Valve-regulated lead-acid storage battery health state prediction method based on improved LSTM neural network

A lead-acid battery, neural network technology, applied in the field of artificial intelligence control of valve-regulated lead-acid batteries in substations, can solve problems such as excessive consumption and environmental pollution, achieve high accuracy, reduce dependence, and improve accuracy.

Active Publication Date: 2020-10-02
CHINA THREE GORGES UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this model has shortcomings in terms of excessive consumption and environmental pollution

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
  • Valve-regulated lead-acid storage battery health state prediction method based on improved LSTM neural network
  • Valve-regulated lead-acid storage battery health state prediction method based on improved LSTM neural network
  • Valve-regulated lead-acid storage battery health state prediction method based on improved LSTM neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0082] see figure 1 , LSTM-based network training, the specific contents include:

[0083] S11. Calculate the connection strength R of neuron i i (t). When the error between the model prediction value and the real value is less than the set threshold, the connection strength is calculated by formula (8).

[0084] S12, update the activation state S of the neuron in the iterative process according to formula (9) i (t+1). That is, neurons with higher connection strength have a greater probability of transitioning to an inactive state. In this way, the dependence of the LSTM prediction model on some input features is reduced.

[0085] see figure 2 , the network training of LSTM based on the Dropout optimization method, the specific contents include:

[0086] S21, LSTM network initialization. Given the number of input nodes m, the number of hidden nodes k, the number of output nodes n, the learning rate yita, and the error threshold σ, specify the dimensions of each weight...

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 valve-regulated lead-acid storage battery health state prediction method based on an improved LSTM neural network. The method comprises the steps: obtaining the floating charge voltage, the average charge current, the average charge duration, the discharge cut-off voltage and the discharge duration input data of a storage battery through daily measurement of an online monitoring device, the capacity of the storage battery being measured through check equalizing charge every two months; with n days being taken as a time span, establishing n-dimensional sample input x(ti); establishing a neural network model comprising a plurality of LSTM neural network units by taking a storage battery capacity data sequence h(ti) as output and the x(ti) as input; in an initial state, assigning a weight matrix W and an offset matrix b in the network by randomly generating a decimal between 0 and 1; and introducing a Dropout algorithm to improve the LSTM neural network model, and improving the training process of the LSTM neural network model. According to the method, the problems of over-low prediction precision and under-fitting caused by insufficient data samples can be reduced, the health state of the transformer substation storage battery is accurately predicted, and the utilization rate of the storage battery is improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence control of valve-regulated lead-acid batteries in substations, and in particular relates to a method for predicting the health state of valve-regulated lead-acid batteries based on an improved LSTM neural network. Background technique [0002] The valve-regulated lead-acid battery pack is the core of the DC power system, and its performance quality is related to the safe and stable operation of the entire substation. However, it is difficult to estimate the health status of substation batteries in actual operation. In order to improve the power supply reliability of the storage battery in an accident state. Because the sealed valve-regulated lead-acid battery has many advantages such as superior performance, simple maintenance, convenient installation, high reliability, and no pollution to the environment, it has many applications in the DC system of the substation. As a backup p...

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): G01R31/392G01R31/379G01R31/367G06N3/04G06N3/08
CPCG01R31/392G01R31/367G01R31/379G06N3/049G06N3/084G06N3/045Y02E60/10
Inventor 舒征宇黄志鹏许布哲沈佶源胡尧方曼琴温馨蕊徐西睿陈明欣
Owner CHINA THREE GORGES 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap