Lithium ion battery health state prediction method based on CRJ network

Abstract

The invention relates to a lithium ion battery health state prediction method based on a CRJ network. The method comprises the steps: forming the CRJ network and training the CRJ network; and monitoring a battery constant-current charging time sequence on line, inputting the battery constant-current charging time sequence into a prediction model, and outputting an available discharging capacity sequence to obtain the health state of batteries. According to the method, the constant-current charging time is used as input, the health state is predicted through the CRJ network, and real-time online prediction of the health state of the lithium ion batteries is achieved; and the method has low requirements on hardware conditions and occupies small memory. The prediction model established after the CRJ network is optimized by adopting an optimization algorithm can be used for health state prediction of batteries of the same type; an IPSO algorithm and an AOA algorithm are combined to form an IAPSOA algorithm, and the IAPSOA optimizing algorithm enhances the search capability and stability of the AOA algorithm, so that network parameters can be better optimized; and the accuracy of obtaining a CRJ network model is high.

Description

technical field [0001] The invention relates to the technical field of battery health state prediction, in particular to a CRJ network-based lithium ion battery health state prediction method. Background technique [0002] Lithium-ion battery state of health (SOH) prediction is a basic and important function of the battery management system, and its purpose is to achieve online, accurate, real-time and fast SOH prediction under limited hardware conditions. There are two main types of existing SOH prediction methods: [0003] Model-based method: This method needs to establish an electrochemical model, an equivalent circuit model or a mathematical model according to the aging mechanism of the battery. The disadvantage of the electrochemical model is that it is difficult to identify the relevant parameters, and more expensive testing equipment is used in the application. The disadvantage of the equivalent circuit model is that the error of model parameter identification will ...

AI Technical Summary

Problems solved by technology

Lithium battery capacity data is difficult to accurately extract online

When the lithium battery is actually used, the discharge process changes irregularly, and the data is of little practical significance

Moreover, the computing power and data storage capacity of the existing battery management system are limited

Among various data-driven methods, there are relatively few models that satisfy the three points of good dynamic performance, low model complexity and high prediction accuracy at the same time.

The echo state network (ESN) has the above advantages, but its own parameters are difficult to choose artificially.

Images