Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Street lamp life prediction method based on wavelet packet-GRU neural network

A neural network, -GRU technology, applied in the field of street lamp life prediction, can solve problems such as affecting the driver's line of sight, hidden dangers, and affecting the appearance of the city.

Inactive Publication Date: 2022-01-11
JIANGSU HENGPENG ELECTRIC GRP CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] With the sharp increase in the number of street lamps, the maintenance of street lamps has attracted more and more attention. Damaged street lamps not only affect the appearance of the city, but also cause great safety hazards.
When the street lights are damaged, the dark road environment greatly affects the driver's sight and leads to road safety accidents

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
  • Street lamp life prediction method based on wavelet packet-GRU neural network
  • Street lamp life prediction method based on wavelet packet-GRU neural network
  • Street lamp life prediction method based on wavelet packet-GRU neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0052] Such as Figure 1-3 As shown, a street lamp life prediction method based on wavelet packet-GRU neural network includes the following steps:

[0053] Step 1: Obtain the parameters such as street lamp voltage, current, brightness and the life of the street lamp, calculate the Pearson correlation coefficient between different parameters and the life of the street lamp, and select the parameters with high correlation as the input data; in the first step, through the following formula Calculate the Pearson correlation coefficient Relation between the parameter data series of parameter a and the data series of life h a :

[0054]

[0055] Where n represents the total length of the street lamp life data sequence, D at and D ht Represents the value of parameter a and street lamp life h in the tth time period, is the average o...

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 street lamp life prediction method based on a wavelet packet-GRU neural network, and the method comprises the following steps: 1, obtaining the voltage, current, brightness and other parameters of a street lamp and the life of the street lamp, calculating a Pearson's correlation coefficient, and selecting the input data with higher correlation; 2, performing Z-score standardization processing on the input data; 3, constructing a street lamp life prediction model; and 4, predicting the life of the street lamp by using the constructed street lamp life prediction model. The street lamp life prediction model based on the wavelet packet-GRU neural network is used for performing high and low frequency decomposition on input data according to frequency bands through the wavelet packet, noise can be effectively filtered, local analysis can be more effectively performed on the input data, then the time correlation of the sequence is analyzed through the GRU neural network, the residual life of the street lamp is effectively predicted, so that a user manager can replace the street lamp to be damaged in advance, and various negative consequences caused by damage of the street lamp are effectively avoided.

Description

technical field [0001] The invention relates to a street lamp life prediction method based on a wavelet packet-GRU neural network, which belongs to the technical field of street lamp life prediction. Background technique [0002] With the continuous development of the urbanization process, urban roads, as the "blood" of the city, are also flourishing. As a necessary road lighting tool, street lamps play an important role in the process of urbanization. Street lights can not only improve driving conditions at night, but also reduce the probability of traffic accidents, improve people's sense of security, and provide a beautiful landscape for the city at night. [0003] With the sharp increase in the number of street lamps, the maintenance of street lamps has attracted more and more attention. Damaged street lamps not only affect the appearance of the city, but also cause great safety hazards. When the street lights are damaged, the dark road environment greatly affects the...

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
IPC IPC(8): G06Q10/04G06N3/04G06N3/08G06K9/62
CPCG06Q10/04G06N3/084G06N3/048G06N3/044G06F18/214
Inventor 武军权袁伶金伟民陈海荣包银鑫陈震王亮施冬冬顾理琴
Owner JIANGSU HENGPENG ELECTRIC GRP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products