Slit detection method, slit detection system and slit detection device

Abstract

The embodiment of the invention discloses a gap detection method, a gap detection system and a gap detection device. A specific embodiment of the method comprises the following steps: carrying out marking plate positioning on ground images in a ground image group to obtain a marking plate position group; according to the position set of the marking plates and the preset height, the inclined supporting assemblies are controlled to conduct position fine adjustment on the overlapped prefabricated shear wall; in response to completion of position fine adjustment, after a preset injection amount of concrete filler is injected into the laminated prefabricated shear wall in a layered manner, ultrasonic scanning and infrared image acquisition are performed on the laminated prefabricated shear wall; and according to the ultrasonic signal, the infrared image and a pre-trained joint part gap positioning model, generating joint part gap information. According to the implementation mode, accurate identification and positioning of the gap possibly existing in the joint part of the laminated prefabricated shear wall and the concrete filler are achieved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of building construction and the field of computer technology, and particularly to a gap detection method, a gap detection system and a device. Background Art

[0002] A composite precast shear wall is a precast shear wall mainly composed of an inner leaf panel, an outer leaf panel, truss reinforcement and an insulation layer. It can quickly build a house in the form of assembly, and has the advantages of reliable quality, convenient construction, energy conservation and environmental protection. However, when injecting concrete into the composite precast shear wall, due to the shrinkage of the concrete filling material, there may be gaps between the concrete filling material and the inner wall of the composite precast shear wall, which affects the pouring compactness and further affects the safety of the building structure. At present, a concrete vibrator is usually used to vibrate the injected concrete filling material to reduce the probability of gaps. However, using the vibration method may still have gaps and cannot accurately identify and locate the gaps.

[0003] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art. Summary of the Invention

[0004] This content part of the present disclosure is used to briefly introduce the concepts, which will be described in detail in the following detailed implementation part. This content part of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] Some embodiments of the present disclosure propose a gap detection method, a gap detection system and a device to solve the technical problems mentioned in the above background art section.

[0006] In a first aspect, some embodiments of the present disclosure provide a gap detection method, which is applied to the joint of a laminated precast shear wall and a concrete filler. The method includes: performing marker board positioning on the ground images in a ground image group to obtain a marker board position group, where the ground image group is collected when the height of the laminated precast shear wall from the ground is a preset height, and the number of marker board positions in the marker board position group is the same as the number of marker boards pre-laid on the ground; in response to that all the marker board positions in the marker board position group are located within a preset area included in the corresponding ground image, and an inclined support assembly is fixed to the outside of the outer leaf board included in the laminated precast shear wall, controlling the inclined support assembly to perform position fine-tuning on the laminated precast shear wall according to the marker board position group and the preset height; in response to the completion of the position fine-tuning, and after injecting a preset injection amount of concrete filler into the laminated precast shear wall in layers, performing ultrasonic scanning and infrared image acquisition on the laminated precast shear wall to obtain ultrasonic signals and infrared images; generating joint gap information according to the ultrasonic signals, the infrared images and a pre-trained joint gap positioning model, where the joint gap information includes: joint gap position and joint gap grade.

[0007] In a second aspect, some embodiments of the present disclosure provide a gap detection system, which is applied to the gap detection method in the first aspect above. The system includes: a detection assembly, where the detection assembly includes: a clamping assembly, an electronic level, a horizontal indicator light, an infrared sensor and a camera. The clamping assembly is a U-shaped structure, and the clamping assembly includes: a first clamping flap and a second clamping flap. The first clamping flap and the second clamping flap are locked by a locking bolt. When the detection assembly is horizontally clamped to the outer leaf board included in the laminated precast shear wall, the first clamping flap is located on the outside of the outer leaf board and the infrared sensor and the camera face downward; an inclined support assembly, where the inclined support assembly includes: a first fixing buckle, a second fixing buckle, a third fixing buckle, a first inclined support rod, a second inclined support rod and a fixing buckle guide rail. The first fixing buckle is arranged on the outside of the outer leaf board, the second fixing buckle is arranged on the outside of the outer leaf board, the third fixing buckle is fixed on the fixing buckle guide rail, the rod length of the second inclined support rod is less than the rod length of the first inclined support rod, and both the first inclined support rod and the second inclined support rod are telescopic rods. The first inclined support rod is obliquely arranged between the ground and the laminated precast shear wall through the first fixing buckle and the third fixing buckle, and the second inclined support rod is obliquely arranged between the ground and the laminated precast shear wall through the second fixing buckle and the third fixing buckle; a marker board, where the marker board is used for auxiliary positioning of the laminated precast shear wall.

[0008] Third aspect, some embodiments of the present disclosure provide a gap detection device, which is applied to the joint of a laminated precast shear wall and a concrete filling. The device includes: a marker board positioning unit configured to perform marker board positioning on the ground images in a ground image group to obtain a marker board position group, wherein the ground image group is collected when the height of the laminated precast shear wall from the ground is a preset height, and the number of marker board positions in the marker board position group is the same as the number of marker boards pre-laid on the ground; a control unit configured to, in response to that all the marker board positions in the marker board position group are located within a preset area included in the corresponding ground image, and an inclined support assembly is fixed on the outer side of the outer leaf board included in the laminated precast shear wall, control the inclined support assembly to perform position fine-tuning on the laminated precast shear wall according to the marker board position group and the preset height; a scanning and acquisition unit configured to, in response to the completion of position fine-tuning and after injecting a preset injection amount of concrete filling into the laminated precast shear wall in layers, perform ultrasonic scanning and infrared image acquisition on the laminated precast shear wall to obtain ultrasonic signals and infrared images; a generation unit configured to generate joint gap information according to the ultrasonic signals, the infrared images and a pre-trained joint gap positioning model, wherein the joint gap information includes: joint gap position and joint gap grade.

[0009] Fourth aspect, some embodiments of the present disclosure provide an electronic device, including: one or more processors; a storage device storing one or more programs thereon, which when executed by the one or more processors, cause the one or more processors to implement the method described in any implementation manner of the first aspect above.

[0010] Fifth aspect, some embodiments of the present disclosure provide a computer-readable medium storing a computer program thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the first aspect above is implemented.

