Mobile phone battery SOC correction method

Abstract

The invention discloses a mobile phone battery SOC correction method, and the method comprises the steps: recording each characteristic physical quantity and a corresponding SOC value before and after H mobile phones of the same model enter a standby state periodically, and forming an original data set; preprocessing the original data set; building a secondary fusion model structure; dividing the preprocessed data set into a training set, a verification set and a test set; training a secondary fusion model by adopting the training set and the verification set; evaluating the secondary fusion model by adopting the test set, if the preset precision is met, implanting the secondary fusion model into a mobile phone battery management system, otherwise, returning to the previous step; and every time the mobile phone enters a standby state, collecting each characteristic physical quantity before and after the battery is standby, and after preprocessing, adopting the secondary fusion model to estimate the SOC of the battery and correct the mobile phone battery management system. Compared with other methods, long-time standing of the battery is not needed, the manager has higher real-time calculation capability and precise impedance measurement equipment, and the SOC correction of the mobile phone can be quickly realized.

Description

technical field [0001] The invention belongs to the field of smart phones, and in particular relates to a mobile phone battery SOC calibration method. Background technique [0002] The accurate estimation of the state of charge (SOC) of the mobile phone battery is the prerequisite for the user to use the mobile phone power reasonably. However, the current mobile phone battery management system has low accuracy in estimating the battery SOC, especially after entering the low battery range below 20%, the SOC estimation is even more inaccurate, and the mobile phone may automatically shut down at any time, causing users to fall into "battery anxiety". Use experience. [0003] At present, there are mainly ampere-hour integration methods, open circuit voltage methods, Kalman filter methods, impedance analysis methods, etc. for battery SOC estimation. Among them, the ampere-hour integration method only needs to measure the battery discharge current, and the calculation is simple....

AI Technical Summary

Problems solved by technology

Among them, the ampere-hour integration method only needs to measure the battery discharge current, and the calculation is simple. It is widely used in the SOC estimation of mobile phone batteries, but the measurement error of the current sensor causes the SOC estimation error to accumulate over time, especially when the battery SOC enters a low level below 20%. After the power interval, the measurement error increases significantly, which affects the user's judgment and planning of the remaining power; the open circuit voltage method judges the SOC based on the open circuit voltage of the battery. It cannot be used during operation; the Kalman filter method requires a strong computing power of the battery management system, and the impedance analysis method requires more measurement components, which are not suitable for mobile phones that require high volume and portability

Images