DIICAN: Dual Time-scale State-Coupled Co-estimation of SOC, SOH and RUL for Lithium-Ion Batteries

• DOI: 10.48550/arxiv.2210.11941
• Publication Date: 2022-01-01
• Authors: Ningbo Cai; Yuwen Qin; Xin Chen; Kai Wu
• Keywords: State of health; State of charge; Degradation; Charge cycle

Accurate co-estimations of battery states, such as state-of-charge (SOC), state-of-health (SOH,) and remaining useful life (RUL), are crucial to the management systems assure safe reliable management. Although external properties charge with aging degree, batteries' degradation mechanism shares similar evolving patterns. Since batteries complicated chemical systems, these states highly coupled intricate electrochemical processes. A state-coupled co-estimation method named Deep Inter Intra-Cycle Attention Network (DIICAN) is proposed in this paper estimate SOC, SOH, RUL, which organizes measurement data into intra-cycle inter-cycle time scales. And extract degradation-related features automatically adapt practical working conditions, convolutional neural network applied. The state attention unit utilized evolution pattern evaluate degree. To account for influence on SOC estimation, incorporated estimation capacity calibration. DIICAN validated Oxford dataset. experimental results show that can achieve SOH RUL high accuracy effectively improve whole lifespan.