Istrazivanja i projektovanja za privreduJournal of Applied Engineering Science

banner
banner
banner
banner
banner
banner
banner
banner

FAULT DETECTION AND SEPARATION OF HYBRID ELECTRIC VEHICLES BASED ON KERNEL ORTHOGONAL SUBSPACE ANALYSIS


DOI: 10.5937/jaes0-45837 
This is an open access article distributed under the CC BY 4.0
Creative Commons License

Volume 21 article 1159 pages: 1192 -1202

Yonghui Wang
Department of Civil Engineering, Faculty of Engineering, Technology and Built Environment, UCSI University,Kuala Lumpur, Malaysia; College of Urban Transportation and Logistics, Shenzhen Technology University, Shenzhen, China

Syamsunur Deprizon*
Department of Civil Engineering, Faculty of Engineering, Technology and Built Environment, UCSI University, Kuala Lumpur, Malaysia; Postgraduate Department, Universitas Bina Darma Palembang, Indonesia

Cong Peng
Department of Civil Engineering, Faculty of Engineering, Technology and Built Environment, UCSI University, Kuala Lumpur, Malaysia

Zhiming Zhang
Department of Civil Engineering, Faculty of Engineering, Technology and Built Environment, UCSI University, Kuala Lumpur, Malaysia

Driving quality and vehicles safety of hybrid electric vehicles (HEVs) are two hot-topic issues in automobile technology. Nowadays, research focuses to more intelligent and convenient HEVs fault detection methods. This paper will focus on the fault detection of HEV powertrain system with a data-driven algorithm. Orthonormal subspace analysis (OSA) is a newly proposed data-driven method which adds the ability of fault separation. Nonetheless, the linear OSA algorithm cannot effectively detect powertrain system faults, since these faults present complex nonlinear characteristics. A new kernel OSA (KOSA) method is proposed to transform the nonlinear problem into a linear problem through the mapping of kernel function and the dimensionality reduction technique of OSA. Testing results on a nonlinear model and real samples of XMQ6127AGCHEVN61 HEV show that KOSA address the nonlinear problems and it performs better than OSA and kernel principal component analysis (KPCA).

View article

1.      Liu, F., Liu, B. (2023). Fault mode detection of a hybrid electric vehicle by using support vector machine. Energy Reports, vol. 9, pp. 137-148, DOI: https://doi.org/10.1016/j.egyr.2023.04.328.

2.      Elsayed, M.E., Hamad, M.S, (2021). Modeling and Analysis of PMSM under Regenerative Braking Operations with Fault-Tolerant for EV/HEV Applications. 2021 31st International Conference on Computer Theory and Applications (ICCTA), pp. 112-119.

3.      Cammalleri, M., Di Dio, V. (2023). Special Issue on Frontiers in Hybrid Vehicles Powertrain. Applied Sciences, vol. 13, no. 11, p. 6367, DOI: https://doi.org/10.3390/app13116367.

4.      Anselma, P.G.J.E. (2021). Optimization-driven powertrain-oriented adaptive cruise control to improve energy saving and passenger comfort. Energies, vol. 14, no. 10, p. 2897, DOI: https://doi.org/10.3390/en14102897.

5.      Jiang, W., Abolfazli, E., (2021). Observer-based control for vehicle platooning with a leader of varying speed. 2021 European Control Conference (ECC), pp. 2-9.

6.      Li, M., Bai, C. (2021). Application of Electronic Diagnosis Technology in New Energy Vehicle Maintenance. Earth and Environmental Science, vol. 680, no. 1, p. 012043, DOI: 10.1088/1755-1315/680/1/012043.

7.      Chen, J. (2021). Model-based validation of diagnostic software with application in automotive systems. IET Cyber-Systems and Robotics, vol. 3, no. 2, pp. 140-149, DOI: https://doi.org/10.1049/csy2.12016.

