CN116823826A - Numerical control machine tool tipping abnormity detection method - Google Patents
Numerical control machine tool tipping abnormity detection method Download PDFInfo
- Publication number
- CN116823826A CN116823826A CN202311092489.5A CN202311092489A CN116823826A CN 116823826 A CN116823826 A CN 116823826A CN 202311092489 A CN202311092489 A CN 202311092489A CN 116823826 A CN116823826 A CN 116823826A
- Authority
- CN
- China
- Prior art keywords
- grid
- clustering
- grids
- gray
- acquiring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title description 7
- 230000000694 effects Effects 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000005856 abnormality Effects 0.000 claims abstract description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 8
- 238000003754 machining Methods 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000007514 turning Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a method for detecting the edge collapse abnormality of a cutter of a numerical control machine tool, which comprises the following steps: acquiring a cutter gray level image; dividing the tool gray image into a plurality of grids according to the gray variance of each grid; acquiring the difference between each grid and the adjacent grids; acquiring each merging grid according to the difference between each grid and the adjacent grids; acquiring initial clustering images according to each merging grid; acquiring the weight of the contour coefficient of each pixel point in each cluster; acquiring the clustering effect of each initial cluster according to the weight of the contour coefficient of each pixel point in each cluster; determining a condition for stopping clustering iteration according to the clustering effect of each initial cluster, and obtaining an accurate clustering result; and identifying the tipping area according to an accurate clustering result. The invention can identify the complete tipping area.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method for detecting the abnormal tipping of a cutter of a numerical control machine tool.
Background
The tool of the numerical control machine tool is one of key components for machining a workpiece, plays an important role in machining such as cutting, turning and drilling of the workpiece, adjusting machining amount and the like, so that the quality, shape, use condition and the like of the tool of the numerical control machine tool directly affect the quality and efficiency of the machined workpiece. Therefore, it is important to properly select and use the tools and to maintain and replace the tools at regular intervals. Among them, the tool tipping of the numerical control machine tool is a common fault phenomenon, especially when processing a large number of workpieces for a long time, the cutter abrasion and stress factors easily cause tipping and fracture of the cutter edge, which easily causes the reduction of the processing efficiency and the processing quality of the numerical control machine tool, and even causes potential safety hazards to the machine tool and the constructors, and causes especially the damage of sharp objects. Therefore, the device can be timely detected by a computer vision technology so as to ensure stable improvement of processing efficiency and quality.
Conventional onesThe clustering algorithm is to manually set the number of clusters and select the positions of the cluster centers according to the experience values, and because the complex aggregate shape of the gray images of the cutter and the surface of the gray images of the cutter are generally influenced by more complex illumination, if the number of clusters and the positions of the selected cluster centers set by the artificial experience values are inaccurate, the result of the clusters is error, and the complete tipping area cannot be accurately segmented.
Disclosure of Invention
The invention provides a method for detecting the abnormal tipping of a cutter of a numerical control machine tool, which aims to solve the existing problems.
The invention discloses a method for detecting the abnormal tipping of a cutter of a numerical control machine tool, which adopts the following technical scheme:
the embodiment of the invention provides a method for detecting the abnormal tipping of a cutter of a numerical control machine tool, which comprises the following steps:
acquiring a cutter gray level image;
dividing the tool gray scale image into a plurality of grids; acquiring the difference between each grid and the adjacent grids; acquiring each merging grid according to the difference between each grid and the adjacent grids; acquiring initial clustering images according to each merging grid;
acquiring contour coefficients of pixel points in each initial cluster in the initial cluster image; acquiring the weight of the contour coefficient of each pixel point in each initial cluster in the initial cluster image; acquiring the clustering effect of each initial cluster according to the weight of the contour coefficient of each pixel point in each initial cluster;
determining a condition for stopping clustering iteration according to the clustering effect of each initial cluster, and obtaining an accurate clustering result;
and identifying the tipping area according to an accurate clustering result.
Preferably, the dividing the gray scale image of the tool into a plurality of grids comprises the following specific steps:
preset variance thresholdEqually dividing a gray level image of a cutter into two grids, acquiring gray level variance of each grid, and if the gray level variance of the grid is larger than a variance threshold +.>Dividing the grid into two grids, if the gray variance of the grid is less than or equal to the variance threshold +.>The grids are not segmented, and so on until the gray variance of all grids in the tool gray image is less than or equal to the variance threshold +.>And stopping to obtain a plurality of grids.