[0011] The above - mentioned various embodiments of the present disclosure have the following beneficial effects: Through the gap detection method of some embodiments of the present disclosure, accurate identification and positioning of possible gaps at the joint of the laminated precast shear wall and the concrete filler are realized. Specifically, first, the marker board positioning is performed on the ground images in the ground image group to obtain the marker board position group. Among them, the above - mentioned ground image group is collected when the height of the laminated precast shear wall from the ground is a preset height, and the number of marker board positions in the marker board position group is the same as the number of marker boards pre - laid on the ground. Secondly, in response to that all the marker board positions in the marker board position group are located within the preset area included in the corresponding ground image, and an inclined support assembly is fixed on the outer side of the outer leaf board included in the above - mentioned laminated precast shear wall, according to the above - mentioned marker board position group and the above - mentioned preset height, the above - mentioned inclined support assembly is controlled to perform position fine - tuning on the above - mentioned laminated precast shear wall. In practice, during the hoisting process of the laminated precast shear wall, workers usually need to manually fine - tune the placement position of the laminated precast shear wall, which will increase the construction risk of workers. Therefore, the present disclosure, through the preset marker board, by means of marker board positioning, performs position fine - tuning of the laminated precast shear wall according to the marker board position and the preset height. Compared with the manual adjustment method, it can not only reduce the error existing in the placement of the shear wall, but also reduce the construction risk. Then, in response to the completion of the position fine - tuning, and after injecting a preset injection amount of concrete filler into the above - mentioned laminated precast shear wall in layers, ultrasonic scanning and infrared image acquisition are performed on the above - mentioned laminated precast shear wall to obtain ultrasonic signals and infrared images. In this way, the filling situation inside the laminated precast shear wall after filling the concrete filler is obtained in the dimensions of ultrasonic signals and infrared images. Finally, according to the above - mentioned ultrasonic signals, the above - mentioned infrared images and a pre - trained joint gap positioning model, joint gap information is generated, where the above - mentioned joint gap information includes: joint gap position and joint gap level. Thus, accurate identification and positioning of the gaps existing at the joint are realized. In summary, the present disclosure realizes accurate identification and positioning of possible gaps at the joint of the laminated precast shear wall and the concrete filler. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Combined with the accompanying drawings and referring to the following specific embodiments, the above - mentioned and other features, advantages and aspects of each embodiment of the present disclosure will become more obvious. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic, and the elements and elements are not necessarily drawn to scale.

[0013] Figure 1 is a flowchart of some embodiments of the gap detection method according to the present disclosure; Figure 2 is a side view of the laminated precast shear wall; Figure 3It is a top view of the detection component; Figure 4 It is a bottom view of the detection component; Figure 5 It is a schematic diagram of the positional relationship among the diagonal support component, the composite precast shear wall, and the detection component from a side view angle; Figure 6 It is a schematic diagram of the positional relationship among the diagonal support component, the composite precast shear wall, the detection component, and the marking plate from a top view angle; Figure 7 It is a simplified schematic diagram of the positional relationship between the diagonal support component and the composite precast shear wall from a side view angle; Figure 8 It is a schematic diagram of the generation process of the joint gap information; Figure 9 It is a schematic structural diagram of some embodiments of the gap detection device according to the present disclosure; Figure 10 It is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed implementation manners

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0015] In addition, it should be noted that for the sake of convenience of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependent relationships.

[0017] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0020] Reference Figure 1 , which shows a flow 100 of some embodiments of a gap detection method according to the present disclosure. The gap detection method is applied to the joint of a laminated precast shear wall and a concrete filler, and includes the following steps: Step 101, perform marker board positioning on the ground images in the ground image group to obtain a marker board position group.

[0021] In some embodiments, the execution subject of the gap detection method (for example, a computing device) can perform marker board positioning on the ground images in the ground image group to obtain a marker board position group. Among them, the ground image group is collected when the height of the laminated precast shear wall from the ground is a preset height. The number of marker board positions in the marker board position group is the same as the number of marker boards pre-laid on the ground. Among them, the laminated precast shear wall can be a precast shear wall composed of an inner leaf panel, an outer leaf panel, truss reinforcement, and a thermal insulation layer. The marker boards can be pre-placed at the corresponding placement positions of the laminated precast shear wall. The marker board position represents the position coordinates of the marker board in the corresponding ground image. In practice, the Tiny-YOLO network can be used to perform marker board positioning on the ground image to obtain the marker board position. In practice, when the hoisting of the laminated precast shear wall has not started, 1 detection component can be fixed on each side of the outer leaf panel included in the laminated precast shear wall to measure the height from the ground through the detection component, and 2 ground images can be collected respectively through the detection components fixed on both sides of the outer leaf panel when the height from the ground is the preset height, as the above-mentioned ground image group. In particular, 2 groups of marker boards are respectively arranged at the placement positions of the laminated precast shear wall, and each group of marker boards includes 2 marker boards. Among them, each group of marker boards corresponds to 1 detection component. Therefore, when the laminated precast shear wall is at the preset height from the ground, normally each ground image collected contains 2 marker boards.

[0022] As an example, refer to Figure 2 The side view of the laminated precast shear wall shown, where the laminated precast shear wall is composed of an inner leaf panel 1, an outer leaf panel 2, truss reinforcement 3, and a thermal insulation layer 4. Specifically, the thermal insulation layer 4 is attached to the inner side of the outer leaf panel 2, and the truss reinforcement 3 is used to be arranged between the inner leaf panel 1 and the outer leaf panel 2. In particular, the materials used in the laminated precast shear wall and their material properties comply with relevant design standards and design specifications. In addition, the thermal insulation layer 4 may not be provided in the laminated precast shear wall. For example, the laminated precast shear wall can be a double-sided laminated shear wall. In addition, the detection component 5 can be clamped on the inner leaf panel 1. When 2 detection components 5 are respectively clamped on both sides of the inner leaf panel 1, the 2 detection components 5 are both horizontally arranged and at the same horizontal height.

[0023] As another example, refer toFigure 3 The top view of the detection component shown, and Figure 4 the bottom view of the detection component shown, wherein the above detection component includes: a clamping component, an electronic level ( Figure 3 and Figure 4 not shown in the figure), a horizontal indicator light 9, an infrared sensor 10 and a camera 11. Among them, the above clamping component is a U-shaped structure. The above clamping component includes: a first clamping flap 6 and a second clamping flap 7. Among them, the above first clamping flap 6 and the above second clamping flap 7 are locked by a locking bolt 8. In particular, through holes with internal threads are provided at corresponding positions of the first clamping flap 6 and the second clamping flap 7. The locking bolt 8 has an external thread. In addition, 2 locking bolts 8 can be provided on the outer side of the second clamping flap 7, wherein, one locking bolt 8 is used for locking between the first clamping flap 6 and the second clamping flap 7. The other locking bolt 8 passes through a through hole with internal threads so that the second clamping flap 7 is closely attached to the outer leaf plate. In particular, rubber gaskets 12 are provided on the inner sides of the first clamping flap 6 and the second clamping flap 7 to improve the degree of fit with the outer leaf plate. In particular, the horizontal indicator light 9 can include: 3 indicator light beads, namely indicator light bead A, indicator light bead B and indicator light bead C. Among them, when indicator light bead A lights up, it indicates that the first clamping component tilts to the left. When indicator light bead B lights up, it indicates that the first clamping component clamps horizontally. When indicator light bead C lights up, it indicates that the first clamping component tilts to the right. The horizontal indicator light 9 can control the lighting and extinguishing of the indicator light beads through the electronic level embedded in the first clamping flap 6. The infrared sensor 10 and the camera 11 are arranged on the first clamping flap 6. The infrared sensor 10 and the horizontal indicator light 9 are arranged back to back. The infrared sensor 10 and the camera 11 are arranged in the same direction. Therefore, when the above detection component is horizontally clamped on the outer leaf plate included in the laminated precast shear wall, the first clamping flap 6 is located outside the outer leaf plate and the infrared sensor 10 and the camera 11 face downward.

