Conclusions A method for diagnosing the abnormal battery charging capacity based on EV operation data was developed in this study. By establishing offline and online diagnosis systems to monitor the charging capacity, the TR caused by overcharging can be effectively identified in time. The following are the most important findings of this study.
A statistics-based method is then used to diagnose battery charging capacity abnormity by analyzing the error distribution of large sets of data. The proposed tree-based prediction model is compared with other state-of-the-art methods and is shown to have the highest prediction accuracy. The holistic diagnosis scheme is verified using unseen data.
During over charging, lithium deposition (mossy or dendritic type) will occ ur at the surface of the a node . Meantime, over de - generation. Temperature is also a very import ant factor affecting battery operation. Under low -temperat ure charging conditions,
Zhang, et al. propose a method for the monitoring and warning of EV charging faults based on a battery model is proposed to judge whether the charging process is normal by comparing the charging response information simulated by the battery model with the battery charging status information. ...
With the development of electric vehicles in China, the fault monitoring and warning systems for the charging process of electric vehicles have received the industry’s attention. A method for the monitoring and warning of electric vehicle charging faults based on a battery model is proposed in this paper.
Various methods for diagnosing power battery faults have been proposed, including knowledge-based, model-based, and data-driven approaches. Knowledge-based fault-diagnosis methods identify faults using prior knowledge. Both fault trees [ 15] and expert systems [ 16] have been used for power battery fault diagnosis.