A method and system for detecting flatness of wood processing based on data analysis

Abstract

The present invention discloses a data analysis-based flatness detection method and system for wood processing, relating to the field of irregular surface detection. The method comprises: using a measuring instrument to measure the surface of the wood to be inspected to generate three-dimensional point cloud data of the wood, and using a distance measurement sensor to obtain the relative distance between the measuring instrument and the wood to be inspected; combining the relative distance measurement result with a Bezier curve to draw a distance curve, and analyzing the changes in the distance curve to obtain the flatness of the wood to be inspected; using the three-dimensional point cloud data to generate a two-dimensional grayscale image of the wood to determine the flatness parameters of the wood surface; and transmitting the flatness parameters to a wood processing controller. By deeply analyzing the microstructure of the wood surface, the present invention reveals the length and area information of the uneven areas on the wood surface, facilitating the automatic adjustment of control parameters based on the actual flatness of the wood, thereby improving the quality and production efficiency of wood processing.

Description

Technical Field

[0001] The present invention relates to the field of irregular surface detection, and in particular to a flatness detection method and system for wood processing based on data analysis. Background Art

[0002] Wood is a natural material widely used in construction, furniture manufacturing, paper production and other fields. It is obtained from trees and has many unique properties, such as renewability, biodegradability and beautiful natural texture. Depending on different needs and applications, wood can be processed and treated in various ways, such as cutting, polishing, painting, etc.

[0003] Wood processing is the process of converting logs into products that can be used in various construction and manufacturing applications. Flatness testing in wood processing is an important link to ensure product quality and compliance with usage requirements. Flatness testing involves the use of various methods and techniques to measure the surface flatness of wood processed parts, and to ensure the adaptability and aesthetics of wood products in processing, assembly or final application.

[0004] However, the existing technology can only determine whether there are uneven areas on the wood surface when performing wood processing flatness detection, but cannot analyze the corresponding size of the uneven area based on the judgment result, and thus cannot optimize the wood processing process based on the detection result.

[0005] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for detecting flatness of wood processing based on data analysis, the method comprising the following steps:

[0008] S1. Use a measuring instrument to measure the surface of the wood to be tested to generate three-dimensional point cloud data of the wood, and use a distance measurement sensor to obtain the relative distance between the measuring instrument and the wood to be tested;

[0009] S2. Combining the relative distance measurement result with the Bezier curve to draw a distance curve, and analyzing the change of the distance curve to obtain the flatness of the wood to be tested;

[0010] S3. If the flatness is greater than the preset value, it indicates that the processed wood meets the requirements, and the wood flatness test is completed. If the flatness is less than the preset value, it indicates that the processed wood does not meet the requirements, and step S4 is executed to perform wood morphology characterization processing to obtain morphological information of the wood surface;

[0011] S4. Generate a two-dimensional grayscale image of the wood using the three-dimensional point cloud data, and process the two-dimensional grayscale image of the wood based on a morphology characterization algorithm to determine the smoothing parameters of the wood surface;

[0012] S5. Send the leveling parameters to the wood processing controller, and the wood processing controller adjusts control parameters during the wood processing based on the leveling parameters.

[0013] Furthermore, the relative distance measurement result is combined with the Bezier curve to draw a distance curve, and the change of the distance curve is analyzed to obtain the flatness of the wood to be tested, which includes the following steps:

[0014] S21. Determine the target contour line according to the wood processing requirements, traverse the numerical points in the target contour line based on the relative distance measurement quantity and the relative distance measurement values, and generate a numerical point set after the traversal is completed;

[0015] S22. Constructing a Bezier curve expression for each set of numerical points, and obtaining the maximum curvature of each set of numerical points based on the Bezier curve expression to obtain a sequence of local curvature maximum values;

[0016] S23. Determine the shear points of the relative distance measurement values ​​according to the local curvature maximum value sequence, and obtain the flatness of the wood to be tested based on the ratio of the number of shear points to the number of relative distance measurements.

