eVehicle Technology
acoustic vehicle alerting system

AVL Develop AI Model to Predict Vehicle Battery Lifetime

Vehicle Battery Lifetime

Extending the vehicle battery lifetime is a shared concern not only among car drivers but also within the United Nations, which

Extending the vehicle battery lifetime is a shared concern not only among car drivers but also within the United Nations, which advocates for a mandated minimum durability for electric vehicle (e-car) batteries. The proposal suggests that these batteries should maintain 80 percent of their original capacity after either five years or 100,000 kilometers of usage. To enhance the vehicle battery lifetime, it becomes imperative to assess their current state and predict future performance. Machine learning proves instrumental in achieving this goal. The approach involves utilizing extensive data to derive empirical values.

The federated learning method comes into play, wherein a model is trained using vast, decentralized datasets from various vehicle fleets. Annalena Belnarsch, a development engineer at AVL, collaborated with the Institute of Automotive Technology at TUM to devise this method. By employing federated learning, each fleet independently trains its neural network, and the knowledge acquired is then consolidated into a global model. Notably, this process eliminates the need for direct access to original equipment manufacturers’ (OEM) proprietary data.

Belnarsch conducted experiments with 50,000 training data samples from the laboratory, illustrating the effectiveness of the approach. In one scenario, a dataset was distributed among ten fleets. Compared to training separate neural networks for each fleet, the federated learning technique significantly improved the accuracy of battery lifetime estimations, resulting in an average reduction of the error value by 32 percent.

The more data the better: How OEMs can improve their battery operation strategy

As a general rule for model training: The more, the better. Even smaller fleets with fewer data sets contribute to better predictability – but also benefit from it – while maintaining a very high level of data protection. The more trained neural networks exist to feed the ‘central model’ can be fed, the more successfully manufacturers can supply their battery management systems with updated models and thus optimize their operating strategy. Incidentally, this also benefits vehicle owners. With the help of AI-based battery analysis, malfunctions can be detected at an early stage. In this way, vehicles can be serviced preventively. This can subsequently contribute to a longer lifetime of the battery or a higher residual value in the event of a possible resale. Considering that a battery costs approx. 150 euros per kWh, precise calculations can be made. 

“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 .

Avatar photo

eVehicle Technology

Join thousands of eVehicle Experts and get the latest updates straight to your inbox!