隐蔽网络攻击下智能网联汽车容错安全控制

打开文本图片集

中图分类号：U461 文献标识码：A DOI:10.3969/j.issn.1674-8484.2025.06.011

（1.东南大学机械工程学院，南京211189，中国；2.清华大学车辆与运载学院，北京100084，中国）

Fault-tolerant and safety control of intelligent connected vehicles under stealthy network attacks

QIU Zhaoyu1,ZHU Xiaoyuan*1, TIAN Guangyu²,YIN Guodong .SchoolofMechanicalandAutomotiveEngineering,XiamenInstituteofTechnology,Xiamen6lo4,China; 2.Fujian KeyLaboratoryofAdvancedDesignand ManufacturingofBuses,Xiamen 36l024,China)

Abstract:Anadaptive neural network control method integrated with dynamic watermark-based attack detection toenhance vehiclesafetywasproposed toaddress thedual safety threats of actuator faultsand stealthyreplayattacksin intellgent connected vehicles.Anadaptive fault-tolerantcontrollerwithdisturbance rejectioncapability was designed by integrating a radial basis function neural network (RBFNN)and a nonlinear disturbance observer (NDO).Additionaly，adynamic watermark sequence was embedded into the control lop,andanatack detection mechanism wasconstructed based onsystemresiduals to identify covert replaynetworkatacks.Finaly,hardware-in-the-loop (HIL)validationwasconductedusingadSPACE-Nl cosimulation platform.The results show that the average error during the fault is reduced by 80.71% ,comparing with thenon-fault-tolerant controller.Furthermore,stealthyreplayattacksaresuccessfullydetected,and the presence of faults enhances the detection effectiveness without causing false alarms.

Keywords:radial basis function neural network (RBFNN);fault-tolerant control; stealthy replayattack detection; dynamic watermarking

在汽车电动化、智能化、网联化的大趋势下，车辆安全将面临更多的挑战[。（剩余20079字）