Surface flatness detection method and system for molding loading and unloading machines

Abstract

The present invention relates to the field of flatness detection technology, and specifically to a surface flatness detection method and system for a molding loading and unloading machine. The method obtains an initial defect index based on the difference in the distance between the block point cloud data of the molding machine surface and the reference plane, and corrects the initial defect index based on the difference in the overall distribution trend of the block point cloud data and the point cloud data of the molding machine surface, as well as the position distribution of the block point cloud data to obtain a corrected defect index; a fitting coefficient is obtained based on the discrete degree of the corrected defect index of each block in a preset direction, the change trend of the overall distribution trend of the block point cloud data of each block in a preset direction, and the corrected defect index, and the fitting coefficient is used to perform plane fitting on the point cloud data, and the flatness of the molding machine surface is detected based on the distance from the point cloud data to the fitting plane. The present invention improves the accuracy of flatness detection of the loading and unloading surfaces of the molding machine.

Description

Technical Field

[0001] The present invention relates to the technical field of flatness detection, and in particular to a surface flatness detection method and system for a molding loading and unloading machine. Background Art

[0002] A molding press is a type of equipment specifically designed for forming materials such as plastics, rubber, ceramics, and glass. It solidifies the plastic material by applying pressure and heat, forming it into the desired shape and size. It is widely used in the automotive, aviation, and construction industries. The flatness of the loading and unloading surfaces of a molding press is a key factor affecting the quality of molded products. Testing the flatness of these surfaces is crucial for ensuring product quality, improving production efficiency, and reducing equipment wear.

[0003] Existing methods usually use a laser beam to scan the upper and lower material surfaces of the molding machine, and construct a three-dimensional height map of the surface through the intensity or position changes of the reflected light, so as to analyze the flatness of the upper and lower material surfaces; however, vibration may occur during the operation of the molding machine, causing fluctuations in the point cloud data generated by the vibration in the upper and lower material surfaces. At the same time, the uneven defects of the upper and lower material surfaces themselves will also cause fluctuations in the point cloud data, causing the point cloud data generated by the normal vibration of the device to be mistakenly identified as uneven defects, and thus the accuracy of the flatness detection of the upper and lower material surfaces of the molding machine is low. Summary of the Invention

[0004] In order to solve the technical problem that the point cloud data of normal vibration during the operation of the molding machine reduces the accuracy of the flatness detection of the loading and unloading surfaces of the molding machine, the purpose of the present invention is to provide a surface flatness detection method and system for the molding machine loading and unloading machine. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a surface flatness detection method for a molding loading and unloading machine, the method comprising:

[0006] Acquire point cloud data of the molding machine surface; divide the point cloud data into a plurality of blocks;

[0007] Obtaining a reference plane for each block, and obtaining an initial defect index for each block based on the difference between the distances of the point cloud data of each block and the reference plane;

[0008] Correcting the initial defect index based on a difference between an overall distribution trend of the point cloud data of each block and an overall distribution trend of the point cloud data of the molding machine surface, as well as a position distribution of the point cloud data of each block, to obtain a corrected defect index for each block;

[0009] Obtaining a fitting coefficient for the point cloud data of each block based on the degree of dispersion of the corrected defect index of all blocks in each preset direction, a changing trend of the overall distribution trend of the point cloud data of all blocks in each preset direction, and the corrected defect index of each block;

[0010] A plane fitting is performed on the point cloud data of the molding machine surface based on the fitting coefficient, and the flatness of the molding machine surface is detected according to the distance from the point cloud data of the molding machine surface to the plane obtained by fitting.

[0011] Furthermore, the step of obtaining a reference plane for each block and obtaining an initial defect index for each block based on a difference in distance between the point cloud data of each block and the reference plane includes:

[0012] Divide the point cloud data of each block into normal point cloud data and abnormal point cloud data;

[0013] Perform plane fitting on the normal point cloud data of each block to obtain a reference plane of the corresponding block, and obtain the quartiles of the distance from each type of point cloud data in each block to the reference plane;

[0014] The quartiles corresponding to each type of point cloud data in each block form an n-tuple, where n is the total number of quartiles corresponding to each type of point cloud data; the distance between the n-tuples of normal point cloud data and abnormal point cloud data in each block is recorded as the distance difference index of each block;

[0015] The interquartile difference of the distance from the normal point cloud data of each block to the reference plane is obtained; the initial defect index of each block is obtained according to the interquartile difference and the distance difference index; the interquartile difference and the distance difference index are both positively correlated with the initial defect index.

[0016] Furthermore, obtaining the correction defect index of each block includes:

[0017] Performing plane fitting on the point cloud data of each block to obtain a second plane of the corresponding block, and performing plane fitting on the point cloud data of the molding machine surface to obtain an overall plane; obtaining a similarity index between the normal vector of the second plane of each block and the overall plane;

[0018] Obtaining a mean square error between all point cloud data of each block and its corresponding point cloud data on the second plane, and recording it as a fitting error of each block;

[0019] Obtaining a first correction coefficient for each block according to the similarity index and the fitting error; the similarity index and the first correction coefficient are negatively correlated, and the fitting error and the first correction coefficient are positively correlated;

[0020] The initial defect index of each block is weighted by using the sum of the first correction coefficient and a constant 1 to obtain a corrected defect index of each block.

[0021] Furthermore, obtaining the fitting coefficient of the point cloud data of each block includes:

[0022] Obtaining the discrete index and the concentrated index of the corrected defect index of all blocks in each preset direction for each block; obtaining the normal vibration index of each block in each preset direction based on the discrete index and the concentrated index;

[0023] Obtain the directional trend index of each block based on the change trend of the overall distribution trend of the point cloud data of all blocks in all preset directions;

[0024] According to the normal vibration index and the directional trend index, a second correction coefficient of each block is obtained; the normal vibration index and the second correction coefficient are negatively correlated, and the directional trend index and the second correction coefficient are positively correlated; the corrected defect index of each block is weighted using the second correction coefficient to obtain a final defect index of each block; the final defect index is negatively correlated and normalized to obtain a fitting coefficient for each point cloud data of each block.

