Steel-concrete combined section disease monitoring method, device, equipment and medium

Abstract

The invention provides a steel-concrete combined section disease monitoring method, device and equipment and a medium, and relates to the technical field of bridge engineering.The method comprises the steps that reflected signal data of a steel-concrete combined section is obtained through electromagnetic detection, and a slice two-dimensional image of an internal structure of the steel-concrete combined section is constructed according to the reflected signal data; performing target identification segmentation on the slice two-dimensional image by adopting a pre-trained model to obtain a monitoring target image; and processing different monitoring target images to obtain displacement monitoring information, steel bar slippage and deformation information and void area volume information, thereby obtaining steel-concrete combined section disease information. According to the method, internal structure information of the steel-concrete combined section is obtained through electromagnetic detection, one-dimensional signals are superposed to generate a two-way two-dimensional profile map, and a detection target is recognized and analyzed through the two-dimensional profile map, so that whether the steel-concrete contact surface is separated or not, whether void exists or not and whether interface slippage exists or not are continuously monitored.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge engineering, and in particular, to a method, device, equipment and medium for monitoring diseases of a steel-concrete composite section. Background Art

[0002] The composite structure technology plays an important role in improving the mechanical properties of main girders and bridge towers. The hybrid girder joint section of a cable-stayed bridge utilizes the composite structure technology to achieve the structural transition and load transfer between the steel girder and the concrete girder. The steel-concrete composite section combines the advantages of steel box girders and concrete box girders. By taking advantage of the relatively small self-weight and high strength of the steel box girder, the span of the bridge can be increased. At the same time, by taking advantage of the large self-weight of concrete, the dead and live load effects of the main span can be balanced. This combination not only improves the stiffness and strength of the bridge structure, but also saves materials and reduces the project cost, having high technical value and economic benefits.

[0003] However, the structure of the steel-concrete composite section is relatively complex, prone to stress concentration and stiffness mutation. At the same time, ordinary concrete has a large late shrinkage and a low bond strength with steel plates, and problems such as interlayer slip, penetration reinforcement loosening, and interlayer voids are likely to occur, seriously affecting the safety of the bridge. Therefore, as a key part of the hybrid girder structure, the steel-concrete composite section needs to be monitored in real-time for its health status. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, device, equipment and medium for monitoring diseases of a steel-concrete composite section to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0005] In a first aspect, the present application provides a method for monitoring diseases of a steel-concrete composite section, including:

[0006] Obtaining reflection signal data of the steel-concrete composite section through electromagnetic detection, and constructing a sliced two-dimensional image of the internal structure of the steel-concrete composite section according to the reflection signal data;

[0007] Performing target recognition and segmentation on the sliced two-dimensional image by using a pre-trained model to obtain a monitored target image, where the monitored target image includes a steel bar reflection image, a steel-concrete contact surface image, and a void image;

[0008] Performing elliptical fitting on the steel bar reflection image to obtain the fitting points of each steel bar, and obtaining steel bar slip and deformation information according to the position change of the fitting points of the steel bars;

[0009] Performing edge extraction on the steel-concrete contact surface image, and drawing the largest inscribed circle between the extracted steel plate edge and the concrete edge, and judging whether there is interface detachment between the steel plate and the concrete according to the size of the largest inscribed circle to obtain interface information;

[0010] Construct a three-dimensional model of the void area based on the void image, and obtain the volume information of the void area;

[0011] Based on the interface information, steel bar slip and deformation information, and the volume information of the void area, obtain the disease information of the steel-concrete joint section.

[0012] In a second aspect, the present application provides a steel-concrete joint section disease monitoring device, including:

[0013] A first construction module, configured to obtain the reflection signal data of the steel-concrete joint section through electromagnetic detection, and construct a sliced two-dimensional image of the internal structure of the steel-concrete joint section according to the reflection signal data;

[0014] A first segmentation module, configured to perform object recognition and segmentation on the sliced two-dimensional image by using a pre-trained model to obtain a monitoring target image, where the monitoring target image includes a steel bar reflection image, a steel-concrete contact surface image, and a void image;

[0015] A first processing module, configured to perform elliptical fitting on the steel bar reflection image to obtain the fitting points of each steel bar, and obtain the steel bar slip and deformation information according to the position change of the fitting points of the steel bars;

