This paper presents a reduced-order electrochemical battery model designed for the online implementation of battery control systems. The model is based on porous-electrode and concentrated-solution theory frameworks and is able to predict voltage as well as the internal electrochemical variables of a battery. The reduction of the model leads to a physics-based one-dimensional discrete-time state-space reduced-order model (ROM), which is especially beneficial for online systems. Models optimized around different operational setpoints are combined to predict cell variables over a wide range of temperatures and state of charges (SOCs) using the output-blending method. A sigma-point Kalman filter is further used to manage inaccuracies generated by the reduction process and experimental-related issues such as measurement error (noise) in the current and voltage sensors. The state-estimation accuracies are measured against a full-order model (FOM) developed in COMSOL. The whole system is able to track the internal variables of the cell, as well as the cell voltage and SOC with very high accuracy, demonstrating its suitability for an online battery control system.

Creating SoC algorithms for Li-ion batteries based on neural networks requires a large amount of training data, since it is necessary to test the batteries under different conditions so that the algorithm learns the relationship between the different inputs and the output. Obtaining such data through laboratory tests is costly and time consuming; therefore, in this article, a neural network has been trained with data generated synthetically using electrochemical models. These models allow us to obtain relevant data related to different conditions at a minimum cost over a short period of time. By means of the different training rounds carried out using these data, it has been studied how the different hyperparameters affect the behaviour of the algorithm, creating a robust and accurate algorithm. To adapt this approach to new battery references or chemistries, transfer learning techniques can be employed.