Innovation in electric vehicles and energy storage from renewable sources are two of the key drivers in the rapid growth of a battery industry that needs to improve performance of battery systems with great urgency. Charging capability, energy density, and costs will all need to improve dramatically.
Machine learning can help, exploiting data to assist the discovery of new battery materials and chemistries, design of improved battery packs, and optimisation of battery management systems. However, in a rapidly-evolving field, this data is often sparse and noisy, requiring the unique capabilities of the Alchemite™ deep learning software.
Optimising production processes and battery chemistry
In a project with industry and academic partners, Intellegens technology is being applied to optimise the production process for lithium ion batteries. Currently, improvements in this process are done by trial-and-error, with a large matrix of experiments. Use of Alchemite™ deep learning software to predict the change in performance of an electrode from changes in the manufacturing processes is helping to focus this experiment and reduce the development time for new battery chemistries.
Data-driven machine learning for battery management
A collaboration between the University of Cambridge, A*STAR and Nanyang Technological University in Singapore, assessed methods for predicting electric vehicle battery states and revealed that a data-driven machine learning model offers the most accurate predictions for state of charge and health. The project provides a case study for machine learning accurately predicting the health and life of a battery, with the potential for manufacturers to embed these methods into their battery devices, improving in-life service for the consumer.
Article: Battery R&D - the rise of machine learning
BEST magazine speaks to Intellegens CTO, Dr Gareth Conduit.
Alchemite™ for batteries
- Design testing programs to achieve objectives with the fewest experiments or prototypes
- Propose new battery materials or chemistries
- Trade-off size, weight, power, charge speed, lifetime, etc. in designing battery packs
- Select and optimise process parameters to improve battery manufacturing
- Inform control systems for battery management, including state of charge and safety monitoring
- Create battery models that can be shared to support collaborative R&D