8.      Kobti, Z. and El-Ghaname, J. (2023). Using Knowledge Graph Embedding for Fault Detection: A Case Study in Electric Vehicle Parts Assembly. The International FLAIRS Conference Proceedings, vol. 36.

9.      Fu, Q. (2022). A DSP-Controlled Permanent Magnet Synchronous Motor Control System for Hybrid Vehicles. International Journal of Antennas and Propagation, vol. 2022, p. 1996502, DOI: https://doi.org/10.1155/2022/1996502.

10.   Wan, P., Liu, B. (2023). Engine modelling architecture study for hybrid electric vehicle diagnosis application. Energy, vol. 282, p. 128408, DOI: https://doi.org/10.1016/j.energy.2023.128408.

11.   Lou, Z., Wang, Y. (2022). A novel multivariate statistical process monitoring algorithm: Orthonormal subspace analysis. Automatica, vol. 138, p. 110148, DOI: https://doi.org/10.1016/j.automatica.2021.110148.

12.   Lou, Z., Hao, W. (2023). Thermal-Imaging-Based PCA Method for Monitoring Process Temperature. Processes, vol. 11, no. 2, p. 589, DOI: https://doi.org/10.3390/pr11020589.

13.   Hao, W., Lu, S. (2023). A Novel Dynamic Process Monitoring Algorithm: Dynamic Orthonormal Subspace Analysis. Processes, vol. 11, no. 7, p. 1935, DOI: https://doi.org/10.3390/pr11071935.

14.   Kanwisher, N., Khosla, M. (2023). Using artificial neural networks to ask ‘why’questions of minds and brains. Trends in Neurosciences, vol. 46, no. 3, pp. 240-254, DOI: https://doi.org/10.1016/j.tins.2022.12.008.

15.   Li, Z., Wang, Y. (2022). Neural Component Analysis for Key Performance Indicator Monitoring. ACS omega, vol. 7, no. 42, pp. 37248-37255, DOI: https://doi.org/10.1021/acsomega.2c03515.

16.   Wang, Y., Lou, Z., (2021). Nonlinear PLS with Neural Component Analysis Structure. 2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes (SAFEPROCESS), pp. 1-4, DOI: 10.1109/SAFEPROCESS52771.2021.9693603.

17.   Costa, V.G., Pedreira, C.E. (2022). Recent advances in decision trees: An updated survey. Artificial Intelligence Review, vol. 56, no. 5, pp. 4765-4800, DOI: https://doi.org/10.1007/s10462-022-10275-5.

18.   Hu, J., Szymczak, S. (2023). A review on longitudinal data analysis with random forest. Briefings in Bioinformatics, vol. 24, no. 2, p. bbad002, DOI: https://doi.org/10.1093/bib/bbad002.

19.   Brophy, J., Hammoudeh, Z. (2022). Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees. Journal of Machine Learning Research, vol. 24, pp. 1-48, DOI: 10.48550/arXiv.2205.00359.

20.   Li, D., Wong, W., (2021). Detection and mitigation of label-flipping attacks in federated learning systems with KPCA and K-means. 2021 8th International Conference on Dependable Systems and Their Applications (DSA), pp. 551-559, DOI: 10.1109/DSA52907.2021.00081.

21.   Yan, X., Guan, T. (2021). Novel double layer BiLSTM minor soft fault detection for sensors in air-conditioning system with KPCA reducing dimensions. Journal of Building Engineering, vol. 44, p. 102950, DOI: https://doi.org/10.1016/j.jobe.2021.102950.

22.   Pande, C.B., Kushwaha, NL. (2023). Comparative assessment of improved SVM method under different kernel functions for predicting multi-scale drought index. Water Resources Management, vol. 37, no. 3, pp. 1367-1399, DOI: https://doi.org/10.1007/s11269-023-03440-0.

23.   Cao, K., Dong, F. (2023). Infrared radiation denoising model of “sub-region-Gaussian kernel function” in the process of sandstone loading and fracture. Infrared Physics & Technology, vol. 129, p. 104583, DOI: https://doi.org/10.1016/j.infrared.2023.104583.

