A vehicle alarm network for high-temperature fault diagnosis of electric vehicles (original) (raw)

Abstract

Manual checking is necessary for electric vehicles because error diagnosis exist in the actual electric vehicle fault diagnosis process. To effectively perform detection tasks, we propose a VANet model to classify the true and the false third-level high-temperature fault of EVs of unbalanced samples. Firstly, we introduce an improved method which is called Weighted SMOTE to mitigate the imbalance between samples, that determines the number of positive and negative samples by calculating the weight of minority samples. Secondly, we design a two-Conv-one-Maxpool module to build the VANet network, using the GAP and the softmax as the output layer. And we add the dropout to reduce hidden layer neurons to avoid overfitting. Finally, we employ the least square method to optimize the custom loss function to deal with the problem of ignoring incorrect label features. The experimental results show that compared with other convolutional networks, our model can enhance the recognition ability of minority fault samples, and has a strong anti-interference ability against sample noise.

Access this article

Log in via an institution

Subscribe and save

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. He R, Yan YZ, Hu DH (2021) Optimised adaptive control methodology for mode transition of hybrid electric vehicle based on the dynamic characteristics analysis. Vehicle System Dynamics 59(8):1282–1303
    Article Google Scholar
  2. Jia YF (2022) China’s industrial economy will stabilize in 2021: the growth rate of new energy vehicles is the first. 21st Century Business Herald, 002
  3. Yang XJ, Yang DB et al (2017) Research on reliability big data analysis technology of new energy vehicles. Highway and Transportation Science and Technology 34(S2):123–127
    Google Scholar
  4. Ministry of Public Security of the People’s Republic of China, The number of private cars in China exceeded 200 million for the first time,and the number of cars in 66 cities exceeded one million. https://app.mps.gov.cn/gdnps/pc/content.jsp?id=7478950 (2020)
  5. Chen ZY, Xiong R et al (2019) Research status and analysis for battery safety accidents in electric vehicles. Journal of Mechanical Engineering 55(24):93–104
    Article Google Scholar
  6. Ministry of Industry and Information Technology in China. GB/T 32960-2016 Technical Specifications of Remote Service and Management System for Electric Vehicles. Beijing: Standards Press of China (2016)
  7. Xiong R, Sun W, Yu Q et al (2020) Research progress, challenges and prospects of fault diagnosis on battery system of electric vehicles. Applied Energy 279:115855
    Article Google Scholar
  8. Chen CP, Zhang L, Wang J et al (2019) Application of fault diagnosis expert system for unmanned vehicle safety. IOP Conference Series: Materials Science and Engineering. IOP Publishing 608(1):012015
    Article Google Scholar
  9. Xu S (2019) A survey of knowledge-based intelligent fault diagnosis techniques. Journal of Physics: Conference Series. IOP Publishing 1187(3):032006
    Google Scholar
  10. Li JQ, Tan F (2014) Capacity fade diagnosis of lithium ion battery pack in electric vehicle base onfuzzy neural network. In: The 6thInternational conference on applied energy. Taipei
  11. Gao DX, Hou JJ, Liang K et al (2018) Fault diagnosis system for electric vehicle charging devices based on fault tree analysis. In: 2018 37th Chinese Control Conference (CCC). IEEE, pp 5055–5059
  12. Zhang J (2020) Reliability analysis of high voltage electric system of pure electric passenger car based on polymorphic fuzzy fault tree. Journal of Intelligent and Fuzzy Systems 38(4):3747–3754
    Article Google Scholar
  13. Qian Q (2020) Research on differential pressure fault and maintenance technology of new energy vehicle power battery. Electronic Test,139-140,18
  14. Zhu X, Wang Z, Wang Y et al (2019) Overcharge investigation of large format lithium-ion pouch cells with Li(Ni0.6Co0.2Mn0.2)O2 cathode for electric vehicles: Thermal runaway features and safety management method. Energy 169:868–880
    Article Google Scholar
  15. Moosavi SS, Dierdir A, Ait-amirat Y et al (2016) Artificial neural network-based fault diagnosis in the AC-DC converter of the power supply of series hybrid electric vehicle. IET Electrical Systems in Transportation 6(2):96–106
    Article Google Scholar
  16. Huang M, Wang J, Yang R (2018) BP Neural network based fault diagnosis in vehicle braking control system. In: 2018 2nd IEEE advanced information management, communicates, electronic and automation control conference (IMCEC), IEEE, pp 794–798
  17. Zhang Y, Li T, Zhao S et al (2020) Electric vehicle charging fault diagnosis based on bp neural network. Journal of Physics: Conference Series. IOP Publishing 1646(1):012046
    Google Scholar
  18. Gong Y, Su X, Qian H, et al. (2018) Research on fault diagnosis methods for the reactor coolant system of nuclear power plant based on DS evidence theory[J]. Annals of Nuclear Energy 112:395–399
    Article Google Scholar
  19. Xia F, Ma X, Zhang H et al (2017) Application of improved D-S evidence theory in fault diagnosis of lithium batteries in electric vehicles. CAAI Trans Intell Syst 12(4):526–537
    Google Scholar
  20. Yang R, Xiong R, Ma S et al (2020) Characterization of external short circuit faults in electric vehicle Li-ion battery packs and prediction using artificial neural networks. Appl Energy 260:114253
    Article Google Scholar
  21. Yao L, Xiao Y, Gong X, et al. (2020) A novel intelligent method for fault diagnosis of electric vehicle battery system based on wavelet neural network. J Power Sources 453:227870
    Article Google Scholar
  22. Peng YS, Xia F, Yuan B et al (2020) Power battery pack fault diagnosis method based on improved CNN and information fusion. Automotive Engineering 42(11):1529–1536
    Google Scholar
  23. Zhang Y, Xing K, Bai R et al (2020) An enhanced convolutional neural network for bearing fault diagnosis based on time–frequency image. Measurement 157:107667
    Article Google Scholar
  24. Fernández A, Garcia S, Herrera F et al (2018) SMOTE For learning from imbalanced data: progress and challenges, marking the 15-year anniversary. Journal of Artificial Intelligence Research 61:863–905
    Article MathSciNet MATH Google Scholar
  25. Kannan R, Vasanthi V (2019) Machine learning algorithms with ROC curve for predicting and diagnosing the heart disease. Soft Computing and Medical Bioinformatics. Springer, Singapore, pp 63–72
    Google Scholar
  26. Kurata G, Saon G (2020) Knowledge Distillation from Offline to Streaming RNN Transducer for End-to-End Speech Recognition. Interspeech, pp 2117–2121
  27. Chimmula VKR, Zhang L (2020) Time series forecasting of COVID-19 transmission in Canada using LSTM networks. Chaos, Solitons and Fractals 135:109864
    Article MATH Google Scholar
  28. Yamada Y, Iwamura M, Akiba T et al (2019) Shakedrop regularization for deep residual learning. IEEE Access 7:186126–186136
    Article Google Scholar
  29. Alippi C, Disabato S, Roveri M (2018) Moving convolutional neural networks to embedded systems: the alexnet and VGG-16 case. In: 2018 17th ACM/IEEE international conference on information processing in sensor networks (IPSN), IEEE, pp 212–223
  30. Snyder D, Garcia-Romero D, Sell G et al (2018) X-vectors: Robust dnn embeddings for speaker recognition. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5329–5333, IEEE
  31. Murphey YL, Chen ZH, Feldkamp LA (2008) An incremental neural learning framework and its application to vehicle diagnostics. Appl Intell 28(1):29–49
    Article Google Scholar
  32. Khorram A, Khalooei M, Rezghi M (2021) End-to-end CNN+ LSTM deep learning approach for bearing fault diagnosis. Appl Intell 51(2):736–751
    Article Google Scholar
  33. Hong J, Wang Z, Yao Y (2019) Fault prognosis of battery system based on accurate voltage abnormity prognosis using long short-term memory neural networks. Appl Energy 251:113381
    Article Google Scholar
  34. Hong J, Wang Z, Chen W et al (2019) Synchronous multi-parameter prediction of battery systems on electric vehicles using long short-term memory networks. Appl Energy 254:113648
    Article Google Scholar

