Rotating body vibration displacement measurement method and system based on lightweight neural network

A technology of vibration displacement and neural network, which is applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as limited sampling constraints, and achieve short-term amnesia avoidance, high fitting degree, and enhanced displacement correlation Effect

Pending Publication Date: 2022-05-27
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the traditional visual vibration measurement method, limited by the inherent sampling constraints of ordinary image sensors, it is impossible to achieve efficient vibration target recognition and correlation tracking for rotating targets in low-resolution videos under the premise of high sampling rates

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
  • Rotating body vibration displacement measurement method and system based on lightweight neural network
  • Rotating body vibration displacement measurement method and system based on lightweight neural network
  • Rotating body vibration displacement measurement method and system based on lightweight neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Example 1: as Figure 1-11 As shown in the figure, a method for measuring vibration displacement of a rotating body based on a lightweight neural network includes: step 1, collecting image data of the rotating body and eddy current data; step 2, labeling the image data of the rotating body to obtain a training data set and a test Data set; Step 3, build a lightweight convolutional neural network model; Step 4, use the training data set to train the model, and obtain a series of weight files to be selected; Step 5, use the test data set to test the weight files to be selected and compare the eddy current data , filter to obtain the optimal weight parameters; step 6, load the optimal weight parameters into the lightweight convolutional neural network model to obtain a frozen model; step 7, input the video data to be detected into the frozen model for detection, and obtain multi-frame target detection results ; Step 8, correlate the multi-frame detection results through th...

Embodiment 2

[0090] Example 2: as Figure 1-11 As shown, an optional specific manner of the present invention will be described in detail below. A method for measuring vibration displacement of a rotating body based on a lightweight neural network, comprising: step 1, synchronously collecting image data of the rotating body and eddy current data; step 2, labeling the collected image data of the rotating body to obtain training data sets and test data step 3, build a lightweight convolutional neural network model; step 4, use the training data set to train the model to obtain a series of weight files to be selected; step 5, use the test data set to test the weight files to be selected and compare the eddy current data, Screen to obtain the optimal weight parameters; step 6, load the optimal weight parameters into the lightweight convolutional neural network model, and use PyTorch to obtain the frozen model; step 7, input the video data to be detected into the frozen model for detection, and...

Embodiment 3

[0133] Embodiment 3: A system for measuring vibration and displacement of a rotating body based on a lightweight neural network, comprising: a collection module for collecting image data of the rotating body and eddy current data; a first obtaining module for labeling the image data of the rotating body , to obtain the training data set and test data set; the model building module is used to build a lightweight convolutional neural network model; the second obtaining module is used to train the model using the training data set and obtain a series of weight files to be selected; the screening module, Use the test data set to test the weight file to be selected and compare the eddy current data to obtain the optimal weight parameter; the third obtaining module is used to load the optimal weight parameter into the lightweight convolutional neural network model to obtain the frozen model; The fourth obtaining module is used for inputting the video data to be detected into the frozen...

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 rotator vibration displacement measurement method and system based on a lightweight neural network. The method comprises the following steps: collecting rotator image data and eddy current data; marking the image data of the rotating body to obtain a training data set and a test data set; building a lightweight convolutional neural network model; training the model by using the training data set to obtain a series of to-be-selected weight files; testing the to-be-selected weight file by using the test data set, comparing the eddy current data, and screening to obtain an optimal weight parameter; loading the optimal weight parameter into the lightweight convolutional neural network model to obtain a frozen model; inputting to-be-detected video data into the freezing model for detection to obtain a multi-frame target detection result; associating multiple frames of detection results through a target tracking branch to obtain rotator displacement data; and performing normalization processing on the obtained displacement data of the rotating body to obtain a vibration displacement curve of the rotating body. The method can be used for measuring the vibration displacement of the rotating body in a video.

Description

technical field [0001] The invention relates to a method and system for measuring vibration displacement of a rotating body based on a lightweight neural network, belonging to the fields of artificial intelligence vibration detection and computer vision tracking. . Background technique [0002] Vibration displacement field measurement of precision components such as rotating bodies, as a necessary means of early health monitoring, can effectively diagnose the service life, fault types and dynamic balance characteristics of mechanical structures such as shafts, bearings and rotors. At present, the displacement measurement of the structure mainly includes contact measurement and non-contact measurement, but the contact type displacement measurement method of acceleration sensor cannot be installed on the body because it is limited by the state characteristics of rotational motion. [0003] As a long-distance, non-contact, non-destructive displacement measurement method, visua...

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): G06T7/246G06T7/70G06N3/04G06N3/08
CPCG06T7/246G06T7/70G06N3/084G06T2207/30204G06N3/045
Inventor 王森柴尚磊杨荣良伍星柳小勤王庆健林森
Owner KUNMING 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