[0025] Furthermore, obtaining the directional trend indicator of each block includes:

[0026] Obtain the angles between the normal vector of the second plane of each block and each coordinate axis of the coordinate system of the point cloud data, and record them as the analysis angles of each block in each dimension; one dimension corresponds to one coordinate axis; sequentially arrange the analysis angles of all blocks in each dimension in each preset direction of each block to obtain an angle sequence of each block in each dimension in each preset direction;

[0027] Obtain a first-order difference sequence of the angle sequence, and record the ratio of the maximum number of consecutive positive numbers and the maximum number of consecutive negative numbers in the first-order difference sequence to the total number of elements in the angle sequence as the local trend index of each block in each preset direction and each dimension; select the maximum value of the local trend index of each block in each preset direction and all dimensions as the overall trend index of each block in each preset direction;

[0028] The cumulative sum of the overall trend indicators of each block in all preset directions is used as the directional trend indicator of each block.

[0029] Furthermore, performing plane fitting on the point cloud data of the molding machine surface based on the fitting coefficient, and detecting the flatness of the molding machine surface according to the distance from the point cloud data of the molding machine surface to the plane obtained by fitting, includes:

[0030] Based on the fitting coefficients, a weighted least square method is used to perform plane fitting on the point cloud data of the molding machine surface to obtain a final reference plane;

[0031] Obtaining the distance from the centroid of the second plane of each block to the final reference plane, and recording it as the judgment distance of each block;

[0032] It is determined whether the judgment distances of all blocks on the surface of the molding machine are less than a preset threshold value. If so, the flatness of the surface of the molding machine is qualified; if not, the flatness of the surface of the molding machine is unqualified.

[0033] Furthermore, dividing the point cloud data of each block into normal point cloud data and abnormal point cloud data includes:

[0034] Perform plane fitting on the point cloud data of each block to obtain the first plane of the corresponding block;

[0035] Obtain the distance between all point cloud data of each block and the first plane, use the maximum inter-class variance method to obtain a partitioning threshold for the distance, and record the point cloud data with a distance less than the partitioning threshold as normal point cloud data, and record the point cloud data with a distance greater than or equal to the partitioning threshold as abnormal point cloud data.

[0036] Furthermore, the similarity index is cosine similarity.

[0037] Furthermore, the step of obtaining the discrete index and the concentrated index of the corrected defect index of all blocks in each preset direction of each block includes:

[0038] The discrete index is the variance of the corrected defect index of all blocks in each preset direction of each block, and the concentrated index is the mean of the corrected defect index of all blocks in each preset direction of each block.

[0039] In a second aspect, another embodiment of the present invention provides a surface flatness detection system for a molding loading and unloading machine, the system comprising:

[0040] A data acquisition module is used to obtain point cloud data of the molding machine surface; and divide the point cloud data into a plurality of blocks;

[0041] A defect analysis module is used to obtain a reference plane for each block and obtain an initial defect index for each block based on the difference in distance between the point cloud data of each block and the reference plane;

[0042] a defect correction module, configured to correct the initial defect index based on a difference between an overall distribution trend of the point cloud data of each block and an overall distribution trend of the point cloud data of the molding machine surface, as well as a position distribution of the point cloud data of each block, and obtain a corrected defect index for each block;

[0043] A fitting coefficient analysis module is used to obtain a fitting coefficient of the point cloud data of each block based on the discrete degree of the corrected defect index of all blocks in each preset direction of each block, the change trend of the overall distribution trend of the point cloud data of all blocks in all preset directions of each block, and the corrected defect index of each block;

[0044] The flatness detection module is used to perform plane fitting on the point cloud data of the molding machine surface based on the fitting coefficient, and detect the flatness of the molding machine surface according to the distance from the point cloud data of the molding machine surface to the fitted plane.

[0045] The present invention has the following beneficial effects:

[0046] In an embodiment of the present invention, the reference plane presents the overall distribution trend of the point cloud data normally displayed in the block, and the difference between the distances of the point cloud data of the block to the reference plane presents the degree of unevenness defects of the block, and an initial defect index is obtained; the point cloud data of the uneven defect of the device itself shows the characteristics of strong bending and jump changes, and the point cloud data fluctuations generated by the vibration of the device have high consistency, and the difference in the overall distribution trend of the point cloud data of the block and the point cloud data of the surface of the molding machine presents the fluctuation consistency of the point cloud data of the block, and the initial defect index is corrected in combination with the position distribution of the point cloud data of the block to obtain a corrected defect index, so as to reduce the dependence of the analysis of uneven defects on the point cloud data generated by the vibration of the device; in actual situations, there may be defects in the device itself with obvious bending around but relatively flat in the middle, and the defects in a certain direction of the bending defect may be divided The direction of the overall distribution trend of the point cloud data of the block shows a trend-like change feature, and the uneven defect characteristics of the block are relatively discrete, while the characteristics of the point cloud data generated by vibration due to the consistent vibration intensity of the device are opposite to the above two characteristics; according to the discrete degree of the corrected defect index of all blocks in the preset direction, the change trend of the overall distribution trend of the point cloud data of all blocks in the preset direction, the corrected defect index is adaptively adjusted to obtain the fitting coefficient, avoiding the misjudgment of large-scale defects easily caused by analyzing only the uneven defects of a single block, and reducing the probability of the point cloud data generated by the vibration of the device being mistakenly identified as the uneven defects of the device itself, so that the fitting plane constructed based on the fitting coefficient accurately represents the overall flatness level of the molding machine surface, and improves the accuracy of detecting the flatness of the molding machine surface based on the distance from the point cloud data to the fitting plane. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A flow chart of the steps of a surface flatness detection method for a molding loading and unloading machine provided in one embodiment of the present invention;

[0049] Figure 2 A flowchart of a method for obtaining fitting coefficients provided by one embodiment of the present invention;

[0050] Figure 3 A system structure diagram of a surface flatness detection system for a molding loading and unloading machine provided by one embodiment of the present invention;

[0051] Figure 4 A schematic diagram of a computer device for detecting surface flatness of a molding loading and unloading machine provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0052] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a surface flatness detection method and system for a molding loading and unloading machine according to the present invention, including its specific implementation, structure, features, and effectiveness. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0053] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0054] The following describes in detail a specific solution of a surface flatness detection method and system for a molding loading and unloading machine provided by the present invention in conjunction with the accompanying drawings.