Download references

Acknowledgements

his work was supported by the Industry-University-Research Innovation Fund of Science and Technology Development Center, MOE (2019ITA03029), Hubei Provincial Natural Science Foundation of China under Grant (2019CFB173),Science and Technology Development Funds of the State Administration of Market Regulation (2021MK-071), the Foundation of Hubei Provincial Key Laboratory of Intelligent Robot (HBIRL 202010) and the Twelfth Graduate Innovation Fund of Wuhan Institute of Technology (CX2020205, CX2020219).

Author information

Authors and Affiliations

  1. Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, 430205, China
    Qing Hou, Jun Liu, Jianxing Zhang & Zihan Xu
  2. School of Computer Science & Engineering, Wuhan Institute of Technology, Wuhan, 430205, China
    Qing Hou, Jun Liu, Jianxing Zhang & Zihan Xu
  3. Hubei Electronic Information Product Quality Supervision, Inspection Institute, Wuhan, 430061, China
    Xiao Chen & Peng Chen

Authors

  1. Qing Hou
  2. Jun Liu
  3. Jianxing Zhang
  4. Zihan Xu
  5. Xiao Chen
  6. Peng Chen

Corresponding author

Correspondence toJun Liu.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

About this article

Cite this article

Hou, Q., Liu, J., Zhang, J. et al. A vehicle alarm network for high-temperature fault diagnosis of electric vehicles.Appl Intell 53, 6230–6247 (2023). https://doi.org/10.1007/s10489-022-03615-z

Download citation

Keywords