Lithium battery state estimation method for distributed energy storage system

Abstract

The invention discloses a lithium battery state estimation method for a distributed energy storage system, and belongs to the field of lithium ion battery application. The method comprises the following steps: establishing a lithium battery health state estimation model based on deep learning by adopting a gated cycle unit recurrent neural network; estimating the state of charge of the lithium battery of the distributed energy storage unit management system in real time by adopting a second-order equivalent circuit model of the lithium battery in combination with an extended Kalman filtering algorithm; and synchronously updating the battery capacity and the lithium battery state-of-health estimation model in the lithium battery state-of-charge estimation process through information interaction. On the premise of not increasing system hardware cost, through information interaction, accurate lithium battery capacity is provided for SOC estimation; meanwhile, a training sample is providedfor a big data SOH estimation model; therefore, the estimation precision of the SOC and SOH of the lithium battery in the system is improved, and subsequent effective completion of energy managementand scheduling of the system is facilitated.

Description

technical field [0001] The invention relates to the application field of lithium ion batteries, in particular to a lithium battery state estimation method for a distributed energy storage system. Background technique [0002] In recent years, with the rapid development of new energy vehicles, lithium-ion battery technology has also been significantly improved. Its energy density has increased year by year, but its price has continued to decline. It is a potential electric energy storage component in the future. At present, large-scale lithium battery energy storage applications still have certain difficulties, and face a series of challenges in terms of safety and cost. The joint scheduling of distributed energy storage units is an important means to give full play to the application value of distributed energy storage in power systems. [0003] In this application scenario, accurate state of charge (State of Charge, SOC) and state of health (State of Health, SOH) of lithiu...

AI Technical Summary

Problems solved by technology

At present, the estimation of the SOC and SOH of the lithium battery by the energy storage unit only depends on the battery management system (Battery Management System, BMS) equipped with each distributed energy storage unit, and the equipped BMS is limited by the cost, and the processor does not have Powerful computing power can only run relatively low-complexity algorithms, resulting in limited accuracy of BMS in estimating the SOC and SOH of lithium batteries

Images