Hybrid energy-storage battery pack fault diagnosis method

Abstract

The invention relates to a hybrid energy-storage battery pack fault diagnosis method, and especially a hybrid energy-storage battery pack fault diagnosis method. The method comprises the following steps: extracting voltage, current, temperature and like information signal data of a monomer battery, and removing noise of the collected signal information data through a filter algorithm to acquire anoriginal sample with fault information, analyzing to extract a feature vector of a battery status from the original information, and regarding the feature vector as an input signal of an improved neural network classifier algorithm; and meanwhile, establishing a battery data training rule with feature vectors and fault types in one-to-one correspondence, wherein the battery data training rule isused for training and testing, wherein a diagnosis method with the diagnosis precision meeting a requirement after testing is used for performing fault positioning on a battery module in the actual operation. The diagnosis method disclosed by the invention has the advantage that the diagnosis method is fast in speed and high in efficiency, the fault battery detection accuracy rate can be improved,and the fault battery can be timely removed.

Description

technical field [0001] The invention relates to a battery pack fault diagnosis technology in an energy storage system, in particular to a hybrid energy storage battery pack fault diagnosis method. Background technique [0002] In the power system, the use of energy storage technology can effectively realize user demand side management, eliminate the difference between day and night peaks and valleys, smooth load, reduce power supply costs, and at the same time promote the utilization of renewable energy, improve the stability of power grid system operation and improve the power grid. Power quality to ensure the reliability of power supply. As a battery system for backup energy, whether the battery is running normally or not directly affects the normal, reliable and safe operation of various equipment in the application field. [0003] The health of a battery pack is determined by the healthiest cell in the pack. A battery pack is generally composed of several single cells ...

AI Technical Summary

Problems solved by technology

[0005] (1) When testing the battery status, the measurement results will be different due to the difference of the measurement equipment and the measurement method;

[0006] (2) The temperature during measurement and the working state of the battery (when charging and discharging at a high rate, the temperature of the battery will rise, which will affect the activity of the battery electrodes) will also lead to inaccurate measurement results;

[0007] (3) The difference in battery type and capacity will also lead to large errors in the measurement results

Images