[0024] It should be noted that the above computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster composed of multiple servers or terminal devices, or can be implemented as a single server or a single terminal device. When the computing device is embodied as software, it can be installed in the above-listed hardware devices. It can be implemented as, for example, multiple software or software modules for providing distributed services, or can be implemented as a single software or software module. No specific limitation is made here.

[0025] In some optional implementation manners of some embodiments, the above execution subject performs marker board positioning on the ground images in the ground image group to obtain a marker board position group, which may include the following steps: The first step is to splice the ground images in the ground image group to obtain a spliced ground image.

[0026] In practice, since there are 2 detection components symmetrically arranged horizontally on both sides of the outer vane plate and each detection component includes a camera, 2 ground images (ground image group) will be collected. Therefore, the ground images in the ground image group can be stitched according to the positional relationship between the corresponding detection components to obtain the stitched ground image.

[0027] In the second step, perform binarization processing on the above-mentioned stitched ground image to generate a binarized ground image.

[0028] In practice, the stitched ground image is a color image conforming to the RGB (Red-Green-Blue) standard, and the marking plate is a black positioning plate. In order to reduce the amount of data processing, it is necessary to perform binarization processing on the above-mentioned stitched ground image to generate a binarized ground image. Specifically, when determining the binarization threshold, the binarization threshold can be automatically determined by the Otsu algorithm.

[0029] In the third step, perform edge detection on the above-mentioned binarized ground image to obtain a set of connected regions.

[0030] Among them, a connected region is a closed region surrounded by the detected edges. In practice, first, an edge detection algorithm such as the Canny operator-based algorithm can be used to extract the edges in the binarized ground image. Then, the region surrounded by the closed edges is used as the connected region to obtain the above-mentioned set of connected regions.

[0031] In the fourth step, for each connected region in the above-mentioned set of connected regions, generate the region features corresponding to the connected region.

[0032] Among them, the region features include: region area, region boundary perimeter, roundness value, polygon approximation value. In practice, the region area can be characterized by the number of pixel points in the connected region. The region boundary perimeter can be the perimeter of the closed edge surrounding the connected region. The roundness value characterizes the degree to which the connected region approaches a theoretical circle. The polygon approximation value characterizes the number of vertices when approximating the closed edge of the connected region with a polygon.

[0033] As an example, see the following partial code for determining the polygon approximation value:

[0034] Among them, arcLength() is used to calculate the region boundary perimeter of the connected region. "peri" represents the region boundary perimeter. approxPolyDP() is used to approximately generate a polygon curve with a specified precision. "peri" characterizes the vertex set of the polygon curve. "Vertices" represents the polygon approximation value.

[0035] As another example, see the following partial code for determining the roundness value:

[0036] Among them, contourArea() is used to calculate the area of the connected region. "area" represents the area of the region. "circularity" represents the circularity value.

[0037] In particular, since the circularity value is often a decimal (floating point number). Therefore, the area of the region, the perimeter of the region boundary, the circularity value, and the polygon approximation value included in the region features are uniformly converted to floating point numbers.

[0038] In the fifth step, according to the region features corresponding to the connected regions, the connected regions in the above-mentioned connected region set are subjected to region clustering to obtain a set of connected region groups, and each connected region in the connected region group corresponds to the same class center.

[0039] In practice, since the sizes of the marker boards are the same (area of the region, perimeter of the region boundary, circularity value, polygon approximation value), when performing region clustering, the connected regions corresponding to the marker boards will be in the same connected region group. Therefore, an algorithm such as the K-means clustering algorithm can be used to perform region clustering on the connected regions in the above-mentioned connected region set by calculating the Euclidean distance between the region features.

[0040] In the sixth step, according to the circularity value and the polygon approximation value included in the region features corresponding to the connected regions, and the number of connected regions in the connected region group, the connected region groups that meet the screening conditions are selected from the above-mentioned set of connected region groups as the target connected region groups.

[0041] In practice, since the sizes of the marker boards are the same and they are all rectangular in shape. At the same time, the number of pre-set marker boards is known. Therefore, the target connected region groups representing the marker boards can be selected by combining the circularity value, the polygon approximation value corresponding to the connected regions, and the number of connected regions in the connected region group. For example, the marker board is rectangular, and 2 groups of marker boards are respectively set at the placement positions of the laminated precast shear walls, and each group of marker boards includes 2 marker boards. Therefore, the polygon approximation value is approximately 4. The number of target connected regions in the target connected region group is 4.

[0042] In the seventh step, the region center positions of the target connected regions in the target connected region group are used as the marker board positions to obtain the above-mentioned set of marker board positions.

[0043] In practice, in a construction scenario, there are protrusions such as gravel, which may cause misidentification of the connected region corresponding to the non-marking board when performing edge detection to extract the connected region. Therefore, by constructing regional features to describe the regional characteristics of the connected region, and through regional clustering and screening conditions, the position group of the marking board is determined. Compared with the method of extracting based on a machine learning network, the extraction speed is faster and the data processing volume is relatively smaller.

[0044] In some optional implementation manners of some embodiments, before the above-mentioned execution subject controls the diagonal support assembly to finely adjust the position of the composite precast shear wall according to the marking board position group and the above-mentioned preset height, in response to that the marking board positions in the marking board position group are all located in the preset region included in the corresponding ground image, and a diagonal support assembly is fixed on the outer side of the outer leaf board included in the composite precast shear wall, the following steps are further included: In response to the existence of a target marking board position in the marking board position group, according to the target marking board position, the position of the composite precast shear wall is adjusted by a tower crane, and the marking board position group is updated according to the updated marking board position corresponding to the target marking board position.

[0045] Among them, the above-mentioned target marking board position indicates that the marking board is located in the non-preset region included in the corresponding ground image. In practice, when the position of the composite precast shear wall is correct, the marking board should be approximately located at the center of the ground image. Therefore, the central region of the ground image can be the preset region. When the marking board position is not located in the preset region, it indicates that there is a large deviation in the composite precast shear wall. Therefore, it is necessary to adjust the position of the composite precast shear wall by a tower crane. Specifically, since the height of the camera from the ground is known (preset height), the marking board position represents the position coordinates of the marking board in the corresponding ground image. Therefore, according to the distance between the optical center of the camera and the target marking board position, and the angle between the line connecting the optical center and the target marking board position and the vertical direction (or horizontal direction), through the principle of similar triangles, the actual movement amount in the actual three-dimensional space (geodetic coordinate system) is obtained, so as to control the position adjustment of the composite precast shear wall by the tower crane according to the actual movement amount, and taking the actual movement amount as an increment, superimposing on the target marking board position to obtain the updated marking board position corresponding to the target marking board position, so as to update the marking board position group.

