Modular five-level current converter fault locating method based on depth convolution network

A technology of deep convolution and fault location, applied in power supply testing, etc., can solve problems such as destructive short-circuit faults, distortion of voltage and current waveforms, and threats to normal operation of the system, to achieve stable operation and convenient decision-making, easy access, and strong MMC Effect of Fault Identification and Localization Capabilities

Active Publication Date: 2017-10-20
XIANGTAN UNIV
View PDF7 Cites 39 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Short-circuit faults are more destructive, so the sub-module drive circuit is generally equipped with a short-circuit protection module. When a short-circuit fault occurs, the sub-module is blocked locally to ensure that the system can still

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
  • Modular five-level current converter fault locating method based on depth convolution network
  • Modular five-level current converter fault locating method based on depth convolution network
  • Modular five-level current converter fault locating method based on depth convolution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0048] Such as figure 1 As shown, a fault location method for a modular five-level converter based on a deep convolutional network includes the following steps:

[0049] 1) select figure 2 The capacitor voltage in the three-phase five-level converter is used as a reference to obtain the capacitor voltage data in the 24 sub-modules in the three-phase five-level converter.

[0050] 2) Convert the original capacitance voltage data into a two-dimensional matrix form similar to an image through preprocessing, and scramble the data set samples for training and testing models. The specific steps are:

[0051] 2-1) For each group of simulation experiments, 24 capacitor voltage signal sequences in the modular five-level converter are selected to form a multi-channel sequence, and the multi-channel sequence is pre-calculated according to the Min-Max normaliza...

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 modular five-level current converter fault locating method based on a depth convolution network, and the method comprises the steps: combining capacitor voltage signals collected by submodules of a modular five-level current converter into a multi-channel sequence; carrying out the sampling of the multi-channel sequence, obtaining a data tape and carrying out the normalization processing, wherein the processed data tape is taken as a gray-scale map and serves as the input of a depth convolution network model; extracting the features of data through a plurality of intersected convolution layers and ponding layers in the depth convolution network model, transmitting a characteristic pattern of the last ponding layer to a full-connection layer for fusion, and achieving the fault classification through a softmax classifier, wherein different types are corresponding to fault submodules at different positions, thereby achieving the detection and position of a fault. According to the invention, the data needed by the method is easy to obtain, and there is no need of an additional sensor, thereby greatly reducing the cost. Moreover, the method is stronger in capabilities of MMC fault recognition and location.

Description

technical field [0001] The invention relates to the field of converter fault location, in particular to a method for fault location of a modular five-level converter based on a deep convolutional network. Background technique [0002] The flexible DC transmission system uses IGBT turn-off devices and high-frequency modulation technology, which overcomes many inherent defects of traditional DC transmission. The core part of the flexible DC transmission system is the converter at both ends of it, which plays the role of rectification and inverter. In the flexible DC transmission system that is actually put into engineering application, there are mainly three types of converters, namely two-level converters, three-level converters and modular multilevel converters (Modular Multilevel Converter, MMC), compared with the previous two converters, the modular multilevel converter can achieve different voltage and power requirements by changing the number of sub-modules in the circui...

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): G01R31/42
CPCG01R31/42
Inventor 段斌屈相帅尹桥宣沈梦君晏寅鑫
Owner XIANGTAN 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

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