A method for predicting the health status of lithium-ion batteries in electric forklifts based on lstm-ffnn

A lithium-ion battery, health status technology, applied in the direction of measuring electricity, measuring devices, measuring electrical variables, etc., can solve problems such as safety problems, economic losses, capacity attenuation, etc., to avoid economic losses and safety problems, stabilize energy supply, The effect of improving accuracy

Active Publication Date: 2021-12-07
ZHEJIANG UNIV +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Lithium-ion batteries cannot provide stable energy after reaching the maximum life, and need to be maintained and replaced in time. If they continue to be used, they may cause economic losses and even cause important safety issues.
[0003] Lithium-ion batteries are an important power source for electric forklifts. In the process of continuous charging and discharging, the performance of the batteries decreases and the capacity decays. After reaching the maximum life, lithium batteries will not be able to provide stable energy for electric forklifts. Continued use will easily lead to economic losses. , and even lead to serious safety problems, and the current monitoring method for the health status of electric forklift lithium batteries has low accuracy and cannot meet the actual industrial needs

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
  • A method for predicting the health status of lithium-ion batteries in electric forklifts based on lstm-ffnn
  • A method for predicting the health status of lithium-ion batteries in electric forklifts based on lstm-ffnn
  • A method for predicting the health status of lithium-ion batteries in electric forklifts based on lstm-ffnn

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0062] Embodiment: A LSTM-FFNN-based method for predicting the state of health of an electric forklift lithium-ion battery in this embodiment, the flow chart is as follows figure 1 As shown, the specific steps are as follows:

[0063] S1: Establish a time-scale parameter prediction model based on LSTM to predict the change of the time-scale parameter open circuit voltage V during the discharge process, including the following steps:

[0064] S11: Set the number of neurons in the input layer of the neural network as L1, set the number of hidden layers of the neural network N1 and the number of neurons L2, and complete the process from the input space U M to the output space U T The mapping of , that is, predict the open circuit voltage at the subsequent time according to the open circuit voltage at the first m moments;

[0065] S12: Set the moving step size as l, decompose and reconstruct the time scale parameter open circuit voltage data, and establish the training sample V ...

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 mainly solves the problem that the prediction method in the prior art has a large amount of calculation and low accuracy of the prediction result; it provides a LSTM-FFNN-based electric forklift lithium-ion battery health state prediction method, which reduces the data required for training the model and improves the lithium ion battery state. The accuracy of battery state of health predictions. It includes the following steps: establishing a time-scale parameter prediction model based on LSTM to predict the change of the time-scale parameter open-circuit voltage V during the discharge process; extracting the cycle-scale parameter discharge time T from the open-circuit voltage V of the time-scale parameter prediction model to the minimum voltage min ; Establish a cycle-scale parameter prediction model based on FFNN to predict the lithium battery capacity C, thereby obtaining the predicted value SOH of the lithium battery state of health. Combining the prediction ability of LSTM for long-term series and the algorithm simplicity of FFNN, the prediction from time-scale parameters to cycle-scale parameters is realized, which reduces the data required for training the model and improves the accuracy of lithium battery health state prediction.

Description

technical field [0001] The invention relates to the technical field of batteries, in particular to a battery health state prediction method. Background technique [0002] Lithium-ion battery is a kind of rechargeable battery. The positive and negative electrodes are generally made of materials containing lithium elements. During the charge and discharge process, lithium ions are extracted from one electrode material, and then moved and embedded in the other electrode material. Lithium-ion batteries have been widely used in various fields due to their high operating voltage, long cycle life, high energy density, and low self-discharge rate. Under the continuous charge and discharge cycle, the material structure of the lithium-ion battery gradually changes under the condition of continuous intercalation and extraction of lithium ions, and more and more defects appear, and the electrochemical performance of the lithium-ion battery gradually declines. . Lithium-ion batteries c...

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 Patents(China)
IPC IPC(8): G01R31/392G01R31/367
CPCG01R31/367G01R31/392
Inventor 童哲铭苗嘉智
Owner ZHEJIANG UNIV
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