System and method for intelligently detecting duct piece splicing quality based on image identification

Abstract

The invention discloses a system and a method for intelligently detecting duct piece splicing quality based on image identification. The detection system comprises an identifier, an image acquisition device, an image processing system and a display device. The method comprises the following steps of: drawing a duct piece slab staggering amount control model according to the inner diameter of each duct piece and a slab staggering allowed deviation; binding the control model with a specified identifier in the system, and correctly identifying the identifier to correspondingly load the model; fixing the specific identifier on a contact between adjacent duct pieces, and acquiring the size of the identifier and the distance between adjacent duct piece contacts; arranging a camera on site, and acquiring an image which comprises the identifier and a duct piece entity simultaneously by using the camera; receiving the acquired image by using the image processing system, running a program, forming an image formed by overlapping the duct piece entity and the duct piece slab staggering amount control model, and inputting the image into display equipment; and intelligently judging whether the slab staggering amount of adjacent duct pieces is consistent with specification requirements or not according to an overlapped image provided by the display equipment.

Description

technical field [0001] The invention relates to a subway shield segment detection technology, in particular to an image recognition-based intelligent detection system and a detection method for segment assembly quality. The image of the segment entity is obtained by the camera, superimposed and compared with the virtual segment model, and the intelligent detection of the segment assembly quality is realized. Background technique [0002] Shield construction technology is widely used in subways, large-scale water diversion projects, and urban municipal construction because of its safety, efficiency, and ability to traverse complex strata. Compared with traditional subway construction methods (such as open-cut method, cover-excavation method, shallow burial and underground excavation method, etc.), the shield method has the advantages of safety, high speed, no influence on ground traffic, and is not affected by climate conditions and is applicable to various It is an effectiv...

AI Technical Summary

Problems solved by technology

None of the above detection methods can meet the requirements of real-time monitoring of the safety status of subway shield segments

Generally speaking, deflection correction control of the shield posture is required at small-radius tunnels during shield construction. Moderate over-excavation or under-excavation is often performed, which is prone to a large number of misalignments, which can easily cause segment damage, cracking, and even leakage. Accidents such as water gushing and sand gushing

In addition, after the tunnel segment structure is assembled, due to the long-term effects of soil loss and creep behind the wall, different degrees of segment misalignment will occur, and even large-scale uneven longitudinal settlement will occur.

With the traditional detection method, it is only possible to find the unsafe state of the shield segment when the subway safety inspection personnel conduct safety inspections, and it is easy to miss the best time to find potential safety hazards

If the method of increasing the frequency of detection is adopted to eliminate the disadvantages of poor real-time performance of the existing mis-station detection, it will lead to the consequence of a substantial increase in detection costs

In addition, the shield segment is a large-scale component. In actual engineering, the diameter of the shield is usually about 6m. If the traditional measuring method or visual inspection method is used during the construction process, it is difficult to detect the difference between the upper segment.

Images