[0016] A second processing module, configured to extract the edge of the steel-concrete contact surface image, and draw the largest inscribed circle between the extracted steel plate edge and the concrete edge, and judge whether there is an interface detachment between the steel plate and the concrete according to the size of the largest inscribed circle to obtain the interface information;

[0017] A third processing module, configured to construct a three-dimensional model of the void area based on the void image, and obtain the volume information of the void area;

[0018] A fourth processing module, configured to obtain the disease information of the steel-concrete joint section based on the interface information, steel bar slip and deformation information, and the volume information of the void area.

[0019] In a third aspect, the present application further provides a steel-concrete joint section disease monitoring device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned steel-concrete joint section disease monitoring method are implemented.

[0020] In a fourth aspect, the present application further provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned steel-concrete joint section disease monitoring method are implemented.

[0021] The beneficial effects of the present invention are:

[0022] The present invention obtains the internal structure information of the steel-concrete joint section through electromagnetic detection, superimposes and converts one-dimensional signals to generate a two-dimensional cross-sectional view, and identifies and analyzes the detection target through the two-dimensional cross-sectional view, so as to continuously monitor whether the steel-concrete contact surface is separated, whether there is void, and whether there is interface slip. The present invention realizes non-destructive penetration detection inside the steel-concrete joint section, and can evaluate the service performance, predict the structural service life, and provide guidance for maintenance decision-making through the accumulated time-series data.

[0023] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is a flowchart of the method for monitoring diseases of the steel-concrete joint section according to the embodiment of the present application;

[0026] Figure 2 It is a schematic diagram of ellipse fitting according to the embodiment of the present application;

[0027] Figure 3 It is a schematic diagram of the device for monitoring diseases of the steel-concrete joint section according to the embodiment of the present application;

[0028] Figure 4 It is a schematic diagram of the equipment for monitoring diseases of the steel-concrete joint section according to the embodiment of the present application.

[0029] Reference signs in the figures: 100 - First construction module; 200 - First segmentation module; 300 - First processing module; 310 - Fitting unit; 320 - First calculation unit; 330 - First processing unit; 340 - Second calculation unit; 350 - Second processing unit; 400 - Second processing module; 410 - Extraction unit; 420 - Generation unit; 430 - Search unit; 440 - Judgment unit; 500 - Third processing module; 510 - Identification unit; 520 - Third calculation unit; 530 - Fourth calculation unit; 540 - Fifth calculation unit; 600 - Fourth processing module; 800 - Equipment for monitoring diseases of the steel-concrete joint section; 801 - Processor; 802 - Memory; 803 - Multimedia component; 804 - I / O interface; 805 - Communication component. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. Components of the embodiments of the present invention generally described and illustrated in the figures herein can be arranged and designed in a variety of different configurations. Therefore, the detailed description of the embodiments of the present invention provided herein is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0031] It should be noted that like reference numerals and letters denote like items in the following figures, and thus, once an item is defined in one figure, further definition and explanation thereof are not required in subsequent figures.

[0032] Existing detection methods for steel-concrete combination diseases mainly rely on contact detection. For the monitoring of interfacial displacement between layers, strain gauges, resistance gauges and other sensing devices are mainly arranged on the surfaces at different positions, and the signals received by different sensors are processed to judge whether there is interfacial slip and further calculate the magnitude of the interfacial slip. Or embedded distributed optical fiber and other sensors are used for perception, which need to be arranged in advance during the construction stage and are not applicable to engineering structures that are not embedded in advance, and the cost is relatively high. For the detection of abnormalities such as voids and detachment of the steel-concrete contact surface in the steel-concrete combination section, pressure gauges, displacement gauges, etc. acting on the surface are used for perception and detection. This method can only qualitatively judge whether there are voids and cannot achieve quantitative measurement of voids. There is also the use of acoustic vibration method for detection, that is, the detection of voids and the like is carried out through echo signals. The above-mentioned conventional detection methods can only qualitatively judge whether there are voids and cannot effectively measure the void volume and the degree of interlayer separation. At the same time, the internal structure of the steel-concrete combination section is complex, and traditional measurement methods cannot effectively identify various internal targets.

