SOC Estimation of Vanadium Redox Flow Batteries Based on the ISCSO-ELM Algorithm.

Area of Science:

• Electrochemistry
• Energy Storage Systems
• Battery Management

Background:

• Vanadium redox flow batteries (VFBFs) are crucial for grid-scale energy storage.
• Accurate state of charge (SOC) estimation is vital for VFB operational efficiency and longevity.
• Battery capacity decay presents a significant challenge for reliable SOC prediction.

Purpose of the Study:

• To develop an accurate electrochemical model for VFBs.
• To integrate an improved sand cat swarm optimization algorithm with an extreme learning machine (ISCSO-ELM) for enhanced SOC estimation.
• To address the impact of capacity decay on VFB SOC prediction.

Main Methods:

• An electrochemical model was established to derive key battery parameters, including ion concentration.
• An extreme learning machine (ELM) was combined with an improved sand cat swarm optimization algorithm (ISCSO).
• The ISCSO-ELM model was applied to SOC estimation, considering VFB capacity decay.

Main Results:

• The electrochemical model successfully provided essential parameters for SOC estimation.
• The ISCSO-ELM approach demonstrated improved effectiveness in predicting the SOC of VFBs.
• The integrated method showed enhanced accuracy in SOC estimation despite capacity fade.

Conclusions:

• The proposed electrochemical model and ISCSO-ELM method offer a robust solution for VFB SOC estimation.
• This approach effectively mitigates challenges posed by VFB capacity decay.
• The findings contribute to more reliable and efficient operation of vanadium redox flow batteries.