[0017] Furthermore, constructing a Bezier curve expression for each set of numerical points, and obtaining the maximum curvature of each set of numerical points based on the Bezier curve expression to obtain a sequence of local curvature maximum values ​​includes the following steps:

[0018] S221, dividing the numerical points in each numerical point set according to a preset parameter ratio, and taking the numerical points corresponding to the initial and end positions as key points of the numerical point set based on the processing results;

[0019] S222. Constructing a Bezier curve for each set of numerical points based on the key points, and defining a corresponding curve expression according to the Bezier curve;

[0020] S223. Calculate the first-order differential and the second-order differential of each numerical point set according to the curve expression, and calculate the maximum curvature of the numerical point set based on the first-order differential and the second-order differential to obtain a local curvature maximum sequence.

[0021] Furthermore, determining the shear points of the relative distance measurement values ​​according to the local curvature maximum sequence, and obtaining the flatness of the wood to be tested based on the ratio of the number of shear points to the number of relative distance measurements includes the following steps:

[0022] S231, traversing the local curvature maximum values ​​in the local curvature maximum value sequence, eliminating the local curvature maximum values ​​in the local curvature maximum value sequence that are smaller than a preset threshold, and obtaining a local curvature maximum value sequence;

[0023] S232, calculating a numerical point screening range according to the relative distance measurement quantity, and traversing a local curvature maximum sequence to determine a local curvature maximum located within the numerical point screening range;

[0024] S233, comparing the local curvature maximum value with the relative distance measurement number to determine the shear point of the relative distance measurement value, and determining the number of shear points;

[0025] S234: Calculate the ratio between the shear point data point and the relative distance measurement number, and use the ratio result as a wood flatness measurement index to obtain a flatness test result of the wood to be tested.

[0026] Furthermore, generating a two-dimensional grayscale image of the wood using the three-dimensional point cloud data, and processing the two-dimensional grayscale image of the wood based on a morphology characterization algorithm to determine the smoothing parameters of the wood surface includes the following steps:

[0027] S41, performing noise reduction filtering on the wood 3D point cloud data, and converting the wood 3D point cloud data into a wood 2D grayscale image using an orthogonal projection method;

[0028] S42, performing edge detection processing on the two-dimensional grayscale image of the wood using a morphology characterization algorithm to obtain an edge detection result, and converting the edge detection result from the original space into the Hough space to generate data points corresponding to the wood surface;

[0029] S43. Analyze the wood surface data points based on the distribution law in the Hough space, and determine the combined size of the wood surface data points according to the analysis results to obtain flattening parameter data.

[0030] Furthermore, analyzing the wood surface data points based on the distribution law in the Hough space, and determining the combined size of the wood surface data points according to the analysis results to obtain the flattening parameter data includes the following steps:

[0031] S431, dividing the data points belonging to the same continuous contour in the Hough space into the same data point set, and grouping every two data points into a group according to the distribution law in the Hough space to complete the data point grouping;

[0032] S432, calculating the probability that the shape enclosed by the straight lines corresponding to the data points in the data point set in the original space is a regular polygon based on the grouping result of the data points;

[0033] S432, calculating the probability that the shape enclosed by the corresponding straight lines of the data points in the original space is a regular polygon based on the extraction results, and determining the geometric shape composed of the data points on the wood surface according to the probability result;

[0034] S433, measuring the length of the corresponding constituent straight lines according to the geometric shape, and obtaining the area corresponding to the set of all data points based on the length result;

[0035] S434: Compare the corresponding areas of each data point set, and determine the flat area and the uneven area on the wood surface based on the comparison result and the evaluation criteria.