Preferably, the step of obtaining the difference between each grid and the adjacent grids includes the following specific steps:
wherein ,indicate->The +.>Variability between individual grids; />The super parameter is set;indicate->Gray variance of the individual grids; />Representation and->Adjacent ones of the grids>Gray variance of the individual grids; />Is an absolute value symbol; />Is a natural constant.
Preferably, the step of obtaining each merging grid according to the difference between each grid and the adjacent grids includes the following specific steps:
presetting a difference threshold, and merging the grid with the adjacent grid when the difference between the grid and the adjacent grid is smaller than the difference threshold, so as to obtain a merged grid.
Preferably, the step of acquiring the initial cluster image according to each merging grid includes the following specific steps:
counting the number of the combined grids, taking the number of the combined grids as the clustering number, randomly selecting one point in each combined grid as an initial clustering center, and acquiring an initial clustering image by using a clustering algorithm.
Preferably, the step of obtaining the weight of the contour coefficient of each pixel point in each initial cluster in the initial cluster image includes the following specific steps:
wherein ,indicate->The weight of the contour coefficient of each pixel point in each initial cluster; />Indicate->The total number of pixel points in the initial cluster; />Indicate->The initial cluster contains +.>The number of pixel points in the merging grid area; />Representing a hyperbolic tangent function; />Is a natural constant.
Preferably, the step of obtaining the clustering effect of each initial cluster according to the weight of the contour coefficient of each pixel point in each initial cluster includes the following specific steps:
wherein ,indicate->Clustering effects of the initial clusters; />Indicate->The +.>A plurality of pixel points; />Indicate->The number of pixel points in the initial cluster; />Indicate->The +.>Contour coefficients of the individual pixel points; />Indicate->The weight of the contour coefficient of each pixel point in each initial cluster; />Represents->The first part of the initial cluster>Euclidean distance from each pixel point to the central pixel point of the initial cluster to which the pixel point belongs.
Preferably, the determining the condition for stopping the clustering iteration according to the clustering effect of each initial cluster to obtain an accurate clustering result includes the following specific steps:
preset difference thresholdObtain->Mean value of clustering effect of all initial clusters after iteration and +.>The difference of the mean value of the clustering effects of all initial clusters after the number of iterations is recorded as +.>When->At this time, the algorithm iterates to +.>Secondary stop and will->The clustering result after the iteration is used as an accurate clustering result when +.>When the algorithm is used, the algorithm continues to iterate until the difference value of the clustering results of the previous iteration and the subsequent iteration is less than +.>Stopping the process, and taking the clustering result after the previous iteration as an accurate clustering result.
Preferably, the step of obtaining the gray variance of each grid includes the following specific steps:
any grid in the gray level image of the cutter is traversed and recorded as the current grid:
in the formula ,representing the gray variance of the current grid; />Representing +.>Line->Gray value of pixel point of column, +.>Representing the average gray value of the pixel points in the current grid; /> and />Representing the side length of the current grid.
Preferably, the identifying the tipping area according to the accurate clustering result includes the following specific steps:
and presetting a gray threshold value, and acquiring a gray variance value of each final cluster, wherein the final cluster with the gray variance value larger than or equal to the gray threshold value is a tipping area.
