| 266 | 0 | 7 |
| Downloads | Citas | Reads |
[Significance] Autonomous vehicles have been widely applied in transportation, logistics, and other fields due to their efficiency, convenience, and intelligence. These vehicles usually rely on a variety of heterogeneous sensors to measure environmental information and then execute real-time decisions accordingly. However, owing to the complexity of multi-sensor system structures and factors such as component aging, vehicle sensors are inevitably prone to faults. Minor faults can cause state monitoring errors, distorting environmental perception information and interfering with the decision-making of intelligent vehicle control systems. Sensor fault diagnosis technology is a key approach to ensuring the safety and reliability of autonomous vehicles, and related research has made significant progress. Nevertheless, this field still faces various challenges regarding practical feasibility and improving diagnostic performance. Therefore, summarizing existing research results, reasonably selecting fault diagnosis schemes, and anticipating future development directions are of great significance. [Progress] Diagnostic methods can be divided into knowledge-driven and data-driven approaches according to whether they rely on prior models and domain knowledge. Knowledge-driven methods comprehensively utilize system models, expert experience, or fuzzy logic to detect and locate faults. Among these, model-based methods use analytical models to design robust residual generators and construct evaluation criteria to achieve fault diagnosis. These approaches are characterized by clear physical meaning and strong interpretability but are difficult to apply to vehicles lacking accurate models. Diagnostic approaches based on expert systems and fuzzy logic transform domain knowledge into diagnostic logic to extract correlated fault information from multiple sensor sources; however, their performance is limited when the rule base is incomplete. Data-driven fault diagnosis does not require explicit models or prior knowledge; instead, it directly mines potential patterns and correlated features from historical data to construct diagnostic systems. Cluster analysis–based methods rely on learning mechanisms to analyze data distribution characteristics and can classify fault modes without requiring large numbers of labeled samples; however, their performance degrades when the number of clusters is improperly selected or when data quality is poor. Support vector machine–based methods achieve fault classification and recognition by constructing a maximum-margin hyperplane but are sensitive to kernel function selection, class imbalance, and complex hyperparameter tuning. Random forest–based methods construct multiple decision trees and perform voting, offering strong classification performance for nonlinear data but exhibiting high model complexity and limited interpretability. Deep learning–based diagnostic methods perform unsupervised pretraining through multiple hidden layers, enabling automatic extraction of fault features from raw data to higher-level representations. These approaches demonstrate excellent performance in handling high-dimensional, nonstationary, and heterogeneous multisource data; However, they face challenges such as scarce fault samples, poor interpretability, and high computational complexity. In addition, an evaluation framework for fault diagnosis methods is integrated, providing a quantitative basis for selecting and optimizing diagnostic techniques. [Conclusions and Prospects] Sensor fault diagnosis techniques have been widely applied in autonomous vehicles to enhance system safety and reliability. Future research directions include hybrid diagnostic systems driven by both knowledge and data, improvements in the generalization and interpretability of data-driven methods, optimization of edge intelligence deployment, and exploration of meta-learning and modular design.
[1]于蕾艳,侯泽宇,吴宝贵,等.无人驾驶汽车垂直泊车路径规划、跟踪实验设计及评价[J].实验技术与管理, 2023, 40(9):55–64, 156.YU L Y, HOU Z Y, WU B G, et al. Experiment design and evaluation of driverless vehicle vertical parking path planning and tracking[J]. Experimental Technology and Management,2023, 40(9):55–64, 156.(in Chinese)
[2]HOSSAIN M N, RAHMAN M M, RAMASAMY D. Advances in intelligent vehicular health monitoring and fault diagnosis:Techniques, technologies, and future directions[J].Measurement, 2025, 253:117618.
[3]FANG Y K, MIN H G, WANG W Q, et al. A fault detection and diagnosis system for autonomous vehicles based on hybrid approaches[J]. IEEE Sensors Journal, 2020, 20(16):9359–9371.
[4]DARÁNYI A, ABONYI J. Fault diagnostics based on the analysis of probability distributions estimated using a particle filter[J]. Sensors, 2024, 24(3):1–19.
[5]CONEJO C, PUIG V, MORCEGO B, et al. Enhancing safety in autonomous vehicles using zonotopic LPV-EKF for fault detection and isolation in state estimation[J]. Control Engineering Practice, 2025, 156:106192.