[0055] Example 1:

[0056] The present invention proposes a surface flatness detection method for a molding loading and unloading machine, please refer to Figure 1 , which shows a flow chart of the steps of a surface flatness detection method for a molding loading and unloading machine provided by one embodiment of the present invention, the method comprising:

[0057] Step S1: Acquire point cloud data of the molding machine surface; divide the point cloud data into multiple blocks.

[0058] The loading and unloading of a molding machine typically refers to the upper and lower molds. During the production process, the workpiece is first placed in the designated blanking position, then the upper material is pressed into the blanking to stamp out the desired shape. Before the upper material is pressed into the blanking, a laser scanner is used to scan the loading surface of the molding machine in operation to obtain point cloud data of the molding surface. This solution is suitable for flatness testing of the loading and unloading surfaces of molding machines that produce products with smooth surfaces.

[0059] Point cloud data belongs to three-dimensional coordinates. In this embodiment, the point cloud data of the lower left corner of the loading surface of the molding machine is selected as the coordinate origin, the long side direction along the molding machine surface or the workbench is selected as the X-axis, the direction perpendicular to the X-axis and parallel to the ground is selected as the Y-axis, and the normal direction of the ground pointing upward to the molding machine surface is the Z-axis to construct a three-dimensional coordinate system; the point cloud data of the molding machine surface is in this three-dimensional coordinate system.

[0060] It should be noted that in other embodiments of the present invention, laser radar and ultrasonic sensors can also be used to obtain point cloud data, and other origins and directions can also be selected to construct a three-dimensional coordinate system. The collection of point cloud data is a well-known technology and is not limited here.

[0061] The feeding surface of the molding machine is relatively large. To ensure the accuracy of flatness detection, the point cloud data of the molding machine surface is divided into blocks. The specific method is as follows: the plane formed by the X-axis and Y-axis in the three-dimensional coordinate system is evenly divided into square areas with a side length of 10 cm; for the point cloud data of the molding machine surface, the point cloud data whose positions on the X-axis and Y-axis are within the same square area constitute a block.

[0062] In other embodiments, the point cloud data of the molding machine surface may be imported into ICEM (Integrated Computer Engineering and Manufacturing) software, and the structured meshing may be performed using the block strategy in the ICEM software to divide the point cloud data of the molding machine surface into a plurality of blocks.

[0063] Step S2: Obtain the reference plane of each block, and obtain the initial defect index of each block based on the difference between the distances between the point cloud data of each block and the reference plane.

[0064] Because the die-stamping machine is in operation during point cloud data collection, the feeder will vibrate during the pressing process. This vibration can cause unevenness on the feeder's surface. Furthermore, any inherent unevenness on the feeder's surface can also manifest as unevenness. Consequently, these unevenness defects can affect the flatness testing of the feeder's surface. Therefore, it's necessary to distinguish whether surface flatness anomalies are due to vibration or to inherent unevenness.

[0065] If the feed surface of the molding machine is uneven, such as bending or local deformation during the pressing process, the point cloud data of the feed surface will show poor consistency. The distance between the point cloud data at the uneven location and the overall plane formed by the point cloud data of the device surface will be far and inconsistent. Therefore, the farther and more inconsistent the distance between the block point cloud data and the reference plane, the greater the possibility that the block is an uneven defect of the device surface itself, and the greater the degree of unevenness of the block. The difference between the distance between the block point cloud data and the reference plane can be used to measure the degree of unevenness of the block, thereby obtaining an initial defect index.

[0066] Preferably, in some possible implementation methods of the embodiments of the present invention, the method for obtaining the initial defect index includes: dividing the point cloud data of each block into normal point cloud data and abnormal point cloud data; performing plane fitting on the normal point cloud data of each block to obtain the reference plane of the corresponding block, and obtaining the quartiles of the distance from each type of point cloud data of each block to the reference plane; forming an n-tuple from the quartiles corresponding to each type of point cloud data of each block, where n is the total number of quartiles corresponding to each type of point cloud data; recording the distance between the n-tuples of normal point cloud data and abnormal point cloud data of each block as the distance difference index of each block; obtaining the quartile difference of the distance from the normal point cloud data of each block to the reference plane; and obtaining the initial defect index of each block based on the quartile difference and the distance difference index.

[0067] The point cloud data of uneven defects often exhibits large fluctuations, resulting in large jumps in the point cloud data. This means that the segmented point cloud data is discontinuous, weakening the plane's characteristics. Therefore, before obtaining a reference plane, it is necessary to divide the segmented point cloud data and select point cloud data with normal flatness from the device to construct a reference plane, thereby improving the accuracy of uneven defect analysis.

[0068] The method for dividing the point cloud data into blocks in this embodiment is: performing plane fitting on the point cloud data of each block to obtain the first plane of the corresponding block; obtaining the distance between all the point cloud data of each block and the first plane, using the maximum inter-class variance method for the distance to obtain the division threshold, and recording the point cloud data with a distance less than the division threshold as normal point cloud data, and recording the point cloud data with a distance greater than or equal to the division threshold as abnormal point cloud data.

[0069] In other embodiments, the point cloud data of each block is clustered based on the distance from the point cloud data of each block to the first plane, and two clusters are obtained, where the K value is equal to the constant 2; the mean of the distance from the point cloud data in each cluster to the first plane is obtained, and the point cloud data in the cluster corresponding to the smallest mean is recorded as normal point cloud data, and the point cloud data in the cluster corresponding to the largest mean is recorded as abnormal point cloud data.

[0070] It should be noted that this embodiment uses the least squares method to perform plane fitting on the segmented point cloud data; other embodiments may also use the Chebyshev method, principal component analysis, and the Random Sample Consensus (RANSAC) algorithm for plane fitting. The least squares method, maximum inter-class variance method, and K-means clustering algorithm are all well-known to those skilled in the art and will not be described in detail here.

