International Journal of Automotive Technology

, Volume 20, Issue 6, pp 1263–1276 | Cite as

Learning To Recognize Driving Patterns For Collectively Characterizing Electric Vehicle Driving Behaviors

  • Chung-Hong LeeEmail author
  • Chih-Hung Wu


As electric vehicle (EV) emerges, it is important to understand how driver's driving behavior is influencing power consumption in an electric vehicle. Driver's personal driving behavior is usually quite distinctive and can be recognized by means of driving patterns after some driving cycles. This paper presents a method combining several machine learning approaches to characterize driving behaviors of electric vehicles. The driving patterns are modeled according to power consumption monitored by the battery management system (BMS), in aspects of individual driver's personal and EV-fleet operations. First, we apply an unsupervised clustering approach to characterize a driver's behaviors by formulating driving patterns. Subsequently, the resulting clustered datasets were used to train machine-learning based classifiers for classification of dataset of EV and EV-fleet driving patterns. The work aims to provide a robust solution to help identify the characteristics of specific types of EVs and their driver behaviors, in order to allow automakers and EV-subsystem providers to gather valuable driving information for product improvement.

Key words

Electric vehicles Data mining Energy management Battery management systems Machine learning 



electric vehicle


electric vehicles


battery management system


growing hierarchical self-organizing maps








vehicle control unit


direct current internal resistance


support vector machine


recurrent neural networks


classification and regression trees


radial basis function


vehicle speed


vehicle acceleration


weight of car


coefficient of rolling resistance


drag coefficient


frontal area




transmitting efficiency


maximal grade climbing radian


power consumption at different speed


static energy of auxiliaries


maximum speed of a vehicle


rated capacity of the battery


charge-discharge efficiency


battery current


actual capacity


initial capacity of the battery.


resistance at end-of-life


actual resistance


initial resistance of a battery module


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



The authors would like to give special thanks to the Luxgen Motor Co., Ltd. for their valuable supports for this research work.


