During the battery's lifespan, AI and machine learning can be used for maintenance to extend its lifespan and maximize performance. Optimizing charging and discharging protocols, identifying hazards, calculating state of health (SoH), calculating loads, and detecting defects will ensure that safety is prioritized, for example, when a battery is used in an electric passenger vehicle.
State of Heat (SoH) calculations, defect identification, and second-life assessments are processes that must be carried out at the end of a battery's life cycle. AI could provide the most accurate information to determine which applications a battery might be suitable for in a second life.
Energy densities, safety and costs of rechargeable batteries
The main issues related to rechargeable batteries are the challenges posed by energy density, the safety of liquid electrolytes, and the extraction of critical materials. Liquid electrolytes tend to become hazardous at high temperatures and pressures, presenting an opportunity for AI and machine learning to perform diagnostics and monitoring throughout the battery's lifespan, helping to maintain a level of safety and reliability that allows for the early detection of any problems.
The limited supply of critical materials such as lithium, nickel, cobalt, and copper can pose challenges for battery manufacturers, along with high extraction costs and negative environmental impact. These factors related to the supply of highly demanded materials incentivize battery reuse and recycling, which can also be facilitated by machine learning techniques.
AI in electric vehicle batteries
Electric vehicles are expected to be one of the largest markets for AI in the battery sector. The potential for AI to benefit and improve the numerous stages of a battery's lifecycle will, in turn, enable better development, testing, and management of electric vehicles. New battery chemistries and structures will be needed to improve energy density, charging, and safety—aspects that electric vehicle manufacturers intend to prioritize. AI's ability to efficiently and effectively explore a wide range of chemical compositions could mean that improvements are seen much faster and with less reliance on trial and error.
The reliability offered by artificial intelligence and machine learning could also be unmatched when it comes to achieving a robust diagnostic, as it can reach levels of safety that were previously impossible. Battery management systems will also allow users to access data as it is analyzed and interpreted, enabling them to be more involved in what is happening with the vehicle.
The IDTechEx report "AI-Driven Battery Technology 2025-2035: Technology, Innovation and Opportunities" provides details on different approaches to machine learning, materials discovery, cell testing and assembly, battery management system analysis and second-life assessments, along with forecasts on the adoption of new technologies.