[6]ELSAYED H, EL-MOWAFY A, ALLAHVIRDI-ZADEH A, et al. A combination of classification robust adaptive kalman filter with PPP-RTK to improve fault detection for integrity monitoring of autonomous vehicles[J]. Remote Sensing, 2025,17(2):1–19.
[7]PARK S, OH K, JEONG Y, et al. Model predictive control-based fault detection and reconstruction algorithm for longitudinal control of autonomous driving vehicle using multi-sliding mode observer[J]. Microsystem Technologies,2020, 26(1):239–264.
[8]PANG H, SHANG Y T, WANG P. Design of a sliding mode observer-based fault tolerant controller for automobile active suspensions with parameter uncertainties and sensor faults[J].IEEE Access, 2020, 8:186963–186975.
[9]LEE J, OH K, YOON Y, et al. Adaptive fault detection and emergency control of autonomous vehicles for fail-safe systems using a sliding mode approach[J]. IEEE Access, 2022, 10:27863–27880.
[10]ZOU S C, ZHAO W Z, LIANG W H, et al. Fault diagnosis and fault-tolerant compensation strategy for wheel angle sensor of steer-by-wire vehicle via extended Kalman filter[J]. IEEE Sensors Journal, 2022, 22(2):1756–1766.
[11]MORADI M, KORDESTANI M, JALALI M, et al. Sensor and decision fusion-based intrusion detection and mitigation approach for connected autonomous vehicles[J]. IEEE Sensors Journal, 2024, 24(13):20908–20919.
[12]FENG Z, YANG R, ZHOU Z, et al. Online fault diagnosis and tolerance based on multiexpert joint belief rule base for sensor failures of vehicles[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72:1–13.
[13]ALSUWIAN T, USMAN M H, AMIN A A. An autonomous vehicle stability control using active fault-tolerant control based on a fuzzy neural network[J]. Electronics, 2022, 11(3165):1–19.
[14]ZHANG H W, GAO Y N, LIU H X, et al. Spatial and temporal characteristic analysis based long short-term memory for detection of sensor fault in autonomous vehicles[J]. Scalable Computing:Practice and Experience, 2024, 25(4):2159–2174.
[15]LI Y, DONG J X. Fault detection unknown input observer for local nonlinear fuzzy autonomous ground vehicles system based on a joint peak-to-peak analysis and zonotopic analysis threshold[J]. IEEE Transactions on Vehicular Technology, 2025,74(5):7226–7236.
[16]OKOLAI B D, ONYEJEGBU L N, ONUODU F E. Autonomous vehicle fault detection and isolation model using stochastic gradient descent[J]. Global Scientific Journals, 2023, 11(8):1202–1216.
[17]IGNATIOUS H A, KHAN M. An overview of sensors in autonomous vehicles[J]. Procedia Computer Science, 2022, 198:736–741.
[18]ORTIZ F M, SAMMARCO M, COSTA L H M K, et al.Applications and services using vehicular exteroceptive sensors:A survey[J]. IEEE Transactions on Intelligent Vehicles, 2023,8(1):949–969.
[19]National Transportation Safety Board. Preliminary report:Highway crash involving Ford Mustang Mach-E with Blue Cruise system[R]. Philadelphia, Pennsylvania, 2024. NTSB Case No. HWY24FH007.
[20]National Transportation Safety Board. Preliminary report:Highway crash involving Ford Mustang Mach-E with Blue Cruise System[R]. San Antonio, Texas, 2024. NTSB Case No.HWY24FH008.
[21]Ecer AI资讯.自动驾驶事故频发四大安全隐患与技术演进瓶颈[EB/OL]. 2025. https://ecweb.ecer.com/topic/cn/detail-284512-autonomous_vehicles_face_safety_challenges_amid_ris ing_accident_reports.html.Ecer AI News. Four major safety hazards and technological bottlenecks in the frequent occurrence of autonomous driving accidents[EB/OL]. 2025. https://ecweb.ecer.com/topic/cn/detail-284512-autonomous_vehicles_face_safety_challenges_amid_rising_accident_reports.html.(in Chinese)
[22]澎湃新闻.自动驾驶事故频发,安全痛点在哪里?[EB/OL].2024. https://www.thepaper.cn/newsDetail_forward_27999935.Pengpai News. Frequent autonomous driving accidents, where are the safety pain points?[EB/OL]. 2024. https://www.thepaper.cn/newsDetail_forward_27999935.(in Chinese)
[23]Associated Press. Waymo recalls 1,200 vehicles after autonomous crashes involving stationary objects[R]. AP News. 2024.
