This paper presents a practical usability investigation of recurrent neural networks (RNNs) to determine the best-suited machine learning method for estimating electric vehicle (EV) batteries’ state of charge. Using models from multiple published sources and cross-validation testing with several driving scenarios to determine the state of charge of lithium-ion batteries, we assessed their accuracy and drawbacks. Five models were selected from various published state-of-charge estimation models, based on cell types with GRU or LSTM, and optimisers such as stochastic gradient descent, Adam, Nadam, AdaMax, and Robust Adam, with extensions via momentum calculus or an attention layer. Each method was examined by applying training techniques such as a learning rate scheduler or rollback recovery to speed up the fitting, highlighting the implementation specifics. All this was carried out using the TensorFlow framework, and the implementation was performed as closely to the published sources as possible on openly available battery data. The results highlighted an average percentage accuracy of 96.56% for the correct SoC estimation and several drawbacks of the overall implementation, and we propose potential solutions for further improvement. Every implemented model had a similar drawback, which was the poor capturing of the middle area of charge, applying a higher weight to the voltage than the current. The combination of these techniques into a single custom model could result in a better-suited model, further improving the accuracy.

This paper presents a Recurrent Neural Network (RNN) model for the State of Charge (SoC) estimation for an Electric Vehicle’s Lithium-Ion battery. A new Autoregressive modification is proposed to improve upon earlier published Machine Learning models to enhance the prediction accuracy and make results less sensitive to varying usage conditions. By building upon earlier published findings, assessing several models’ ability to estimate charge using a history window of sensory data, this work proposes, implements, and reports its methods of improving accuracy by introducing the State of Charge as part of sensory inputs in a Feed-Forward manner. The method is based on the Autoregressive implementation of neural network model training, where successively calculated charge values are used as input in the subsequent predictions, but the potential inaccuracies with those predictions that might otherwise cause significant and rapid divergence are accounted for within a modified recursive training procedure. As a result, with a slight increase in training time, the accuracy of the output prediction for three different realistic charge–discharge driving profiles doubled compared to the two best previously published models. Overall, the test results have demonstrated the usability of the current model in actual driving scenarios, making such models a viable replacement to estimation approaches used in electric vehicle battery management systems.

This research was a step towards a new Battery Management System inside electric vehicles. It is based on using Machine Learning techniques and powerful Tensor capable devices to use Neural Networks to predict the accurate State of Charge of Lithium-Ion cells rather than applying traditional methods of battery capacity measurement. It is meant to prolong the utilisation of energy inside a vehicle by relying on the history of efficient driving behaviours and employing that information to model the capabilities of similar cells. This thesis investigated several published methods and proposed a novel approach, bringing higher accuracy results.