Real-time Calculation Method of Three-core Cable Conductor Temperature Based on RBF Neural Network

A three-core cable and neural network technology, applied in the field of three-core cable running state monitoring, can solve the problems of long calculation process, complicated modeling process by finite element method, and difficulty in meeting engineering requirements, and achieve excellent search for optimal solutions. Ability, training and learning speed, the effect of strong nonlinear mapping ability

Inactive Publication Date: 2019-01-25
HOHAI UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although a very mature calculation model has been established in the traditional method, the above-mentioned methods have certain limitations. The transient thermal circuit model is established under many idealized conditions, and it is difficult to meet the engineering requirements in practical applications. The modeling process of the method is complex, and the calculation process takes a long time
In the existing technical literature, the research on the real-time temperature calculation method of the above-mentioned cable conductor is based on the high-voltage single-core cable, but the research on the real-time temperature calculation method of the three-core cable conductor is rarely involved.

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
  • Real-time Calculation Method of Three-core Cable Conductor Temperature Based on RBF Neural Network
  • Real-time Calculation Method of Three-core Cable Conductor Temperature Based on RBF Neural Network
  • Real-time Calculation Method of Three-core Cable Conductor Temperature Based on RBF Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Embodiments of the invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0032] Such as figure 1 Shown, the three-core cable conductor temperature real-time calculation method based on RBF neural network provided by the present invention comprises the following steps:

[0033] Step 1. Measure the operating data of some parameters of the three-core cable, including the operating current of the three-core cable conductor, the real-time temperature of the outer skin of the cable, and the real-time temperature of the cable conductor.

[0034] Step 2, take the three-core cable conductor current, the cable outer skin temperature as input, and the cable conductor real-time temperature as output, and establish a three-layer feedforward RBF neural ne...

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 real-time calculation of the temperature of a three-core cable conductor based on an RBF neural network. The method first measures the operating data of some parameters of the three-core cable, including the operating current of the three-core cable conductor, the real-time temperature of the outer skin of the cable, and the real-time temperature of the cable conductor; Then, the current of the three-core cable conductor and the temperature of the outer skin of the cable are used as input, and the real-time temperature of the cable conductor is used as the output to establish a three-layer feed-forward RBF neural network model; As a learning algorithm, train and determine the RBF neural network model with better performance; finally, input the real-time collected three-core cable conductor current and cable outer skin temperature into the trained RBF network, and then calculate and output the real-time temperature of the three-core cable conductor . The method of the invention can not be affected by the external complex environment and the physical parameters of the cable itself, and has the advantages of accurately and dynamically calculating the temperature of the conductor of the three-core cable.

Description

technical field [0001] The invention relates to a method for real-time calculation of the temperature of a three-core cable conductor based on an RBF neural network, and belongs to the technical field of three-core cable operation state monitoring. Background technique [0002] Ampacity is an important parameter of power cables. It refers to the long-term working temperature of the insulating layer that does not exceed the maximum operating current corresponding to the rated value. Accurate calculation and evaluation of ampacity are crucial to the safe operation of power cables and short-term expansion It has important engineering significance. The life of the cable mainly depends on the life of its insulation layer, and the conductor core temperature during the operation of the cable is the decisive factor affecting the life of the insulation material. For cables with different insulation materials, the allowable operating temperature is clearly stipulated. Under normal ov...

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): G06F17/50G06N3/04
CPCG16Z99/00G06N3/044
Inventor 马宏忠付明星施恂山许洪华刘宝稳
Owner HOHAI 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