NASA Logo, National Aeronautics and Space Administration


Batteries, composed of multiple electro-chemical cells, are complex systems whose internal state variables are either inaccessible to sensors or hard to measure under operational conditions. In addition, battery performance is strongly influenced by ambient environmental and load conditions. Consequently, inference and estimation techniques need to be applied on indirect measurements, anticipated operational conditions and historical data. The algorithms under consideration are:

  • Autoregressive Integrated Moving Average (ARIMA)
    • data-driven approach
    • linear model
    • used for baseline comparison with other approaches
  • Extended Kalman Filter (EKF)
    • classical approach to non-linear state estimation
    • use of model
    • relatively fast execution time (although slower than data-driven techniques)
  • Relevance Vector Machine (RVM)
    • state of the art in nonlinear probabilistic regression
    • very fast
  • Particle Filter (PF)
    • state of the art for nonlinear non-Gaussian state estimation
    • slower than Kalman Filter
    • uses model

Autoregressive Integrated Moving Average

Extended Kalman Filter

Relevance Vector Machine

Particle Filter

Particle Filter flowchart: PF Flowchart

First Gov logo
NASA Logo -