[0033] Embodiment 1

[0034] See Figure 1 , to solve the existing technical problems, the present application provides a method for monitoring diseases in the steel-concrete combination section, including steps S100, S200, S300, S400, S500, and S600;

[0035] Step S100: Obtain the reflection signal data of the steel-concrete combination section through electromagnetic detection, and construct a sliced two-dimensional image of the internal structure of the steel-concrete combination section according to the reflection signal data. Specifically:

[0036] An electromagnetic signal transmitting device that uses multiple arrays and multi-angle transmissions, and is synchronously equipped with a reflected signal receiving device. The bridge is detected in two directions: horizontally and vertically;

[0037] The higher the transmission frequency of the signal transmitting device, the shallower the detection depth and the higher the resolution. The vertical resolution is:

[0038]

[0039] where Δr is the vertical resolution of the electromagnetic wave signal, V is the propagation speed of the electromagnetic wave in the medium, and f c is the center frequency of the transmitted signal.

[0040] The horizontal resolution is:

[0041]

[0042] where Δl is the horizontal resolution of the electromagnetic wave detecting object, d is the burial depth of the object, V is the propagation speed of the electromagnetic wave in the medium, and f c is the center frequency of the transmitted signal.

[0043] To ensure the penetration detection of all internal conditions of the steel-concrete composite section, the longitudinal resolution required for monitoring is determined by the thickness of the steel plate and the diameter of the steel bars in the steel-concrete composite section. It is required that the longitudinal resolution is not less than the minimum value of the steel plate thickness or the steel bar diameter. When calculating the horizontal resolution, it is required that d takes the maximum depth of the steel-concrete composite section, and the horizontal resolution is selected based on the minimum distance between adjacent steel bar layouts.

[0044] According to the above principles, the appropriate transmission power and frequency are selected according to the structural dimensions to achieve the distinction between the steel plate and the concrete interface, the distinction between horizontal and vertical steel bars, and the penetration detection of the composite section.

[0045] The signal transmitter emits high-frequency electromagnetic waves, and the reflected signal receiving device (receiving antenna) receives the reflected waves, records the time difference and amplitude between transmission and reception, and obtains the reflected signal data. The reflected signal data is processed through operations such as filtering, gain, signal superposition, and offset correction. The time-domain data is converted into depth-domain data, and the collected data is plotted into a two-dimensional profile according to the position of the survey line to construct a sliced two-dimensional image of the internal structure of the steel-concrete composite section.

[0046] The sliced two-dimensional image is the image of several cross-sections of the steel-concrete composite section, including horizontal sliced images and vertical sliced images. The horizontal sliced images are parallel to the bridge deck, and the vertical sliced images are perpendicular to the traffic lane.

[0047] S200. Use a pre-trained model to perform target recognition and segmentation on the sliced two-dimensional image to obtain a monitoring target image, where the monitoring target image includes a steel bar reflection image, a steel-concrete contact surface image, and a void image;

[0048] The internal part of the steel-concrete joint section is composed of different substances such as steel plates, steel bars, cast concrete, and air, which will present different morphological characteristics on two-dimensional images. First, a large number of two-dimensional sectional views of the steel-concrete joint section are collected for data annotation to construct databases of steel bar reflection images, steel-concrete contact surface images, and void images. Based on the Faster-RCNN model, target recognition training is carried out. The trained model can identify the steel-concrete (steel plate and concrete mixture) contact surface, steel bars, and voids in the image, and obtain the two-dimensional coordinate positions of the targets in the image. According to the two-dimensional coordinate positions, segmentation is performed to obtain separate images of each target, and each target is numbered. The numbering rule is to label based on the center coordinates of the target. This number can reflect the actual position corresponding to the image, facilitating the subsequent calculation of the actual depth and position of the disease area.

[0049] In this step, the target detection algorithm is used to intelligently detect the targets of interest in the image, realize target classification and screening, remove the interference of unclear information, and accurately obtain various targets and spatial positions.