[0071] The point cloud data of the uneven defective position of the feeding surface of the molding machine itself exhibits strong bending and jumping characteristics; although the point cloud data generated by the vibration of the device shows strong uneven characteristics, the vibration of the device surface is consistent, so that the fluctuations of the point cloud data generated by the vibration of the device in all blocks are highly consistent. Therefore, the more inconsistent the distance between the abnormal point cloud data and the normal point cloud data of the block to the reference plane, the greater the possibility that the block will show the unevenness defect of the device itself, and the greater the degree of unevenness defect. The n-tuple reflects the fluctuation of the distance from each type of point cloud data to the reference plane. The larger the distance difference index, the more inconsistent the distance between the normal point cloud data and the abnormal point cloud data of the block to the reference plane, and the greater the possibility that the block will show the unevenness defect of the device itself.

[0072] The interquartile difference of the distance from the normal point cloud data of the block to the reference plane reflects the concentration of the normal point cloud data distribution. If the interquartile difference is smaller, the normal point cloud distribution of the block is more concentrated, and the point cloud data of the block is more likely to be caused by the vibration of the device. On the contrary, the point cloud data of the block is more likely to be caused by the unevenness defect of the device itself, and the unevenness defect is more obvious.

[0073] In summary, both the interquartile difference and the distance difference index are positively correlated with the initial defect index. In this embodiment of the present invention, the product of the interquartile difference of the distance from the normal point cloud data of each block to the reference plane and the distance difference index is used as the initial defect index for each block. In this embodiment of the present invention, the correlation between the interquartile difference, the distance difference index, and the initial defect index can also be constructed through other basic mathematical operations, which are not limited or elaborated here.

[0074] It should be noted that there are two types of point cloud data in this embodiment, namely normal point cloud data and abnormal point cloud data; the quartiles include: upper quartile and lower quartile, and the quartiles corresponding to each type of point cloud data in each block constitute an n-tuple as a binary group, where .

[0075] Step S3: Based on the difference between the overall distribution trend of the point cloud data of each block and the overall distribution trend of the point cloud data of the molding machine surface, as well as the position distribution of the point cloud data of each block, the initial defect index is corrected to obtain the corrected defect index of each block.

[0076] The analysis of the initial defect index depends on the presence of point cloud data in the block caused by the vibration of the device. If the point cloud data of the block are all uneven defects of the device itself, it is easy to make the division of normal point cloud data and abnormal point cloud data in step S2 inaccurate, which in turn leads to a large error in the initial defect index. In this case, the initial defect index needs to be corrected.

[0077] Compared to the unevenness caused by device vibration, the unevenness of the device itself is more pronounced, causing the positional distribution of the unevenness defect's segmented point cloud data to be further away from the overall distribution trend. Furthermore, the greater the difference between the overall distribution trend of the segmented point cloud data and the overall distribution trend of the point cloud data on the molding machine surface. Therefore, based on the difference in the overall distribution trend of the segmented point cloud data and the overall distribution trend of the point cloud data on the molding machine surface, as well as the positional distribution of the segmented point cloud data, the initial defect index is corrected to further improve the accuracy of segmented unevenness defect analysis.

[0078] Preferably, in some possible implementation methods of the embodiments of the present invention, the method for obtaining the corrected defect index includes: performing plane fitting on the point cloud data of each block to obtain the second plane of the corresponding block, and performing plane fitting on the point cloud data of the molding machine surface to obtain the overall plane; obtaining the similarity index between the second plane of each block and the normal vector of the overall plane; obtaining the mean square error between all point cloud data of each block and its corresponding point cloud data on the second plane, which is recorded as the fitting error of each block; obtaining the first correction coefficient of each block based on the similarity index and the fitting error; the similarity index and the fitting error are both positively correlated with the first correction coefficient; and using the sum of the first correction coefficient and the constant 1, weighted processing is performed on the initial defect index of each block to obtain the corrected defect index of each block.

[0079] Since inaccurate segmentation of the point cloud data blocks can lead to errors in the initial defect index, this embodiment performs plane fitting on all the point cloud data blocks to obtain a second plane for subsequent analysis. This embodiment uses the least squares method to perform plane fitting on each block of point cloud data and the point cloud data of the molding machine surface.

[0080] For each block of point cloud data, if the number of point cloud data points that are due to uneven defects of the device itself is greater, and the deformation of the block point cloud data is more obvious, then the fitting error of the block point cloud data during plane fitting will be greater, and the fitting error will reflect the positional distribution of the block point cloud data. At the same time, the greater the impact of the uneven defects on the device surface on the second plane of the block, the more obvious the local unevenness of the block, and the greater the difference between the direction of the second plane of the block and the direction of the device surface. Therefore, the greater the fitting error of the block point cloud data during plane fitting, and the greater the difference between the direction of the second plane of the block and the direction of the device surface, the more likely the block point cloud data is due to uneven defects on the device surface itself, and the less likely it is point cloud data generated by device vibration.

[0081] The normal vector of the second plane reflects the overall distribution trend of the point cloud data of the block, and the normal vector of the overall plane reflects the overall distribution trend of the point cloud data of the molding machine surface. If the similarity index between the normal vectors of the second plane of the block and the overall plane is smaller, it means that the direction difference between the overall distribution trend of the point cloud data of the block and the overall distribution trend of the device surface is greater, and the possibility that the point cloud data of the block belongs to the unevenness defect of the device surface itself is greater. If the fitting error is larger, it means that the unevenness feature of the point cloud data of the block is more obvious, and the possibility that the point cloud data of the block belongs to the unevenness defect of the device surface itself is greater; furthermore, the smaller the initial defect index of the block is than the actual defect level, the initial defect index of the block should be increased, and the first correction coefficient should be larger. Therefore, the similarity index and the first correction coefficient are negatively correlated, and the fitting error and the first correction coefficient are positively correlated. In an embodiment of the present invention, the similarity index between the normal vectors of the second plane of each block and the overall plane is negatively correlated, and the product of the mapping result and the fitting error is normalized to obtain the first correction coefficient of each block.

[0082] In the embodiment of the present invention, the correlation between the similarity index, the fitting error and the first correction coefficient may also be constructed through other basic mathematical operations, which will not be limited or elaborated herein.

