Smart Battery Management System for Electric Vehicles: Self-learning Algorithms for Simultaneous State and Parameter Estimation, and Stress Detection

Electric vehicles (EVs) are the future means of transportation systems due to their cost-effective and environment-friendly nature. The rapid advancement in energy storage technologies such as lithium-ion (Li-ion) battery with high energy density has accelerated the acceptance of EVs in recent years. Efficient and safe operation of Li-ion batteries in EVs requires an intelligent and smart battery management system (BMS) capable of learning the health degradation for accurately estimating the state-of-charge (SOC) and the state-of-health (SOH). This will add autonomy to the BMS in health-conscious decision making such as fast charging, discharging, cell balancing, and optimal power and energy management. The design of smart BMS requires the development of 1) enhanced SOC and SOH dependent parameter-varying dynamical model of Li-ion battery and 2) real-time learning algorithms to learn the parameter-varying model. The enhanced electric circuit model (ECM) of the Li-ion battery, by incorporating the SOH indicators such as capacity loss and power loss, both under normal and accelerated degradation conditions, can also be used to detect internal faults and stress. The existing BMSs use the constant parameter electro-chemical or electric circuit model of the battery for the estimation of SOC and SOH. These estimation approaches require the complete knowledge of the model, found experimentally or estimated adaptively a-priori. The use of constant parameters model leads to inaccuracy in the long run since the model parameters vary with both SOC and SOH. Further, the parameter variations are accelerated under degradation conditions, such as extreme weather, internal faults and stress, and aggressive driving profiles. The proposed research will investigate the effects of both normal and accelerated degradation on the battery health to develop a SOC and SOH dependent parameter-varying electric circuit model of Li-ion battery and learning algorithms to learn the developed model. The proposed model will integrate the capacity and health dynamics into the model to facilitate simultaneous and real-time estimation of the internal parameters along with SOC and SOH. The self-learning algorithms will learn the battery health in real-time to provide the EV drivers with continuously updated range information based on current health, which will help in reducing the range anxiety. Moreover, the proposed novel technical approach for the smart BMS offers a number of advantages over the existing ones including a realistic SOC and SOH-dependent model, which can further be used to optimize the Li-ion battery charging, power and energy management functions, and computationally efficient real-time machine learning algorithms for implementing on hardware. The intellectual merit of the proposed research is the development of smart BMS with human brain-like complex learning for accurate estimation of the health and remaining life of the Li-ion battery. This involves significant intellectual challenges related to the development of the SOC and SOH dependent model and real-time learning of highly nonlinear and time-varying dynamics. The proposed research points towards a unified design and will lead to a significant increase in the safety, capabilities, and autonomy of the BMS for Li-ion batteries. The success of this project will provide the necessary tools for smart BMS design leading to an efficient and safe operation of EVs. The research aligns with the vision of TranSET of overcoming transportation challenges in Region-6 by using innovative approaches.


  • English


  • Status: Completed
  • Funding: $ 110000
  • Contract Numbers:


  • Sponsor Organizations:

    Office of the Assistant Secretary for Research and Technology

    University Transportation Centers Program
    Department of Transportation
    Washington, DC  United States  20590
  • Managing Organizations:

    Transportation Consortium of South-Central States (Tran-SET)

    Louisiana State University
    Baton Rouge, LA  United States  70803
  • Project Managers:

    Mousa, Momen

  • Performing Organizations:

    Oklahoma State University, Stillwater

    School of Civil & Environmental Engineering
    Stillwater, OK  United States  74078
  • Principal Investigators:

    Sahoo, Avimanyu

  • Start Date: 20200801
  • Expected Completion Date: 20220201
  • Actual Completion Date: 0
  • USDOT Program: University Transportation Centers Program

Subject/Index Terms

Filing Info

  • Accession Number: 01757544
  • Record Type: Research project
  • Source Agency: Transportation Consortium of South-Central States (Tran-SET)
  • Contract Numbers: 69A3551747106
  • Files: UTC, RIP
  • Created Date: Nov 11 2020 9:35AM