[24]智能车联.全球自动驾驶道路测试车辆安全运行数据[R].2024.Intelligent Connected Vehicles. Global autonomous driving road test vehicle safety operation data[R]. 2024.(in Chinese)
[25]National Transportation Safety Board. Collision between vehicle controlled by developmental automated driving system and pedestrian[R]. Tempe, Arizona, 2018. NTSB Case No.HWY18MH010.
[26]MOHAMED A, REN J, EL-GINDY M, et al. Literature survey for autonomous vehicles:sensor fusion, computer vision,system identification and fault tolerance[J]. International Journal of Automation and Control, 2018, 12(4):555–581.
[27]FRANCO V W, WANG Y Y, KHOJANDI A, et al. Real-time sensor anomaly detection and identification in automated vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(3):1264–1276.
[28]XIONG H Y, WANG Z J, WU G H, et al. Steering actuator fault diagnosis for autonomous vehicle with an adaptive denoising residual network[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:1–13.
[29]KHAN S, YAIRI T. A review on the application of deep learning in system health management[J]. Mechanical Systems and Signal Processing, 2018, 107:241–265.
[30]SACORANSKY D, MARSHALL J A, HASHTRUDI-ZAAD K.Towards unsupervised filtering of millimetre-wave radar returns for autonomous vehicle road following[C]//2023 IEEE International Conference on Robotics and Automation(ICRA):London UK, IEEE, 2023:6995–7001.
[31]JAN S U, LEE Y D, SHIN J, et al. Sensor fault classification based on support vector machine and statistical time-domain features[J]. IEEE Access, 2017, 5:8682–8690.
[32]JEONG Y N, SON S R, LEE B K. The lightweight autonomous vehicle self-diagnosis(LAVS)using machine learning based on sensors and multi-protocol IoT gateway[J]. Sensors, 2019,19(2534):1–11.
[33]ABBOUSH M, KNIEKE C, RAUSCH A. Intelligent identification of simultaneous faults of automotive software systems under noisy and imbalanced data using ensemble LSTM and random forest[J]. IEEE Access, 2023, 11:140022–40040.
[34]JAVED A R, USMAN M, REHMAN S U, et al. Anomaly detection in automated vehicles using multistage attentionbased convolutional neural network[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(7):4291–4300.
[35]MIN H G, FANG Y K, WU X, et al. A fault diagnosis framework for autonomous vehicles with sensor self-diagnosis[J]. Expert Systems with Applications, 2023, 224:1–13.
[36]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):1–7.
[37]HARBAOUI N, MAKKAWI K, AIT-TMAZIRTE N, et al.Context adaptive fault tolerant multi-sensor fusion:Towards a fail-safe multi operational objective vehicle localization[J].Journal of Intelligent&Robotic Systems, 2024, 110(1):1–19.
[38]WANG H, LI Y F. Bioinspired membrane learnable spiking neural network for autonomous vehicle sensors fault diagnosis under open environments[J]. Reliability Engineering&System Safety, 2023, 233:1–14.
[39]ZHANG L, LYU S W, TRINKLE J. A dynamic bayesian approach to real-time estimation and filtering in grasp acquisition[C]//2013 IEEE International Conference on Robotics and Automation(ICRA):Karlsruhe Gemany, 2013:85–92.
[40]JEONG Y. Model predictive control based integrated fault tolerant controller for autonomous vehicles with four-wheel independent steering, driving and braking systems[J]. Vehicle System Dynamics, 2024, 9:1–25.
[41]HU H Y, TANG M H, CHEN G Y, et al. Design of a fault-tolerant control algorithm for four-wheel steering vehicle steering locking based on dynamic model reconstruction[J].SAE International Journal of Vehicle Dynamics Stability and NVH, 2025, 9(4):1–22.