The technical scheme of the invention has the beneficial effects that: according to the scheme, a cutter gray image is obtained, and the cutter gray image is divided into a plurality of grids according to gray variance of each grid; acquiring each merging grid according to the difference between each grid and the adjacent grids; acquiring initial clustering images according to each merging grid; acquiring the weight of the contour coefficient of each pixel point in each cluster; acquiring the clustering effect of each initial cluster according to the weight of the contour coefficient of each pixel point in each cluster; determining a condition for stopping clustering iteration according to the clustering effect of each initial cluster, and obtaining an accurate clustering result; and identifying the tipping area according to an accurate clustering result. According to the scheme, the number of the combined grids is used as the clustering number, one point is selected in each combined grid to serve as an initial clustering point, an initial clustering image is obtained, the problem that the clustering effect is poor due to the clustering number set by an artificial experience value is solved, the clustering effect of each initial clustering cluster is built through the initial clustering image, the accurate iteration stop times are obtained according to the clustering effect of each initial clustering cluster, the accurate clustering result is obtained, and the problem that the clustering effect is poor due to the fact that the position of a clustering center selected by the artificial experience value is inaccurate is solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of steps of a method for detecting tool tipping abnormality of a numerical control machine tool.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a method for detecting the abnormal tipping of a tool of a numerical control machine tool according to the invention, which is specific to the implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The invention provides a specific scheme of a numerical control machine tool tipping abnormity detection method, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting a tool tipping abnormality of a numerically-controlled machine tool according to an embodiment of the present invention is shown, and the method includes the following steps:
s101, acquiring a cutter gray level image.
And installing an industrial camera on the numerical control machine tool to shoot an image of the cutter, keeping the camera stable when installing the industrial camera so as to avoid blurring or distortion of the image, ensuring the quality of the acquired image of the cutter by adjusting camera parameters, and carrying out graying treatment on the acquired image of the cutter to obtain a gray image of the cutter for facilitating subsequent analysis.
S102, dividing a gray level image of a cutter into a plurality of grids; acquiring the difference between each grid and the adjacent grids; acquiring each merging grid according to the difference between each grid and the adjacent grids; and acquiring initial clustering images according to each merging grid.
Compared with the traditional tool tipping detection method, the tool tipping detection method based on the machine vision technology has the advantages of accurate detection result, high detection speed, simple operation and the like, can effectively reduce the burden of operators and improve the automation level and the production efficiency of production, andthe clustering segmentation algorithm is to cluster a given data set into K clusters according to the distance between data points, so that the points in the clusters are tightly connected together as much as possible, and the distance between the clusters is as large as possible, thereby achieving the image segmentation result, but the traditional method is that>The clustering algorithm is to manually set the number of clusters and select the positions of the cluster centers according to the experience values, and because the complex aggregate shape of the gray images of the cutter and the surface of the gray images of the cutter are generally influenced by more complex illumination, if the number of clusters set by the artificial experience values and the positions of the selected cluster centers are inaccurate, the clustering result is in error and the edge-collapse areas cannot be accurately segmented, so that the method firstly obtains the number of clusters according to the image characteristics, obtains the initial clustered images according to the number of clusters, constructs the clustering effect of each cluster through the initial clustered images, and obtains more accurate iteration stop times and accurate clustering results.
It should be further noted that, because the complex aggregate shape of the tool and the surface of the tool generally has a complex illumination influence, in order to facilitate processing an image, the image is firstly divided into regular grids according to a grid division algorithm, and according to the image characteristics, the difference exists between the surface of the tipping area and the normal area, so that the difference in gray scale can be caused by the difference in reflection of illumination, and therefore, the method divides the image into a plurality of grids through the gray scale variance of the grids.
In the embodiment of the invention, any grid in the gray image of the cutter is traversed and marked as the current grid, and the gray variance of the current grid is obtained:
in the formula ,representing the gray variance of the current grid; />Representing +.>Line->Gray value of pixel point of column, +.>Representing the average gray value of the pixel points in the current grid; /> and />Representing the side length of the current grid.
In the embodiment of the invention, firstly, the gray level image of the cutter is equally divided into two grids, and if the gray level variance is larger than the variance threshold valueIf there is a gray level variance less than or equal to the variance threshold +.>The mesh is no longer segmented. Repeating the above steps until the gray variance of all grids in the gray image of the tool is less than or equal to the variance threshold +.>I.e. the meshing of the image is completed, in the embodiment of the invention, the variance threshold is setIn other embodiments, the practitioner can set the variance threshold according to the actual implementation>。
It should be noted that, dividing the gray scale image of the tool into a plurality of grids, dividing the regions with similar characteristics into different grids, and directly taking the number of the divided grids as the number of clusters at this time is inaccurate, so the method combines the gray variance and Euclidean distance of each grid to obtain the difference between the adjacent grids, combines the adjacent grids by setting a difference threshold value, and takes the number of the combined grids as the number of clusters.