[0046] Step 102, in response to that the marking board positions in the marking board position group are all located in the preset region included in the corresponding ground image, and a diagonal support assembly is fixed on the outer side of the outer leaf board included in the composite precast shear wall, control the diagonal support assembly to finely adjust the position of the composite precast shear wall according to the marking board position group and the preset height.

[0047] In some embodiments, the above-mentioned execution entity may, in response to the positions of the marker boards in the marker board position group all being located within the preset area included in the corresponding ground image, and an inclined support assembly being fixed to the outer side of the outer leaf board included in the laminated precast shear wall, control the inclined support assembly to finely adjust the position of the laminated precast shear wall according to the marker board position group and the preset height. In practice, when the positions of the marker boards are all located within the preset area included in the corresponding ground image, it indicates that only minor adjustments are required. At this time, it is obviously no longer applicable to use a tower crane for large-scale adjustments. Therefore, it is necessary to control the inclined support assembly to finely adjust the position of the laminated precast shear wall according to the marker board position group and the preset height based on the inclined support assembly. The main body of the inclined support assembly is composed of inclined support rods. Specifically, the telescopic amount and displacement amount of the hydraulic rod can be obtained through geometric relationships based on the outer leaf board, the marker board position group, the preset height, and the position and inclination angle of the inclined support assembly. Thus, the inclined support assembly is controlled to finely adjust the position of the laminated precast shear wall.

[0048] As an example, refer to Figure 5 the schematic diagram of the positional relationship among the inclined support assembly, the laminated precast shear wall, and the detection assembly from the side view shown in Figure 6 and the schematic diagram of the positional relationship among the inclined support assembly, the laminated precast shear wall, the detection assembly, and the marker board from the top view shown in Figure 6Two sets of horizontally arranged diagonal support components are shown. According to actual needs, for example, to provide greater diagonal support force, more sets of diagonal support components can be set, which is not limited here. Next, two detection components 5 are symmetrically arranged horizontally on both sides of the outer leaf panel 1, and each detection component 5 includes a camera. Therefore, two ground images (ground image group) will be collected. Therefore, the ground images in the ground image group can be stitched according to the positional relationship between the corresponding detection components 5 to obtain the stitched ground image. In addition, two sets of marker plates 19 are respectively arranged at the placement positions of the composite precast shear wall, and each set of marker plates includes two marker plates 19.

[0049] In some optional implementation manners of some embodiments, in response to that the marker plate positions in the marker plate position group are all located within the preset area included in the corresponding ground image, and the diagonal support component is fixed on the outer side of the outer leaf panel included in the composite precast shear wall, the execution subject controls the diagonal support component to perform position fine-tuning on the composite precast shear wall according to the marker plate position group and the preset height, including the following steps: First step, perform movement amount projection according to the marker plate position group and the preset height to determine the first movement amount and the second movement amount.

[0050] Wherein, the first movement amount represents the movement amount of the composite precast shear wall along the first direction, and the second movement amount represents the movement amount of the composite precast shear wall along the second direction.

[0051] As an example, further refer to Figure 6 , from a top view perspective, taking the moving direction of the third fixing buckle on the fixing buckle guide rail as the X-axis, the direction perpendicular to the moving direction of the third fixing buckle on the fixing buckle guide rail as the Y-axis, and the direction of the composite precast shear wall along the gravity direction as the Z-axis to construct a coordinate system (where the Z-axis is not shown in Figure 6 ). Therefore, the position fine-tuning of the composite precast shear wall can be decomposed into movement components along the X-axis, Y-axis, and Z-axis respectively. Specifically, since the height of the camera from the ground is known (preset height), the marker plate position represents the position coordinates of the marker plate in the corresponding ground image. Therefore, according to the distance between the optical center of the camera and the marker plate position, and the angle between the line connecting the optical center and the marker plate position and the vertical direction (or horizontal direction), the actual movement amount in the actual three-dimensional space (geodetic coordinate system) is obtained through the principle of similar triangles as the first movement amount and the second movement amount.

[0052] As an example, assume that the displacement amounts of the marker board moving from the marker board position in the ground image to the preset area along the X-axis and Y-axis are x1 and y1 respectively. According to the distance from the optical center to the center of the CMOS (Complementary Metal-Oxide-Semiconductor), and the distance between the camera and the ground (preset height), through the principle of similar triangles, the displacement amount of the precast shear wall with superposed form along the X-axis direction can be obtained as the first displacement amount, and the displacement amount of the precast shear wall with superposed form along the Y-axis direction can be obtained as the second displacement amount.

[0053] In the second step, the above preset height is determined as the third displacement amount.

[0054] Among them, the third displacement amount represents the displacement amount along the third direction, and the above first direction, the above second direction, and the above third direction are perpendicular to each other. In practice, the first direction is parallel to the X-axis. The second direction is parallel to the Y-axis. The third displacement direction is parallel to the Z-axis.

[0055] In the third step, through the fixed buckle guide rail and the above-mentioned diagonal support assembly, the precast shear wall with superposed form is controlled to move the above first displacement amount along the above first direction.

[0056] Among them, the diagonal support assembly and the fixed buckle guide rail are connected by a fixed buckle, and the fixed buckle guide rail is arranged on the ground. At this time, it is not necessary to adjust the support angle and the change of the rod length of the first diagonal support rod and the second diagonal support rod included in the diagonal support assembly. Only through the fixed buckle guide rail and the above-mentioned diagonal support assembly, the precast shear wall with superposed form is controlled to horizontally move the above first displacement amount along the above first direction.

[0057] In the fourth step, in response to the completion of the movement along the above first direction, according to the first initial angle and the first initial rod length corresponding to the diagonal support assembly and the above second displacement amount, the first angle change amount and the first rod telescopic amount corresponding to the diagonal support assembly are determined.