[0083] The fitting error in this embodiment is the mean square error of all point cloud data of the block and its corresponding point cloud data on the second plane, which is equal to the mean of the squares of the distances between all point cloud data of the block and its corresponding point cloud data on the second plane; other embodiments can also replace the mean square error with the root mean square error and the mean absolute error, etc., which is no longer limited here.

[0084] This embodiment uses the cosine similarity between the normal vectors of the second plane of the block and the overall plane as the similarity index; another embodiment uses the Pearson correlation coefficient between the normal vectors of the second plane of the block and the overall plane as the similarity index; other embodiments can also negatively correlate the Euclidean distance or Manhattan distance between the normal vectors of the second plane of the block and the overall plane and normalize them to obtain the similarity index.

[0085] In a specific implementation of the embodiment of the present invention, the modified defect index is expressed as follows:

[0086]

[0087]

[0088] Where, is the corrected defect index of the kth block on the molding machine surface; is the first correction coefficient of the kth block of the molding machine surface; is the initial defect index of the kth block on the surface of the molding machine; is the fitting error of the kth block of the molding machine surface; is the normal vector of the second plane of the kth block on the molding machine surface; is the normal vector of the global plane; is the similarity index between the normal vector of the second plane of the kth block on the surface of the molding machine and the overall plane; cos is the cosine function; Norm is the normalization function.

[0089] It should be noted that when correcting defect indicators When the value is larger, the probability that the kth block belongs to the unevenness defect of the device surface itself is greater, and the initial defect index of the kth block is smaller than the actual defect degree. right Perform weighted processing to increase the correction defect index ; When correcting defect indicators The smaller the value, the greater the possibility that the kth block belongs to the point cloud data generated by the vibration of the device. The closer to the actual defect level. In this embodiment, the constant 1 is subtracted , to achieve Other embodiments may use other negative correlation mapping methods, which will not be given as examples here.

[0090] Step S4: According to the discrete degree of the corrected defect index of all blocks in each preset direction of each block, the changing trend of the overall distribution trend of the point cloud data of all blocks in all preset directions of each block, and the corrected defect index of each block, the fitting coefficient of the point cloud data of each block is obtained.

[0091] Since the initial defect index and the corrected defect index take into account the uneven characteristics of the point cloud data of a single block, only the local deformation of the loading surface of the molding machine during operation is analyzed. In actual situations, defects may occur with obvious curvature around but a relatively flat middle part. For example, the curvature generated during the large-scale molding process. The flat position in the middle is an uneven defect but exhibits strong planar characteristics. As a result, only analyzing the uneven defects of a single block can easily lead to misjudgment of large-scale defects.

[0092] The deformation caused by extrusion reflects the bending defect of the equipment through all blocks in a certain direction. If a bending defect occurs on the surface of the device, the overall distribution trend of the point cloud data of the blocks in a certain direction on the device surface will show a trend change feature. If the bending defect on the device surface is caused by device vibration, the vibration intensity of all blocks is consistent, so the distance from the point cloud data generated by device vibration in different blocks to its overall distribution trend remains consistent. Therefore, the overall distribution trend direction of the point cloud data of all blocks in a certain direction is basically consistent. At the same time, because the bending defect caused by the large-scale molding process shows a strong uneven feature around the periphery, but a strong flat feature in the flat center, that is, the degree of dispersion of the corrected defect index of the blocks in a certain direction is more obvious.

[0093] Therefore, the discrete degree of the corrected defect index of each block in all blocks in each preset direction and the changing trend of the overall distribution trend of the point cloud data of each block in all preset directions can further adjust the corrected defect index, and further improve the accuracy of the uneven defects shown by the blocks, thereby improving the accuracy of the fitting coefficient.

[0094] See also Figure 2 , which shows a flowchart of a method for obtaining fitting coefficients provided by an embodiment of the present invention, the method comprising:

[0095] Step S410: obtaining the discrete index and the concentrated index of the corrected defect index of all blocks in each preset direction; obtaining the normal vibration index of each block in each preset direction according to the discrete index and the concentrated index.

[0096] If the discrete index is smaller, the corrected defect index of all blocks in each preset direction is closer, which means that the possibility of each block in each preset direction being a defect caused by device vibration is greater, and the normal vibration index is larger; conversely, the possibility of each block in each preset direction being a bending defect caused by extrusion is greater, and the normal vibration index is smaller.

[0097] It should be noted that variance, standard deviation and range can all reflect the degree of discreteness of a set of data. In this embodiment, the variance of the corrected defect index of all blocks in each preset direction of each block is selected as the discrete index. In other embodiments, the variance can be replaced by indicators such as standard deviation and range to obtain the discrete index.

[0098] The concentration index reflects the overall level of unevenness defects for each block in each preset direction. Because the unevenness defects caused by device vibration are smaller than the unevenness defects of the device itself, the corrected defect index for blocks located in uneven locations caused by device vibration is smaller. The smaller the concentration index, the smaller the unevenness defects for each block in each preset direction, indicating a greater likelihood that the defects in each block in each preset direction are caused by device vibration, and the higher the normal vibration index.

[0099] It should be noted that the mean, median and mode can all reflect the centralized distribution trend of a set of data. In this embodiment, the mean of the corrected defect indicators of all blocks in each preset direction of each block is selected as the centralized indicator. In other embodiments, the mean can be replaced with indicators such as the median or mode to obtain the centralized indicator.

[0100] Therefore, the discrete index is negatively correlated with the concentrated index and the normal vibration index. In this embodiment of the present invention, the product of the discrete index and the concentrated index for each block in each preset direction is negatively correlated to obtain the normal vibration index for each block in each preset direction. This embodiment uses an exponential function with a natural constant as the base for negative correlation mapping. The specific method is to first take the negation of the product of the discrete index and the concentrated index for each block in each preset direction, and use this negation as the exponent of the exponential function with the natural constant as the base, thereby achieving negative correlation mapping.

[0101] In this embodiment, the preset directions include: directions parallel to the X-axis and Y-axis of the three-dimensional coordinate system in step S1, that is, the directions of the rows and columns of each block, which can be set by the implementer according to the specific situation.

