SOC Estimation of Lithium Iron Phosphate Batteries Based on Pressure Feature and VMD-LSTM

The State of Charge (SOC) is a key parameter for measuring the remaining capacity of new energy vehicle batteries. It not only directly reflects the driving range of the vehicle but also plays an indispensable role in ensuring operational safety and extending battery lifespan. Accurate estimation of SOC provides strong support for the safe and reliable operation of electric vehicles. During the charging and discharging process of lithium iron phosphate batteries, the intercalation and deintercalation of lithium ions cause deformation of the electrode's lattice structure, leading to the expansion and contraction of the electrode volume. This, in turn, exerts stress on the limited internal space of the battery, which is mainly manifested as changes in battery pressure monitored by sensors. To address the issues of insufficient information and low estimation accuracy associated with the use of electrical signals in traditional data-driven methods, this study introduces pressure characteristic signals based on electrical signals and proposes a lithium-ion battery SOC estimation method using a Long Short-Term Memory (LSTM) neural network combined with Variational Mode Decomposition (VMD). Due to the instability of pressure signals, VMD is applied to decompose the lithium-ion battery pressure data into multiple subsequence modal components. Meanwhile, a sliding window function is introduced to enhance the LSTM network's ability to retain long-term information. Experimental results show that under dynamic working conditions of Urban Dynamometer Driving Schedule (UDDS) and Full Urban Driving Schedule (FUDS), the SOC estimation error of the VMD-LSTM network considering pressure characteristics is 1.24%. In contrast, the SOC estimation error of the LSTM network using only electrical signals is 6.13%, representing a significant improvement. This verifies the superiority of the proposed method.