[0050] S300. Perform ellipse fitting on the steel bar reflection image to obtain the fitting points of each steel bar. According to the position change of the fitting points of the steel bars, obtain the steel bar slip and deformation information;

[0051] First, perform ellipse fitting on the recognized and segmented steel bar image to obtain a fitting curve. The general ellipse fitting equation of the fitting curve is:

[0052] Ax 2 +Bxy+Cy 2 +Dx+Ey+F=0

[0053] Among them, (x, y) are the coordinates of the points on the ellipse, and A, B, C, D, E, and F are constants. By taking the derivative of x and the limitation that the slope of the ellipse is 0 (limiting the major axis or minor axis of the ellipse to be parallel to the coordinate axes), it is obtained that:

[0054]

[0055] Substitute x into the general ellipse equation, that is:

[0056]

[0057] Solve for the coordinates of x and y to obtain two sets of coordinate values (the upper and lower vertices of the ellipse). Take the upper vertex of the ellipse as the fitting point of the steel bar. See Figure 2 , and this fitting point represents the coordinate position of the steel bar in the two-dimensional slice image. Number the fitting points of each steel bar based on the fitting point coordinates.

[0058] Calculating the steel bar slip: Calculate the coordinate change value of the fitting points of the steel bars with the same number in the reflected images of adjacent steel bars; the adjacent steel bar reflected images are the steel bar reflected images with adjacent acquisition times; thus, the change of the steel bar position over time can be obtained, so as to analyze the slip amount and slip direction of the steel bars.

[0059] According to the coordinate change value of the fitting points of the steel bars, the steel bar slip information is obtained. For example, if the change value of the fitting point coordinates compared with the initial coordinates exceeds the preset threshold, it is determined that interfacial slip has occurred, that is, there is a problem of poor bonding and relative rubbing between the steel bar and the concrete layer.

[0060] It should be noted that in this step, a three-dimensional structure of the internal steel bar layout in the steel-concrete joint section can be constructed through transverse slice images and longitudinal slice images, and the displacements of the steel bars in the transverse and longitudinal directions can be obtained, and combined to judge the movement of the steel bars.

[0061] Optionally, in some embodiments, it is not necessary to monitor the interfacial slip of all internal steel bars, but it is preferable to monitor the steel bars at the edge position of the steel-concrete joint section. For example, the fitting point of the steel bar closest to the electromagnetic wave emitting device in the two-dimensional image of the horizontal slice is selected, and the coordinate change of this fitting point is monitored.

[0062] Calculating the steel bar deformation: Calculate the distance between the fitting points of adjacent steel bars in the same steel bar reflected image.

[0063] According to the change of the distance between the fitting points of adjacent steel bars in the adjacent steel bar reflected images, the steel bar deformation information is obtained. The adjacent steel bar reflected images are the steel bar reflected images with adjacent acquisition times. Thus, the change of the distance between the steel bars over time can be obtained, so as to judge whether the steel bars are deformed; at the same time, according to the three-dimensional structure of the steel bar layout, it can be judged in which direction the steel bar itself is deformed.

[0064] S400. Perform edge extraction on the steel-concrete contact surface image, and draw the largest inscribed circle between the extracted steel plate edge and the concrete edge, and judge whether there is interface detachment between the steel plate and the concrete according to the size of the largest inscribed circle, so as to obtain the interface information, including:

[0065] S410. Perform edge extraction and curve fitting on the steel-concrete contact surface image to obtain two curves.

[0066] S420. Generate a Voronoi diagram based on the two curves, and obtain a sequence of symmetric points of the two curves according to the Voronoi diagram.

[0067] The Voronoi diagram is composed of a set of continuous polygons formed by the perpendicular bisectors of the lines connecting adjacent points. Specifically, points on the curve are evenly sampled as generating points. The edges of the generated Voronoi diagram are regarded as the axes of symmetry between the curves, and the intersection points of the axes of symmetry and the lines connecting the two generating points are found to obtain symmetric points, thus constructing a sequence of symmetric points.

[0068] S430. Search for the point farthest from the two curves in the sequence of symmetric points to obtain the center of the largest inscribed circle;

[0069] S440. Based on the distances from the center of the largest inscribed circle to the two curves, determine whether there is interface detachment between the steel plate and the concrete to obtain interface information. Specifically, the steel-concrete contact surface can be pre-tested to obtain the size of the diameter of the largest inscribed circle in the state of no interface detachment, and a detachment threshold is set by adding a 10% tolerance to this size. When the diameter of the largest inscribed circle is greater than the detachment threshold, it is determined that there is interface detachment between the steel plate and the concrete.