[0036] In a second aspect, the present invention further provides a wood processing flatness detection system based on data analysis, the wood processing flatness detection system comprising:

[0037] The detection data acquisition module uses a measuring instrument to measure the surface of the wood to be detected to generate three-dimensional point cloud data of the wood, and uses a distance measurement sensor to obtain the relative distance between the measuring instrument and the wood to be detected;

[0038] The flatness detection module combines the relative distance measurement results with the Bezier curve to draw a distance curve, and analyzes the changes in the distance curve to obtain the flatness of the wood to be tested;

[0039] Execute the judgment and analysis module. If the flatness is greater than the preset value, it means that the processed wood meets the requirements, and then complete the wood flatness detection. If the flatness is less than the preset value, it means that the processed wood does not meet the requirements, and then execute the step of the morphological information determination module to perform wood morphology characterization processing to obtain the morphological information of the wood surface;

[0040] A morphological information determination module is used to generate a two-dimensional grayscale image of the wood using the three-dimensional point cloud data of the wood, and to process the two-dimensional grayscale image of the wood based on a morphological characterization algorithm to determine the smoothing parameters of the wood surface;

[0041] The processing control adjustment module is used to send the leveling parameters to the wood processing controller, and the wood processing controller adjusts the control parameters of the wood during the processing based on the leveling parameters.

[0042] The beneficial effects of the present invention are:

[0043] 1. The present invention can obtain high-precision and high-resolution wood surface shape data by generating three-dimensional point cloud data of the wood surface, and analyze the flatness of the wood surface based on relative distance measurement and Bezier curve drawing distance curve, providing data support for further processing and decision-making. At the same time, after the flatness analysis is completed, the two-dimensional grayscale image and morphology characterization algorithm can be used to deeply analyze the microstructure of the wood surface, revealing the length and area information of the uneven areas on the wood surface, facilitating the automatic adjustment of control parameters according to the actual flatness of the wood, thereby improving the quality and production efficiency of wood processing.

[0044] 2. After confirming the target contour line according to the specific needs of wood processing, the present invention traverses the numerical points in the target contour line and generates a numerical point set based on the number and value of relative distance measurements, thereby ensuring the integrity and meticulousness of the data. The curvature maximum value of each numerical point set is obtained through the Bezier curve, and a local curvature maximum sequence is generated to further identify the key change areas on the wood surface, that is, potential uneven areas. Finally, the shear point of the relative distance measurement value is determined according to the local curvature maximum sequence, which can accurately identify slight changes in the surface and reflect the local flatness of the wood surface, thereby improving the accuracy of wood flatness detection.

[0045] 3. The present invention pre-improves the quality of three-dimensional point cloud data through noise reduction and filtering processing, selects orthogonal projection to convert the three-dimensional point cloud data into a two-dimensional grayscale image, and performs edge detection processing using a morphology characterization algorithm. It can accurately identify the key geometric edges and features of the wood surface, determine the combined size of the wood surface data points, and obtain flattening parameter data, providing a judgment basis for subsequent wood processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0047] Figure 1 This is a flow chart of a method for detecting flatness of wood processing based on data analysis according to an embodiment of the present invention;

[0048] Figure 2 The present invention is a block diagram of a wood processing flatness detection system based on data analysis according to an embodiment of the present invention.

[0049] In the picture:

[0050] 1. Detection data acquisition module; 2. Flatness detection module; 3. Execution judgment and analysis module; 4. Shape information determination module; 5. Processing control and adjustment module. DETAILED DESCRIPTION

[0051] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0052] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0053] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0054] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0055] See also Figure 1 The present invention provides a method for detecting flatness of wood processing based on data analysis, and the method comprises the following steps:

[0056] S1. Use a measuring instrument to measure the surface of the wood to be inspected to generate three-dimensional point cloud data of the wood, and use a distance measurement sensor to obtain the relative distance between the measuring instrument and the wood to be inspected.

[0057] In this embodiment, a measuring instrument is used to measure the surface of the wood to be inspected to generate three-dimensional point cloud data of the wood, and a distance measuring sensor is used to obtain the relative distance between the measuring instrument and the wood to be inspected. A three-dimensional scanner can be used to set the working range and scanning path of the measuring instrument according to the size and shape of the wood. The measuring instrument moves along the preset path and continuously scans the wood surface using laser or other sensing technology to generate three-dimensional point cloud data from multiple angles; and the distance measuring sensor is used to obtain the relative distance between the measuring instrument and the wood.