  1. Awad, M. and Khanna, R. (2015). Deep Neural Networks. Efficient Learning Machines. Apress. Berkeley, USA, 127–147.CrossRefGoogle Scholar
  2. Barandiaran, I. (1998). The random subspace method for constructing decision forests. IEEE Trans. Pattern Analysis and Machine Intelligence 20, 8, 832–844.CrossRefGoogle Scholar
  3. Barre, A, Deguilhem, B., Grolleau, S., Gerard, M., Suard, F. and Riu, D. (2013). A review on lithium-ion battery ageing mechanisms and estimations for automotive applications. J. Power Sources, 241, 680–689.CrossRefGoogle Scholar
  4. Belt, J. R. (2010). Battery Test Manual for Plug-in Hybrid Electric Vehicles, 1–70.Google Scholar
  5. Breiman, L., Friedman, J. H., Olshen, R. A. and Stone, C. J. (1984). Classification and Regression Trees. Chapman & Hall/CRC. New York, USA.zbMATHGoogle Scholar
  6. Chang, W. Y. (2013). The state of charge estimating methods for battery: A review. Applied Mathematic, 2013, Article ID 953792, 1–8.zbMATHGoogle Scholar
  7. Chen, Z., Mi, C. C, Fu, Y., Xu, J. and Gong, X. (2013). Online battery state of health estimation based on genetic algorithm for electric and hybrid vehicle applications. J. Power Sources, 240, 184–192.CrossRefGoogle Scholar
  8. Cuma, M. U. and Koroglu, T. (2015). A comprehensive review on estimation strategies used in hybrid and battery electric vehicles. Renewable and Sustainable Energy Reviews, 42, 517–531.CrossRefGoogle Scholar
  9. Dubarry, M., Bonnet, M., Dailliez, B., Teeters, A. and Liaw, B. Y. (2005). Analysis of electric vehicle usage of a Hyundai Santa Fe fleet in Hawaii. J. Asian Electric Vehicles 3, 1, 657–663.CrossRefGoogle Scholar
  10. Duran, A., Ragatz, A., Prohaska, R., Kelly, K. and Kevin, W. (2014). Characterization of in-use medium duty electric vehicle driving and charging behavior. Proc. IEEE Int. Electric Vehicle Conf., Florence, Italy.Google Scholar
  11. Ecker, M., Nieto, N, Kabitz, S., Schmalstieg, J., Blanke, H., Warnecke, A. and Sauer, D. U. (2014). Calendar and cycle life study of Li(NiMnCo)O2-based 18650 lithium-ion batteries. J. Power Sources, 248, 839–851.CrossRefGoogle Scholar
  12. Hartigan, J. A. and Wong, M. A. (1979). Algorithm AS 136: A k-means clustering algorithm. J. Royal Statistical Society 28, 1, 100–108.zbMATHGoogle Scholar
  13. Helmbrecht, M., Olaverri-Monreal, C, Bengler, K., Vilimek, R. and Keinath, A. (2014). How electric vehicles affect driving behavioral patterns. IEEE Intelligent Transportation Systems Magazine 6, 3, 22–32.CrossRefGoogle Scholar
  14. Hinton, G. E., Osindero, S. and The, Y W. (2006). A fast learning algorithm for deep belief nets. Neural Computation 18, 7, 1527–1554.MathSciNetCrossRefzbMATHGoogle Scholar
  15. Ho, T. K. (1995). Random decision forests. Proc. 3rd Int. Conf. Document Analysis and Recognition, Montreal, Quebec, Canada.Google Scholar
  16. Jung, M. F., Sirkin, D., Gur, T. M. and Steinert, M. (2015). Displayed uncertainty improves driving experience and behavior: The case of range anxiety in an electric car. Proc. 33rd Annual ACM Conf. Human Factors in Computing Systems, Seoul, Korea.Google Scholar
  17. Lee, C. H. and Wu, C. H. (2015). A novel big data modeling method for improving driving range estimation of EVs. IEEE Access, 3, 1980–1993.CrossRefGoogle Scholar
  18. Lee, C. H. and Wu, C. H. (2016). A data driven approach to create an extensible EV driving data model. Proc. 3rd Multidisciplinary Int. Social Networks Conf. SocialInformatics, Union, New Jersey, USA.Google Scholar
  19. Liaw, B. Y. (2004). Fuzzy logic based driving pattern recognition for driving cycle analysis. J. Asian Electric Vehicles 2, 1, 551–556.CrossRefGoogle Scholar
  20. Liaw, B. Y. and Dubarry, M. (2007). From driving cycle analysis to understanding battery performance in real-life electric hybrid vehicle operation. J. Power Sources 174, 1, 76–88.CrossRefGoogle Scholar
  21. Liu, Z., Wu, Q., Christensen, L., Rautiainen, A. and Xue, Y (2015). Driving pattern analysis of nordic region based on national travel surveys for electric vehicle integration. J. Modern Power Systems and Clean Energy 3, 2, 180–189.CrossRefGoogle Scholar
  22. Loisel, R., Pasaoglu, G. and Thiel, C. (2014). Large-scale deployment of electric vehicles in Germany by 2030: An analysis of grid to vehicle and vehicle to grid concepts. Energy Policy, 65, 432–443.CrossRefGoogle Scholar
  23. Lu, L., Han, X., Li, J., Hua, J. and Ouyang, M. (2013). A review on the key issues for lithium-ion battery management in electric vehicles. J. Power Sources, 226, 272–288.CrossRefGoogle Scholar
  24. Meissner, E. and Richter, G. (2003). Battery monitoring and electrical energy management: Precondition for future vehicle electric power systems. J. Power Sources 116, 1-2, 79–98.CrossRefGoogle Scholar
