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

Vibration damper detection method based on deep learning algorithm

A technology of deep learning and detection methods, applied in neural learning methods, calculations, computer components, etc., can solve the problems of communication blind areas that cannot be monitored in real time, and achieve the effect of solving communication blind areas that cannot be monitored in real time and saving labor costs

Inactive Publication Date: 2021-06-04
HANGZHOU ELECTRIC EQUIP MFG
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of the above-mentioned background technology, and provide a method for detecting a shockproof hammer based on a deep learning algorithm. This method does not require personnel control, and has advantages in terms of safety and cost. There are defects that the technology cannot monitor in real time in the communication blind area

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
  • Vibration damper detection method based on deep learning algorithm
  • Vibration damper detection method based on deep learning algorithm
  • Vibration damper detection method based on deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] 1) Collect pictures and video data of anti-vibration hammers from multiple angles (such as Figure 7 shown), added to the data set;

[0058] 2) Preprocess the collected images to generate similar images (see Figure 8 ; Figure 8 Middle: Figure a is the original image, Figure B is the image after adding Gaussian noise, and Figure c is the image after adding salt and pepper noise), expanding the data set;

[0059] 3) Use an image labeling tool such as labelImg to label the target detection object (such as Figure 9 shown):

[0060] 4) Input the calibrated simulation data set into the MobileNet V3 network to extract features

[0061] Specifically, by modifying the MobileNet network, for the input image size of 416×416, the dimensions of the final output feature map are 13×13, 26×26, 52×52, corresponding to the input image of 13×13, 26× 26, 52×52 grids, each grid predicts a variety of boxes (boxes) size, each box (box) contains 4 coordinate values, 1 confidence level ...

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 relates to a detection method of an electrical apparatus. According to the technical scheme, the shockproof hammer detection method based on the deep learning algorithm comprises the following steps: 1, collecting video data containing a shockproof hammer, and taking images frame by frame to generate a data set; searching related images through a network, and adding the images into a data set; 2, preprocessing the collected data, and expanding the data to generate similar images; 3, marking the vibration damper in the collected data set to obtain coordinates of a candidate frame containing a target object; 4, marking the preprocessed data set, inputting the marked data set into a MobileNet V3 network, and extracting feature maps of three dimensions after network processing; 5, inputting the feature map into a Yolo V3 module for training; inputting the trained optimal neural network model parameters into the line patrol robot; and 6, enabling the line patrol robot to detect the stockbridge damper on the power transmission line. The method is good in safety and low in cost.

Description

technical field [0001] The invention relates to a detection method of electric equipment, in particular to a detection method of a power transmission line anti-vibration hammer. Background technique [0002] Transmission lines are an important part of the power system, responsible for the long-distance transmission of electrical energy. Under the influence of strong wind, the wires vibrate violently and bend frequently for a long time, which causes fatigue damage to the wires and poses a serious safety hazard. At present, the main method to reduce the frequency of wire vibration caused by wind is to use fittings. Anti-vibration hammer is one of the important anti-vibration components of high-voltage cables. Utilizing the inertia of the anti-vibration hammer head, it consumes the vibration energy transmitted to the conductor through the wind, and reduces the vibration damage of the overhead transmission line. Transmission lines are located in different regions and climates...

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): G06K9/00G06K9/36G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06V20/10G06V10/20G06V10/40G06V2201/07G06F18/22G06F18/24G06F18/214
Inventor 陈建新张欣俞曙江李蒙
Owner HANGZHOU ELECTRIC EQUIP MFG
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