[0058] S2. Combining the relative distance measurement result with the Bezier curve to draw a distance curve, and analyzing the change of the distance curve to obtain the flatness of the wood to be tested.

[0059] In this embodiment, the relative distance measurement result is combined with the Bezier curve to draw a distance curve, and the change of the distance curve is analyzed to obtain the flatness of the wood to be tested, including the following steps:

[0060] S21. Determine the target contour line according to the wood processing requirements, traverse the numerical points in the target contour line based on the relative distance measurement quantity and the relative distance measurement values, and generate a numerical point set after the traversal is completed;

[0061] S22. Constructing a Bezier curve expression for each set of numerical points, and obtaining the maximum curvature of each set of numerical points based on the Bezier curve expression to obtain a sequence of local curvature maximum values;

[0062] S23. Determine the shear points of the relative distance measurement values ​​according to the local curvature maximum value sequence, and obtain the flatness of the wood to be tested based on the ratio of the number of shear points to the number of relative distance measurements.

[0063] Specifically, when confirming the target contour line according to the wood processing requirements, and traversing the numerical points in the target contour line based on the number and numerical value of relative distance measurements to generate a numerical point set, the contour line can be set according to the wood processing requirements, including the expected use environment and functional requirements, to determine the required flatness standard, that is, the target level of flatness. The contour line represents a specific height or distance on the wood surface. The target contour line is traversed, and the numerical points that meet the conditions are selected and recorded according to the set standards. The numerical point set is extracted and generated from the traversed data.

[0064] Specifically, constructing a Bezier curve expression for each set of numerical points, and obtaining the maximum curvature of each set of numerical points based on the Bezier curve expression to obtain a sequence of local curvature maximum values ​​includes the following steps:

[0065] S221, dividing the numerical points in each numerical point set according to a preset parameter ratio, and taking the numerical points corresponding to the initial and end positions as key points of the numerical point set based on the processing results;

[0066] S222. Constructing a Bezier curve for each set of numerical points based on the key points, and defining a corresponding curve expression according to the Bezier curve;

[0067] S223. Calculate the first-order differential and the second-order differential of each numerical point set according to the curve expression, and calculate the maximum curvature of the numerical point set based on the first-order differential and the second-order differential to obtain a local curvature maximum sequence.

[0068] Among them, the calculation formula for the maximum curvature of the numerical point set is:

[0069] ;

[0070] Where Lmax represents the maximum curvature of the numerical point set, b represents the curve value of the numerical point set, dm(t) represents the first-order differential value corresponding to the t-th numerical point set, dn(t) represents the second-order differential value corresponding to the t-th numerical point set, and t represents the number of numerical point sets.

[0071] Specifically, determining the shear points of the relative distance measurement values ​​according to the local curvature maximum sequence, and obtaining the flatness of the wood to be tested based on the ratio of the number of shear points to the number of relative distance measurements includes the following steps:

[0072] S231, traversing the local curvature maximum values ​​in the local curvature maximum value sequence, eliminating the local curvature maximum values ​​in the local curvature maximum value sequence that are smaller than a preset threshold, and obtaining a local curvature maximum value sequence;

[0073] S232, calculating a numerical point screening range according to the relative distance measurement quantity, and traversing a local curvature maximum sequence to determine a local curvature maximum located within the numerical point screening range;

[0074] S233, comparing the local curvature maximum value with the relative distance measurement number to determine the shear point of the relative distance measurement value, and determining the number of shear points;

[0075] S234: Calculate the ratio between the shear point data point and the relative distance measurement number, and use the ratio result as a wood flatness measurement index to obtain a flatness test result of the wood to be tested.

