Thyristor fault diagnosis method for series 12-pulse phase-controlled rectifier circuit

A technology of thyristor failure and phase-controlled rectification, which is applied in neural learning methods, measuring electricity, measuring electrical variables, etc., can solve the problems that the fault sample interval is not easy to change, easy to fall into local minimum points, and lack of flexibility, etc., to achieve reduction The effect of high calculation volume, fast diagnosis speed and high diagnosis accuracy

Inactive Publication Date: 2019-11-29
XI AN JIAOTONG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for diagnosing thyristor faults in series 12-pulse phase-controlled rectifier circuits to solve the problem of wavelet changes in the processing algorithm for periodic fault voltage signals in the prior art and for fault sample intervals in processing smooth signal algorithms Once established, it is difficult to change and lack of flexibility. The fault pattern recognition link overcomes the defects of weak generalization ability and easy to fall into local minimum points of neural network detection methods.

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
  • Thyristor fault diagnosis method for series 12-pulse phase-controlled rectifier circuit
  • Thyristor fault diagnosis method for series 12-pulse phase-controlled rectifier circuit
  • Thyristor fault diagnosis method for series 12-pulse phase-controlled rectifier circuit

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0044] first part:

[0045] Such as figure 1 As shown, a method for diagnosing thyristor faults in series 12-pulse phase-controlled rectification circuits provided by the present invention includes the following steps:

[0046] Step 1. Determine the number of thyristor fault types and states in the series-connected 12-pulse phase-controlled rectifier circuit: according to figure 2 The schematic diagram of the series 12-pulse phase-controlled rectifier circuit shown and the working principle of the rectifier circuit are used to classify the faults of the thyristors in actual operation. When a type of thyristor fails, VR i with VR j The fault voltage waveforms are the same, but the time axis is shifted, so they can be classified into one category. When two thyristors fail, VR i 、VR j Fault voltage waveform and VR i+n 、VR j+n The fault voltage ...

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 thyristor fault diagnosis method for a series 12-pulse phase-controlled rectifier circuit. The thyristor fault diagnosis method comprises the steps of 1, determining the number of thyristor fault state types in the series 12-pulse phase-controlled rectifier circuit; 2, extracting fault features by adopting a periodic and discretization method; 3, collecting a fault sample; 4, performing learning training on the sample by using a PNN network; 5, classifying the fault conditions; and 6, performing performance test on the fault of the actual circuit, and verifying the feasibility of the method. The design is novel, simple and feasible, the processing method for discrete sampling and normalization of the continuous periodic waveform has the advantages of high diagnosis precision, high diagnosis speed and simple steps; the signal processing link overcomes the defects that once a sample interval in wavelet change processing stationary signals is established, the sample interval is difficult to change and the flexibility is insufficient, and the fault mode link overcomes the defects that a neural network detection method is weak in normative ability and is easy to fall into local minimum points.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of power electronic devices, and in particular relates to a method for fault diagnosis of a thyristor of a series 12-pulse phase-controlled rectifier circuit. Background technique [0002] Power electronics technology is not only an important part of modern industrial systems, but also the key to the development of the electrical automation industry. Studying the faults of power electronic circuits is helpful for predicting, identifying, diagnosing and repairing the faults of various components in power electronics and electric drives, which is of great significance to the electric power industry and related industries. Power electronics fault diagnosis technology mainly includes fault test point selection, fault signal processing and feature extraction, fault classification and identification and other steps. Taking the rectifier circuit as an example, the fault diagnosis system generall...

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): G06N3/04G06N3/08G06K9/62G01R31/26
CPCG06N3/08G01R31/2601G06N3/047G06F18/24
Inventor 张丹丹路灿
Owner XI AN JIAOTONG 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