In the embodiment of the invention, the difference between each grid and the adjacent grid is obtained according to the gray variance and Euclidean distance of each grid:
in the formula ,indicate->The +.>Variability between individual grids; use->The normalization method normalizes the difference; />For setting the super parameters, the embodiment of the invention sets the super parametersIn other embodiments, the practitioner may set +.>，/>Indicate->Gray variance of the individual grids; />Representation and->Adjacent ones of the grids>Gray variance of the individual grids, which is used in the embodiment of the inventionThe method normalizes the gray variance to make the value range of the gray variance be [0,1 ]]；/>Is an absolute value symbol; />Indicate->The +.>The difference in gray variance between the grids indicates that the features of adjacent grids are similar when the difference between the adjacent grids is smaller, and should be combined.
In the embodiment of the invention, a difference threshold value is presetIn other embodiments, the practitioner can set +.>When the variability between each grid and its neighboring grid is less than the variability threshold, merging that grid with its neighboring grid; when the difference between each grid and the adjacent grid is larger than or equal to a difference threshold value, the grids are not combined with the adjacent grids, and a plurality of combined grids are obtained.
Counting the number of the combined grids, taking the number of the combined grids as the clustering number, randomly selecting one point in each combined grid as an initial clustering center, and usingThe clustering algorithm obtains an initial clustered image.
So far, an initial clustering center in the cutter gray level image is obtained, and an initial clustering image is obtained.
S103, acquiring contour coefficients of pixel points in each initial cluster in the initial cluster image; acquiring the weight of the contour coefficient of each pixel point in each initial cluster in the initial cluster image; and obtaining the clustering effect of each initial cluster according to the weight of the contour coefficient of each pixel point in each initial cluster.
It should be noted that, based on the effect and accuracy of the initial cluster image acquired in the step S102, a larger error may occur, so that the identification of the tipping area cannot be performed according to the clustering result, so that the method needs to quantify the clustering effect of the initial cluster in the obtained initial cluster image, and further determine the clustering iteration stop condition according to the obtained clustering effect of each initial cluster, thereby obtaining an accurate clustering result. The conventional method for evaluating the clustering effect mainly determines the clustering effect of each cluster according to the sum of the distances from each pixel point in each cluster to the clustering center of the each pixel point, so that the influence degree of each pixel point on the clustering effect of the cluster where the each pixel point is located is determined by the distance from each pixel point in each cluster to the clustering center of the each pixel point, namely, when the pixel point is far from the clustering center, the influence degree of the pixel point on the clustering effect is larger, the clustering effect is worse, when the pixel point is near to the clustering center, the influence degree of the pixel point on the clustering effect is smaller, the clustering effect is better, but the clustering effect is determined only by the distance between the pixel point and the clustering center point, and the fact that the variances of the pixel points in different clusters are different is not considered possibly results in that the clusters with larger variances are divided into a plurality of smaller clusters in an error. The contour coefficient can not only quantify the compactness of each pixel point and the cluster to which the pixel point belongs, but also quantify the separation degree of the pixel point and other clusters, so that the contour coefficient of each pixel point and the distance from the pixel point to the cluster center are combined to calculate the clustering effect of the current cluster, the difference between the pixel point and other pixel points in the similar clusters can be quantified, and the influence of variance caused by only using the distance relation can be prevented.
In the embodiment of the invention, the contour coefficient of each pixel point in each initial cluster in the initial cluster image is obtained.
It should be further noted that, since a point is optionally selected as a cluster center in the merging grid to perform clustering, when the number of pixels of the corresponding merging grid in each initial cluster in the obtained initial cluster image is greater, it is indicated that the better the clustering effect of the initial cluster is, the closer to 1 the contour coefficient of each pixel in the initial cluster is, and therefore, a greater weight is set for the contour coefficient of each pixel in the initial cluster to adjust the contour coefficient.
In the embodiment of the invention, the weight of the contour coefficient of each pixel point in each initial cluster is calculated:
in the formula ,indicate->The weight of the contour coefficient of each pixel point in each initial cluster; />Indicate->The total number of pixel points in the initial cluster; />Indicate->The initial cluster contains +.>The number of pixel points in the merging grid area; />Indicate->The initial cluster contains +.>The number of pixels of the merging grid and the +.>The ratio of the total number of pixel points in the initial cluster; />For normalizing the values; />The larger the value is, the more->The higher the similarity of the pixel points in the initial cluster, the larger the contour coefficient of the initial cluster, and the larger the weight is set for the initial cluster.