24.   Liu, A., Zhao, D. (2023). A data classification method based on particle swarm optimisation and kernel function extreme learning machine. Enterprise Information Systems, vol. 17, no. 3, p. 1913764, DOI: https://doi.org/10.1080/17517575.2021.1913764.

25.   Fang, H., Tao, W. (2022). Nonlinear dynamic process monitoring based on two-step dynamic local kernel principal component analysis. Processes, vol. 10, no. 5, p. 925, DOI: https://doi.org/10.3390/pr10050925.

26.   Kono, S., Sato, M. (2021). Partial least squares structural squation modeling (PLS-SEM) analysis for social and management research: a literature review. Journal of Leisure Research, vol. 54, no. 3, pp. 309-329, DOI: https://doi.org/10.1080/00222216.2022.2066492.

27.   Allegrini, F., Olivieri, A. C. (2023). Two sides of the same coin: kernel partial least-squares (KPLS) for linear and non-linear multivariate calibration. Talanta Open, vol. 7, p. 100235, DOI: https://doi.org/10.1016/j.talo.2023.100235.

28.   Guo, H., Sun, J. (2023). Quality-Related Process Monitoring and Diagnosis of Hot-Rolled Strip Based on Weighted Statistical Feature KPLS. Sensors, vol. 23, no. 13, p. 6038, DOI: https://doi.org/10.3390/s23136038.

29.   Guo, H., Sun, J. (2023). Fault Diagnosis of Check Valve Based on KPLS Optimal Feature Selection and Kernel Extreme Learning Machine. Coatings, vol. 12, no. 9, p. 1320, DOI: https://doi.org/10.3390/coatings12091320.

30.  Yuan, P., Zhao, L. (2022). KPLS-based Mach number prediction for multi-mode wind tunnel flow system. Processes, vol. 10, no. 9, p. 1718, DOI: https://doi.org/10.3390/pr10091718.

31.   Zhang, K., Zhang, K. (2023). Prediction of gas explosion pressures: A machine learning algorithm based on KPCA and an optimized LSSVM. Journal of Loss Prevention in the Process Industries, vol. 83, p. 105082, DOI: https://doi.org/10.1016/j.jlp.2023.105082.

32.   Wang, C., Zheng, J. (2022). Deeppipe: Operating condition recognition of multiproduct pipeline based on KPCA-CNN. Journal of Pipeline Systems Engineering and Practice, vol. 13, no. 2, p. 04022006, DOI: https://doi.org/10.1061/(ASCE)PS.1949-1204.0000641.

33.   Arowolo, M. O., Ogundokun, R. O. (2022). Machine learning approach using KPCA-SVMs for predicting COVID-19. Healthcare informatics for fighting COVID-19 and future epidemics, pp. 193-209, DOI: https://doi.org/10.1007/978-3-030-72752-9_10.

34.  Duan, Y., Huang, F. (2023). Intelligent spectrum sensing algorithm for cognitive internet of vehicles based on KPCA and improved CNN. Peer-to-Peer Networking and Applications, vol. 16, no. 5, pp. 2202-2217, DOI: https://doi.org/10.1007/s12083-023-01501-0.

35.  Yang, F., Ma, Z. (2022). Image classification with parallel KPCA‐PCA network. Computational Intelligence, vol. 38, no. 2, pp. 397-415, DOI:  https://doi.org/10.1111/coin.12503.

36.  Huang, L., Qin, J. (2023). Normalization techniques in training DNNs: Methodology, analysis and application. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 8, pp. 10173-10196, DOI:  10.1109/TPAMI.2023.3250241.

37.   Pan, C., Tan, J. (2021). Prediction intervals estimation of solar generation based on gated recurrent unit and kernel density estimation. Neurocomputing, vol. 453, pp. 552-562, DOI: https://doi.org/10.1016/j.neucom.2020.10.027.