[0102] Step S420: obtaining a directional trend index for each block according to a change trend of the overall distribution trend of the point cloud data of all blocks in all preset directions.

[0103] Preferably, in some possible implementation methods of the embodiments of the present invention, the method for obtaining the directional trend index includes: obtaining the angle between the normal vector of the second plane of each block and each coordinate axis of the coordinate system in which the point cloud data is located, and recording it as the analysis angle of each block in each dimension; one dimension corresponds to one coordinate axis; arranging the analysis angles of all blocks in each dimension in each preset direction of each block in sequence to obtain the angle sequence of each block in each dimension in each preset direction; obtaining the first-order difference sequence of the angle sequence, and recording the ratio of the maximum value of the number of consecutive positive numbers and the number of consecutive negative numbers in the first-order difference sequence to the total number of elements in the angle sequence as the local trend index of each block in each dimension in each preset direction; selecting the maximum value of the local trend indicators of each block in all dimensions in each preset direction as the overall trend indicator of each block in each preset direction; and taking the cumulative sum of the overall trend indicators of each block in all preset directions as the directional trend index of each block.

[0104] Due to the vibration of the device, the direction of the overall distribution trend of the point cloud data of all blocks in a certain direction remains basically stable, while the bending of the feeding surface caused by the molding process causes the direction of the overall distribution trend of the point cloud data of the blocks in a certain direction to show a trend change. In order to facilitate analysis, the analysis angles of all blocks in each dimension in each preset direction are arranged according to the order of the blocks in the preset direction to obtain an angle sequence.

[0105] If the unevenness defect exhibits a curved characteristic, the overall change trend of the point cloud data for each block in the preset direction will show a trend change. That is, the analysis angle in the angle sequence will show a certain degree of monotonic change, resulting in a large number of consecutive positive and negative numbers in the first-order difference sequence of the angle sequence. If the unevenness defect manifests as vibration generated by the operation of the device, the fitting direction will not have a clear directional characteristic, resulting in the analysis angle in the angle sequence showing randomness. In this case, the first-order difference sequence of the analysis angle will not contain a large range of consecutive positive or negative numbers.

[0106] The continuous positive numbers and continuous negative numbers in the first-order difference sequence of the angle sequence can reflect the monotonic change of the analysis angle. The more the number of continuous positive numbers and the number of continuous negative numbers, the more obvious the monotonic change of the analysis angle. In this embodiment, the ratio of the maximum number of continuous positive numbers and the maximum number of continuous negative numbers in the first-order difference sequence of the angle sequence to the total number of elements in the angle sequence is used as the local trend indicator. If the local trend indicator is larger, it means that the direction of the second plane of each block in the preset direction shows a more obvious trend change, and the possibility that each block will present its own bending defect in each preset direction is greater; conversely, the possibility that the unevenness defect of each block in each preset direction is caused by the vibration of the device is greater. The maximum value of the local trend indicators of each block in all dimensions in each preset direction is selected as the overall trend indicator of each block in each preset direction.

[0107] Consider the trend changes in multiple preset directions, consider the bending defects of each block in multiple preset directions to improve the accuracy of the bending defects of the blocks, and take the cumulative sum of the overall trend indicators of each block in all preset directions as the directional trend index of each block; if the directional trend index is larger, the possibility that each block belongs to the bending defect of the device itself is greater, conversely, the possibility that it belongs to the vibration defect of the device is greater.

[0108] It should be noted that the coordinate system of the point cloud data is defined in step S1 ; in this embodiment, there are three dimensions, and one coordinate axis of the three-dimensional coordinate system of the point cloud data corresponds to one dimension.

[0109] Step S430: Obtain a second correction coefficient for each block based on the normal vibration index and the directional trend index; the normal vibration index is negatively correlated with the second correction coefficient, and the directional trend index is positively correlated with the second correction coefficient; use the second correction coefficient to weight the corrected defect index of each block to obtain the final defect index of each block; negatively correlate and normalize the final defect index to obtain the fitting coefficient of each point cloud data of each block.

[0110] If the normal vibration index is smaller and the directional trend index is larger, the likelihood that the block is a bending defect of the device itself is greater, the corrected defect index is more accurate, and the degree of adjustment to the corrected defect index should be smaller. Conversely, the likelihood that the block is a defect caused by device vibration is greater, the error in the corrected defect index is greater, and the degree of adjustment to the corrected defect index should be larger. The larger the second correction index, the smaller the degree of adjustment to the corrected defect index. Therefore, the normal vibration index and the second correction coefficient are negatively correlated, while the directional trend index and the second correction coefficient are positively correlated.

[0111] This solution constructs a final reference plane for measuring flatness by fitting point cloud data from the molding machine surface. This final reference plane should be constructed using point cloud data from the device with normal flatness. Point cloud data with larger final defect indices are more likely to represent inherent unevenness defects in the device, resulting in larger measurement errors. To ensure the accuracy of the final reference plane, point cloud data with larger final defect indices should be assigned smaller weights when fitting the plane, while point cloud data with smaller final defect indices should be assigned larger weights when fitting the plane, improving the accuracy of the plane fitting. Therefore, the final defect indices need to be negatively correlated and normalized to obtain the fitting coefficient.

[0112] In a specific implementation of the embodiment of the present invention, the fitting coefficient of the point cloud data is expressed as follows:

[0113]

[0114] Where, The fitting coefficient of each point cloud data in each block; is the overall trend index of the kth block on the surface of the molding machine in the vth preset direction; V is the total number of preset directions, and in this embodiment, V takes an empirical value of 2; is the directional trend indicator of the kth block on the surface of the molding machine; is the normal vibration index of the kth block on the surface of the molding machine; is the second correction coefficient of the kth block on the molding machine surface; is the corrected defect index of the kth block on the molding machine surface; is the final defect index of the kth block on the surface of the molding machine; a is a preset positive number with an empirical value of 0.1, which is used to prevent the denominator from being zero, resulting in meaningless fractions; Norm is the normalization function.

