Digital factory production equipment data real-time monitoring method and system

By collecting and analyzing the thermal images of the die-casting machine and identifying the temperature abnormalities of the junction pixel points, the problem of difficulty in detecting small bubble defects in the junction area of ​​the casting thickness is solved, and more accurate temperature abnormality detection and casting quality control are achieved.

CN119027884AActive Publication Date: 2024-11-26SHENZHEN XINGUAN PRECISION TECH CO LTD

Patent Information

Application Number
CN202411499299.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-25
Publication Date
2024-11-26
Estimated Expiration
2044-10-25

AI Technical Summary

Technical Problem

Traditional die casting machines are difficult to detect small bubble defects in the junction of different thicknesses of castings, resulting in unstable casting quality.

Method used

By collecting thermal images of castings, clustering to obtain different regions, obtain the edge lines and temperature differences of the junction pixel points, calculate the degree of edge fluctuation and temperature difference, analyze the temperature changes in different thickness areas, obtain the temperature abnormality and fault degree, and perform the Threshold judgment is made to identify the temperature abnormality area.

Benefits of technology

It improves the detection accuracy of small bubble defects in the junction of different thicknesses, helps to understand the internal heat conduction of the castings, and ensures the quality and molding stability of the castings.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027884A_ABST
    Figure CN119027884A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of image data processing, in particular to a digital factory production equipment data real-time monitoring method and system.The method comprises the steps that thermal images of a casting are collected and clustered, and a plurality of areas of the casting are obtained; obtaining the edge fluctuation degree and the temperature difference degree of each boundary pixel point; obtaining two areas with different thicknesses corresponding to each boundary pixel point through the edge lines where the boundary pixel points are located, obtaining the temperature fault degree of the pixel points of the two areas with different thicknesses corresponding to each boundary pixel point, and obtaining the temperature anomaly expression degree of each boundary pixel point in combination with the temperature difference degree of each boundary pixel point; and based on the temperature anomaly representation degree and the edge fluctuation degree, the temperature anomaly degree of each junction pixel point is obtained, threshold judgment is carried out, the temperature anomaly junction pixel points are obtained, and an abnormal temperature area is determined. The invention aims to improve the accuracy of defect detection of small bubbles in boundary zones with different thicknesses.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a method and system for real-time monitoring of production equipment data in a digital factory. Background Art

[0002] The rise of digital factories marks the entry of the manufacturing industry into a new production model. As an important production equipment, die-casting machines have significantly improved production efficiency and quality management through the application of intelligent and data-based technologies. Die-casting machines mainly rely on the operator's experience and manual adjustments to control the production process. With the mature application of the Internet of Things, big data analysis and artificial intelligence, die-casting machines have been comprehensively upgraded and integrated in digital factories.

[0003] The traditional temperature detection of die-casting machines is to detect the temperature distribution of the die-casting machine body and the mold surface through infrared thermal imagers to ensure that the overall temperature distribution is uniform, thereby ensuring the quality of the casting and the stability of the molding. During the die-casting process, there may be thickness variations in different parts of the casting. This thickness variation will cause different cooling rates and metal fluidity in different parts. During the solidification process of the metal, the gas cannot be fully discharged, forming bubbles. It is difficult to detect small bubble defects at the junction of different thicknesses by detecting temperature anomalies through the difference in temperature at different locations. Summary of the invention

[0004] The present invention provides a method and system for real-time monitoring of production equipment data in a digital factory to solve the existing problems.

[0005] A digital factory production equipment data real-time monitoring method and system of the present invention adopts the following technical solutions: An embodiment of the present invention provides a method for real-time monitoring of production equipment data in a digital factory, the method comprising the following steps: Collect thermal images of the casting, cluster the thermal images, and obtain several regions of the casting; Obtaining the edge line where each boundary pixel point in the boundary zone of different regions of the casting is located, and obtaining the edge fluctuation degree of each boundary pixel point according to the temperature difference of the pixel points on the edge line where each boundary pixel point is located; According to the temperature changes on both sides of the edge line where each boundary pixel point is located, the temperature difference degree of each boundary pixel point is obtained; through the edge line where the boundary pixel point is located, two different thickness areas corresponding to each boundary pixel point are obtained, and the temperature changes of the pixels in the two different thickness areas are analyzed to obtain the temperature fault degree of the pixels in the two different thickness areas corresponding to each boundary pixel point; according to the temperature difference degree of each boundary pixel point and the temperature fault degree of the corresponding pixels in the two different thickness areas, the temperature anomaly expression degree of each boundary pixel point is obtained; According to the temperature anomaly expression degree and edge fluctuation degree of each boundary pixel point, the temperature anomaly degree of each boundary pixel point is obtained; A threshold is determined for the temperature anomaly degree of each boundary pixel, the temperature anomaly boundary pixels are obtained, and the abnormal temperature area is determined.

