Chinese researchers have proposed a new type of deep learning model – an artificial intelligence that allows accurate prediction of the life of lithium-ion batteries, reports Xinhua. This type of battery is extremely widely used today, especially in electric cars.
The results of the studies were published in the journal IEEE Transactions on Transportation Electrification.
The deep learning model effectively eliminates the need for a large amount of data from charging tests and offers a new idea for real-time battery life prediction.
The paper notes that accurately predicting the life of lithium-ion batteries is essential for the normal and efficient operation of electrical devices. However, such an assessment faces significant challenges due to the non-linear capacity degradation process and the uncertain operating conditions of this type of battery.
Researchers from the Dalian Institute of Chemical Physics (DICP) of the Chinese Academy of Sciences and Xi’an Jiaotong University proposed a deep learning model based on a small amount of charge cycle data that predicts the current life cycle of the target battery and remaining useful life. The model can accurately predict the battery’s current cycle and remaining useful life using only 15 charge cycle data. According to the results of the experiment, this data can make an extremely accurate prediction.
The proposed model is expected to provide a comprehensive solution for intelligent management of lithium-ion batteries.
#Battery #secrets #revealed