[0070] S500. Construct a three-dimensional model of the void area based on the void image and obtain the volume information of the void area;

[0071] Identify the void areas in the void images of the transverse slice image and the longitudinal slice image; perform pixel statistics on the void areas, and calculate the void area of each void area in the slice based on the pixel calibration coefficient. The pixel calibration coefficient is used to convert the pixel size to the actual size.

[0072] By calculating the coincidence coordinates of the void areas of adjacent transverse slice images, stack the void areas to obtain the first overlapping area; adjacent transverse slice images are two slice images that overlap in space. Align the coincident coordinates, and a three-dimensional structure of the void area can be constructed by stacking several consecutive adjacent slices. The first overlapping area is the overlapping area perpendicular to the image plane direction.

[0073] By calculating the coincidence coordinates of the void areas of adjacent longitudinal slice images, stack the void areas to obtain the second overlapping area;

[0074] Construct a three-dimensional model of the void area based on the first overlapping area and the second overlapping area, and calculate the volume information of the void area according to the three-dimensional model of the void area.

[0075] The stacking directions of the first overlapping region and the second overlapping region are perpendicular to each other. The stacking depth of the first overlapping region is the length direction of the second overlapping region, and vice versa. Inside the steel-concrete combined section, there may be multiple independent void regions. For example, there are two void regions, and their coordinates in the transverse slice image overlap, but it is impossible to determine whether the two void regions are connected in space only through the transverse slice image. In this case, it is necessary to combine the longitudinal slice image analysis. According to the depths where the two void regions are located, find their coordinates in the longitudinal slice image, and see if these two coordinates are connected in the longitudinal slice image. If so, the two void regions are connected.

[0076] This step realizes the three-dimensional space segmentation of the void region through the above-mentioned two-way coincidence coordinate calculation, and multiple independent three-dimensional void regions can be obtained to construct a three-dimensional model. Calculate the three-dimensional volume of the void region according to the spatial intersection coordinates of the transverse slice image and the longitudinal slice image at the edge of the segmented void region, and the actual underground position of the void region can be obtained through the coordinates.

[0077] S600. Obtain the disease information of the steel-concrete combined section based on the interface information, steel bar slip and deformation information, and void region volume information;

[0078] The above information is collected at a certain frequency and continuously monitored. The slice data collected each time is detected, calculated, and identified according to the above process. When interface detachment, steel bar slip or deformation, or voids are identified, an early warning is issued. At the same time, data can be accumulated in the time dimension. Obtain the interface slip amount, relative displacement amount of steel bars, interface detachment amount between steel plate and concrete, and void volume of the steel-concrete combined section in the time dimension, summarize to obtain the disease information, and conduct performance evaluation through time series analysis, predict the service life of the structure, and formulate maintenance decisions based on the disease information to guide the maintenance practice of the steel-concrete combined section.

[0079] Embodiment 2

[0080] This application also provides a steel-concrete combined section disease monitoring device, including:

[0081] The first construction module 100 is used to obtain the reflected signal data of the steel-concrete combined section through electromagnetic detection, and construct a two-dimensional slice image of the internal structure of the steel-concrete combined section according to the reflected signal data;

[0082] The first segmentation module 200 is used to perform target recognition and segmentation on the two-dimensional slice image by using a pre-trained model to obtain a monitoring target image, and the monitoring target image includes a steel bar reflection image, a steel-concrete contact surface image, and a void image;

[0083] The first processing module 300 is configured to perform elliptical fitting on the steel bar reflection image to obtain the fitting points of each steel bar, and obtain steel bar slip and deformation information according to the position change of the fitting points of the steel bars;

[0084] The second processing module 400 is configured to extract the edges of the steel-concrete contact surface image, draw the largest inscribed circle between the extracted steel plate edge and the concrete edge, and determine whether there is interface detachment between the steel plate and the concrete according to the size of the largest inscribed circle to obtain interface information;

[0085] The third processing module 500 is configured to construct a three-dimensional model of the void area based on the void image and obtain the void area volume information;

[0086] The fourth processing module 600 is configured to obtain steel-concrete joint section disease information based on the displacement monitoring information, steel bar slip and deformation information, and void area volume information.