[0076] The step of comparing the local curvature maximum value with the relative distance measurement quantity to determine the shear point of the relative distance measurement value includes the following steps:

[0077] When the number of local curvature maxima within the numerical point screening range is greater than or equal to the number of relative distance measurements, the curvature maximum of the target numerical point is determined according to the corresponding local curvature maximum;

[0078] The local curvature maximum value within the numerical point screening range is replaced by the target numerical point curvature maximum value, and the pixel point corresponding to the maximum curvature value in the final screened curvature value is determined as the shear point.

[0079] S3. If the flatness is greater than the preset value, it means that the processed wood meets the requirements, and the wood flatness detection is completed. If the flatness is less than the preset value, it means that the processed wood does not meet the requirements, and step S4 is executed to perform wood morphology characterization processing to obtain morphological information of the wood surface.

[0080] S4. Generate a two-dimensional grayscale image of the wood using the three-dimensional point cloud data of the wood, and process the two-dimensional grayscale image of the wood based on a morphology characterization algorithm to determine the flatness parameters of the wood surface.

[0081] In this embodiment, generating a two-dimensional grayscale image of the wood using the three-dimensional point cloud data of the wood, and processing the two-dimensional grayscale image of the wood based on the morphology characterization algorithm to determine the smoothing parameters of the wood surface includes the following steps:

[0082] S41, performing noise reduction filtering on the wood 3D point cloud data, and converting the wood 3D point cloud data into a wood 2D grayscale image using an orthogonal projection method;

[0083] S42, performing edge detection processing on the two-dimensional grayscale image of the wood using a morphology characterization algorithm to obtain an edge detection result, and converting the edge detection result from the original space into the Hough space to generate data points corresponding to the wood surface;

[0084] S43. Analyze the wood surface data points based on the distribution law in the Hough space, and determine the combined size of the wood surface data points according to the analysis results to obtain flattening parameter data.

[0085] Specifically, when performing noise reduction filtering on the three-dimensional point cloud data of wood and converting these data into two-dimensional grayscale images through orthogonal projection, noise reduction algorithms such as Gaussian filtering, median filtering or other point cloud noise reduction techniques can be applied to remove or reduce the impact of noise; the processed point cloud data must be integrated and aligned as necessary to ensure that all data are based on the same reference frame, and the data must be downsampled or compressed for easy processing and conversion while retaining key geometric information.

[0086] Orthogonal projection is selected to process point cloud data. This method can compress three-dimensional data into two-dimensional data without changing the characteristics of the object. A two-dimensional grayscale image is generated by mapping the three-dimensional coordinates of the point cloud to a two-dimensional plane and converting the density or height of the points into grayscale values.

[0087] Specifically, when using a morphological characterization algorithm to perform edge detection processing on a two-dimensional grayscale image of wood to obtain an edge detection result, and converting the edge detection result from the original space into the Hough space to generate data points corresponding to the wood surface, a morphological algorithm can be used to enhance the structural edges in the image, and an edge detection algorithm (such as a Canny edge detector) is applied to identify and extract the edges of the wood surface; according to the edge detection result, the parameters of the Hough transform, such as the resolution of the angle and distance, are set, the edge points in the image space are mapped to the Hough space, and the position of each point is converted into a curve in the parameter space; in the Hough space, the intersection points of different curves represent the straight lines or shape edges in the original image, and these intersection points are extracted from the Hough space, and these points represent specific straight lines or edges on the wood surface.

