Reconstruction method and device for internal three-dimensional structure of oriented strand board and storage medium
By acquiring and processing the shaving images during the slab paving process, combining computer vision and density gradient data, the three-dimensional structure of directional particle board is reconstructed, and the problem of X-ray tomography cannot be detected is solved, achieving efficient three-dimensional structure detection.
Patent Information
- Application Number
- CN202510390041.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-31
- Publication Date
- 2025-07-18
AI Technical Summary
X-ray tomography technology cannot detect the three-dimensional structure of directional particle board slab paving, and the equipment cost is high and the applicability is low, resulting in a decrease in detection efficiency.
By obtaining the original image of each layer of shavings during the slab paving process, using a pre-constructed computer vision model for shavings segmentation, extracting two-dimensional contour, position coordinates and layer index information, and calculating the compression rate with the cross-section density gradient data, reconstructing the three-dimensional structure of directional particle board.
Without using X-ray tomography equipment, the detection of the three-dimensional structure during slab paving is realized, reducing economic costs, expanding applicability and improving detection efficiency.
Smart Images
Figure CN120339544A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of oriented strand structural material processing, and in particular to a method, a device and a storage medium for reconstructing the internal three-dimensional structure of an oriented strand board. Background Art
[0002] Oriented Strand Board (OSB) is a multi-layer structural board made from small-diameter timber, thinning timber, wood core, etc., which is processed into long flakes by special equipment and then made into flakes through processes such as drying, gluing, directional paving and hot pressing.
[0003] At present, the main known means of detecting the internal structure of OSB is to use radiation penetration. X-ray tomography (X-ray CT) is a reliable method for detecting the internal 3D structure of wood. This method is also used to visualize the internal 3D structure of OSB and quantify the pore distribution. This technology can only be used to detect the internal 3D structure of slab specimens, but not the 3D structure of slabs during installation. The applicable specimen size is limited. In addition, due to the high equipment cost of X-ray CT, the economic cost is increased in disguise, the applicability is low, and the detection efficiency is reduced.
[0004] Therefore, there is an urgent need for a method, device and storage medium for reconstructing the internal three-dimensional structure of an oriented strand board to solve the above-mentioned technical problems. Summary of the invention
[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method, device and storage medium for reconstructing the internal three-dimensional structure of an oriented strand board, which can solve the technical problems that X-ray tomography technology cannot detect the three-dimensional structure during the slab paving process, and the detection efficiency is reduced due to the high equipment cost and low applicability of X-ray tomography (X-ray CT).
[0006] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for reconstructing the internal three-dimensional structure of an oriented strand board, comprising: Obtaining the original image A of each layer of wood shavings during the slab paving process; The original image A is segmented into stacked wood chips by using a pre-built computer vision model to obtain a single-layer wood chip distribution image B, and the two-dimensional contour, position coordinates and layer index information of a single piece of wood chip in the single-layer wood chip distribution image B are extracted; Obtaining cross-sectional density gradient data of the slab, calculating the compression rate of each layer of wood chips in the thickness direction of the slab based on the cross-sectional density gradient data, and calculating the actual thickness of each layer of wood chips in the slab according to the compression rate; Reconstruct the three-dimensional structure inside the oriented strand board based on the two-dimensional contour, position coordinates, layer index information, and actual thickness.
[0007] Further, obtaining the image A of each layer of strands during the mat forming process includes: During the process of laying each layer of strands, an industrial camera at a fixed position is used to capture the surface image of the mat. The ghosting of the strands is eliminated by an auxiliary light source, and the height of the camera is adjusted as the thickness of the mat increases to keep the shooting distance constant.
[0008] Further, the optimization steps of the computer vision model include: Filter the mask image generated based on the original image A through a preset area range to remove the noise and mis-identified areas in the original image A; Compare the filtered mask image with the original image A, further adjust the mask image, and merge the adjusted mask images to generate the single-layer strand distribution image B.
[0009] Further, the area range is 20 - 70 cm², which is used to retain the effective strand masks.
[0010] Further, the expression for calculating the compression ratio of each layer of strands in the thickness direction of the mat is: , where is the compression ratio at the thickness of , is the average density of the mat before hot pressing, is the density at the thickness of of the mat after hot pressing.
[0011] Further, the expression for calculating the actual thickness of the mat based on the compression ratio is: , where is the thickness of the nth layer of strands after hot pressing, and H is the preset thickness of the strands before hot pressing.
[0012] Further, reconstructing the three-dimensional structure inside the oriented strand board includes: Based on the position coordinates and layer index information of the single strands in the single-layer strand distribution image B, stretch the two-dimensional contour by the actual thickness distance of each layer of strands in the thickness direction to form a three-dimensional grid model. Generate an OBJ format file containing vertex coordinates and patch topology based on the three-dimensional grid model, and input the OBJ format file into 3D modeling software to realize the structure visualization.