[0087] As an optional implementation manner, the first processing module 300 includes:

[0088] The fitting unit 310 is configured to perform elliptical fitting on the steel bar reflection image and obtain the vertex coordinates of each ellipse, and use the vertex coordinates as the fitting points of each steel bar;

[0089] The first calculation unit 320 is configured to number the fitting points of each steel bar according to the vertex coordinates, and calculate the coordinate change value of the fitting points of the steel bars with the same number in adjacent steel bar reflection images; the adjacent steel bar reflection images are steel bar reflection images with adjacent acquisition times;

[0090] The first processing unit 330 is configured to obtain steel bar slip information according to the coordinate change value of the fitting points of the steel bars;

[0091] The second calculation unit 340 is configured to calculate the distance between adjacent fitting points of steel bars in the same steel bar reflection image;

[0092] The second processing unit 350 is configured to obtain steel bar deformation information according to the change in the distance between adjacent fitting points of steel bars in adjacent steel bar reflection images.

[0093] As an optional implementation manner, the second processing module 400 includes:

[0094] The extraction unit 410 is configured to extract the edges of the steel-concrete contact surface image to obtain two curves;

[0095] The generation unit 420 is configured to generate a Voronoi diagram based on the two curves, and obtain a sequence of symmetric points of the two curves according to the Voronoi diagram;

[0096] A search unit 430 for searching for the point farthest from the two curves in the sequence of symmetry points to obtain the center of the largest inscribed circle;

[0097] A judgment unit 440 for judging whether there is an interface detachment between the steel plate and the concrete according to the distances from the center of the largest inscribed circle to the two curves, and obtaining interface information.

[0098] As an optional implementation manner, the sliced two-dimensional image includes a transverse sliced image and a longitudinal sliced image; the third processing module 500 includes:

[0099] An identification unit 510 for identifying the void areas in the void images of the transverse sliced image and the longitudinal sliced image;

[0100] A third calculation unit 520 for stacking the void areas by calculating the overlapping coordinates of the void areas of adjacent transverse sliced images to obtain a first overlapping area;

[0101] A fourth calculation unit 530 for stacking the void areas by calculating the overlapping coordinates of the void areas of adjacent longitudinal sliced images to obtain a second overlapping area;

[0102] A fifth calculation unit 540 for constructing a three-dimensional model of the void area based on the first overlapping area and the second overlapping area, and calculating the volume information of the void area according to the three-dimensional model of the void area.

[0103] Embodiment 3

[0104] Corresponding to the above method embodiment, in this embodiment, a steel-concrete joint section disease monitoring device is further provided. The steel-concrete joint section disease monitoring device described below can be correspondingly referred to the steel-concrete joint section disease monitoring method described above.

[0105] Figure 3 It is a block diagram of a steel-concrete joint section disease monitoring device 800 shown according to an exemplary embodiment. As Figure 3As shown, the steel-concrete composite section disease monitoring device 800 includes a processor 801 and a memory 802. The steel-concrete composite section disease monitoring device 800 may also include one or more of a multimedia component 803, an input / output (I / O) interface 804, and a communication component 805. Among them, the processor 801 is used to control the overall operation of the steel-concrete composite section disease monitoring device 800 to complete all or part of the steps in the above-mentioned steel-concrete composite section disease monitoring method. The memory 802 is used to store various types of data to support the operation of the steel-concrete composite section disease monitoring device 800. These data may include, for example, commands for any application or method operating on the steel-concrete composite section disease monitoring device 800, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, and so on. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0106] The multimedia component 803 may include a screen and an audio component. Among them, the screen may be a touch screen, for example, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, and the microphone is used to receive external audio signals.

[0107] The received audio signal may be further stored in the memory 802 or sent through the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules. The above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the steel-concrete composite section disease monitoring device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them. Therefore, the corresponding communication component 805 may include: a Wi-Fi module, a Bluetooth module, and an NFC module.

[0108] In an exemplary embodiment, the device 800 for mutual signature and verification of digital files may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the above-mentioned method for monitoring diseases of the steel-concrete composite section.