[0006] Furthermore, the specific method of obtaining the edge line where each boundary pixel point is located is: In the boundary area between any two different regions, the boundary area is the common edge of the two different regions. The boundary pixel point is recorded as The edge line where the boundary pixels are located.

[0007] Furthermore, obtaining the edge fluctuation degree of each boundary pixel point includes: The first The edge line where the boundary pixel points are located is All pixels outside the boundary pixels are recorded as The adjacent pixel points on the edge line where the first boundary pixel point is located; The specific calculation formula for the edge fluctuation degree of the boundary pixel point is: in, Indicates The degree of edge fluctuation of the boundary pixels; Indicates The temperature of the boundary pixel; Indicates The boundary pixel point is located on the edge line The temperature of adjacent pixels; Indicates The number of adjacent pixels on the edge line where the boundary pixel is located; represents the linear normalization function.

[0008] Furthermore, the specific method for obtaining the temperature difference degree of each boundary pixel point is: Based on the edge line where each intersection pixel point is located, a window is constructed for each intersection pixel point to obtain the first part and the second part of the window of each intersection pixel point, as well as several adjacent pixels in the window of each intersection pixel point; The specific calculation formula for the temperature difference between the boundary pixels is: in, Indicates The degree of temperature difference between the boundary pixels; Indicates The temperature of the boundary pixel; Indicates The window of the boundary pixels The temperature of adjacent pixels; Indicates the number of pixels in the window except the central pixel; Indicates The first part of the window of the boundary pixel The pixel points in the second part The absolute value of the temperature difference of each pixel; Indicates the number of pixels in the first and second parts of the window; represents the linear normalization function; represents the absolute value function.

[0009] Furthermore, the window is constructed for each intersection pixel point respectively, and the first part and the second part in the window of each intersection pixel point are obtained, and a plurality of adjacent pixels in the window of each intersection pixel point include: First The intersection pixel is the center pixel, and the The edge line where the boundary pixel point is located is In the vertical direction of the tangent line at the intersection pixel points, a through the window The edge line where the boundary pixel point is located is The tangent line at the boundary pixel point divides the window into the first part and the second part, and all the pixels in the window are recorded as the The adjacent pixels of the window of the intersection pixels.

[0010] Furthermore, the edge line where the boundary pixel point is located is used to obtain two different thickness regions corresponding to each boundary pixel point, and the temperature changes of the pixels in the two different thickness regions are analyzed to obtain the temperature fault degree of the pixels in the two different thickness regions corresponding to each boundary pixel point, including: The first The two different regions corresponding to the boundary area where the boundary pixel points are located are recorded as Two areas of different thicknesses corresponding to the intersection pixels; In the two different thickness areas corresponding to the boundary pixel points, the thickness area with the largest pixel point temperature average is recorded as the thicker area, and the area with the smallest pixel point temperature average is recorded as the thinner area. The traversal order is from left to right for the boundary pixels. For each pixel point on the edge line where the boundary pixel points are located, the pixel points closest to each pixel point in the thicker area and the thinner area are selected respectively, and the pixels are used as the pixel points at the corresponding positions of each pixel point on the edge line of the thicker area and the thinner area; The first The thinner area corresponding to the boundary pixel The temperature of the pixel at the position is related to the temperature of the thicker area. The absolute value of the temperature difference of the pixel point at the position is recorded as The two regions of different thicknesses corresponding to the boundary pixels are in The temperature change of the pixel at each position; Get the The two regions of different thicknesses corresponding to the boundary pixels are in The temperature changes of the pixels at all positions on the edge line where the boundary pixels are located form a temperature sequence according to the traversal order; The curvature of the temperature series is obtained by the finite difference method, and the curvature of the temperature series is normalized. The normalized result is recorded as The temperature fault degree of the pixels in the two different thickness areas corresponding to the boundary pixels.

[0011] Furthermore, obtaining the temperature anomaly expression degree of each boundary pixel point includes: The first The temperature difference between the first and second boundary pixels is The product of the temperature fault degree of the pixels of the two different thickness areas corresponding to the boundary pixels is recorded as The temperature anomaly expression of the boundary pixels.

[0012] Furthermore, obtaining the temperature anomaly degree of each boundary pixel point includes: The first The product of the temperature of the boundary pixel, the temperature anomaly expression and the edge fluctuation degree is recorded as The temperature anomaly degree of the boundary pixel.

[0013] Furthermore, obtaining the temperature anomaly boundary pixel point includes: When When the temperature anomaly of the first boundary pixel is greater than or equal to the preset anomaly threshold, the The boundary pixel points are recorded as temperature anomaly boundary pixels; When When the temperature anomaly of the first boundary pixel is less than the preset anomaly threshold, The boundary pixel point is recorded as the normal temperature boundary pixel point.

[0014] The present invention also proposes a real-time monitoring system for digital factory production equipment data, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned real-time monitoring method for digital factory production equipment data.

[0015] The beneficial effects of the technical solution of the present invention are: collecting thermal images of the casting, clustering the thermal images, and obtaining several areas of the casting, which is helpful to identify the temperature distribution characteristics of different parts; obtaining the edge line of each junction pixel point in the junction zone of different areas of the casting, and obtaining the edge fluctuation degree of each junction pixel point, which is conducive to determining the local characteristics of the temperature change on the junction line, and helping to identify the area with drastic temperature change on the edge line; according to the temperature changes on both sides of the edge line where each junction pixel point is located, the degree of temperature difference of each junction pixel point is obtained, and the temperature dividing line between different areas is determined, providing a basis for abnormality detection; through the edge line where the junction pixel point is located, two different thickness areas corresponding to each junction pixel point are obtained, and the temperature of the pixel points in the two different thickness areas is analyzed. The temperature fault degree of the pixel points in two different thickness areas corresponding to each junction pixel point is obtained to reveal the temperature change characteristics of the internal structure of the casting, which helps to understand the heat conduction inside the casting, especially the difference in heat distribution in different thickness areas; the temperature anomaly expression degree of each junction pixel point is obtained according to the temperature difference degree of each junction pixel point and the temperature fault degree of the pixel points in two different thickness areas; the temperature anomaly degree of each junction pixel point is obtained according to the temperature anomaly expression degree and edge fluctuation degree of each junction pixel point, which is conducive to accurately identifying the temperature anomaly area; the temperature anomaly degree of each junction pixel point is judged by a threshold, the temperature anomaly junction pixel point is obtained and the abnormal temperature area is determined, so as to improve the accuracy of small bubble defect detection in the junction area of ​​different thicknesses. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0017] Figure 1 The present invention is a flowchart of the steps of a method for real-time monitoring of digital factory production equipment data. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a method and system for real-time monitoring of production equipment data in a digital factory proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] 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.

[0020] The following is a detailed description of a method and system for real-time monitoring of production equipment data in a digital factory provided by the present invention in conjunction with the accompanying drawings.

[0021] See also Figure 1 , which shows a flowchart of a method for real-time monitoring of digital factory production equipment data provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Collect thermal images of the casting, cluster the thermal images, and obtain several regions of the casting.

[0022] The thermal images of castings in the production process of die-casting machines are collected by infrared thermal imagers, and the temperature of each pixel in the thermal images of castings is obtained. The DBSCAN clustering algorithm is used to cluster all pixels in the thermal images of castings according to the temperature of each pixel. The distance measurement uses the absolute value of the difference between the temperatures of the pixels to obtain several clusters. Each cluster corresponds to several regions, and thus several regions of the casting are obtained.

[0023] Step S002: Obtain the edge line where each boundary pixel point in the boundary zone of different regions of the casting is located, and obtain the edge fluctuation degree of each boundary pixel point according to the temperature difference of the pixel points on the edge line where each boundary pixel point is located.

[0024] It should be noted that during the die-casting process, the die-casting machine affects the solidification rate and thermal conductivity of the metal due to the uneven thickness of different areas of the casting, which in turn affects the release of gas and the uniformity of metal fluidity during the solidification process. The thicker areas have slower heat conduction and relatively slower solidification rates, so the gas in the area cannot be effectively discharged and the metal flow rate is not enough to push the gas out, forming bubbles during the solidification process; some areas of the casting have large differences in thickness, resulting in uneven metal fluidity, which in turn generates bubbles at the junction of different areas of the casting. The bubbles at the junction of different areas of the casting will change the thermal conductivity of the metal, resulting in uneven temperature distribution around the junction, causing abnormal temperature changes, that is, local temperature fluctuations. The temperature anomaly will cause large fluctuations at the edges of different areas of the cluster.