[0013] In a second aspect, the present invention provides a mechanical equipment fault identification device, including: The acquisition module is used to obtain the original image A of each layer of wood chips during the slab paving process; The extraction module is used to perform layered wood chip segmentation on the original image A through a pre-built computer vision model, obtain the single-layer wood chip distribution image B, and extract the two-dimensional contour, position coordinates, and layer index information of the single wood chip in the single-layer wood chip distribution image B; The calculation module is used to obtain the cross-sectional density gradient data of the slab, calculate the compression ratio of each layer of wood chips in the thickness direction of the slab based on the cross-sectional density gradient data, and calculate the actual thickness of each layer of wood chips in the slab according to the compression ratio; The reconstruction module is used to reconstruct the internal three-dimensional structure of the oriented strand board based on the two-dimensional contour, position coordinates, layer index information, and actual thickness.
[0014] In a third aspect, the present invention provides an electronic terminal, including a processor and a memory connected to the processor. A computer program is stored in the memory. When the computer program is executed by the processor, the steps of the method described in any one of the above are executed.
[0015] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in any one of the above are implemented.
[0016] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: During the paving process of the oriented strand board (OSB), the present invention obtains the original image A of each layer of wood chips during the paving process; uses a pre-built computer vision model to identify and segment the original image A of the wood chips, extracts the contour information, position coordinates, and layer index information of the single wood chip; combines the cross-sectional density gradient (VDP) data, calculates the compression ratio in the thickness direction of the slab, calculates the actual thickness of each layer of wood chips based on the compression ratio, finally determines the accurate position coordinates of each layer of wood chips in the thickness direction, and finally uses 3D modeling software to reconstruct the internal three-dimensional structure of the OSB; realizes the detection of the three-dimensional structure during the slab paving process without using X-ray tomography equipment, and removes the size limitation on the test piece, improving the detection efficiency while reducing the economic cost and expanding the adaptability. Description of the Drawings
[0017] Figure 1 is a flowchart of a method for reconstructing the internal three-dimensional structure of an oriented strand board provided by an embodiment of the present invention; Figure 2 is a schematic diagram of the OSB multi-layer structure of a method for reconstructing the internal three-dimensional structure of an oriented strand board provided by an embodiment of the present invention; Figure 3It is a schematic diagram of the core code a of the computer vision processing model in a method for reconstructing the internal three-dimensional structure of oriented strand board provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the core code b of the computer vision processing model in a method for reconstructing the internal three-dimensional structure of oriented strand board provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the core code c of the computer vision processing model in a method for reconstructing the internal three-dimensional structure of oriented strand board provided by an embodiment of the present invention.
[0018] Figure 6 It is a schematic diagram of the core code d of the computer vision processing model in a method for reconstructing the internal three-dimensional structure of oriented strand board provided by an embodiment of the present invention. Detailed implementation manners
[0019] The technical solutions of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present application and the embodiments are detailed descriptions of the technical solutions of the present application, rather than limitations on the technical solutions of the present application. Without conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.
[0020] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.
[0021] VDP, the vertical density profile (VDP) refers to the density distribution of the board in the thickness direction. VDP is one of the key factors affecting the physical and mechanical properties of oriented strand board (OSB). A reasonable VDP can optimize the strength, stiffness and stability of the board. Traditional measurement methods include using equipment such as a cross-sectional density scanner. In recent years, computer vision technology has been applied to the online monitoring of VDP. By processing the photos collected during the hot pressing process, the density can be quickly and accurately identified and calculated. Embodiment 1:
[0022] Figure 1 It is a flowchart of the method for reconstructing the internal three-dimensional structure of the oriented strand board in Embodiment 1 of the present invention. This flowchart only shows the logical order of the method described in this embodiment. On the premise of not conflicting with each other, in other possible embodiments of the present invention, the steps shown or described can be completed in a different order Figure 1 from that shown.
