong, LIU Lingqiao, LE Vuong, et al. Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection[C] //2019 IEEE/CVF International Conference on Computer Vision(ICCV). Seoul, Korea: IEEE, 2020: 1705-1714.
[11] BREUNIG M M, KRIEGEL H P, NG R T, et al. LOF: identifying density-based local outliers[C] //SIGMOD'00: Proceedings of the 2000 ACM SIGMOD Intern-ational Conference on Management of Data. Dallas, USA: ACM, 2000: 93-104.
[12] 庄池杰, 张斌, 胡军, 等. 基于无监督学习的电力用户异常用电模式检测[J].中国电机工程学报, 2016, 36(2):379-387. ZHUANG Chijie, ZHANG Bin, HU Jun, et al. Anomaly detection for power consumption patterns based on unsupervised learning[J]. Proceedings of the CSEE, 2016, 36(2): 379-387.
[13] DING Nan, MA Haoxuan, GAO Huanbo, et al. Real-time anomaly detection based on long short-term memory and gaussian mixture model[J]. Computers & Electrical Engineering. 2019, 79: 106458.
[14] PROVOTAR O I, LINDER Y M, VERES M M. Unsupervised anomaly detection in time series using LSTM-based autoencoders[C] //2019 IEEE International Conference on Advanced Trends in Information Theory(ATIT). Kyiv, Ukraine: IEEE, 2019: 513-517.
[15] NANDURI A, SHERRY L. Anomaly detection in aircraft data using recurrent neural networks(RNN)[C] //Integrated Communications Navigation & Surveillance. Herndon, USA: IEEE, 2016: 5C2-1-5C2-8.
[16] FEI T L, KAI M T, ZHOU Z H. Isolation forest[C] //IEEE International Conference on Data Mining. Pisa, Italy: IEEE, 2008: 413-422.
[17] SHAHRAKI A, ABBASI M, HAUGEN Y. Boosting algorithms for network intrusion detection: a comparative evaluation of real adaboost, gentle AdaBoost and modest adaBoost[J]. Engineering Applications of Artificial Intelligence, 2020, 94: 103770.
[18] ZAHID Y, TAHIR M A, DURRANI M N. Ensemble learning using bagging and and inception-v3 for anomaly detection in surveillance videos[C] //2020 IEEE International Conference on Image Processing(ICIP). Abu Dhabi, United Arab Emirates: IEEE, 2020: 588-592.
[19] ZHONG Ying, CHEN Wenqi, WANG Zhiliang, et al. HELAD: a novel network anomaly detection model based on heterogeneous ensemble learning[J]. Computer Networks, 2019: 107049.
[20] FANG Yukun, MIN Haigen, WANG Wuqi, et al. A fault detection and diagnosis system for autonomous vehicles based on hybrid approaches[J]. IEEE Sensors Journal, 2020, 20(16): 9359-9371.
[21] 闵海根, 方煜坤, 吴霞, 等. 网联交通环境下的车-车通信故障诊断方法[J]. 山东大学学报(工学版), 2021,51(6):84-92. MIN Haigen, FANG Yukun, WU Xia, et al. Fault diagnosis of vehicle-to-vehicle communication in networked traffic environment[J]. Journal of Shandong University(Engineering Science), 2021, 51(6): 84-92.
[22] SAFAVI S, SAFAVI M A, HAMID H, et al. Multi-sensor fault detection, identification, isolation and health forecasting for autonomous vehicles[J]. Sensors, 2021, 21(7): 2547.
[23] PANG Guansong, SHEN Chunhua, CAO Longbin, et al. Deep learning for anomaly detection: a review[J]. ACM Computing Surveys, 2021, 54(2): 1-38.
[1] 傅桂霞,邹国锋,毛帅,潘金凤,尹丽菊. 融合Gabor特征与卷积特征的小样本行人重识别[J]. 山东大学学报 (工学版), 2021, 51(3): 22-29.
[2] 张大鹏,刘雅军,张伟,沈芬,杨建盛. 基于异质集成学习的虚假评论检测[J]. 山东大学学报 (工学版), 2020, 50(2): 1-9.
[3] 梁志祥,刘晓明,牟颖,刘玉田. 基于深度学习的新能源爬坡事件预测方法[J]. 山东大学学报 (工学版), 2019, 49(5): 24-28.
[4] 张宗堂,王森,孙世林. 一种针对不平衡数据分类的集成学习算法[J]. 山东大学学报 (工学版), 2019, 49(4): 8-13.
[5] 秦军,张远鹏,蒋亦樟,杭文龙. 多代表点自约束的模糊迁移聚类[J]. 山东大学学报 (工学版), 2019, 49(2): 107-115.
[6] 朱晓强,钟麦英. 基于强跟踪H-/H∞优化的无人机系统故障检测[J]. 山东大学学报 (工学版), 2019, 49(1): 66-74.
[7] 沈冬冬,周风余,栗梦媛,王淑倩,郭仁和. 基于集成深度神经网络的室内无线定位[J]. 山东大学学报 (工学版), 2018, 48(5): 95-102.
[8] 张璞,刘畅,王永. 基于特征融合和集成学习的建议语句分类模型[J]. 山东大学学报 (工学版), 2018, 48(5): 47-54.
[9] 沈冀,马志强,李图雅,张力. 面向短文本情感分析的词扩充LDA模型[J]. 山东大学学报(工学版), 2018, 48(3): 120-126.
[10] 陈杰,钟麦英,张利刚. 基于L2范数最小估计的无人机飞控系统故障检测[J]. 山东大学学报(工学版), 2017, 47(5): 89-95.
[11] 张米露,王天真,汤天浩,辛斌. 一种模式关联主元分析的海流机故障检测方法[J]. 山东大学学报(工学版), 2017, 47(5): 123-129.
[12] 陈志文, 彭涛, 阳春华, 何章鸣,杨超, 杨笑悦. 基于改进的典型相关分析的故障检测方法[J]. 山东大学学报(工学版), 2017, 47(5): 44-50.
[13] 李洪阳,何潇. 基于SCKF方法的非线性随机动态系统故障诊断方法[J]. 山东大学学报(工学版), 2017, 47(5): 130-135.
[14] 杨瑞. 基于稀疏表示的间歇故障检测方法及仿真[J]. 山东大学学报(工学版), 2017, 47(5): 51-56.
[15] 刘洋. 乘性故障对开闭环系统故障诊断性能的影响[J]. 山东大学学报(工学版), 2017, 47(5): 38-43.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发