AVL using AI to predict battery lifetime

December 02, 2023

AVL and the Institute of Automotive Technology at the Technical University of Munich (TUM) have developed a method to predict and optimize the lifespan of electric vehicle (EV) batteries using artificial intelligence (AI).

This method employs federated learning approaches to train a global neural network with a wealth of decentrally stored data from various vehicle fleets, without sharing the data or compromising data protection. The AI model then serves as a foundation for calculating the remaining useful lifetime of the battery.

The United Nations has proposed that e-car batteries should retain 80 percent of their original capacity after five years or 100,000 kilometers of use. To optimize battery lifespan, it’s crucial to determine the current state and predict future behavior. This can be achieved with machine learning, using large amounts of data to generate empirical values.

“Each fleet trains its own neural network. The knowledge gained is then transferred to a global model. Hence, no one has to access an OEM’s original data,” explains Annalena Belnarsch, a development engineer at AVL. She developed the method with TUM and tested it using 50,000 training data samples from the lab. “For example, we distributed a data set over ten fleets. Compared to training one neural network per fleet, we were able to estimate the battery lifetime much more accurately thanks to Federated Learning. On average, the error value was reduced by 32 percent.”

The more data used for model training, the better the predictability. Even smaller fleets with fewer data sets can contribute to and benefit from this predictability, while maintaining a high level of data protection. The more trained neural networks exist to feed the ‘central model’, the more successfully manufacturers can supply their battery management systems with updated models and optimize their operating strategy. This also benefits vehicle owners, as AI-based battery analysis can detect malfunctions early, allowing for preventive servicing and potentially extending the battery’s lifespan or increasing its residual value in the event of a resale.

“One of the biggest challenges in training AI models for battery aging prediction is generating a large data set, as the vehicle data required for this includes sensitive personal or operational information. One solution to this is federated learning, in which all vehicle data remains local to the respective fleet operator and yet an aging model can be trained collaboratively without having to upload one’s own data to a server and thus risk data privacy violations or data leaks,” says Thomas Kröger, Research Associate at the Institute of Automotive Technology at TUM.

“The mutual exchange between science, research and industry is driving the necessary paradigm shift toward sustainable mobility. The Technical University of Munich has been associated with AVL List GmbH in this regard for many years, and their joint work is dedicated, among other things, to making electrified driving even more attractive to people,” says Prof. Markus Lienkamp, head of the Institute of Automotive Technology at TUM and a board member of the VDI Association for Automotive and Transport Engineering.