[0023] The three-dimensional internal structure reconstruction method of the oriented strand board provided in this embodiment can be applied to a terminal and can be executed by a mechanical equipment fault identification device. The device can be implemented in a software and / or hardware manner and can be integrated into the terminal, such as any smart phone, tablet computer or computer device with a communication function. Refer to Figures 1 to 6 As shown, the method of this embodiment specifically includes the following steps: Step 1: During the process of paving each layer of wood chips, an industrial camera at a fixed position is used to capture the surface image of the slab, and the original image A of each layer of wood chips during the paving process of the slab is obtained. It should be noted that when the original image A is obtained, the layer index information mentioned below can be obtained, and the layer index information remains unchanged during the subsequent processing of the original image A. In this embodiment, the size of each layer of the wood chips is 150 ± 50 mm in length, 25 ± 10 mm in width, and 0.5 mm in thickness, the image resolution is not less than 3000 × 3000 pixels, the pixel accuracy is 0.15 mm, and the adhesive used is phenolic resin with a solid content of 43%; after obtaining the image, the ghosting of the wood chips can also be eliminated through an auxiliary light source, and the height of the camera is adjusted as the thickness of the slab increases to keep the shooting distance constant; specifically, lay wood chips on the slab, and use an industrial camera to take pictures of the slab after each layer is laid until the number of laid layers reaches 145 layers (i.e., Figure 2 n in the appendix), after hot pressing is completed, the OSB is stored in an indoor environment for 72 hours, and then 12 specimens of 50 × 50 mm 2 are processed.
[0024] Step 2: Use a pre-constructed computer vision model to segment the stacked wood chips in the original image A to obtain a single-layer wood chip distribution image B, and extract the two-dimensional contour, position coordinates and layer index information of a single wood chip in the single-layer wood chip distribution image B; Among them, the optimization steps of the computer vision model include: Screen the mask image generated based on the original image A through a preset area range to remove the noise and mis-identified areas in the original image A. In this embodiment, the area range can be 20 - 70 cm² to retain the effective wood chip mask; compare the screened mask image with the original image A, further adjust the mask image, and merge the adjusted mask images to generate a single-layer wood chip distribution image B, which is manifested as removing the sub-surface wood chips and retaining only the single-layer wood chip distribution image B of the surface wood chip image, more accurately reflecting the true shape of the wood chips in the original image.
[0025] Step 3: Obtain the cross-sectional density gradient data of the slab (it can be known from the foregoing description of the specification how to obtain the cross-sectional density gradient data of the slab blank, which belongs to the prior art and will not be elaborated here. In this embodiment, the GreCon DAX6000 instrument is finally used to measure the VDP of all specimens.), and calculate the compression ratio of the flakes in each layer in the thickness direction of the slab based on the cross-sectional density gradient data: , wherein, is the compression ratio at the thickness of , is the average density of the slab before hot pressing, with the unit of g / cm³, is the density at the thickness of the slab after hot pressing, with the unit of g / cm³; Calculate the actual thickness of the flakes in each layer of the slab according to the compression ratio: , wherein, is the thickness of the nth layer of flakes after hot pressing, and H is the preset thickness of the flakes before hot pressing. In this embodiment, H can be 0.5 mm.
[0026] Step 4: Reconstruct the internal three-dimensional structure of the oriented strand board based on the two-dimensional contour, position coordinates, layer index information and actual thickness, including: Based on the position coordinates and layer index information of the single flake in the single-layer flake distribution image B of the single-layer flake distribution image B, it should be noted that when calculating the actual thickness of each layer of flakes and, it can be combined with the position coordinates and layer index information of the single flake to obtain the accurate position coordinates of each layer of flakes in the thickness direction, so that the two-dimensional contour can be stretched along the thickness direction by the actual thickness distance of each layer of flakes to form a three-dimensional grid model. Based on the three-dimensional grid model, an OBJ format file containing vertex coordinates and patch topology is generated, and the OBJ format file is input into 3D modeling software. In this embodiment, the modeling software can be selected as Blender (which is the prior art and will not be elaborated here) to realize structure visualization. The method provided in this embodiment is applicable to on-line monitoring in laboratories or production lines, and the reconstruction result is used to analyze the structure-property relationship of OSB and optimize the preparation process. Embodiment 2:
[0027] Embodiment 2 of the present invention provides a device for reconstructing the internal three-dimensional structure of an oriented strand board, including: An acquisition module for acquiring the original image A of each layer of flakes during the paving process of the slab; An extraction module for segmenting the laminated flakes of the original image A through a pre-constructed computer vision model to obtain a single-layer flake distribution image B, and extracting the two-dimensional contour, position coordinates and layer index information of the single flake in the single-layer flake distribution image B; A calculation module, configured to obtain cross-sectional density gradient data of a slab, calculate the compression ratios of the wood chips in each layer in the thickness direction of the slab based on the cross-sectional density gradient data, and calculate the actual thicknesses of the wood chips in each layer of the slab according to the compression ratios; A reconstruction module, configured to reconstruct the internal three-dimensional structure of an oriented strand board based on the two-dimensional contour, position coordinates, layer index information, and actual thickness.
[0028] The internal three-dimensional structure reconstruction of the oriented strand board provided in the second embodiment of the present invention can execute the method for reconstructing the internal three-dimensional structure of the oriented strand board provided in the first embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Embodiment Three:
[0029] The third embodiment of the present invention further provides an electronic terminal, including a processor and a memory connected to the processor. A computer program is stored in the memory, and the processor is configured to operate according to the instruction to execute the steps of the method described in the first embodiment.
