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

An Arc Recognition Method Based on Improved Alexnet

A recognition method and arc-burning technology, applied in the field of image recognition, can solve the problems of many parameters and low training efficiency, and achieve the effect of high recognition accuracy, deep network structure and reducing the number of parameters

Active Publication Date: 2022-03-25
CHENGDU NAT RAILWAYS ELECTRICAL EQUIP
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] AlexNet is a classic that was proposed in 2012 and achieved the best results in ImageNet that year, but the traditional AlexNet model has too many parameters and the training efficiency is low. This invention proposes an improved AlexNet model and applies it to Identification of catenary arcing

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
  • An Arc Recognition Method Based on Improved Alexnet
  • An Arc Recognition Method Based on Improved Alexnet
  • An Arc Recognition Method Based on Improved Alexnet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to have a clearer understanding of the technical features, objects and effects of the present invention, the specific embodiments of the present invention will now be described with reference to the accompanying drawings.

[0030] like figure 1 As shown, an arc identification method based on improved AlexNet, the method is applied to arc identification but is not limited to arc identification, including the following steps:

[0031] S1. Establish a convolutional neural network and obtain a training model;

[0032] S2. Get an image;

[0033] S3. Input the collected images into the training model for arc recognition;

[0034] Further, step S1 includes:

[0035] S11. Establish a convolutional neural network and initialize it;

[0036] S12. Extract images from the server storing image data and perform preprocessing, including cropping, compression, de-averaging, and normalization;

[0037] S13. Add a label to each image. The image that contains arcs is rated a...

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 an arc burning recognition method based on improved AlexNet, comprising the following steps: S1. Establishing a convolutional neural network and obtaining a training model; S2. Obtaining an image; S3. Inputting the obtained image into the training model for image recognition; The convolutional neural network is an improved AlexNet network. The structure of the improved AlexNet network is an input layer, multiple sequentially connected convolutional layers, a fully connected layer, and an output layer; the convolutional layer connected to the input layer adopts M×M Convolution kernel architecture, and the remaining convolution layers use 1×M and M×1 convolution kernel architectures; the present invention uses 1×M and M×1 size convolution kernels in series to replace the M×M size volume in the original AlexNet network The accumulation kernel greatly reduces the number of parameters, and adds a non-linear layer to make the network structure deeper; simplifies the model, greatly shortens the training time, improves the training efficiency, and the recognition accuracy is higher than the original AlexNet network.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to an arc recognition method based on improved AlexNet. Background technique [0002] The arc of the railway catenary is caused by the galloping of the catenary, the bouncing of the pantograph, and the ionization of the air into a conductor due to the voltage exceeding the endurance of the air. Intermittent, causing abnormal deceleration and acceleration during train operation, increasing the discomfort during the journey. Through the arc alarm, the faulty contact line or pantograph can be repaired in time, reducing the risk of railway power supply safety accidents. occurs; after the arc alarm is transmitted back to the data terminal, it needs to be confirmed by manual interpretation. If the false alarm rate is too high, it will cost a lot of labor costs, and if the false alarm rate is too high, it will increase the probability of accidents. Therefore, , Effectively identifying the...

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): G06V20/10G06N3/04G06N3/08
CPCG06N3/084G06V20/10G06N3/045
Inventor 范国海张娜何洪伟何进
Owner CHENGDU NAT RAILWAYS ELECTRICAL EQUIP
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