[0109] In another exemplary embodiment, a computer-readable storage medium including program commands is also provided. When the program commands are executed by a processor, the steps of the above-mentioned method for monitoring diseases of the steel-concrete composite section are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 802 including program commands, and the above program commands may be executed by the processor 801 of the device 800 for monitoring diseases of the steel-concrete composite section to complete the above-mentioned method for monitoring diseases of the steel-concrete composite section.

[0110] Embodiment 4

[0111] Corresponding to the above method embodiment for monitoring diseases of the steel-concrete composite section, a readable storage medium is also provided in this embodiment. A readable storage medium described below can be mutually corresponded and referred to the above-mentioned method for monitoring diseases of the steel-concrete composite section.

[0112] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method embodiment for monitoring diseases of the steel-concrete composite section are implemented.

[0113] The readable storage medium may specifically be various readable storage media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disc that can store program codes.

[0114] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0115] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for monitoring steel-concrete joint section defects, characterized in that: include Acquire reflection signal data of the steel-concrete joint section by electromagnetic detection, and construct a slice two-dimensional image of the internal structure of the steel-concrete joint section according to the reflection signal data; Using a pre-trained model to perform target recognition and segmentation on the slice two-dimensional image to obtain a monitoring target image, wherein the monitoring target image includes a steel bar reflection image, a steel-concrete contact surface image, and a void image; Performing ellipse fitting on the steel bar reflection image to obtain fitting points of each steel bar, and obtaining steel bar slip and deformation information according to position changes of the fitting points of the steel bar; Performing edge extraction on the steel-concrete contact surface image, and drawing a maximum inscribed circle between the extracted steel plate edge and the concrete edge, judging whether there is interface detachment between the steel plate and the concrete according to the size of the maximum inscribed circle, and obtaining interface information; constructing a three-dimensional model of the hollow area based on the hollow image, and obtaining volume information of the hollow area; Based on the interface information, the steel bar slip and deformation information and the void area volume information, the steel-concrete joint section disease information is obtained.

2. The steel-concrete joint section disease monitoring method according to claim 1 is characterized in that: Performing ellipse fitting on the steel bar reflection image to obtain fitting points of each steel bar, and obtaining steel bar slippage and deformation information according to position changes of the fitting points of the steel bar, including: Performing ellipse fitting on the steel bar reflection image, and obtaining the vertex coordinates of each ellipse, and using the vertex coordinates as fitting points of each steel bar; According to the vertex coordinates, the fitting points of each steel bar are numbered, and the coordinate change values ​​of the fitting points of the steel bars with the same number in the adjacent steel bar reflection images are calculated; the adjacent steel bar reflection images are steel bar reflection images acquired at adjacent times; According to the coordinate change value of the fitting point of the steel bar, the steel bar slip information is obtained; Calculate the spacing between the fitting points of adjacent steel bars in the same steel bar reflection image; The steel bar deformation information is obtained according to the change of the spacing between the fitting points of the adjacent steel bars in the reflection images of the adjacent steel bars.

3. The method for monitoring steel-concrete joint section defects according to claim 1 is characterized in that: Edge extraction is performed on the steel-concrete contact surface image, and a maximum inscribed circle is drawn between the edge of the steel plate and the edge of the concrete. Whether there is interface detachment between the steel plate and the concrete is directly determined based on the maximum inscribed circle, and interface information is obtained, including: Perform edge extraction on the steel-concrete contact surface image to obtain two curves; Generate a Voronoi diagram based on the two curves, and obtain a symmetric point sequence of the two curves according to the Voronoi diagram; Find the point farthest from the two curves in the symmetrical point sequence to obtain the center of the largest inscribed circle; According to the distance from the center of the maximum inscribed circle to the two curves, it is judged whether there is interface separation between the steel plate and the concrete, and the interface information is obtained.