Calculating the clustering effect of each initial cluster:
wherein ,indicate->Clustering effects of the initial clusters; />Indicate->The +.>A plurality of pixel points; />Indicate->The number of pixel points in the initial cluster; />Indicate->The +.>The contour coefficient of each pixel is known +.>When->A closer to 1 indicates a better clustering effect, a closer to-1 indicates a worse clustering effect, and the embodiment of the invention uses +.>Mapping the value range of the contour coefficient to +.>When the clustering effect of the sample points is better, then +.>The closer to 0; />Indicate->The weight of the contour coefficient of each pixel point in each initial cluster; />Represents->The first part of the initial cluster>The Euclidean distance from each pixel point to the central pixel point of the initial cluster to which the pixel point belongs; when->The larger the clustering effect is, the better the clustering effect is, when +.>The smaller the clustering effect is, the better, therefore when +.>Minimum value of->The better the clustering effect of the initial clusters.
So far, according to the initial clustering images, the evaluation index of the clustering effect of each initial clustering cluster is constructed.
S104, determining a condition for stopping clustering iteration according to the clustering effect of each initial cluster, and obtaining an accurate clustering result.
It should be noted that due toThe algorithm value is suitable for clustering of convex clusters, and for the cluster shape after combination, the regularity is not strong, then larger error can occur in the clustering effect, so the algorithm needs to improve the clustering quality through continuous iteration, but the optimal clustering effect can not be found out if the iteration times are too small, otherwise, the situation of overfitting can occur, so the method has the advantages that the difference of the clustering effects in the process of quantization iteration is smaller than the set difference threshold value. The iteration of the algorithm is stopped at this time and the clustering result before the iteration is obtained as an accurate clustering result.
In the present inventionIn an embodiment, obtain the firstMean value and first of clustering effects of all initial clusters after iterationThe difference of the mean value of the clustering effects of all initial clusters after the number of iterations is recorded as +.>When->When the algorithm iterates to +.>Secondary stop and get->The clustering result after the iteration is an accurate clustering result whenWhen the clustering result of the two previous and subsequent iterations is less than +.>And stopping, and obtaining the clustering result after the previous iteration as an accurate clustering result. Setting a variance threshold in embodiments of the present inventionIn other embodiments, the practitioner can set +.>Is a value of (2).
So far, according to the evaluation index of the clustering effect, determining the condition of stopping the clustering iteration and obtaining an accurate clustering result.
S105, identifying a complete tipping area according to an accurate clustering result.
Needs to be as followsIn the present embodiment, since the chipping region generally contains more gradation information than the surrounding region, a gradation threshold is setThe gray variance value of each final cluster is obtained, zero-mean normalization processing is carried out on all the gray variance values, wherein the final cluster with the gray variance value larger than or equal to the gray threshold value is the tipping area, and in the embodiment of the invention, the following steps are set>In other embodiments, the practitioner can set +.>Is a value of (2). At the moment, workers can process the tipping area, so that the machining efficiency and the machining quality of the numerical control machine tool are guaranteed, and the personal safety of the machine tool and the workers is also guaranteed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. The method for detecting the abnormal tipping of the cutter of the numerical control machine tool is characterized by comprising the following steps of:
acquiring a cutter gray level image;
dividing the tool gray scale image into a plurality of grids; acquiring the difference between each grid and the adjacent grids; acquiring each merging grid according to the difference between each grid and the adjacent grids; acquiring initial clustering images according to each merging grid;
acquiring contour coefficients of pixel points in each initial cluster in the initial cluster image; acquiring the weight of the contour coefficient of each pixel point in each initial cluster in the initial cluster image; acquiring the clustering effect of each initial cluster according to the weight of the contour coefficient of each pixel point in each initial cluster;
determining a condition for stopping clustering iteration according to the clustering effect of each initial cluster, and obtaining an accurate clustering result;
and identifying the tipping area according to an accurate clustering result.