[0058] As an example, refer to Figure 7 the schematic diagram of the positional relationship between the diagonal support assembly and the precast shear wall with superposed form under the simplified side view angle shown, where Figure 7 the left side represents the positional relationship between a diagonal support assembly and the precast shear wall with superposed form under the side view angle after the movement along the above first direction is completed. Figure 7 the right side represents the positional relationship between a diagonal support assembly and the precast shear wall with superposed form under the side view angle after the movement along the above second direction is completed. Specifically, since the diagonal support assembly includes: the first diagonal support rod and the second diagonal support rod, therefore, the first initial angle includes 2 angle values, which are respectively " " and " ". Among them, " "Characterize the included angle value between the first diagonal support rod and the horizontal ground." "Characterize the included angle value between the second diagonal support rod and the horizontal ground. Similarly, the first initial rod length includes 2 initial rod length values, which are respectively" "and" ". Among them," "Characterize the current rod length of the first diagonal support rod." "Characterize the current rod length of the second diagonal support rod. 'Point A' is the connection point between the first fixed buckle corresponding to the first diagonal support rod and the outer leaf board included in the laminated precast shear wall. 'Point B' is the connection point between the second fixed buckle corresponding to the second diagonal support rod and the outer leaf board included in the laminated precast shear wall. 'Point C' is the connection point between the third fixed buckle and the ground." "Characterize the second displacement. The first angle change amount includes 2 angle change amounts, which are respectively" "and" "(not shown in the figure). Among them," "Represents the angle change amount of the first diagonal support rod." "Represents the angle change amount of the second diagonal support rod. The first rod expansion amount includes 2 rod expansion amounts, which are respectively" "and" "(not shown in the figure). Among them," "Represents the rod expansion amount of the first diagonal support rod." "Represents the rod expansion amount of the second diagonal support rod." "Represents the rod length of the first diagonal support rod after horizontally moving the first displacement along the above first direction." "Represents the rod length of the first diagonal support rod after horizontally moving the second displacement along the above first direction." "Represents the included angle value between the first diagonal support rod and the horizontal ground after horizontally moving the second displacement along the above first direction." "Represents the included angle value between the second diagonal support rod and the horizontal ground after horizontally moving the second displacement along the above first direction." "Represents" "Horizontal component of" "Horizontal component of or" "Represents" "Horizontal component of" "Horizontal component of or. Therefore, according to the trigonometric relationship between the rod length and the included angle, the first angle change amount and the first rod expansion amount can be obtained."

[0059] Taking the first diagonal support rod included in the diagonal support assembly as an example, the angle change amount corresponding to the first diagonal support rod can be obtained through the following formula group" "Length variation of the diagonal rod" ":

[0060] Taking the second diagonal support rod included in the diagonal support assembly as an example, the angle variation corresponding to the second diagonal support rod can be obtained through the following set of formulas "Length variation of the diagonal rod" ":

[0061] Fifth step, according to the above first angle variation and the above first rod length variation, through the above diagonal support assembly, control the above composite precast shear wall to move the above second movement amount along the above second direction.

[0062] Sixth step, in response to the completion of the movement along the above second direction, according to the second initial angle and the second initial rod length corresponding to the diagonal support assembly and the above third movement amount, determine the second angle variation and the second rod length variation corresponding to the diagonal support assembly.

[0063] Wherein, the second initial angle represents the included angle between the diagonal support assembly and the ground after moving the second movement amount along the above second direction. The second initial rod length represents the length of the support rod of the diagonal support assembly after moving the second movement amount along the above second direction. In practice, referring to the calculation process of determining the second angle variation and the second rod length variation in the above fourth step, the second angle variation and the second rod length variation can be obtained according to the trigonometric relationship between the rod length and the included angle, which will not be elaborated here.

[0064] Seventh step, according to the above second angle variation and the second rod length variation, through the above diagonal support assembly, control the above composite precast shear wall to move the above third movement amount along the above third direction.

[0065] Step 103, in response to the completion of the position fine-tuning and after injecting a preset injection amount of concrete filler into the composite precast shear wall in layers, perform ultrasonic scanning and infrared image acquisition on the composite precast shear wall to obtain ultrasonic signals and infrared images.

[0066] In some embodiments, the above execution subject can, in response to the completion of the position fine-tuning and after injecting a preset injection amount of concrete filler into the composite precast shear wall in layers, perform ultrasonic scanning and infrared image acquisition on the composite precast shear wall to obtain ultrasonic signals and infrared images. In practice, after injecting a preset injection amount of concrete filler into the composite precast shear wall in layers through a concrete pump truck, the outer leaf panel of the composite precast shear wall can be scanned by an ultrasonic radar, and the image of the outer leaf panel of the composite precast shear wall can be acquired by an infrared camera, so as to obtain ultrasonic signals and infrared images.

[0067] Step 104: Generate joint gap information according to the ultrasonic signal, the infrared image, and a pre-trained joint gap positioning model.

[0068] In some embodiments, the above-mentioned execution entity may generate joint gap information according to the ultrasonic signal, the infrared image, and a pre-trained joint gap positioning model. The joint gap information includes: the joint gap position and the joint gap level. The joint gap level may characterize the gap specification level of the joint. In practice, first, the infrared image and the ultrasonic signal can be spatially aligned to form a dual-channel input including an infrared image channel and an ultrasonic signal channel. Then, the ultrasonic signal and the infrared image are respectively subjected to feature extraction and joint gap positioning through a convolutional neural network model (CNN, Convolutional Neural Networks) and a Faster R-CNN (Faster Region-based Convolutional Neural Networks) network model to obtain the joint gap information. Among them, the convolutional neural network model and the Faster R-CNN network model serve as the joint gap positioning model.

[0069] Optionally, the joint gap positioning model includes: an ultrasonic signal feature extraction module, an infrared image feature extraction module, a feature embedding module, a feature decoding module, a joint gap position locator, and a joint gap level classifier. In practice, the ultrasonic signal feature extraction module uses an RNN (Recurrent Neural Networks) model. The infrared image feature extraction module uses a residual neural network model. The feature embedding module divides the ultrasonic signal features extracted by the ultrasonic signal feature extraction module and the infrared features extracted by the infrared image feature extraction module into blocks according to their positions, obtaining an ultrasonic signal feature block matrix and an infrared image feature block matrix. Then, for each block region, a block vector (U, I, P) is constructed based on the position relationship. Here, U represents the ultrasonic signal feature block corresponding to the block region. I represents the infrared image feature block corresponding to the block region, and P represents the position vector corresponding to the block region. Then, the feature embedding module embeds the ultrasonic signal feature block, position vector, and infrared image feature corresponding to the block region to obtain a block vector, and further obtains a block vector matrix. The feature decoding module is based on the Transformer structure with an attention mechanism. Specifically, the feature decoding module consists of a multi-head attention mechanism module and a feed-forward network. The joint gap position locator uses a Faster R-CNN Head as the positioning head to output the joint gap position. The joint gap level classifier includes three fully connected layers and an activation function. Among them, the three fully connected layers are used for adjusting the feature dimension, and the activation function uses the Softmax function. The joint gap positioning model of the present disclosure realizes accurate joint gap recognition by combining ultrasonic signals and infrared images. In particular, considering that ultrasonic signals and infrared images are two different modalities of data, the conventional method of extracting features one by one and obtaining two sets of positioning positions and then screening fails to effectively consider the feature correlation between the two different modalities of data. Therefore, the joint gap positioning model of the present disclosure first performs preliminary feature extraction of ultrasonic signals and infrared images through the ultrasonic signal feature extraction module and the infrared image feature extraction module respectively. Then, through the feature embedding module, according to the position relationship, the infrared image features (blocks) and ultrasonic signal feature blocks corresponding to the same position are position-bound and embedded. Then, the decoder performs overall feature processing on the multi-modal embedded features. Finally, the joint gap position locator and the joint gap level classifier output the positioning position (joint gap position) and the gap level (joint gap level). For example, the gap level can include: a first-level gap level and a second-level gap level. Among them, the first-level gap level indicates the existence of a relatively large gap. The second-level gap level indicates the existence of a relatively small gap.

