On-line estimating method for SOH of new energy automobile power battery

Abstract

A on-line estimating method for the SOH of a new energy automobile power battery includes the steps that S1, an SOH predicating model of the battery is established and optimized, and an improved Elman network (OIF Elman network) algorithm having an output-input feedback mechanism is adopted; S2, input parameters of the SOH model of the battery are selected; internal resistance, currents and temperature of the battery serve as the input parameters of the model; S3, operation is performed under the Matlab7.1 environment; S4, verification is performed. When the number of sample points is few, the OIF Elman network is obviously superior to an Elman network in whether training speed or predication precision. The generalization capacity of the OIF Elman network is improved, the requirement for the number of training samples is lowered, besides, the predication precision can be improved, and the on-line estimating method can be successfully applied to predicating the SOH of the power battery.

Description

technical field [0001] The invention relates to a method for online estimation of SOH (battery cycle life) of a power battery of a new energy vehicle. Background technique [0002] Power battery is the core of new energy vehicles, the biggest bottleneck in new energy vehicle technology and cost, and the core link in the new energy vehicle industry chain. With the massive consumption of global oil resources and other energy sources, air pollution, climate and environmental degradation have further aggravated. Under the background of over 50% dependence on foreign energy and the development of low-carbon economy, the development of new energy vehicles has become the general trend. [0003] Compared with traditional cars, electric vehicles have incomparable advantages, but they still face many technical and cost problems, mainly in the mileage of a single charge of electric vehicles, battery life, charging equipment (public facilities), etc. The power battery system life predi...

AI Technical Summary

Problems solved by technology

In practical applications, the battery mechanism model should be used as much as possible, but its disadvantage is that the battery mechanism model requires fine parameters and is highly complex, making it difficult to establish a complete aging mechanism model; the key to feature-based prediction is to find Sensitive feature parameters, feature online testing methods, and description of the relationship between features and battery health status; based on the principle of data-driven, the idea of ​​data-driven should be assisted when the description of the mechanism model cannot be realized, and rules should be mined from the data. The fitting formula or neural network model purely based on data-driven has certain limitations in practical application, and it should be combined with data-driven ideas on the basis of mechanism or feature models

Images