Automatic bridge bolt come-off identification method based on neural network
A neural network and automatic identification technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as not allowing maintenance personnel to go on the bridge for inspection, maintenance personnel are difficult to reach, and the number of bolts is large, etc., to achieve The effect of reducing maintenance costs, reducing input costs, and improving recognition accuracy
Inactive Publication Date: 2016-09-07
CHINA MAJOR BRIDGE ENERGINEERING +1
View PDF4 Cites 16 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] At present, my country's long-span bridge business is developing rapidly, and the number of bridges is increasing, so the safety of bridges is becoming more and more important. The bolts on the bridge play a key role in the entire structure of the bridge. In order to maintain the safety of the bridge, it is necessary Regularly check the bolts on the bridge to determine whether they have fallen off, but the number of bolts on the entire bridge is large, and some positions are difficult for maintenance personnel to reach, so it is difficult to overhaul, especially for high-speed rail bridges. Maintenance personnel are not allowed to go to the bridge for inspection at all, and the light is poor at night, making it difficult to clearly inspect the bolts
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 Construction
[0032] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0033] see figure 1 As shown, the present invention provides a method for automatic identification of bridge bolts falling off based on neural network, which is used to monitor the bolts on the bridge and judge whether they fall off. The method specifically includes the following steps:
[0034] Step S1: System construction: install several cameras on the bridge, and connect the cameras to the server of the monitoring center at the same time;
[0035] Step S2: Area division and marking: manually divide the bridge into multiple monitoring areas, each monitoring area has one or more bolts, each camera is responsible for monitoring one or more monitoring areas, and then in each monitoring area Post a black and white positioning mark in the shape of "back" horizontally. The middle of the positioning mark is black, and then manually record the monitoring area tha...
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 an automatic bridge bolt come-off identification method based on the neural network, and relates to the bridge monitoring field. The method comprises the steps that S1) a bridge is provided with cameras, and the cameras are connected with a server of a monitoring center; S2) the bridge is divided into multiple monitoring areas; S3) the cameras collect images, in which bolts are complete and come off, in the monitoring areas, and transmit the images to the server; S4) a neural network model is established, and the images collected in the S3) are used to train the neural network; S5) the cameras collect images each area and transmit the images to the server; and S6) the neural network identifies images of the step S5) to determine whether a bolt comes off. The method of the invention can be used to monitor bridge bolts accurately and conveniently.
Description
technical field [0001] The invention relates to the field of bridge monitoring, in particular to a neural network-based automatic identification method for bridge bolt shedding. Background technique [0002] At present, my country's long-span bridge business is developing rapidly, and the number of bridges is increasing, so the safety of bridges is becoming more and more important. The bolts on the bridge play a key role in the entire structure of the bridge. In order to maintain the safety of the bridge, it is necessary Regularly check the bolts on the bridge to determine whether they have fallen off, but the number of bolts on the entire bridge is large, and some positions are difficult for maintenance personnel to reach, so it is difficult to overhaul, especially for high-speed rail bridges. On the ground, the maintenance personnel are not allowed to go to the bridge for inspection at all, and the light is poor at night, so it is difficult to clearly inspect the bolts. Co...
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 Applications(China)
IPC IPC(8): G06K9/00G06N3/08H04N7/18
CPCH04N7/181G06N3/08G06V20/20
Inventor 刘有桥赵大成戴新军简珍珍陈斌王翔金昌根吴来义岳青
Owner CHINA MAJOR BRIDGE ENERGINEERING