Fault diagnosis system for transformer winding based on correlation dimension and random forest

A fault diagnosis system and technology for transformer windings, which are applied in electrical winding testing, instruments, and measurement of electrical variables, etc., can solve the problem of not being able to find potential transformer faults in real time, and achieve the effect of remote real-time monitoring and automatic diagnosis.

Pending Publication Date: 2018-11-23
ANHUI UNIV OF SCI & TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional methods for detecting transformer winding faults include: frequency response method, low-voltage pulse method, short-circuit impedance method, etc. However, the above methods can only be measured offline, and cannot detect potential faults in transformer operation in real time online

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
  • Fault diagnosis system for transformer winding based on correlation dimension and random forest
  • Fault diagnosis system for transformer winding based on correlation dimension and random forest
  • Fault diagnosis system for transformer winding based on correlation dimension and random forest

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] The transformer winding fault diagnosis system on which the present invention is based is as follows: figure 1 As shown, the system uses STM32 microcontroller as the control core to form a signal acquisition and uploading circuit. The three sensors use piezoelectric acceleration sensors that convert vibration signals into 4-20mA current signals. The current signals from the sensors pass through the I / V conversion circuit. Convert to 0-3.3V voltage signal. Since the vibration frequency range of the transformer winding is 10-2000Hz, the signal filter circuit is designed as a band-pass filter of 10-2000Hz. In order to ensure the accuracy of the signal, the signal acquisition part is composed of 16-bit ADC. The power supply part is realized by 5V and 3.3V regulator chips. The NB-IOT circuit is realized by the BC95 chip. The NB-IOT circuit communicates with the microcontroller through the serial port, and the collected data is connected to the Ethernet through the base sta...

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 fault diagnosis system for a transformer winding based on a correlation dimension and a random forest. The system employs an STM32 single-chip microcomputer as a control coreto form a signal collection uploading circuit, and the single-chip microcomputer collects a converted and filtered winding vibration signal, and then the signal is uploaded to an upper computer through an NB-IOT network. The upper computer carries out the phase space reconstruction of a signal sequence through programmed software, and calculates a feature quantity: the correlation dimension. Afterwards, the correlation dimension is taken as the characteristic, and a random forest model is used for recognizing the fault and non-fault windings. The system achieves the mining of the features ofthe vibration signal of the winding in a high-dimensional space, employs the random forest for diagnosis, can improve the recognition accuracy of the fault winding, and achieves the automatic online state monitoring of the transformer winding through the NB-IOT network.

Description

technical field [0001] The invention relates to the technical field of transformer fault diagnosis, in particular to a transformer winding fault diagnosis system based on correlation dimension and random forest. Background technique [0002] Transformer is an important component in the power system, which plays a vital role in the safe and reliable operation of the power grid. The characteristics of the transformer winding directly affect the short-circuit resistance of the transformer. According to statistics, transformer faults caused by winding deformation account for about 25% of the total faults. Therefore, monitoring the performance of transformer windings and diagnosing its fault status can detect potential faults in time, prevent sudden transformer accidents, and improve the safety, reliability and economy of transformer operation. [0003] Transformer winding faults mainly include radial and axial tension and compression faults, axial nesting faults, winding torsi...

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 Applications(China)
IPC IPC(8): G01R31/06
CPCG01R31/72
Inventor 宋晓
Owner ANHUI UNIV OF SCI & TECH
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