Restricted accessResearch articleFirst published online 2025
Study on collaboration of a machine learning-based fault detector and a fault tolerant direct yaw moment controller for distributed drive electric vehicles
Distributed drive electric vehicles (DDEVs) equip independent motors on all drive wheels. Therefore, faulty motors can significantly impact the operational efficiency and safety of these vehicles. The impact is especially notable under challenging driving conditions, such as slippery roads, compared to normal driving conditions. Hence, to ensure comfortable and safe driving conditions, it is crucial to explore fault detection and fault-tolerant control systems. This study introduces a novel collaborative system that integrates an online fault detector, based on support vector machines (SVMs), with a fault-tolerant controller utilizing direct yaw moment control. The proposed system efficiently identifies types and locations of motor faults and dynamically adjusts the torque output of the functioning motors to mitigate various faulty motor scenarios. The fault detector is trained offline using SVM using phase current signals of the motors. SVM is chosen because it requires less training data compared to other machine learning techniques. The proposed fault-tolerant controller utilizes sliding mode control (SMC) for effective direct yaw moment control of the DDEV. The effectiveness of the proposed system is validated through simulations and prototype testing.
GelmanovaZSZhabalovaGGSivyakovaGA, et al. Electric cars. Advantages and disadvantages. J Phys Conf Ser2018; 1015(5): 304–325.
2.
BabanezhadHShahrakiMColakI, et al. The impact of the presence of a high number of electric vehicles in future smart cities – a review. Elect Power Compon Syst2024; 0: 1–12.
3.
LiangJLuYWangF, et al. A robust dynamic game-based control framework for integrated torque vectoring and active front-wheel steering system. IEEE Trans Intell Transp Syst2023; 24(7): 7328–7341.
4.
SalimiSNassiriSBayatA, et al. Lateral coefficient of friction for characterizing winter road conditions. Can J Civ Eng2016; 43(1): 73–83.
5.
LiuLShiKYuanX, et al. Multiple model-based fault-tolerant control system for distributed drive electric vehicle. J Braz Soc Mech Sci Eng2019; 41: 1–15.
6.
ZhengJWangZWangD, et al. Review of fault diagnosis of PMSM drive system in electric vehicles. In: Proceeding of 36th Chinese control conference (CCC), 2017, pp.7426–7432.
7.
ChoiCLeeW.Design and evaluation of voltage measurement-based sectoral diagnosis method for inverter open switch faults of permanent magnet synchronous motor drives. IET Electric Power Appl2012; 6(8): 526–532.
8.
ZhengPZhaoJLiuR, et al. Magnetic characteristics investigation of an axial-axial flux compound-structure PMSM used for HEVs. IEEE Trans Magn2010; 46(6): 2191–2194.
9.
RoseroJRomeralLOrtegaJA, et al. Demagnetization fault detection by means of Hilbert Huang transform of the stator current decomposition in PMSM. In: Proceeding of 2008 IEEE international symposium on industrial electronics, 2008, pp.172–177.
10.
Osorio-GordilloGLDarouachMBoutat-BaddasL, et al. Dynamical observer-based control for descriptor systems. IMA J Math Control Inf2018; 35(3): 707–734.
11.
KimMCLeeJHWangDH, et al. Induction motor fault diagnosis using support vector machine, neural networks, and boosting methods. Sensors2023; 23(5): 2585.
12.
AnKLuJZhuQ, et al. Edge solution for real-time motor fault diagnosis based on efficient convolutional neural network. IEEE Trans Instrum Meas2023; 72: 1–12.
13.
SeyedmohammadiJZeinadiniANavidiMN, et al. A new robust hybrid model based on support vector machine and firefly meta-heuristic algorithm to predict pistachio yields and select effective soil variables. Ecol Inform2023; 74: 102002.
14.
ZhengYGeYMuhsenS, et al. New ridge regression, artificial neural networks and support vector machine for wind speed prediction. Adv Eng Softw2023; 179: 103426.
15.
HołaACzarneckiS.Random forest algorithm and support vector machine for nondestructive assessment of mass moisture content of brick walls in historic buildings. Autom Constr2023; 149: 104793.
16.