2. The method for detecting abnormal edge collapse of a tool of a numerical control machine tool according to claim 1, wherein the dividing of the gray scale image of the tool into a plurality of grids comprises the following specific steps:
preset variance thresholdEqually dividing a gray level image of a cutter into two grids, acquiring gray level variance of each grid, and if the gray level variance of the grid is larger than a variance threshold +.>Dividing the grid into two grids, if the gray variance of the grid is less than or equal to the variance threshold +.>The grids are not segmented, and so on until the gray variance of all grids in the tool gray image is less than or equal to the variance threshold +.>And stopping to obtain a plurality of grids.
3. The method for detecting the tool tipping abnormality of the numerically-controlled machine tool according to claim 1, wherein the step of obtaining the difference between each grid and the adjacent grids comprises the following specific steps:
wherein ,indicate->The +.>Variability between individual grids; />The super parameter is set; />Indicate->Gray variance of the individual grids; />Representation and->Adjacent ones of the grids>Gray variance of the individual grids; />Is an absolute value symbol; />Is a natural constant.
4. The method for detecting the tool tipping abnormality of the numerically-controlled machine tool according to claim 1, wherein the step of acquiring each combined grid according to the difference between each grid and the adjacent grids comprises the following specific steps:
presetting a difference threshold, and merging the grid with the adjacent grid when the difference between the grid and the adjacent grid is smaller than the difference threshold, so as to obtain a merged grid.
5. The method for detecting the tool tipping abnormality of the numerically-controlled machine tool according to claim 1, wherein the step of acquiring the initial cluster image according to each merging grid comprises the following specific steps:
counting the number of the combined grids, taking the number of the combined grids as the clustering number, randomly selecting one point in each combined grid as an initial clustering center, and acquiring an initial clustering image by using a clustering algorithm.
6. The method for detecting the tool tipping abnormality of the numerical control machine tool according to claim 1, wherein the step of obtaining the weight of the contour coefficient of each pixel point in each initial cluster in the initial cluster image comprises the following specific steps:
wherein ,indicate->The weight of the contour coefficient of each pixel point in each initial cluster; />Indicate->The total number of pixel points in the initial cluster; />Indicate->The initial cluster contains +.>The number of pixel points in the merging grid area;representing a hyperbolic tangent function; />Is a natural constant.
7. The method for detecting the tool tipping abnormality of the numerically-controlled machine tool according to claim 1, wherein the step of obtaining the clustering effect of each initial cluster according to the weight of the contour coefficient of each pixel point in each initial cluster comprises the following specific steps:
wherein ,indicate->Clustering effects of the initial clusters; />Indicate->The +.>A plurality of pixel points;indicate->The number of pixel points in the initial cluster; />Indicate->The +.>Contour coefficients of the individual pixel points; />Indicate->The weight of the contour coefficient of each pixel point in each initial cluster; />Represents->The first part of the initial cluster>Euclidean distance from each pixel point to the central pixel point of the initial cluster to which the pixel point belongs.
8. The method for detecting the tool tipping abnormality of the numerically-controlled machine tool according to claim 1, wherein the determining the condition for stopping the clustering iteration according to the clustering effect of each initial cluster, and obtaining the accurate clustering result, comprises the following specific steps:
preset difference thresholdObtain->Mean value of clustering effect of all initial clusters after iteration and +.>The difference of the mean value of the clustering effects of all initial clusters after the number of iterations is recorded as +.>When->At this time, the algorithm iterates to +.>Secondary stop and will->The clustering result after the iteration is used as an accurate clustering result when +.>When the algorithm is used, the algorithm continues to iterate until the difference value of the clustering results of the previous iteration and the subsequent iteration is less than +.>Stopping the process, and taking the clustering result after the previous iteration as an accurate clustering result.
9. The method for detecting the tool tipping abnormality of the numerically-controlled machine tool according to claim 2, wherein the step of obtaining the gray variance of each grid comprises the following specific steps:
any grid in the gray level image of the cutter is traversed and recorded as the current grid:
in the formula ,representing the gray variance of the current grid; />Representing +.>Line->Gray value of pixel point of column, +.>Representing the average gray value of the pixel points in the current grid; /> and />Representing the side length of the current grid.