[0030] The electronic terminal provided in the third embodiment of the present invention can execute the method for reconstructing the internal three-dimensional structure of the oriented strand board provided in the first embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Embodiment Four:
[0031] The fourth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first embodiment are implemented, and it has the corresponding functional modules and beneficial effects for executing the method.
[0032] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, an apparatus, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0033] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatuses), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the processFigure 1 means for the functions specified in one process or more processes and / or boxes Figure 1 or more boxes.
[0034] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in the process Figure 1 one process or more processes and / or boxes Figure 1 or more boxes.
[0035] These computer program instructions may also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 one process or more processes and / or boxes Figure 1 or more boxes.
[0036] The above is only the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention..
Claims
1. A method for reconstructing the three-dimensional internal structure of oriented strand board, characterized in that Including: Obtaining the original image A of each layer of wood chips during the slab paving process; Performing laminated wood chip segmentation on the original image A through a pre-constructed computer vision model to obtain a single-layer wood chip distribution image B, and extracting the two-dimensional contour, position coordinates, and layer index information of single wood chips in the single-layer wood chip distribution image B; Obtaining the cross-sectional density gradient data of the slab, calculating the compression ratio of each layer of wood chips in the thickness direction of the slab based on the cross-sectional density gradient data, and calculating the actual thickness of each layer of wood chips in the slab according to the compression ratio; Reconstructing the internal three-dimensional structure of the oriented strand board based on the two-dimensional contour, position coordinates, layer index information, and actual thickness.
2. The method for reconstructing the three-dimensional internal structure of the oriented strand board according to claim 1, characterized in that Obtaining the image A of each layer of wood chips during the slab paving process includes: During the paving of each layer of wood chips, using an industrial camera at a fixed position to capture the surface image of the slab, eliminating the ghosting of wood chips through an auxiliary light source, and adjusting the camera height as the slab thickness increases to keep the shooting distance constant.
3. The method for reconstructing the internal three-dimensional structure of the oriented strand board according to claim 1, characterized in that The optimization steps of the computer vision model include: Screening the mask image generated based on the original image A through a preset area range to remove the noise and mis-identified areas in the original image A; Comparing the screened mask image with the original image A, further adjusting the mask image, and merging the adjusted mask images to generate a single-layer wood chip distribution image B.
4. The method for reconstructing the three-dimensional internal structure of the oriented strand board according to claim 3, characterized in that, The area range is 20 - 70 cm², which is used to retain the effective wood chip mask.
5. The method for reconstructing the internal three-dimensional structure of the oriented strand board according to claim 1, characterized in that, The expression for calculating the compression ratio of each layer of wood chips in the thickness direction of the slab is: ， Among them, is the compression ratio at the thickness, is the average density of the slab before hot pressing, and is the density at the thickness of the slab after hot pressing.
6. The method for reconstructing the three-dimensional internal structure of the oriented strand board according to claim 5, wherein, The expression for calculating the actual thickness of each layer of wood chips in the slab according to the compression ratio is: ， Among them, is the thickness of the nth layer of particles after hot pressing, and H is the pre-set thickness of the particles before hot pressing.
7. The method for reconstructing the three-dimensional internal structure of the oriented strand board according to claim 2, wherein Reconstructing the internal three-dimensional structure of the oriented strand board includes: Based on the position coordinates and layer index information of single wood chips in the single-layer wood chip distribution image B, stretching the two-dimensional contour by the actual thickness distance of each layer of wood chips in the thickness direction to form a three-dimensional grid model, generating an OBJ format file containing vertex coordinates and patch topology based on the three-dimensional grid model, and inputting the OBJ format file into 3D modeling software to realize structure visualization.
8. A three-dimensional structure reconstruction device for the interior of oriented strand board, characterized in that, Including: An acquisition module for obtaining the original image A of each layer of wood chips during the slab paving process; An extraction module for performing laminated wood chip segmentation on the original image A through a pre-constructed computer vision model to obtain a single-layer wood chip distribution image B, and extracting the two-dimensional contour, position coordinates, and layer index information of single wood chips in the single-layer wood chip distribution image B; A calculation module for obtaining the cross-sectional density gradient data of the slab, calculating the compression ratio of each layer of wood chips in the thickness direction of the slab based on the cross-sectional density gradient data, and calculating the actual thickness of each layer of wood chips in the slab according to the compression ratio; A reconstruction module for reconstructing the internal three-dimensional structure of the oriented strand board based on the two-dimensional contour, position coordinates, layer index information, and actual thickness.
9. An electronic terminal, characterized in that, Including a processor and a memory connected to the processor, and a computer program is stored in the memory. When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are executed.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.