[42]胡杰,李源洁,耿號,等.基于深度学习的汽车故障知识图谱构建[J].汽车工程, 2023, 45(1):52–60, 85.HU J, LI Y J, GENG H, et al. Construction of vehicle fault knowledge graph based on deep learning[J]. Automotive Engineering, 2023, 45(1):52–60, 85.(in Chinese)
[43]GAO Z W, CECATI C, DING S X, et al. A survey of fault diagnosis and fault-tolerant techniques—partⅠ:Fault diagnosis with model-based and signal-based approaches[J]. IEEE Transactions on Industrial Electronics, 2015, 62(6):3757–3767.
[44]YU Q Q, WAN C J, LI J F, et al. A model-based sensor fault diagnosis scheme for batteries in electric vehicles[J]. Energies,2021, 14(4):1–15.
[45]GOODMAN J, HILAL W, GADSDEN S, et al. Comparison of SVSF-KF adaptive estimation algorithms on an electrohydrostatic actuator subject to a fault[J]. IEEE Sensors Journal, 25(2):2905–2920.
[46]KHODARAHMI M, MAIHAMI V. A review on Kalman filter models[J]. Archives of Computational Methods in Engineering,2023, 30(1):727–747.
[47]SHI Q, ZHANG H. Fault diagnosis of an autonomous vehicle with an improved SVM algorithm subject to unbalanced datasets[J]. IEEE Transactions on Industrial Electronics, 2021,68(7):6248–6256.
[48]ZUO Y, LAI C Y, IYER K L V. A review of sliding mode observer based sensorless control methods for PMSM drive[J].IEEE Transactions on Power Electronics, 2023, 38(9):11352–11367.
[49]罗石,杨勤,朱长顺,等.基于传感器融合技术的专家系统[J].交通科学与工程, 2013, 29(3):67–71.LUO S, YANG Q, ZHU C S, et al. Expert system based on sensor fusion technology[J]. Journal of Traffic and Transportation Engineering, 2013, 29(3):67–71.(in Chinese)
[50]胡杰,张潇,魏敏,等.基于模糊BN和改进证据理论的车辆故障定位方法[J].汽车工程, 2023, 45(10):1975–1983.HU J, ZHANG X, WEI M, et al. Vehicle fault location method based on fuzzy BN and improved evidence theory[J]. Automotive Engineering, 2023, 45(10):1975–1983.(in Chinese)
[51]ZHANG H, ZHANG Q, LIU J, et al. Fault detection and repairing for intelligent connected vehicles based on dynamic Bayesian network model[J]. IEEE Internet of Things Journal,2018, 5(4):2431–2440.
[52]SAXENA A, WU B, VACHTSEVANOS G. Integrated diagnosis and prognosis architecture for fleet vehicles using dynamic case-based reasoning[C]//IEEE Systems Readiness Technology Conference(AUTOTESTCON):Orlando USA, 2005:96–102.
[53]RAJA K V, SIDDHARTH R, YUVARAJ S, et al. An artificial intelligence based automated case-based reasoning(CBR)system for severity investigation and root-cause analysis of road accidents:Comparative analysis with the predictions of ChatGPT[J]. Journal of Engineering Research, 2024, 12(4):895–903.
[54]LEI Y, YANG B, JIANG X, et al. Applications of machine learning to machine fault diagnosis:A review and roadmap[J].Mechanical Systems and Signal Processing, 2020, 138:1–39.
[55]ZHAO R, YAN R Q, CHEN Z H, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019, 115:213–237.
[56]LI X, ZHANG W, DING Q. A robust intelligent fault diagnosis method for rolling element bearings based on deep distance metric learning[J]. Neurocomputing, 2018, 310:77–95.
[57]KHAN S, YAIRI T. A review on the application of deep learning in system health management[J]. Mechanical Systems and Signal Processing, 2018, 107:241–265.
[58]ZHOU R, HUANG H Q, LEE J H, et al. Identifying typical pre-crash scenarios based on in-depth crash data with deep embedded clustering for autonomous vehicle safety testing[J].Accident Analysis&Prevention, 2023, 191(107218):1–14.
[59]WANG B, WANG G W, WANG Y W, et al. A K-means clustering method with feature learning for unbalanced vehicle fault diagnosis[J]. Smart and Resilient Transportation, 2021,3(2):162–176.