10. The method for detecting the abnormal tipping of the cutter of the numerical control machine tool according to claim 1, wherein the step of identifying the tipping area according to the accurate clustering result comprises the following specific steps:
and presetting a gray threshold value, and acquiring a gray variance value of each final cluster, wherein the final cluster with the gray variance value larger than or equal to the gray threshold value is a tipping area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311092489.5A CN116823826B (en) | 2023-08-29 | 2023-08-29 | Numerical control machine tool tipping abnormity detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311092489.5A CN116823826B (en) | 2023-08-29 | 2023-08-29 | Numerical control machine tool tipping abnormity detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116823826A true CN116823826A (en) | 2023-09-29 |
| CN116823826B CN116823826B (en) | 2023-11-03 |
Family
ID=88127740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311092489.5A Active CN116823826B (en) | 2023-08-29 | 2023-08-29 | Numerical control machine tool tipping abnormity detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823826B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117056764A (en) * | 2023-10-11 | 2023-11-14 | 唐山市南堡经济开发区航天万源新能源有限公司 | Intelligent protection method and system for generator set |
| CN117173208A (en) * | 2023-11-01 | 2023-12-05 | 浙江鸿昌铝业有限公司 | Error judgment method for sawing process of aluminum profile based on data analysis |
| CN117689657A (en) * | 2024-02-02 | 2024-03-12 | 深圳市福源晖科技有限公司 | Flexible circuit board patch abnormality detection method and system |
| CN117708613A (en) * | 2023-12-25 | 2024-03-15 | 北京中微盛鼎科技有限公司 | Industrial chain collaborative operation-oriented digital resource matching method |
| CN117764893A (en) * | 2024-01-08 | 2024-03-26 | 惠州市惠阳区兆顺益五金加工有限公司 | Numerical control machine tool wear identification method and system |
| CN117808810A (en) * | 2024-03-01 | 2024-04-02 | 陕西长空齿轮有限责任公司 | Hobbing cutter abrasion image recognition and measurement method and system |
| CN117808811A (en) * | 2024-03-01 | 2024-04-02 | 陕西中盛天泽复合材料科技有限公司 | Numerical control machine tool tipping abnormity detection method |
| CN117911956A (en) * | 2024-03-19 | 2024-04-19 | 洋县阿拉丁生物工程有限责任公司 | Dynamic monitoring method and system for processing environment of food processing equipment |
| CN117808810B (en) * | 2024-03-01 | 2024-05-28 | 陕西长空齿轮有限责任公司 | Hobbing cutter abrasion image recognition and measurement method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184216A (en) * | 2011-05-04 | 2011-09-14 | 武汉大学 | Automatic clustering method based on data field grid division |
| CN110109415A (en) * | 2019-04-26 | 2019-08-09 | 华中科技大学 | A kind of more grid cutter shaft optimization methods based on Density Clustering |
| US20210041588A1 (en) * | 2019-08-09 | 2021-02-11 | Petrochina Company Limited | Method for identifying boundary of sedimentary facies, computer device and computer readable storage medium |
| CN116309572A (en) * | 2023-05-19 | 2023-06-23 | 无锡康贝电子设备有限公司 | Intelligent recognition method for numerical control machine tool components based on images |
-
2023
- 2023-08-29 CN CN202311092489.5A patent/CN116823826B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184216A (en) * | 2011-05-04 | 2011-09-14 | 武汉大学 | Automatic clustering method based on data field grid division |
| CN110109415A (en) * | 2019-04-26 | 2019-08-09 | 华中科技大学 | A kind of more grid cutter shaft optimization methods based on Density Clustering |
| US20210041588A1 (en) * | 2019-08-09 | 2021-02-11 | Petrochina Company Limited | Method for identifying boundary of sedimentary facies, computer device and computer readable storage medium |
| CN116309572A (en) * | 2023-05-19 | 2023-06-23 | 无锡康贝电子设备有限公司 | Intelligent recognition method for numerical control machine tool components based on images |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117056764B (en) * | 2023-10-11 | 2024-01-09 | 唐山市南堡经济开发区航天万源新能源有限公司 | Intelligent protection method and system for generator set |
| CN117056764A (en) * | 2023-10-11 | 2023-11-14 | 唐山市南堡经济开发区航天万源新能源有限公司 | Intelligent protection method and system for generator set |