[0115] Step S5: performing plane fitting on the point cloud data of the molding machine surface based on the fitting coefficient, and detecting the flatness of the molding machine surface according to the distance from the point cloud data of the molding machine surface to the fitted plane.

[0116] The fitting coefficients are used as weights for plane fitting of each point cloud data point, and the weighted least squares method is used to plane fit the point cloud data of the molding machine surface to obtain the final reference plane. The weighted least squares method is well known to those skilled in the art and will not be described in detail here.

[0117] Obtain the distance from the centroid of the second plane of each block to the final reference plane, and record it as the judgment distance of each block; determine whether the judgment distances of all blocks on the surface of the molding machine are less than the preset threshold value. If so, the flatness of the surface of the molding machine is qualified; if not, the flatness of the surface of the molding machine is unqualified, and the relevant parameters of the molding machine need to be adjusted so that the judgment distance greater than the preset threshold value is less than the preset threshold value, or a new material with qualified flatness is installed to maintain the normal flatness of the surface of the molding machine.

[0118] The centroid of the second plane of each block reflects the spatial position of the second plane. The distance from the centroid to the final reference plane can reflect the overall level of the distance from the point cloud data of each block to the final reference plane. The judgment distance can measure the distance between the block and the surface of the device, which is used to detect the flatness of the surface of the molding machine.

[0119] It should be noted that the threshold value in this embodiment is set to an empirical value of 0.15 mm, which can be adjusted by the implementer based on specific circumstances. Other embodiments may use the distance from the center of gravity of the second plane of the segment or the center of the convex hull to the final reference plane as the judgment distance. The surface flatness detection method for both loading and unloading materials in a molding machine is the same.

[0120] This solution adaptively sets the weight of the point cloud data for plane fitting according to the degree of unevenness defects of the block in which the point cloud data is located, so that the final reference plane represents the overall flatness level of the molding machine surface, thereby improving the accuracy of the molding machine surface flatness detection.

[0121] So far, the present invention is completed.

[0122] Example 2:

[0123] The present invention proposes a surface flatness detection system for a molding loading and unloading machine, please refer to Figure 3 , which shows a system structure diagram of a surface flatness detection system for a molding loading and unloading machine provided by one embodiment of the present invention, the system comprising:

[0124] The data acquisition module 610 is used to obtain point cloud data of the molding machine surface; divide the point cloud data into multiple blocks;

[0125] The defect analysis module 620 is used to obtain a reference plane for each block and obtain an initial defect index for each block based on the difference between the distances of the point cloud data of each block and the reference plane.

[0126] The defect correction module 630 is configured to correct the initial defect index based on the difference between the overall distribution trend of the point cloud data of each block and the overall distribution trend of the point cloud data of the molding machine surface, as well as the position distribution of the point cloud data of each block, to obtain a corrected defect index for each block;

[0127] The fitting coefficient analysis module 640 is used to obtain the fitting coefficient of the point cloud data of each block based on the degree of dispersion of the corrected defect index of all blocks in each preset direction, the change trend of the overall distribution trend of the point cloud data of all blocks in each preset direction, and the corrected defect index of each block;

[0128] The flatness detection module 650 is used to perform plane fitting on the point cloud data of the molding machine surface based on the fitting coefficient, and detect the flatness of the molding machine surface according to the distance from the point cloud data of the molding machine surface to the fitted plane.

[0129] It should be noted that the device provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. In addition, the surface flatness detection system for a molding loading and unloading machine provided in the above embodiment and the surface flatness detection method embodiment for a molding loading and unloading machine are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0130] Example 3:

[0131] Figure 4 A schematic diagram of a computer device for detecting surface flatness of a molding loading and unloading machine provided by one embodiment of the present invention. For example, Figure 4 As shown, the computer device includes: a memory 701, a processor 702, and a computer program 703 stored in the memory 701 and running on the processor 702, wherein when the processor 702 executes the computer program 703, the computer device can execute any one of the surface flatness detection methods for molding loading and unloading machines introduced above.

[0132] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a surface flatness detection method for a molding loading and unloading machine provided in an embodiment of the present application.

[0133] In this embodiment, the device can be divided into functional modules based on the above-described method examples. For example, each functional module can be mapped to a specific functional module, or two or more functions can be integrated into a single processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used.

[0134] It should be understood that the device provided in this embodiment is used to execute the above-mentioned surface flatness detection method for a molding loading and unloading machine, and thus can achieve the same effect as the above-mentioned implementation method.

[0135] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a device, the processing module may be used to control and manage the operation of the device. The storage module may be used to support the device in executing mutual program codes, etc.

[0136] The processing module may be a processor or controller that implements or executes the various exemplary logic blocks, modules, and circuits disclosed herein. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor (DSP) and a microprocessor, and the like. The storage module may be a memory.

[0137] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0138] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0139] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A surface flatness detection method for a molding loading and unloading machine, characterized in that: The method includes: Acquire point cloud data of the molding machine surface; divide the point cloud data into a plurality of blocks; Obtaining a reference plane for each block, and obtaining an initial defect index for each block based on the difference between the distances of the point cloud data of each block and the reference plane; Correcting the initial defect index based on a difference between an overall distribution trend of the point cloud data of each block and an overall distribution trend of the point cloud data of the molding machine surface, as well as a position distribution of the point cloud data of each block, to obtain a corrected defect index for each block; Obtaining a fitting coefficient for the point cloud data of each block based on the degree of dispersion of the corrected defect index of all blocks in each preset direction, a changing trend of the overall distribution trend of the point cloud data of all blocks in each preset direction, and the corrected defect index of each block; A plane fitting is performed on the point cloud data of the molding machine surface based on the fitting coefficient, and the flatness of the molding machine surface is detected according to the distance from the point cloud data of the molding machine surface to the plane obtained by fitting.