4. The steel-concrete joint section disease monitoring method according to claim 1 is characterized in that: The slice two-dimensional image includes a transverse slice image and a longitudinal slice image; a three-dimensional model of the void area is constructed based on the void image, and volume information of the void area is obtained, including: Identifying a void area in the void images of the transverse slice image and the longitudinal slice image; The overlapped coordinates of the empty areas of adjacent transverse slice images are calculated, and the empty areas are stacked to obtain a first overlapping area; The overlapped coordinates of the empty areas of the adjacent longitudinal slice images are calculated, and the empty areas are stacked to obtain a second overlapping area. A three-dimensional model of the hollow area is constructed based on the first overlapping area and the second overlapping area, and volume information of the hollow area is calculated according to the three-dimensional model of the hollow area.

5. A steel-concrete joint section disease monitoring device, characterized in that: include: The first construction module is used to obtain reflection signal data of the steel-concrete combination section through electromagnetic detection, and to construct a slice two-dimensional image of the internal structure of the steel-concrete combination section according to the reflection signal data; A first segmentation module is used to perform target recognition and segmentation on the slice two-dimensional image using a pre-trained model to obtain a monitoring target image, wherein the monitoring target image includes a steel bar reflection image, a steel-concrete contact surface image, and a void image; A first processing module is used to perform ellipse fitting on the steel bar reflection image to obtain fitting points of each steel bar, and obtain steel bar slip and deformation information according to position changes of the fitting points of the steel bar; The second processing module is used to extract the edge of the steel-concrete contact surface image, draw a maximum inscribed circle between the extracted steel plate edge and the concrete edge, and determine whether there is interface detachment between the steel plate and the concrete according to the size of the maximum inscribed circle to obtain interface information; A third processing module is used to construct a three-dimensional model of the hollow area based on the hollow image and obtain volume information of the hollow area; The fourth processing module is used to obtain the steel-concrete joint section disease information based on the displacement monitoring information, the steel bar slip and deformation information and the void area volume information.

6. The steel-concrete joint section disease monitoring method according to claim 5 is characterized in that: The first processing module comprises: A fitting unit, used for performing ellipse fitting on the steel bar reflection image, obtaining the vertex coordinates of each ellipse, and using the vertex coordinates as fitting points of each steel bar; A first calculation unit is used to number the fitting points of each steel bar according to the vertex coordinates, and calculate the coordinate change value of the fitting points of the steel bars with the same number in the adjacent steel bar reflection images; the adjacent steel bar reflection images are steel bar reflection images acquired at adjacent times; A first processing unit is used to obtain steel bar slip information according to the coordinate change value of the fitting point of the steel bar; A second calculation unit is used to calculate the spacing between the fitting points of adjacent steel bars in the same steel bar reflection image; The second processing unit is used to obtain steel bar deformation information according to the change of the spacing between the fitting points of adjacent steel bars in the reflection images of adjacent steel bars.

7. The method for monitoring steel-concrete joint section defects according to claim 5 is characterized in that: The second processing module comprises: An extraction unit, used for performing edge extraction on the steel-concrete contact surface image to obtain two curves; A generating unit, configured to generate a Voronoi diagram based on the two curves, and obtain a sequence of symmetric points of the two curves according to the Voronoi diagram; A searching unit, used for searching the point farthest from the two curves in the symmetrical point sequence to obtain the center of the largest inscribed circle; The judging unit is used to judge whether there is interface separation between the steel plate and the concrete according to the distance from the center of the maximum inscribed circle to the two curves, so as to obtain interface information.

8. The method for monitoring steel-concrete joint section defects according to claim 5 is characterized in that: The slice two-dimensional image includes a transverse slice image and a longitudinal slice image; the third processing module includes: An identification unit, used for identifying a hollow area in the hollow images of the transverse slice image and the longitudinal slice image; A third calculation unit is used for calculating the coincidence coordinates of the empty areas of adjacent transverse slice images, stacking the empty areas, and obtaining a first overlapping area; A fourth calculation unit is used for calculating the coincidence coordinates of the missing regions of adjacent longitudinal slice images, stacking the missing regions, and obtaining a second overlapping region; A fifth calculation unit is used to construct a three-dimensional model of the hollow area based on the first overlapping area and the second overlapping area, and calculate the volume information of the hollow area according to the three-dimensional model of the hollow area.

9. A steel-concrete joint section disease monitoring device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the steel-concrete joint section defect monitoring method as described in any one of claims 1 to 4 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the steel-concrete joint section defect monitoring method according to any one of claims 1 to 4 are implemented.

Images