A Fault Diagnosis Method for Heating System of Drying Room Based on Extension Neural Network

A heating system and fault diagnosis technology, applied in the direction of biological neural network model, etc., can solve the problem of inability to effectively diagnose the fault of the heating system of the drying room

Active Publication Date: 2016-09-14
HUAWEI TEHCHNOLOGIES CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the deficiency that the existing automobile painting line cannot effectively diagnose the failure of the heating system of the drying room, the present invention makes full use of the characteristics of qualitative and quantitative description methods of extenics to deal with the characteristics of structured knowledge and combines the characteristics of the parallel structure of the neural network to make the neural network The network completes the extension reasoning process with the help of the parallel distributed processing structure, and realizes the fault diagnosis function of the drying room heating system of the coating line

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 Fault Diagnosis Method for Heating System of Drying Room Based on Extension Neural Network
  • A Fault Diagnosis Method for Heating System of Drying Room Based on Extension Neural Network
  • A Fault Diagnosis Method for Heating System of Drying Room Based on Extension Neural Network

Examples

Experimental program
Comparison scheme
Effect test

example

[0101] Example: The fault diagnosis method of the drying room heating system based on the extension neural network, including the following process:

[0102] 1) Establishment of extension neural network model of drying room heating system

[0103] According to the empirical formula, the number of hidden layer nodes m is determined, and the value is between 1 and 10. In this experiment, m=10, and the extension neural network model of the drying room heating system is constructed as attached Figure 4 .

[0104] 2), model training

[0105] After the network model is established, a large amount of sufficient training is carried out on it, and the neuron activation functions are all logarithmic Sigmoid functions.

[0106] The specific training steps are as follows:

[0107] 1) Let the number of network iterations t=0, Δ (0) ji =0.1, η + =1.2, η - =0.5, and set the training target g and the maximum number of iterations e;

[0108] 2) Calculate the first-order partial deriva...

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

A fault diagnosis method for drying room heating system based on extension neural network, which uses the qualitative and quantitative description of extension to deal with the characteristics of structured knowledge and combines the characteristics of parallel structure of neural network, so that the neural network can complete the possible Extend the reasoning process. First, according to the monitoring parameters and fault types of the heating system equipment in the drying room, a matter-element input and output model based on the extension neural network is established; then the sample parameters are fully trained, and the extension distance of the output eigenvalue is calculated. distance and preset equipment safety intervals to realize equipment fault diagnosis function.

Description

technical field [0001] The invention relates to the field of fault diagnosis of electromechanical equipment, in particular to a fault diagnosis method for a heating system of a drying room. technical background [0002] Automobile painting line is composed of pretreatment system, electrophoresis system, drying room system, etc. It is an uncertain, complicated and changeable object. Reliable and accurate monitoring of the coating line and timely early warning and diagnosis of potential faults are the basic conditions to ensure the stable operation of various system equipment. In the prior art, it is impossible to effectively diagnose the failure of the drying room heating system. Contents of the invention [0003] In order to overcome the deficiency that the existing automobile painting line cannot effectively diagnose the failure of the heating system of the drying room, the present invention makes full use of the characteristics of qualitative and quantitative descriptio...

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 叶永伟任设东叶连强钱志勤葛沈浩
Owner HUAWEI TEHCHNOLOGIES CO LTD
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