Method for predicting residual life of storage battery of simulation transformer substation in intermittent working mode

A technology of life prediction and working mode, applied in power generation prediction, design optimization/simulation, electrical components and other directions in AC network, it can solve the problems of the complexity of battery degradation law and the existence of regeneration phenomenon, and achieve accurate remaining life prediction, The effect of reducing complexity and non-stationarity and improving prediction accuracy

Pending Publication Date: 2021-12-28
SKILL TRAINING CENT OF STATE GRID JIANGSU ELECTRIC POWER CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The simulated substation battery is used as an emergency and replacement power supply, and its working mode is intermittent, which will lead to the regeneration phenomenon of the capacity in the normal degradation process, making the battery degradation law appear random, complex and non-stationary, and it is difficult to use the traditional single prediction model. it accurately predicts

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for predicting residual life of storage battery of simulation transformer substation in intermittent working mode
  • Method for predicting residual life of storage battery of simulation transformer substation in intermittent working mode
  • Method for predicting residual life of storage battery of simulation transformer substation in intermittent working mode

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] Next, the technical solution of the present invention will be described in detail in conjunction with the accompanying drawings:

[0016] figure 1 The simulation substation DC power supply system battery remaining life prediction flowchart, the present invention is a combination of the prediction method based on optimization KELM VMD decomposition and Bat for predicting remaining life of the battery, the following specific embodiments:

[0017] Step 1, real-time acquisition operation of the battery status signals, including the operating current and voltage, and calculates the battery discharge capacity at the current discharge cycle capacity estimation method based on so as to acquire the capacity degradation of data at different cycles Q (t) (t = 1, ..., K).

[0018] Step 2, the battery capacity degradation VMD decomposed data, obtaining the N different modalities sequence {u 1 (1), u 1 (2), ..., u 1 (K)}, {u 2 (1), u 2 (2), ..., u 2 (K)}, ..., {u N (1), u N (2), ..., u ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a method for predicting the residual life of a storage battery of a simulation transformer substation in an intermittent working mode, and the method specifically comprises the steps: 1) collecting a working state signal of the storage battery, and obtaining the original data of battery capacity degradation; 2) carrying out variational mode decomposition on the storage battery capacity degradation data to obtain subsequences of different scales; 3) establishing each sub-sequence prediction model based on the optimized kernel extreme learning machine, and optimizing regularization parameters and kernel parameters of the KELM model by adopting a bat algorithm to obtain sub-sequence prediction values; 4) superposing the sub-sequence predicted values, finally obtaining a capacity predicted value, and estimating the remaining life of the storage battery in combination with a failure threshold. Aiming at the non-stationary and non-monotonic characteristics of the storage battery degradation of the direct-current power supply system of the simulation transformer substation in the intermittent working mode, the capacity degradation data is subjected to modal decomposition, the signal complexity is effectively reduced, the Bat is utilized to optimize the sub-sequence prediction model parameters, and the local time sequence characteristics of the capacity degradation are better captured; therefore, the battery remaining life prediction precision is improved.

Description

Technical field [0001] The present invention relates to a batch method of predicting remaining life of the battery operating mode simulation substation belongs to the field of battery technology health management. Background technique [0002] Substation responsible regional power supply task is an important hub for the grid. Simulation substation DC power supply substation protection system means switching control equipment, equipment simulation run, a battery is a direct current power source in a key ring, which may be replaced quickly when power or as a backup power substation fault simulation, when the station when an exception occurs or AC power is interrupted, which can effectively remove the fault circuit simulation to ensure the normal operation of the substation. Battery performance degradation or failure will lead to unstable power supply substation or even cause accidents. Therefore, the need to study the remaining battery life (Remaining UsefulLife, RUL) forecasting t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F30/27H02J3/00
CPCG06F30/27H02J3/004H02J2203/20
Inventor 李世倩任罡季宁朱伟陶红鑫胡晓丽张洁华孙吕祎魏蔚吴双
Owner SKILL TRAINING CENT OF STATE GRID JIANGSU ELECTRIC POWER CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products