WannerDNybackaMWallmarkO, et al. Experimental implementation of a fault handling strategy for electric vehicles with individual-wheel drives. In: RosenbergerMPlöchlMSixKJohannesJ (eds.) Dynamics of vehicles on roads and tracks. CRC Press: London, UK, 2016, pp.147–152.
17.
ChenROuJ.A hybrid fault-tolerant control strategy for four-wheel independent drive vehicles. Adv Mech Eng2021; 13(9): 16878140211045486.
18.
MaLMeiKDingS.Direct yaw-moment control design for in-wheel electric vehicle with composite terminal sliding mode. Nonlinear Dyn2023; 111(18): 17141–17156.
19.
RaksincharoensakPNagaiMShinoM.Lane keeping control strategy with direct yaw moment control input by considering dynamics of electric vehicle. Veh Syst Dyn2006; 44: 192–201.
20.
IlešŠvecMMakarunP, et al. Stabilizing direct yaw moment control based on a flexible set-membership constraint. In: Proceeding of 30th Mediterranean conference on control and automation (MED), 2022, pp.289–294.
21.
Lidfors LindqvistAWalkerPD. Handling dynamics of a lightweight solar-electric vehicle with direct yaw moment control. In: KlompMBruzeliusFNielsenJHillemyrA (eds.) Advances in dynamics of vehicles on roads and tracks. Gothenburg, Sweden: Springer Cham, 2019, pp.1169–1177.
22.
KomurcugilHBiricikSBayhanS, et al. Sliding mode control: overview of its applications in power converters. IEEE Ind Electron Mag2020; 15(1): 40–49.
23.
MaLChengCGuoJ, et al. Direct yaw-moment control of electric vehicles based on adaptive sliding mode. Math Biosci Eng2023; 20(7): 13334–13355.
24.
PatilSSWanaskarVShendgePD, et al. Sliding mode and inertial delay based direct yaw moment control for AGVs. In: Proceedings of the 6th international conference for convergence in technology (I2CT), 2021, pp.1–6.
25.
LiangZWangZDuanJ, et al. Backup pattern for traction system of FWIA electric vehicle to guarantee maneuverability and stability in presence of motor faults and failures. J Franklin Inst2024; 361: 106714.
26.
BonciAIndriMKermenovR, et al. Comparison of PMSMs motor current signature analysis and motor torque analysis under transient conditions. In: Proceedings of 2021 IEEE international conference on industrial informatics (INDIN), 2021, pp.1–6.
27.
LiuDInoueHKanemaruM.Robust motor current signature analysis (MCSA)-based fault detection under varying operating conditions. In: Proceedings of 25th international conference on electrical machines and systems (ICEMS), 2022, pp.1–5.
28.
GrenierDLouisJP.Modeling for control of non-sinewave permanent-magnet synchronous drives by extending park’s transformation. Math Comput Simul1995; 38(4-6): 445–452.
29.
HuJZouJXuF, et al. An improved PMSM rotor position sensor based on linear Hall sensors. IEEE Trans Magn2012; 48(11): 3591–3594.
30.
MuhammadEValiARKashaniniaA, et al. Coordination of active front steering and direct yaw control systems using MIMO sliding mode control. Int J Control Autom Syst2024; 22(1): 1–15.
SunTWongPKWangX.Back propagation neural network-based fault diagnosis and fault tolerant control of distributed drive electric vehicles based on sliding mode control-based direct yaw moment control. Vehicles2023; 6: 93–119.
33.
JiangSBWongPKGuanR, et al. An efficient fault diagnostic method for three-phase induction motors based on incremental broad learning and non-negative matrix factorization. IEEE Access2019; 7: 17780–17790.
34.
GawthropPJMcGookinE.A LEGO-based control experiment. IEEE Control Syst2004; 24(5): 43–56.
35.
HsiaSCHsuCY.Real-time monitor and control system for abnormal motor vibrations. IEEE Trans Instrum Meas2024; 73: 1–11.
36.
WuWSivaparthipanCBSanz-PrietoI.Application of automobile modelling optimization design based on virtual reality technology. J Interconnect Netw2022; 22(02): 2143007.