2. A surface flatness detection method for a molding loading and unloading machine according to claim 1, characterized in that: The step of obtaining a reference plane for each block and obtaining an initial defect index for each block based on a difference in distance between the point cloud data of each block and the reference plane includes: Divide the point cloud data of each block into normal point cloud data and abnormal point cloud data; Perform plane fitting on the normal point cloud data of each block to obtain a reference plane of the corresponding block, and obtain the quartiles of the distance from each type of point cloud data in each block to the reference plane; The quartiles corresponding to each type of point cloud data in each block form an n-tuple, where n is the total number of quartiles corresponding to each type of point cloud data; The distance between the n-tuples of normal point cloud data and abnormal point cloud data of each block is recorded as the distance difference index of each block; The interquartile difference of the distance from the normal point cloud data of each block to the reference plane is obtained; the initial defect index of each block is obtained according to the interquartile difference and the distance difference index; the interquartile difference and the distance difference index are both positively correlated with the initial defect index.

3. The surface flatness detection method for a molding loading and unloading machine according to claim 1, characterized in that: The obtaining of the correction defect index of each block includes: Performing plane fitting on the point cloud data of each block to obtain a second plane of the corresponding block, and performing plane fitting on the point cloud data of the molding machine surface to obtain an overall plane; obtaining a similarity index between the normal vector of the second plane of each block and the overall plane; Obtaining a mean square error between all point cloud data of each block and its corresponding point cloud data on the second plane, and recording it as a fitting error of each block; Obtaining a first correction coefficient for each block according to the similarity index and the fitting error; the similarity index and the first correction coefficient are negatively correlated, and the fitting error and the first correction coefficient are positively correlated; The initial defect index of each block is weighted by using the sum of the first correction coefficient and a constant 1 to obtain a corrected defect index of each block.

4. The surface flatness detection method for a molding loading and unloading machine according to claim 3, characterized in that: The step of obtaining the fitting coefficient of the point cloud data of each block includes: Obtaining the discrete index and the concentrated index of the corrected defect index of all blocks in each preset direction for each block; obtaining the normal vibration index of each block in each preset direction based on the discrete index and the concentrated index; Obtain the directional trend index of each block based on the change trend of the overall distribution trend of the point cloud data of all blocks in all preset directions; According to the normal vibration index and the directional trend index, a second correction coefficient of each block is obtained; the normal vibration index and the second correction coefficient are negatively correlated, and the directional trend index and the second correction coefficient are positively correlated; the corrected defect index of each block is weighted using the second correction coefficient to obtain a final defect index of each block; the final defect index is negatively correlated and normalized to obtain a fitting coefficient for each point cloud data of each block.

5. The surface flatness detection method for a molding loading and unloading machine according to claim 4, characterized in that: The step of obtaining the directional trend indicator of each block includes: Obtain the angles between the normal vector of the second plane of each block and each coordinate axis of the coordinate system of the point cloud data, and record them as the analysis angles of each block in each dimension; one dimension corresponds to one coordinate axis; sequentially arrange the analysis angles of all blocks in each dimension in each preset direction of each block to obtain an angle sequence of each block in each dimension in each preset direction; Obtain a first-order difference sequence of the angle sequence, and record the ratio of the maximum number of consecutive positive numbers and the maximum number of consecutive negative numbers in the first-order difference sequence to the total number of elements in the angle sequence as the local trend index of each block in each preset direction and each dimension; select the maximum value of the local trend index of each block in each preset direction and all dimensions as the overall trend index of each block in each preset direction; The cumulative sum of the overall trend indicators of each block in all preset directions is used as the directional trend indicator of each block.

6. The surface flatness detection method for a molding loading and unloading machine according to claim 3, characterized in that: The performing plane fitting on the point cloud data of the molding machine surface based on the fitting coefficient, and detecting the flatness of the molding machine surface according to the distance between the point cloud data of the molding machine surface and the plane obtained by fitting, includes: Based on the fitting coefficients, a weighted least square method is used to perform plane fitting on the point cloud data of the molding machine surface to obtain a final reference plane; Obtaining the distance from the centroid of the second plane of each block to the final reference plane, and recording it as the judgment distance of each block; It is determined whether the judgment distances of all blocks on the surface of the molding machine are less than a preset threshold value. If so, the flatness of the surface of the molding machine is qualified; if not, the flatness of the surface of the molding machine is unqualified.

7. The surface flatness detection method for a molding loading and unloading machine according to claim 2, characterized in that: The step of dividing each block of point cloud data into normal point cloud data and abnormal point cloud data includes: Perform plane fitting on the point cloud data of each block to obtain the first plane of the corresponding block; Obtain the distance between all point cloud data of each block and the first plane, use the maximum inter-class variance method to obtain a partitioning threshold for the distance, and record the point cloud data with a distance less than the partitioning threshold as normal point cloud data, and record the point cloud data with a distance greater than or equal to the partitioning threshold as abnormal point cloud data.

8. The surface flatness detection method for a molding loading and unloading machine according to claim 3, characterized in that: The similarity index is cosine similarity.

9. The surface flatness detection method for a molding loading and unloading machine according to claim 4, characterized in that: The step of obtaining the discrete index and the concentrated index of the corrected defect index of all blocks in each preset direction of each block includes: The discrete index is the variance of the corrected defect index of all blocks in each preset direction of each block, and the concentrated index is the mean of the corrected defect index of all blocks in each preset direction of each block.

10. A surface flatness detection system for a molding loading and unloading machine, characterized in that: The system includes: A data acquisition module is used to obtain point cloud data of the molding machine surface; and divide the point cloud data into a plurality of blocks; A defect analysis module is used to obtain a reference plane for each block and obtain an initial defect index for each block based on the difference in distance between the point cloud data of each block and the reference plane; a defect correction module, configured to correct the initial defect index based on a difference between an overall distribution trend of the point cloud data of each block and an overall distribution trend of the point cloud data of the molding machine surface, as well as a position distribution of the point cloud data of each block, and obtain a corrected defect index for each block; A fitting coefficient analysis module is used to obtain a fitting coefficient of the point cloud data of each block based on the discrete degree of the corrected defect index of all blocks in each preset direction of each block, the change trend of the overall distribution trend of the point cloud data of all blocks in all preset directions of each block, and the corrected defect index of each block; The flatness detection module is used to perform plane fitting on the point cloud data of the molding machine surface based on the fitting coefficient, and detect the flatness of the molding machine surface according to the distance from the point cloud data of the molding machine surface to the fitted plane.

Images