[0070] In some alternative implementations of some embodiments, the above-mentioned execution entity generates joint gap information according to the above-mentioned ultrasonic signal, the above-mentioned infrared image, and a pre-trained joint gap positioning model, including: In the first step, the above-mentioned ultrasonic signal feature extraction module extracts features from the above-mentioned ultrasonic signal to generate ultrasonic signal features.

[0071] As an example, refer to Figure 8 the schematic diagram of the generation process of the joint gap information shown in the figure. Among them, the above-mentioned execution entity extracts features from the above-mentioned ultrasonic signal 801 through the ultrasonic signal feature extraction module 803 to generate ultrasonic signal features 805.

[0072] In the second step, the above-mentioned infrared image feature extraction module extracts image features from the above-mentioned infrared image to generate infrared image features.

[0073] As an example, further refer to Figure 8 , where the above-mentioned execution entity extracts image features from the above-mentioned infrared image 802 through the above-mentioned infrared image feature extraction module 804 to generate infrared image features 806. In particular, the ultrasonic signal feature extraction module 803 and the infrared image feature extraction module 804 can perform feature extraction in parallel to accelerate the feature extraction speed.

[0074] In the third step, the above-mentioned feature embedding module embeds the ultrasonic signal features and the above-mentioned infrared image features to obtain embedded features.

[0075] As an example, further refer to Figure 8 , where, since the ultrasonic signal is obtained by scanning the outer vane, and the infrared image is an image of the outer vane, therefore, a block vector (U, I, P) is constructed for each block region according to the position relationship. Among them, U represents the ultrasonic signal feature block corresponding to the block region. I represents the infrared image feature block corresponding to the block region, and P represents the position vector corresponding to the block region. Then, the feature embedding module 807 embeds the ultrasonic signal feature block, the position vector, and the infrared image feature block corresponding to the block region to obtain a block vector, and further obtains a block vector matrix (embedded features 808).

[0076] In the fourth step, the above-mentioned feature decoding module decodes the above-mentioned embedded features to obtain decoded features.

[0077] As an example, then refer to Figure 8 , the above-mentioned execution entity can decode the above-mentioned embedded features 808 through the feature decoding module 809 to obtain decoded features 810.

[0078] Step 5: Based on the above decoded features and the above joint gap position locator, perform joint gap positioning to obtain the joint gap position included in the above joint gap information.

[0079] As an example, continue to refer to Figure 8 , the above execution entity can perform joint gap positioning through the decoded feature 810 and the above joint gap position locator 811 to obtain the joint gap position 813 included in the above joint gap information.

[0080] Step 6: Based on the local feature corresponding to the above joint gap position in the above decoded features and the above joint gap grade classifier, generate the joint gap grade included in the above joint gap information.

[0081] As an example, further refer to Figure 8 , the above execution entity can generate a joint gap grade vector 814 based on the local feature corresponding to the above joint gap position in the above decoded features and the above joint gap grade classifier 812, and then obtain the joint gap grade. Among them, the joint gap grade vector 814 includes the confidence levels corresponding to different grades.

[0082] Optionally, the above method further includes: Step 1: Based on the above joint gap information, generate a concrete filling visualization diagram for the above laminated precast shear wall.

[0083] In practice, the position corresponding to the joint gap position included in the joint part gap information in the infrared image can be framed and the joint gap grade can be marked as the concrete filling visualization diagram.

[0084] Step 2: Send the above concrete filling visualization diagram to the control terminal.

[0085] Among them, the above control terminal is used to control the injection of concrete filler into the above laminated precast shear wall.

[0086] The above embodiments of the present disclosure have the following beneficial effects: Through the gap detection method of some embodiments of the present disclosure, accurate identification and positioning of possible gaps at the joint between the laminated precast shear wall and the concrete filling are achieved. Specifically, first, the marker board positioning is performed on the ground images in the ground image group to obtain the marker board position group, where the ground image group is collected when the height of the laminated precast shear wall from the ground is a preset height, and the number of marker board positions in the marker board position group is the same as the number of marker boards pre-laid on the ground. Secondly, in response to that all the marker board positions in the marker board position group are located within the preset area included in the corresponding ground image, and an inclined support assembly is fixed on the outer side of the outer leaf board included in the laminated precast shear wall, according to the marker board position group and the preset height, the inclined support assembly is controlled to perform position fine-tuning on the laminated precast shear wall. In practice, during the hoisting process of the laminated precast shear wall, it is usually necessary for workers to manually fine-tune the placement position of the laminated precast shear wall, which will increase the construction risk of the workers. Therefore, the present disclosure uses the preset marker board, through the marker board positioning method, and performs position fine-tuning of the laminated precast shear wall according to the marker board position and the preset height. Compared with the manual adjustment method, it can not only reduce the error existing in the placement of the shear wall, but also reduce the construction risk. Then, in response to the completion of the position fine-tuning, and after injecting a preset injection amount of concrete filling into the laminated precast shear wall in layers, ultrasonic scanning and infrared image acquisition are performed on the laminated precast shear wall to obtain ultrasonic signals and infrared images. In this way, the filling condition inside the laminated precast shear wall after filling the concrete filling is obtained in the dimensions of ultrasonic signals and infrared images. Finally, according to the ultrasonic signals, the infrared images and the pre-trained joint gap positioning model, joint gap information is generated, where the joint gap information includes: joint gap position and joint gap grade. Thus, accurate identification and positioning of the gaps existing at the joint are achieved. In summary, the present disclosure realizes accurate identification and positioning of possible gaps at the joint between the laminated precast shear wall and the concrete filling.

[0087] Further, the present disclosure provides a gap detection system, which is applied to the joint between the laminated precast shear wall and the concrete filling and is applied to the aforementioned gap detection method. Specifically, refer to Figure 2 、 Figure 3 、 Figure 4 、 Figure 5 and Figure 6 . Among them, the gap detection system includes: a detection component 5, an inclined support component and a marker board 19.

[0088] Among them, the above detection component includes: a clamping component, an electronic level, a horizontal indicator light 9, an infrared sensor 10, and a camera 11. Among them, the above clamping component is of a U-shaped structure, and the above clamping component includes: a first clamping flap 6 and a second clamping flap 7. Among them, the first clamping flap 6 and the second clamping flap 7 are locked by a locking bolt 8. Among them, when the detection component is horizontally clamped to the outer leaf panel included in the laminated precast shear wall, the first clamping flap 6 is located outside the outer leaf panel and the infrared sensor 10 and the camera 11 face downward.

