Design and Implementation of a Smart Lithium-Ion Battery System with Real-Time Fault Diagnosis Capability for Electric Vehicles

• Published in: Energies (Basel) Vol. 10; no. 10; p. 1503
• Main Authors: Gao, Zuchang, Chin, Cheng, Chiew, Joel, Jia, Junbo, Zhang, Caizhi
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01-10-2017
• Subjects: Aircraft industry; Algorithms; Artificial intelligence; Balancing; Cell number; Computer applications; Configurations; Control theory; Electric power systems; electric vehicle; Electric vehicles; Energy; energy-storage system; Extended Kalman filter; Fault diagnosis; Fuzzy logic; Kalman filters; Learning algorithms; Lithium; lithium-ion; Lithium-ion batteries; Machine learning; Neural networks; protection; Researchers; State space models; Support vector machines; Beijing China; Singapore; United States > US; China; Japan
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en10101503

[...]the machine learning-based estimation methods (also called data-driven approaches), such as the artificial neural network–fuzzy logic (FL) [16] and support vector machine [17] methods. [...]the state-space model-based estimation methods (such as using the extended Kalman filter (EKF)) reduce the convergent time but increase the computational load of the BMS [21,22]. [...]the smart battery-power system has the following features: (1) compatibility and flexibility with different kinds of LIBs and battery pack configurations; (2) capability for SOC self-initialization and self-adjustment; (3) capability for fault diagnosis and self-recovery; and (4) ability to provide a human–machine interface for status report and system configuration, locally or in the cloud. [...]battery-cell balancing is required for the cells that are unbalanced, that is, when the SOC of one or more cells are unequal. [...]there are n + 1 (n is the cell number in the battery pack) wires from the cells to the balancing board.