| CN117173208A (en) * | 2023-11-01 | 2023-12-05 | 浙江鸿昌铝业有限公司 | Error judgment method for sawing process of aluminum profile based on data analysis |
| CN117708613A (en) * | 2023-12-25 | 2024-03-15 | 北京中微盛鼎科技有限公司 | Industrial chain collaborative operation-oriented digital resource matching method |
| CN117708613B (en) * | 2023-12-25 | 2024-05-14 | 北京中微盛鼎科技有限公司 | Industrial chain collaborative operation-oriented digital resource matching method |
| CN117764893A (en) * | 2024-01-08 | 2024-03-26 | 惠州市惠阳区兆顺益五金加工有限公司 | Numerical control machine tool wear identification method and system |
| CN117689657B (en) * | 2024-02-02 | 2024-04-16 | 深圳市福源晖科技有限公司 | Flexible circuit board patch abnormality detection method and system |
| CN117689657A (en) * | 2024-02-02 | 2024-03-12 | 深圳市福源晖科技有限公司 | Flexible circuit board patch abnormality detection method and system |
| CN117808810A (en) * | 2024-03-01 | 2024-04-02 | 陕西长空齿轮有限责任公司 | Hobbing cutter abrasion image recognition and measurement method and system |
| CN117808811A (en) * | 2024-03-01 | 2024-04-02 | 陕西中盛天泽复合材料科技有限公司 | Numerical control machine tool tipping abnormity detection method |
| CN117808810B (en) * | 2024-03-01 | 2024-05-28 | 陕西长空齿轮有限责任公司 | Hobbing cutter abrasion image recognition and measurement method and system |
| CN117911956A (en) * | 2024-03-19 | 2024-04-19 | 洋县阿拉丁生物工程有限责任公司 | Dynamic monitoring method and system for processing environment of food processing equipment |
| CN117911956B (en) * | 2024-03-19 | 2024-05-31 | 洋县阿拉丁生物工程有限责任公司 | Dynamic monitoring method and system for processing environment of food processing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116823826B (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116823826B (en) | Numerical control machine tool tipping abnormity detection method | |
| CN115082467B (en) | Building material welding surface defect detection method based on computer vision | |
| CN115035120B (en) | Machine tool control method and system based on Internet of things | |
| CN114494210B (en) | Plastic film production defect detection method and system based on image processing | |
| CN116703251B (en) | Rubber ring production quality detection method based on artificial intelligence | |
| CN116934740B (en) | Plastic mold surface defect analysis and detection method based on image processing | |
| CN115984271A (en) | Metal burr identification method based on angular point detection | |
| CN117372436B (en) | Wind power blade fault detection method based on image data | |
| CN112907519A (en) | Metal curved surface defect analysis system and method based on deep learning | |
| CN115431101A (en) | Method and system for detecting state of numerical control machine tool | |
| CN115240146B (en) | Intelligent machine tool assembly acceptance method based on computer vision | |
| CN116152749B (en) | Intelligent gear wear monitoring method based on digital twin | |
| CN115359053A (en) | Intelligent detection method and system for defects of metal plate | |
| CN114998341B (en) | Gear defect detection method and system based on template matching | |
| CN114187286A (en) | Wood plate surface machining quality control method based on machine vision | |
| CN117315289A (en) | Aeroengine blade contour edge detection method based on image processing | |
| CN112258532B (en) | Positioning and segmentation method for callus in ultrasonic image | |
| CN116432052B (en) | Quality detection method for clamp for new energy automobile die | |
| CN116503403B (en) | Defect detection method of metal cutting tool bit based on image processing | |
| CN116740044B (en) | Copper pipe milling surface processing method and system based on visual detection and control | |
| CN115578390B (en) | Welding control method for deaerator | |
| CN114850967B (en) | Method and system for detecting cutter abrasion state based on man-in-loop | |
| CN111915630B (en) | Ceramic material grain segmentation algorithm based on data and model combined driving | |
| CN112508945A (en) | Nondestructive testing method for solid rocket engine based on computer vision | |
| CN116912241B (en) | CNC machine adjustment optimization method and system based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |