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

SiC power tube online fault diagnosis method based on extreme learning machine

A technology of extreme learning machine and fault diagnosis, applied in neural learning methods, biological models, computer components, etc., can solve problems such as network complexity, and achieve the effect of simple network structure, fast learning speed, and few parameters

Pending Publication Date: 2021-02-05
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the ELM algorithm also has certain problems. The input weights and hidden layer thresholds in the ELM algorithm are randomly given. Usually, it is necessary to set more hidden layer nodes to achieve the ideal accuracy, but more hidden layer nodes The number will make the network more complex

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
  • SiC power tube online fault diagnosis method based on extreme learning machine
  • SiC power tube online fault diagnosis method based on extreme learning machine
  • SiC power tube online fault diagnosis method based on extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Attached below Figure 1-5 The technical solution of the present invention is described in detail.

[0025] The present invention designs a SiC power tube online fault diagnosis method based on the improved crow search algorithm to optimize the extreme learning machine. The basic structural principle of the converter composed of the SiC power tube is as follows figure 1 Shown (take the Buck circuit as an example). This converter includes a DC power supply, capacitors, inductors, resistors, diodes and SiC MOSFET switch tubes. It mainly relies on SiC MOSFETs to achieve voltage conversion and is widely used in aviation power supplies. The SiC MOSFET has a high failure rate in the harsh environment for a long time, and its various failure models are as follows: figure 2 shown.

[0026] An online fault diagnosis method for SiC power tubes based on the improved crow search algorithm to optimize the extreme learning machine, such as image 3 As shown, the specific operati...

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 SiC power tube online fault diagnosis method based on an extreme learning machine, and belongs to the field of aviation power supply state monitoring and diagnosis. Accordingto the invention, the input weight and the hidden layer threshold of the extreme learning machine are optimized by using the improved graffiti search algorithm, and the optimized extreme learning machine model is used in the aspect of SiC MOSFET fault diagnosis, so that local optimization and global optimization can be achieved, and the method is suitable for the field of SiC MOSFET fault diagnosis. According to the method, the defects that when the extreme learning machine is optimized through the chicken swarm algorithm, local optimum is likely to happen, and premature convergence occurs are overcome, and compared with an existing SiC MOSFET fault diagnosis method, the method has the advantages of being high in learning speed, few in artificially-set parameters, simple in network structure and the like.

Description

technical field [0001] The invention discloses an online fault diagnosis method for a SiC power tube based on an extreme learning machine, and belongs to the field of state monitoring and fault diagnosis of aviation power supplies. Background technique [0002] With the vigorous development of new fields of power electronics such as electric vehicles, multi-electric aircraft and new energy, higher requirements are put forward for the performance indicators of power electronic devices such as efficiency, high temperature resistance, and high voltage resistance. The switching tubes in power converters tend to use SiC MOSFETs with excellent performance such as high temperature resistance, high frequency and high blocking voltage to replace Si tube devices. Therefore, SiC power tubes are increasingly used in high frequency, high voltage, high efficiency and other fields. widely used. [0003] Because SiC MOSFETs work in harsh environments such as high temperature, high pressure...

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): G06F30/367G06F30/27G06N3/00G06N3/04G06N3/08G06K9/62
CPCG06F30/367G06F30/27G06N3/006G06N3/08G06N3/045G06F18/24
Inventor 崔江范士颖王莉
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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