[0088] Specifically, analyzing the wood surface data points based on the distribution law in the Hough space, and determining the combined size of the wood surface data points according to the analysis results to obtain the flattening parameter data includes the following steps:

[0089] S431, dividing the data points belonging to the same continuous contour in the Hough space into the same data point set, and grouping every two data points into a group according to the distribution law in the Hough space to complete the data point grouping;

[0090] S432, calculating the probability that the shape enclosed by the straight lines corresponding to the data points in the data point set in the original space is a regular polygon based on the grouping result of the data points;

[0091] S432, calculating the probability that the shape enclosed by the corresponding straight lines of the data points in the original space is a regular polygon based on the extraction results, and determining the geometric shape composed of the data points on the wood surface according to the probability result;

[0092] S433, measuring the length of the corresponding constituent straight lines according to the geometric shape, and obtaining the area corresponding to the set of all data points based on the length result;

[0093] S434: Compare the corresponding areas of each data point set, and determine the flat area and the uneven area on the wood surface based on the comparison result and the evaluation criteria.

[0094] The judging criteria include:

[0095] If the corresponding areas of two adjacent sets of data points are equal, it means that this area is a flat area;

[0096] If the area difference between two adjacent sets of data points exceeds the set tolerance, it indicates that this area is a non-flat area, and the areas corresponding to the data points in the non-flat area are added together as the range value of the non-flat area.

[0097] S5. Send the leveling parameters to the wood processing controller, and the wood processing controller adjusts control parameters during the wood processing based on the leveling parameters.

[0098] In this embodiment, when the leveling parameters are sent to the wood processing controller and the wood processing controller adjusts the control parameters of the wood during the processing based on the leveling parameters, the processing control parameters that need to be adjusted can be determined based on the flatness parameters of the wood, such as tool depth, feed rate or other mechanical settings; ensure that the leveling parameters can be securely transmitted to the processing controller through an appropriate communication protocol (such as TCP / IP, Modbus, OPC, etc.), and send the parameters from the analysis system to the processing controller.

[0099] After receiving the leveling parameters, the processing controller analyzes the data and adjusts the settings of the mechanical equipment as needed. The controller automatically adjusts the processing parameters based on the received parameters, such as adjusting the tool position, changing the speed of the machine tool, or applying different processing strategies.

[0100] See also Figure 2 The present invention also provides a wood processing flatness detection system based on data analysis, the wood processing flatness detection system comprising:

[0101] The detection data acquisition module 1 uses a measuring instrument to measure the surface of the wood to be detected to generate three-dimensional point cloud data of the wood, and uses a distance measurement sensor to obtain the relative distance between the measuring instrument and the wood to be detected;

[0102] Flatness detection module 2 combines the relative distance measurement result with the Bezier curve to draw a distance curve, and analyzes the change of the distance curve to obtain the flatness of the wood to be tested;

[0103] Execute the judgment and analysis module 3. If the flatness is greater than the preset value, it means that the processed wood meets the requirements, and then complete the wood flatness detection. If the flatness is less than the preset value, it means that the processed wood does not meet the requirements, and then execute the step of the morphological information determination module to perform wood morphology characterization processing to obtain morphological information of the wood surface;

[0104] a morphological information determination module 4, configured to generate a two-dimensional grayscale image of the wood using the three-dimensional point cloud data of the wood, and to process the two-dimensional grayscale image of the wood based on a morphological characterization algorithm to determine the smoothing parameters of the wood surface;

[0105] The processing control adjustment module 5 is used to send the leveling parameters to the wood processing controller, and the wood processing controller adjusts the control parameters of the wood during the processing based on the leveling parameters.

