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

Method of temporary temperature calculation method based on BP neural network

A BP neural network and cable conductor technology, applied in the field of transient temperature calculation of three-core cable conductors, can solve problems such as lack of research, and achieve the effect of convenient and fast calculation

Inactive Publication Date: 2018-07-20
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the above methods are applied to the calculation of the transient temperature of the single-core cable conductor, but the research on the calculation of the transient temperature of the three-core cable conductor is relatively scarce

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 of temporary temperature calculation method based on BP neural network
  • Method of temporary temperature calculation method based on BP neural network
  • Method of temporary temperature calculation method based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] Such asfigure 1 As shown, the calculation method of transient temperature of three-core cable conductor based on BP neural network includes the following steps:

[0040] Step 1. Selection of training samples; selection of ampacity experimental data, including cable conductor current, cable sheath temperature and cable conductor temperature;

[0041] Step 2, network training; electrify the cable conductors in the training sample in step 1; use the particle swarm optimization algorithm to perform a primary optimization, and then use the BP algorithm to perform a secondary optimization method to train the network;

[0042] Taking the cable conductor current, the cable sheath temperature as input, and the cable conductor temperature as output, a neural network is constructed. This neural network is a 2-8-8-1 four-layer BP neural network. Its topology is as follows: figure 2 shown.

[0043] Set the number of particles in the particle swarm m=40, initialize the particle swa...

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 computing the transient state temperature of a three-core cable conductor on the basis of a BP neural network. The method comprises the following steps of (1) selecting training samples, wherein carrying capacity data are selected, the carrying capacity data comprise cable conductor currents, cable sheath temperature and cable conductor temperature; (2) training the network, wherein the four-layer BP neural network is established, primary optimization is first carried out by utilizing a particle swarm algorithm, and then secondary optimization is carried out by utilizing a BP algorithm to enable the network to be trained; (3) computing the transient state temperature of the cable conductor, wherein the real-time collected cable conductor currents and the real-time collected cable sheath temperature are input into the network trained in the step (2), and the cable conductor temperature can be figured out. The method for computing the transient state temperature of the three-core cable conductor on the basis of the BP neural network has the advantages that the cable conductor temperature can be computed accurately and dynamically without taking the physical property parameters of a cable into consideration.

Description

technical field [0001] The invention relates to a technique for calculating the transient temperature of a three-core cable conductor, in particular to a calculation method for the transient temperature of a three-core cable conductor based on a BP neural network. Background technique [0002] The current carrying capacity is the maximum current that the cable can transmit under continuous load, and it is an important parameter for cable operation. Under the action of this current, the working temperature of the wire core reaches but does not exceed the long-term heat-resistant temperature of the main insulation of the cable (XLPE is 90°C), so as to ensure the life of the cable. If the current carrying capacity is too large and the working temperature of the core exceeds the allowable value, the life of the cable will be greatly shortened than the expected life. If the ampacity is too small, but the copper or aluminum of the cable core is not fully utilized. Therefore, as ...

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): G06N3/02
Inventor 牛海清吴炬卓叶开发
Owner SOUTH CHINA UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com