Applications of lithium-ion batteries are widespread, ranging from electric vehicles to energy storage systems. In spite of nearly meeting the target in terms of energy density and cost, enhanced safety, lifetime, and second-life applications, there remain challenges. As a result of the difference between the electric characteristics of the cells, the degradation process is accelerated for battery packs containing many cells. The development of new generation battery solutions for transportation and grid storage with improved performance is the goal of this paper, which introduces the novel concept of Smart Battery that brings together batteries with advanced power electronics and artificial intelligence (AI). The key feature is a bypass device attached to each cell that can insert relaxation time to individual cell operation with minimal effect on the load. An advanced AI-based performance optimizer is trained to recognize early signs of accelerated degradation modes and to decide upon the optimal insertion of relaxation time. The resulting pulsed current operation has been proven to extend lifetime by up to 80% in laboratory aging conditions. The Smart Battery unique architecture uses a digital twin to accelerate the training of performance optimizers and predict failures. The Smart Battery technology is a new technology currently at the proof-of-concept stage.

The importance of accurate estimation of the state-of-health (SOH) for Lithium-ion (Li-ion) batteries is going to increase as Li-ion batteries become more integrated into daily life. As the reliance on Li-ion batteries increases so does the need for battery pack size optimisation and the extension of battery lifetime. Data-driven methods for estimation of the SOH of Li-ion batteries have shown to have good performance under laboratory conditions, but often fail to achieve similar performance when used in real life applications. This is a consequence of the field data seldomly matching the laboratory data, which is a necessary condition of most data-driven methods. A method which aims to account for discrepancies between laboratory and field data is transfer learning. This paper shows how the transfer learning algorithm kernel mean matching can be used to transfer both multiple linear regression (MLR) and bootstrapped random vector functional link (BRVFL) models from the laboratory to the field. It is shown that these methods can achieve mean absolute percentage errors (MAPE’s) smaller than 1% on both laboratory and field data simultaneously.

Lithium-ion batteries have emerged as the primary power source for electric mobilities. To ensure the safe operation of the batteries throughout their lifespan, accurate remaining useful lifetime (RUL) prediction is required. This paper proposes ensemble strategies that integrate two different Gaussian process regression (GPR) methods and model-based methods to enhance the robustness of the prediction. The first GPR is based on the forward extrapolation of the measured capacity sequence. The second GPR is based on the extrapolation of the measured feature and then inputs the predicted feature into a capacity estimation model. The first ensemble strategy is the weighted ensemble method, which uses the least squares method to determine the weighted coefficients. The second strategy is a more conservative method, which chooses the fastest degradation path between two basic methods at each prediction step. The third strategy is particle filter (PF) to combine the predicted data from different methods. The batteries aged by a real forklift aging profile and open access dataset are used to verify the proposed methods. The results of all methods based on different percent of data are analyzed. The results show that individual methods may obtain different prediction results, while ensemble strategies have accurate and robust predictions. The PF for capacity-based and feature-based methods has the best performance with the absolute error of RUL less than 23 full equivalent cycles, error of prediction steps less than 1, and negligible simulation time for forklift dataset.

Battery design is linked to real-world applications using a battery-design-aware machine learning framework built on a digital twin model, ultimately contributing to safer and longer-lasting next-generation batteries.