[0106] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented using electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0107] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A method for detecting flatness of wood processing based on data analysis, characterized in that: The flatness detection method for wood processing comprises the following steps: S1. Using a measuring instrument to measure the surface of the wood to be inspected to generate three-dimensional point cloud data of the wood, and using a distance measurement sensor to obtain the relative distance between the measuring instrument and the wood to be inspected; the data processing module also includes processing the relative distance; S2. Combining the relative distance measurement result with the Bezier curve to draw a distance curve, and analyzing the change of the distance curve to obtain the flatness of the wood to be tested; S3. If the flatness is greater than a preset value, it indicates that the processed wood meets the requirements, and the wood flatness test is completed. If the flatness is less than the preset value, it indicates that the processed wood does not meet the requirements, and step S4 is executed to perform wood morphology characterization processing to obtain morphological information of the wood surface; wherein the flatness is equal to the preset value, it indicates that the processed wood meets the requirements; S4, generating a two-dimensional grayscale image of the wood using the three-dimensional point cloud data, and processing the two-dimensional grayscale image of the wood based on a morphology characterization algorithm to determine a flattening parameter of the wood surface; the flattening parameter is outputted via an output module; S5. Sending the leveling parameters to the wood processing controller, which adjusts control parameters during the wood processing based on the leveling parameters; The method of combining the relative distance measurement result with the Bezier curve to draw a distance curve, and analyzing the change of the distance curve to obtain the flatness of the wood to be tested includes the following steps: S21. Determine the target contour line according to the wood processing requirements, traverse the numerical points in the target contour line based on the relative distance measurement quantity and the relative distance measurement values, and generate a numerical point set after the traversal is completed; S22. Constructing a Bezier curve expression for each set of numerical points, and obtaining the maximum curvature of each set of numerical points based on the Bezier curve expression to obtain a sequence of local curvature maximum values; S23, determining the shear points of the relative distance measurement values ​​according to the local curvature maximum value sequence, and obtaining the flatness of the wood to be tested based on the ratio of the number of shear points to the number of relative distance measurements; The method of generating a two-dimensional grayscale image of the wood using the three-dimensional point cloud data of the wood, and processing the two-dimensional grayscale image of the wood based on the morphology characterization algorithm to determine the smoothing parameters of the wood surface includes the following steps: S41, performing noise reduction filtering on the wood 3D point cloud data, and converting the wood 3D point cloud data into a wood 2D grayscale image using an orthogonal projection method; S42. Performing edge detection processing on the two-dimensional grayscale image of the wood using a morphology characterization algorithm to obtain an edge detection result, and converting the edge detection result from the original space into the Hough space to generate data points corresponding to the wood surface; wherein, when converting the edge detection result from the original space into the Hough space to generate data points corresponding to the wood surface, a morphology algorithm is used to enhance structural edges in the image, and an edge detection algorithm is applied to identify and extract edges of the wood surface; S43. Analyze the wood surface data points based on the distribution law in the Hough space, and determine the combined size of the wood surface data points according to the analysis results to obtain flattening parameter data.

2. A method for detecting flatness of wood processing based on data analysis according to claim 1, characterized in that: The step of constructing a Bezier curve expression for each set of numerical points, obtaining the maximum curvature of each set of numerical points based on the Bezier curve expression, and obtaining a sequence of local curvature maximum values ​​comprises the following steps: S221, dividing the numerical points in each numerical point set according to a preset parameter ratio, and taking the numerical points corresponding to the initial and end positions as key points of the numerical point set based on the processing results; S222. Constructing a Bezier curve for each set of numerical points based on the key points, and defining a corresponding curve expression according to the Bezier curve; S223. Calculate the first-order differential and the second-order differential of each numerical point set according to the curve expression, and calculate the maximum curvature of the numerical point set based on the first-order differential and the second-order differential to obtain a local curvature maximum sequence.

3. The method for detecting flatness of wood processing based on data analysis according to claim 2, characterized in that: The calculation formula for the maximum curvature of the numerical point set is: ； Where, L max Represents the maximum curvature of a set of numerical points, b represents the curve value of a set of numerical points, d m ( t ) indicates the t The first-order differential value corresponding to the set of numerical points, d n ( t ) indicates the t The second-order differential value corresponding to the set of numerical points, t Indicates the number of numerical point sets.