  25. Mwasilu, F., Justo, J. J., Kim, E. K., Do, T. D. and Jung, J. W (2014). Electric vehicles and smart grid interaction: A review on vehicle to grid and renewable energy sources integration. Renewable and Sustainable Energy Reviews, 34, 501–516.CrossRefGoogle Scholar
  26. Rauber, A., Merkl, D. and Dittenbach, M. (2000). The growing hierarchical self-organizing map. Proc. IEEE-INNS-ENNS Int. Joint Conf. Neural Networks, Como, Italy.Google Scholar
  27. Rauber, A., Merkl, D. and Dittenbach, M. (2002). The growing hierarchical self-organizing map: Exploratory analysis of high-dimensional data. IEEE Trans. Neural Networks 13, 6, 1331–1341.CrossRefzbMATHGoogle Scholar
  28. Ripley, B. D. (2007). Pattern Recognition and Neural Networks. Cambridge University Press. Cambridge, UK.zbMATHGoogle Scholar
  29. Saxena, S., Floch, C. L., MacDonald, J. and Moura, S. (2015). Quantifying EV battery end-of-life through analysis of travel needs with vehicle powertrain models. J. Power Sources, 282, 265–276.CrossRefGoogle Scholar
  30. Smart, J. and Schey, S. (2012). Battery electric vehicle driving and charging behavior observed early in the EV project. Int. J. Alternative Powertrains 1, 1, 27–33.CrossRefGoogle Scholar
  31. Staackmann, M., Liaw, B. Y. and Yun, D. Y. Y (1997). Dynamic driving cycle analyses using electric vehicle time-series data. Proc. Thirty-Second Intersociety Energy Conversion Engineering Conf., Honolulu, Hawaii, USA.Google Scholar
  32. Tanim, T. R., Rahn, C. D. and Wang, C. Y. (2015). State of charge estimation of a lthium ion cell based on a temperature dependent and electrolyte enhanced single particle model. Energy, 80, 731–739.CrossRefGoogle Scholar
  33. Vapnik, V. (2013). The Nature of Statistical Learning Theory. Springer Science and Business Media. New York, USAzbMATHGoogle Scholar
  34. Vapnik, V. and Chapelle, O. (2000). Bounds on error expectation for support vector machines. Neural Computation 12, 9, 2013–2036.CrossRefGoogle Scholar
  35. Vatanparvar, K., Wan, J. and Faruque, M. A. A. (2015). Battery-aware energy-optimal electric vehicle driving management. Proc. IEEE/ACM Int. Symp. Low Power Electronics and Design (ISLPED), Rome, Italy.Google Scholar
  36. Verwer, S., De Weerdt, M. and Witteveen, C. (2011). Learning driving behavior by timed syntactic pattern recognition. Proc. 22nd Int. Joint Conf. Artificial Intelligence, Barcelona, Spain.Google Scholar
  37. Walsh, C., Carroll, S., Eastlake, A. and Blythe, P. (2010). Electric Vehicle Driving Style and Duty Variation Performance Study. Cenex Corp. Loughborough, UK.Google Scholar
  38. Wang, L. and Wen, X. (1999). Dynamic match and optimizing design of electric vehicle powertrain. Proc. IEEE Int. Vehicle Electronics Conf. (IVEC'99), Changchun, China.Google Scholar
  39. Wangm, R. and Lukic, S. M. (2011). Review of driving conditions prediction and driving style recognition based control algorithms for hybrid electric vehicles. Proc. IEEE Vehicle Power and Propulsion Conf, Chicago, Illinois, USA.Google Scholar
  40. Wu, Q., Nielsen, A. H., Ostergaard, J., Cha, S. T., Marra, F., Chen, Y and Traholt, C. (2010). Driving pattern analysis for electric vehicle (EV) grid integration study. Proc. IEEE PES Innovative Smart Grid Technologies Conf. Europe (ISGT Europe), Gothenberg, Sweden.Google Scholar
  41. Xiaohua, Z., Haitao, M., Xu, X. and Wang, Q. (2008). Parameter design for power train and performance simulation of electrical city bus. Proc. IEEE Vehicle Power and Propulsion Conf, Harbin, China.Google Scholar
  42. Yan, Q., Zhang, B. and Kezunovic, M. (2014). Optimization of electric vehicle movement for efficient energy consumption. Proc. North American Power Symp. (NAPS), Pullman, Washington, USA.Google Scholar
  43. Yang, H. C, Lee, C. H. and Chen, D. W (2009). A method for multilingual text mining and retrieval using growing hierarchical self-organizing maps. J. Information Science 35, 1, 3–23.CrossRefGoogle Scholar
  44. Younes, Z., Boudet, L., Suard, F., Gerard, M. and Rioux, R. (2013). Analysis of the main factors influencing the energy consumption of electric vehicles. Proc. Int. Electric Machines & Drives Conf, Chicago, Illinois, USA.Google Scholar
  45. Zhang, Q. and White, R. E. (2008). Calendar life study of Li-ion pouch cells: Part 2: Simulation. J. Power Sources 179, 2, 785–792.CrossRefGoogle Scholar
  46. Zhang, Y., Zhang, C. and Zhang, X (2013). State-of-charge estimation of the lithium-ion battery system with time-varying parameter for hybrid electric vehicles. IET Control Theory & Applications 8, 3, 160–167.MathSciNetCrossRefGoogle Scholar

Copyright information

© KSAE/ 111-18 2019

Authors and Affiliations

  1. 1.Department of Electrical EngineeringNational Kaohsiung University of Science and TechnologyKaohsiungTaiwan

Personalised recommendations