Joint Parameterization of Hybrid Physics-Based and Machine Learning Li-Ion Battery Model
Jackson Fogelquist, Xinfan Lin
TL;DR
The paper tackles parameter identification for electrochemical hybrid residual models under substantial system uncertainties. It introduces a Kennedy–O’Hagan calibration approach, modeling the discrepancy as a Gaussian process and incorporating a downsampling strategy to manage large time-series data. In simulation, the method yields mean parameter estimation errors that are an order of magnitude smaller than conventional least squares and reduces voltage RMSE by about 54%, while preserving the physical interpretability of electrochemical states. This framework is generalizable beyond battery models and can enhance online BMS capabilities by robustly calibrating parameters in the presence of unmodeled dynamics and measurement noise.
Abstract
Electrochemical hybrid battery models have major potential to enable advanced physics-based control, diagnostic, and prognostic features for next-generation lithium-ion battery management systems. This is due to the physical significance of the electrochemical model, which is complemented by a machine learning model that compensates for output prediction errors caused by system uncertainties. While hybrid models have demonstrated robust output prediction performance under large system uncertainties, they are highly susceptible to the influence of uncertainties during parameter identification, which can compromise the physical significance of the model. To address this challenge, we present a parameter estimation framework that explicitly considers system uncertainties through a discrepancy function. The approach also incorporates a downsampling procedure to address the computational barriers associated with large time-series data sets, as are typical in the battery domain. The framework was validated in simulation, yielding several mean parameter estimation errors that were one order of magnitude smaller than those of the conventional least squares approach. While developed for the high-uncertainty, electrochemical hybrid modeling context, the estimation framework is applicable to all models and is presented in a generalized form.