A Computer Vision-Based Automatic Elimination Method of Structural False Modal Parameters
A technology of computer vision and modal parameters, applied in computer parts, calculation, neural learning methods, etc., can solve problems such as low efficiency of manual selection, affecting real-time early warning of structural health monitoring system, difficulty in realizing online automatic analysis of structural modal, etc. , to achieve the effect of improving the level of intelligence and realizing automatic identification
Active Publication Date: 2022-04-05
HARBIN INST OF TECH
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention provides a computer vision-based method for automatically eliminating structural false modal parameters, which is used to solve the problem that the accurate result of modal parameter identification is mainly judged by humans. In the face of massive structural monitoring data, the manual selection method is inefficient and difficult to realize structural Modal online automatic analysis seriously affects the real-time early warning and other functions of the structural health monitoring system
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 2
[0064] The structural vibration response data of a bridge from May to September has been obtained. A total of 14 vertical vibration sensors are installed on this bridge, which are evenly distributed in pairs on 7 sections of the bridge. This calculation example plans to use the data in May and June to create a mode shape image data set, and finally realize the automatic identification of the first six vertical modal parameters of the bridge data in July, August, and September. The calculation process is as follows figure 2 shown.
[0065] Determine which modality needs to be recognized
[0066] First, it is necessary to analyze the bridge vibration response data in the frequency domain to determine the spectrum range of the mode to be identified. Such as image 3 As shown, from the power spectrum of bridge sensor vibration data, it can be found that the first few low-frequency modes have been included in the frequency domain range from 0 Hz to 0.5 Hz. Then, in order to ma...
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
Login to View More Abstract
The invention discloses a method for automatically eliminating structural false modal parameters based on computer vision. Use the existing data of the structure to be tested to draw the mode shape diagram; perform manual calibration according to the order of the false mode and the real mode and make it into a data set of the structure to be tested; use the data set of the structure to be tested to train the mode shape image classification Input the response signal of the structure to be tested into the modal parameter solver; get the recognition result of the real modal parameters and false modal parameters of the structure to be tested; carry out effective classification of each order; use the automatic classifier to realize Automatic classification of the modal parameters of the structure to be measured. The accurate results of modal parameter identification are mainly judged by humans. In the face of massive structural monitoring data, the manual selection method is inefficient, and it is difficult to realize the online automatic analysis of structural modal, which seriously affects the real-time early warning and other functions of the structural health monitoring system. question.
Description
technical field [0001] The invention relates to the fields of structural health monitoring and computer vision, in particular to a method for automatically eliminating structural false modal parameters based on computer vision. Background technique [0002] Major engineering structures will inevitably be damaged during service, and these damages will threaten the normal use and safety of the structure. Structural health monitoring can use the sensor network and data management and analysis equipment installed on the structure to establish an early warning network to realize real-time perception, identification and diagnosis of structural load, damage and safety status, and can effectively guarantee the service safety of building structures. [0003] Structural modal parameter identification is a classic inverse problem of structural dynamics. Structural modal parameters (frequency, mode shape and damping ratio) are identified through the input and output data of actual struc...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/44G06N3/045G06F2218/08G06F2218/12G06F18/241
Inventor 鲍跃全翟伟大刘大伟李惠
Owner HARBIN INST OF TECH