To address the issues of slow convergence, susceptibility to local optima, and limited evaluation metrics in identifying and localizing acceleration faults in hybrid electric vehicles (HEVs), this study proposes a fault diagnosis method based on an improved genetic algorithm (IGA) optimized least squares support vector machine (LSSVM). The proposed IGA introduces adaptive crossover and mutation mechanisms to enhance search efficiency and employs the F1-score as the fitness evaluation metric, thereby improving robustness in recognizing imbalanced multi-class fault data. The experimental results demonstrate that the proposed IGA-LSSVM model achieves an overall diagnostic accuracy of 96.28% on the test set. Compared with the GA-LSSVM model, the accuracy is improved by approximately 6%, and the F1-score is increased to 0.95. These results verify the effectiveness and practicality of the proposed method for multi-class fault diagnosis tasks.
UroojANasirA.Review of intelligent energy management techniques for hybrid electric vehicles. J Energy Storage2024; 92: 112132.
2.
ShiDLiuSShenY, et al. Analysis and optimization of transient mode switching behavior for power split hybrid electric vehicle with clutch collaboration. Automot Innov2024; 7: 150–165.
3.
WangFWuTNiY, et al. Torsional oscillation suppression-oriented torque compensate control for regenerative braking of electric powertrain based on mixed logic dynamic model. Mech Syst Signal Process2023; 190: 110114.
4.
CaiYYuXWangH, et al. Hybrid physics and neural network model for lateral vehicle dynamic state prediction. Proc Inst Mech Eng Part D: J Automob Eng2022; 238(1): 3–17.
5.
TakaraLMarianiVCCoelhoLD.Novel engine fault diagnosis framework based on machine learning and MiniRocket feature extraction using multi-correlation feature selection and predictive power score. Expert Syst Appl2025; 293: 128662.
6.
OuyangJLinZHuL, et al. Voltage faults diagnosis for lithium-ion batteries in electric vehicles using optimized graphical neural network. Sci Rep2025; 15: 27328.
7.
KhaneghahMZAlzayedMChaouiH.Fault detection and diagnosis of the electric motor drive and battery system of electric vehicles. Machines2023; 11: 713.
8.
HuangQC.Research on dynamic truck scale fault diagnosis method based on IPSO-SVM. Electromech Eng2024; 41: 1–12.
9.
ZhuZLiuHLeiW, et al. Optimising wellbore annular leakage detection and diagnosis model: a signal feature enhancement and hybrid intelligent optimised LSSVM approach. Mech Syst Signal Process2025; 228: 112451.
10.
LiuJSongYYuX.Risk assessment study of hydrogen energy storage system based on KPCA-TSO-LSSVM. Int J Hydrogen Energy2024; 79: 931–942.
11.
MaYLiangXShengG, et al. Noniterative sparse LS-SVM based on globally representative point selection. IEEE Trans Neural Netw Learn Syst2021; 32(2): 788–798.
12.
KaramiANiakiSTA. An online support vector machine algorithm for dynamic social network monitoring. Neural Netw2024; 171: 497–511.
13.
RenJWangZPangY, et al. Genetic algorithm-assisted an improved AdaBoost double-layer for oil temperature prediction of TBM. Adv Eng Inform2022; 52: 101563.
14.
LinF.Supervised learning in neural networks: feedback-network-free implementation and biological plausibility. IEEE Trans Neural Netw Learn Syst2022; 33(12): 7888–7898.
15.
BlumeSBenedensTSchrammD.Hyperparameter optimization techniques for designing software sensors based on artificial neural networks. Sensors2021; 21: 8435.
16.
LiJHeHLiL.CGAN-MBL for reliability assessment with imbalanced transmission gear data. IEEE Trans Instrum Meas2019; 68(9): 3173–3183.
17.
ChangJYaoJChenX, et al. Knowledge-driven domain adaptation strategy for rotating machinery fault diagnosis under varying working condition. Meas Sci Technol2024; 35(5): 056110.
18.
LiJPangJFanX.Optimization of 5G base station coverage based on self-adaptive mutation genetic algorithm. Comput Commun2024; 225: 83–95.
19.
XuTNiuYCaoZ.Attack-tolerant control for Markovian jump systems with stochastic sampling: a sliding mode scheme. Automatica2024; 161: 111496.
20.
AwadAHawashAAbdalhaqB.A genetic algorithm (GA) and swarm-based binary decision diagram (BDD) reordering optimizer reinforced with recent operators. IEEE Trans Evol Comput2023; 27(3): 535–549.
21.
BorghiGPareschiL.Kinetic description and convergence analysis of genetic algorithms for global optimization. Commun Math Sci2025; 23: 641–668.
22.
LiuJXiaY.A hybrid intelligent genetic algorithm for truss optimization based on deep neutral network. Swarm Evol Comput2022; 73: 101120.
WangYZhengHZHuangX.Sparrow search optimization algorithm based on multi-stage scheduling framework. Acta Electron Sin2024; 52(9): 3086–3096.
25.
WenhaoFBolanLJingxianT, et al. Study on energy management strategy for a P2 diesel HEV considering low temperature environment. Energy2025; 318: 134771.
26.
KumarSBhattacharjeeA.A comprehensive review on energy management strategies for fuel-cell-based electric vehicles. Energy Technol2025; 13(4): 2401341.
27.
ShaoYLinJCSrivastavaG, et al. Multi-objective neural evolutionary algorithm for combinatorial optimization problems. IEEE Trans Neural Netw Learn Syst2023; 34(4): 2133–2143.