4. The method for detecting flatness of wood processing based on data analysis according to claim 3, characterized in that: The method of determining the shear points of the relative distance measurement values ​​according to the local curvature maximum sequence and obtaining the flatness of the wood to be tested based on the ratio of the number of shear points to the number of relative distance measurements comprises the following steps: S231, traversing the local curvature maximum values ​​in the local curvature maximum value sequence, eliminating the local curvature maximum values ​​in the local curvature maximum value sequence that are smaller than a preset threshold, and obtaining a local curvature maximum value sequence; S232, calculating a numerical point screening range according to the relative distance measurement quantity, and traversing a local curvature maximum sequence to determine a local curvature maximum located within the numerical point screening range; S233, comparing the local curvature maximum value with the relative distance measurement number to determine the shear point of the relative distance measurement value, and determining the number of shear points; S234: Calculate the ratio between the shear point data point and the relative distance measurement number, and use the ratio result as a wood flatness measurement index to obtain a flatness test result of the wood to be tested.

5. The method for detecting flatness of wood processing based on data analysis according to claim 4, characterized in that: The step of comparing the local curvature maximum value with the relative distance measurement quantity to determine the shear point of the relative distance measurement value comprises the following steps: When the number of local curvature maxima within the numerical point screening range is greater than or equal to the number of relative distance measurements, the curvature maximum of the target numerical point is determined according to the corresponding local curvature maximum; The local curvature maximum value within the numerical point screening range is replaced by the target numerical point curvature maximum value, and the pixel point corresponding to the maximum curvature value in the final screened curvature value is determined as the shear point.

6. The method for detecting flatness of wood processing based on data analysis according to claim 5, characterized in that: The analyzing of the wood surface data points based on the distribution law in the Hough space and determining the combined size of the wood surface data points according to the analysis results to obtain the flattening parameter data comprises the following steps: S431, dividing the data points belonging to the same continuous contour in the Hough space into the same data point set, and grouping every two data points into a group according to the distribution law in the Hough space to complete the data point grouping; S432, calculating the probability that the shape enclosed by the straight lines corresponding to the data points in the data point set in the original space is a regular polygon based on the grouping result of the data points; S432, calculating the probability that the shape enclosed by the corresponding straight lines of the data points in the original space is a regular polygon based on the extraction results, and determining the geometric shape composed of the data points on the wood surface according to the probability result; S433, measuring the length of the corresponding constituent straight lines according to the geometric shape, and obtaining the area corresponding to the set of all data points based on the length result; S434: Compare the corresponding areas of each data point set, and determine the flat area and the uneven area on the wood surface based on the comparison result and the evaluation criteria.

7. The method for detecting flatness of wood processing based on data analysis according to claim 6, characterized in that: The judging criteria include: If the corresponding areas of two adjacent sets of data points are equal, it means that this area is a flat area; If the area difference between two adjacent sets of data points exceeds the set tolerance, it indicates that this area is a non-flat area, and the areas corresponding to the data points in the non-flat area are added together as the range value of the non-flat area.

8. A wood processing flatness detection system based on data analysis, used to implement the wood processing flatness detection method based on data analysis according to any one of claims 1 to 7, characterized in that: The wood processing flatness detection system includes: The detection data acquisition module uses a measuring instrument to measure the surface of the wood to be detected to generate three-dimensional point cloud data of the wood, and uses a distance measurement sensor to obtain the relative distance between the measuring instrument and the wood to be detected; The flatness detection module combines the relative distance measurement results with the Bezier curve to draw a distance curve, and analyzes the changes in the distance curve to obtain the flatness of the wood to be tested; Execute the judgment and analysis module. If the flatness is greater than the preset value, it means that the processed wood meets the requirements, and then complete the wood flatness detection. If the flatness is less than the preset value, it means that the processed wood does not meet the requirements. Then use the morphological information determination module to perform wood morphology characterization processing to obtain the morphological information of the wood surface; A morphological information determination module is used to generate a two-dimensional grayscale image of the wood using the three-dimensional point cloud data of the wood, and to process the two-dimensional grayscale image of the wood based on a morphological characterization algorithm to determine the smoothing parameters of the wood surface; The processing control adjustment module is used to send the leveling parameters to the wood processing controller, and the wood processing controller adjusts the control parameters of the wood during the processing based on the leveling parameters.

Images