[0089] Among them, the above diagonal support component includes: a first fixing buckle 13, a second fixing buckle 14, a third fixing buckle 15, a first diagonal support rod 16, a second diagonal support rod 17, and a fixing buckle guide rail 18. Among them, the first fixing buckle 13 is arranged outside the outer leaf panel. The second fixing buckle 14 is arranged outside the outer leaf panel. The third fixing buckle 15 is fixed on the fixing buckle guide rail 18. The rod length of the second diagonal support rod 17 is less than the rod length of the first diagonal support rod 16. The first diagonal support rod 16 and the second diagonal support rod 17 are both telescopic rods. The first diagonal support rod 16 is obliquely arranged between the ground and the laminated precast shear wall through the first fixing buckle 13 and the third fixing buckle 15. The second diagonal support rod 17 is obliquely arranged between the ground and the laminated precast shear wall through the second fixing buckle 14 and the third fixing buckle 15.

[0090] Among them, the above marking plate 19 is used for auxiliary positioning of the laminated precast shear wall.

[0091] Optionally, both the detection component and the diagonal support component further include: a wireless communication component.

[0092] Among them, the control instructions and component status between the detection component and the diagonal support component are mutually transmitted through the wireless communication component. In addition, considering the limitation of the transmission power of the wireless communication component, it may affect the transmission of control instructions and component status with the tower crane. Therefore, the gap detection system may further include: a signal repeater for wireless signal enhancement and long-distance transmission of signals.

[0093] Further reference Figure 9 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a gap detection device. These device embodiments correspond to Figure 1 the method embodiments shown, and the gap detection device can be specifically applied to various electronic devices.

[0094] Such as Figure 9As shown, the gap detection device 900 of some embodiments includes: a marker board positioning unit 901, a control unit 902, a scanning and acquisition unit 903, and a generation unit 904. Among them, the marker board positioning unit 901 is configured to perform marker board positioning on the ground images in the ground image group to obtain a marker board position group, where the ground image group is collected when the height of the precast shear wall from the ground is a preset height, and the number of marker board positions in the marker board position group is the same as the number of marker boards pre-laid on the ground; the control unit 902 is configured to, in response to that all the marker board positions in the marker board position group are located within the preset area included in the corresponding ground image, and an inclined support assembly is fixed to the outside of the outer leaf board included in the precast shear wall, control the inclined support assembly to perform position fine-tuning on the precast shear wall according to the marker board position group and the preset height; the scanning and acquisition unit 903 is configured to, in response to the completion of position fine-tuning and after injecting a preset injection amount of concrete filler into the precast shear wall in layers, perform ultrasonic scanning and infrared image acquisition on the precast shear wall to obtain ultrasonic signals and infrared images; the generation unit 904 is configured to generate joint gap information according to the ultrasonic signals, the infrared images, and a pre-trained joint gap positioning model, where the joint gap information includes: joint gap position and joint gap level.

[0095] It can be understood that the units described in the gap detection device 900 correspond to the respective steps in the method described in the reference Figure 1 description. Therefore, the operations, features, and beneficial effects described above for the method also apply to the gap detection device 900 and the units included therein, and will not be repeated here.

[0096] Next, refer to Figure 10 , which shows a schematic structural diagram of an electronic device (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. Figure 10 The electronic device shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present disclosure. As Figure 10As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus. Among them, the memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium can store an operating system and computer programs. The computer programs include program instructions that, when executed, can cause the processor to execute any of the above methods. The processor is used to provide computing and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the operation of the computer programs in the non-volatile storage medium. When the computer programs are executed by the processor, the processor can be caused to execute any of the above methods. The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 10 the structure shown in is only a block diagram of some structures related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0097] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0098] Among them, in one embodiment, the above-mentioned processor is used to run a computer program stored in the memory to implement the following steps: perform marker board positioning on the ground images in the ground image group to obtain a marker board position group, where the above-mentioned ground image group is collected when the height of the laminated precast shear wall from the ground is a preset height, and the number of marker board positions in the marker board position group is the same as the number of marker boards pre-laid on the ground; in response to that all the marker board positions in the marker board position group are located within the preset area included in the corresponding ground image, and an inclined support assembly is fixed on the outer side of the outer leaf board included in the above-mentioned laminated precast shear wall, according to the above-mentioned marker board position group and the above-mentioned preset height, control the above-mentioned inclined support assembly to perform position fine-tuning on the above-mentioned laminated precast shear wall; in response to the completion of the position fine-tuning, and after injecting a preset injection amount of concrete filler into the above-mentioned laminated precast shear wall in layers, perform ultrasonic scanning and infrared image acquisition on the above-mentioned laminated precast shear wall to obtain ultrasonic signals and infrared images; generate joint gap information according to the above-mentioned ultrasonic signals, the above-mentioned infrared images and a pre-trained joint gap positioning model, where the above-mentioned joint gap information includes: joint gap position and joint gap grade.

[0099] The embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, and the computer program includes program instructions, and the method implemented when the program instructions are executed can refer to the various embodiments of the above method of the present disclosure.

[0100] Among them, the above-mentioned computer-readable storage medium may be an internal storage unit of the above-mentioned computer device in the foregoing embodiment, such as the hard disk or memory of the above-mentioned computer device. The above-mentioned computer-readable storage medium may also be an external storage device of the above-mentioned computer device, such as a plug-in hard disk equipped on the above-mentioned computer device, a smart media card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc.

[0101] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or system. Without further limitations, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0102] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) disclosed in the embodiments of the present disclosure that have similar functions.

Claims

1. A method for detecting gaps, which is applied to the joint of a laminated precast shear wall and a concrete filler, and is characterized in that, Including: Performing marker board positioning on the ground images in the ground image group to obtain a marker board position group, where the ground image group is collected when the height of the precast shear wall from the ground is a preset height, and the number of marker board positions in the marker board position group is the same as the number of marker boards pre-laid on the ground; In response to that all the marker board positions in the marker board position group are located within the preset area included in the corresponding ground image, and an inclined support assembly is fixed on the outer side of the outer leaf board included in the precast shear wall, controlling the inclined support assembly to perform position fine-tuning on the precast shear wall according to the marker board position group and the preset height; In response to the completion of the position fine-tuning and after injecting a preset injection amount of concrete filler into the precast shear wall in layers, performing ultrasonic scanning and infrared image acquisition on the precast shear wall to obtain ultrasonic signals and infrared images; Generating joint gap information according to the ultrasonic signals, the infrared images and a pre-trained joint gap positioning model, where the joint gap information includes: joint gap position and joint gap grade.

2. The method according to claim 1, characterized in that, Before the step of in response to that all the marker board positions in the marker board position group are located within the preset area included in the corresponding ground image, and an inclined support assembly is fixed on the outer side of the outer leaf board included in the precast shear wall, controlling the inclined support assembly to perform position fine-tuning on the precast shear wall according to the marker board position group and the preset height, the method further includes: In response to the existence of a target marker board position in the marker board position group, performing position adjustment on the precast shear wall by a tower crane according to the target marker board position, and updating the marker board position group according to the updated marker board position corresponding to the target marker board position, where the target marker board position indicates that the marker board is located in a non-preset area included in the corresponding ground image.