[60]SINAGA K P, YANG M S. Unsupervised K-means clustering algorithm[J]. IEEE Access, 2020, 8:80716–80727.
[61]LIU T M, YU H, BLAIR R H. Stability estimation for unsupervised clustering:A review[J]. Wiley Interdisciplinary Reviews:Computational Statistics, 2022, 14(6):1–17.
[62]夏金泽,孙浩铭,胡盛辉,等.基于图像信息约束的三维激光点云聚类方法[J].光电工程, 2023, 50(2):37-49.XIA J, SUN H M, HU S H, et al. 3D laser point cloud clustering method based on image information constraints[J]. OptoElectronic Engineering, 2023, 50(2):37–49.(in Chinese)
[63]DING S, HAO M, CUI Z, et al. Application of multi-SVM classifier and hybrid GSAPSO algorithm for fault diagnosis of electrical machine drive system[J]. ISA Transactions, 2023,133:529–538.
[64]AMIRI A F, OUDIRA H, CHOUDER A, et al. Faults detection and diagnosis of PV systems based on machine learning approach using random forest classifier[J]. Energy Conversion and Management, 2024, 301(118076):1–15.
[65]CHEN S Z, YANG R, ZHONG M , et al. A random forest and model-based hybrid method of fault diagnosis for satellite attitude control systems[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 72(3518413):1–13.
[66]HOSSAIN M N, RAHMAN M M, RAMASAMY D. Artificial intelligence-driven vehicle fault diagnosis to revolutionize automotive maintenance:a review[J]. Computer Modeling in Engineering&Sciences(CMES), 2024, 141(2):951–996.
[67]ZHANG D X, HAN X Q, DENG C Y. Review on the research and practice of deep learning and reinforcement learning in smart grids[J]. CSEE Journal of Power and Energy Systems,2018, 4(3):362–370.
[68]HU Z L, HE T, ZENG Y H, et al. Fast image recognition of transmission tower based on big data[J]. Protection and Control of Modern Power Systems, 2018, 3(2):1–10.
[69]HOU W, LI W, LI P. Fault diagnosis of the autonomous driving perception system based on information fusion[J]. Sensors,2023, 23(11):5110.
[70]PAN H H, SUN W C, SUN Q M, et al. Deep learning based data fusion for sensor fault diagnosis and tolerance in autonomous vehicles[J]. Chinese Journal of Mechanical Engineering, 2021,34(3):171–181.
[71]刘俊孚,岑健,黄汉坤,等.零小样本旋转机械故障诊断综述[J].计算机工程与应用, 2024, 60(15):42–54.LIU J F, CEN J, HUANG H K, et al. Review on zero or few sample rotating machinery fault diagnosis[J]. Journal of Computer Engineering&Applications, 2024, 60(15):42–54.(in Chinese)
[72]孙彦武,张陈登,张丽华,等.基于机器学习的大规模云桌面实验室计算机故障预警模型构建研究[J].实验技术与管理, 2025, 42(4):220–226.SUN Y W, ZHANG C D, ZHANG L H, et al. Research on the construction of computer faults prewarning models for largescale cloud desktop laboratories based on machine learning[J].Experimental Technology and Management, 2025, 42(4):220–226.(in Chinese)
[73]NAHMIAS M A, DELIMA T F, TAIT A N, et al. Photonic multiply-accumulate operations for neural networks[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2019, 26(1):1–18.
[74]DING S X. Model-based fault diagnosis techniques:Design schemes, algorithms, and tools[M]. 2nd Edition, Berlin, Germany:Springer, 2013.
Basic Information:
DOI：10.16791/j.cnki.sjg.2026.02.014
China Classification Code:U472.9;U463.6;TP212
Citation Information:
[1]SONG Yang,ZHENG Weihang,ZHANG Xiaoyu.A review of sensor fault diagnosis for autonomous vehicles[J].Experimental Technology and Management,2026,43(02):118-129.DOI:10.16791/j.cnki.sjg.2026.02.014.
Fund Information:
国家自然科学基金项目(62103032,62371032); 北京市教育委员会科学研究计划项目(KM202410016009); 北京建筑大学“建大英才”项目(JDYC20220820); 青年教师科研能力提升计划(X21082)
2025-09-04
2025
2025-11-14
2025
2025-11-07
1
2026-02-27
2026-02-27
2026-02-27