3. The method according to claim 2, characterized in that, The method further includes: Generating a concrete filling visualization diagram for the precast shear wall according to the joint gap information; Sending the concrete filling visualization diagram to a control terminal, where the control terminal is used to control the injection of the concrete filler into the precast shear wall.

4. The method according to claim 3, characterized in that, The step of performing marker board positioning on the ground images in the ground image group to obtain a marker board position group includes: Performing image stitching on the ground images in the ground image group to obtain a stitched ground image; Performing binarization processing on the stitched ground image to generate a binarized ground image; Performing edge detection on the binarized ground image to obtain a set of connected regions, where a connected region is a closed region surrounded by the detected edges; For each connected region in the set of connected regions, generating a region feature corresponding to the connected region, where the region feature includes: region area, region boundary perimeter, roundness value, polygon approximation value; Performing region clustering on the connected regions in the set of connected regions according to the region features corresponding to the connected regions to obtain a set of connected region groups, and each connected region in the connected region group corresponds to the same class center; Select a connected region group that meets the screening criteria from the set of connected region groups as the target connected region group according to the roundness value and polygon approximation value included in the region features corresponding to the connected region, and the number of connected regions in the connected region group; Use the region center position of the target connected region in the target connected region group as the marker board position to obtain the marker board position group.

5. The method according to claim 4, characterized in that, In response to that all the marker board positions in the marker board position group are located within the preset region included in the corresponding ground image, and an inclined support assembly is fixed on the outer side of the outer leaf panel included in the laminated precast shear wall, according to the marker board position group and the preset height, control the inclined support assembly to perform position fine-tuning on the laminated precast shear wall, including: Perform movement amount projection according to the marker board position group and the preset height to determine a first movement amount and a second movement amount, where the first movement amount represents the movement amount of the laminated precast shear wall along the first direction, and the second movement amount represents the movement amount of the laminated precast shear wall along the second direction; Determine the preset height as a third movement amount, where the third movement amount represents the movement amount along the third direction, and the first direction, the second direction, and the third direction are perpendicular to each other; Control the laminated precast shear wall to move the first movement amount along the first direction through the fixed buckle guide rail and the inclined support assembly, where the inclined support assembly and the fixed buckle guide rail are connected by a fixed buckle, and the fixed buckle guide rail is arranged on the ground; In response to the completion of the movement along the first direction, determine the first angle change amount and the first rod telescopic amount corresponding to the inclined support assembly according to the first initial angle and the first initial rod length corresponding to the inclined support assembly and the second movement amount; Control the laminated precast shear wall to move the second movement amount along the second direction through the inclined support assembly according to the first angle change amount and the first rod telescopic amount; In response to the completion of the movement along the second direction, determine the second angle change amount and the second rod telescopic amount corresponding to the inclined support assembly according to the second initial angle and the second initial rod length corresponding to the inclined support assembly and the third movement amount, where the second initial angle represents the included angle between the inclined support assembly and the ground after moving the second movement amount along the second direction, and the second initial rod length represents the length of the support rod of the inclined support assembly after moving the second movement amount along the second direction; Control the laminated precast shear wall to move the third movement amount along the third direction through the inclined support assembly according to the second angle change amount and the second rod telescopic amount.

6. The method according to claim 5, characterized in that, The joint gap positioning model includes: an ultrasonic signal feature extraction module, an infrared image feature extraction module, a feature embedding module, a feature decoding module, a joint gap position locator, and a joint gap grade classifier. Generating joint gap information according to the ultrasonic signal, the infrared image, and the pre-trained joint gap positioning model includes: The ultrasonic signal is subjected to feature extraction by the ultrasonic signal feature extraction module to generate ultrasonic signal features; The infrared image is subjected to image feature extraction by the infrared image feature extraction module to generate infrared image features; The ultrasonic signal features and the infrared image features are subjected to feature embedding by the feature embedding module to obtain the embedded features; The embedded features are subjected to feature decoding by the feature decoding module to obtain the decoded features; Based on the decoded features and the joint gap position locator, the joint gap is located to obtain the joint gap position included in the joint gap information; Based on the local features corresponding to the joint gap position in the decoded features and the joint gap level classifier, the joint gap level included in the joint gap information is generated.

7. A gap detection system that applies the gap detection method according to any one of claims 1 to 6, characterized in that, It includes: A detection component, wherein the detection component includes: a clamping component, an electronic level, a level indicator, an infrared sensor, and a camera. The clamping component is of a U-shaped structure and includes a first clamping flap and a second clamping flap. The first clamping flap and the second clamping flap are locked by a locking bolt. When the detection component is horizontally clamped to the outer leaf panel included in the precast shear wall with superimposed layers, the first clamping flap is located outside the outer leaf panel and the infrared sensor and the camera face downward; An inclined support component, wherein the inclined support component includes: a first fixed buckle, a second fixed buckle, a third fixed buckle, a first inclined support rod, a second inclined support rod, and a fixed buckle guide rail. The first fixed buckle is arranged outside the outer leaf panel, the second fixed buckle is arranged outside the outer leaf panel, the third fixed buckle is fixed on the fixed buckle guide rail, the rod length of the second inclined support rod is less than the rod length of the first inclined support rod, both the first inclined support rod and the second inclined support rod are telescopic rods, the first inclined support rod is obliquely arranged between the ground and the precast shear wall with superimposed layers through the first fixed buckle and the third fixed buckle, and the second inclined support rod is obliquely arranged between the ground and the precast shear wall with superimposed layers through the second fixed buckle and the third fixed buckle; A marking plate, which is used for auxiliary positioning of the precast shear wall with superimposed layers.

8. A gap detection device applied to the joint of a laminated precast shear wall and a concrete filling, characterized in that, It includes: A marking plate positioning unit configured to perform marking plate positioning on the ground images in the ground image group to obtain a marking plate position group, where the ground image group is collected when the height of the precast shear wall with superimposed layers from the ground is a preset height, and the number of marking plate positions in the marking plate position group is the same as the number of marking plates pre-laid on the ground; A control unit configured to, in response to that the marking plate positions in the marking plate position group are all located within the preset area included in the corresponding ground image, and an inclined support component is fixed outside the outer leaf panel included in the precast shear wall with superimposed layers, control the inclined support component to perform position fine-tuning on the precast shear wall with superimposed layers according to the marking plate position group and the preset height; A scanning and acquisition unit, configured to perform ultrasonic scanning and infrared image acquisition on the laminated precast shear wall after the position fine-tuning is completed and a preset injection amount of concrete filler is injected into the laminated precast shear wall in layers, so as to obtain ultrasonic signals and infrared images; A generation unit, configured to generate joint gap information according to the ultrasonic signals, the infrared images and a pre-trained joint gap positioning model, wherein the joint gap information includes: joint gap positions and joint gap grades.

Images