[0025] Specifically, in the boundary area between any two different areas, the boundary area is the common edge of the two different areas, and the first The boundary pixel point is recorded as The edge line where the intersection pixel point is located; The edge line where the boundary pixel points are located is All pixels outside the boundary pixels are recorded as The adjacent pixels on the edge line where the boundary pixel is located are The temperature difference of the pixel points on the edge line where the boundary pixel points are located is obtained. The edge fluctuation degree of the boundary pixels.

[0026] Further, The specific calculation formula for the edge fluctuation degree of the boundary pixel point is: in, Indicates The degree of edge fluctuation of the boundary pixels; Indicates The temperature of the boundary pixel; Indicates The boundary pixel point is located on the edge line The temperature of adjacent pixels; Indicates The number of adjacent pixels on the edge line where the boundary pixel is located; Represents a linear normalization function, and the normalized object is all the boundary pixels. .

[0027] It should be noted that Indicates The average temperature of all adjacent pixels on the edge line where the boundary pixel is located, It means the The absolute value of the difference between the temperature of the first boundary pixel and the average temperature of all adjacent pixels on the edge line where it is located measures the The difference between the temperature of the first boundary pixel and the average temperature of other pixels in the direction of the temperature boundary change. The larger the value, the The temperature around the junction pixels changes unevenly. Indicates The relative size of the temperature difference between the first boundary pixel and the surrounding pixels is The temperature of the boundary pixel point, the larger the value, the The temperature difference between a boundary pixel and its surrounding environment has a more significant impact on its own temperature. The larger the value, the The greater the edge fluctuation of the boundary pixels.

[0028] Step S003: According to the temperature changes on both sides of the edge line where each junction pixel point is located, the degree of temperature difference of each junction pixel point is obtained; through the edge line where the junction pixel point is located, two different thickness areas corresponding to each junction pixel point are obtained, and the temperature changes of the pixels in the two different thickness areas are analyzed to obtain the degree of temperature fault of the pixels in the two different thickness areas corresponding to each junction pixel point; according to the temperature difference degree of each junction pixel point and the temperature fault degree of the pixels in the corresponding two different thickness areas, the temperature anomaly expression degree of each junction pixel point is obtained.

[0029] It should be noted that by analyzing The temperature difference between the boundary pixel and the adjacent pixel on the edge line is obtained. After analyzing the edge fluctuation degree of the first boundary pixel, The temperature difference between the boundary pixel and the adjacent pixel on the edge line cannot fully reflect the temperature anomaly of the pixel points in the boundary zone of different regions. Therefore, it is necessary to consider the temperature difference of the boundary pixel on both sides of the edge line and the temperature difference of the pixel points in different thickness areas for further analysis.

[0030] It should be noted that when no bubbles are generated in the boundary zone of different areas, the temperature difference on both sides of the boundary zone is large. The bubbles generated in the boundary zone of different areas have a significant impact on the temperature distribution of the surrounding environment, that is, the temperature of any boundary pixel point in the boundary zone changes on both sides of the edge line. When the temperature of the boundary pixel point on both sides of the edge line changes greatly, the temperature difference of the pixels at the corresponding positions on both sides is small. At this time, the temperature of the boundary pixel point may be abnormal.

[0031] Specifically, in the border area, The intersection pixel is the center pixel, and the The edge line where the boundary pixel point is located is In the vertical direction of the tangent line at the intersection pixel points, a through the window The edge line where the boundary pixel point is located is The tangent line at the boundary pixel point divides the window into the first part and the second part, and all the pixels in the window are recorded as the The adjacent pixels in the window of the boundary pixel point; in this embodiment, , To construct the window, if the boundary pixel is close to the boundary of the thermal image and the complete window cannot be obtained, the quadratic linear interpolation is used to fill the window.

[0032] It should be noted that the greater the temperature difference between the corresponding pixel points in the first part and the second part, the The smaller the possibility of abnormal temperature of the boundary pixel point, the smaller the possibility of abnormal temperature of the boundary pixel point. The change in the temperature data of the first boundary pixel and all adjacent pixels in the window determines the The degree of temperature difference between the boundary pixels.

[0033] Specifically, The specific calculation formula for the temperature difference between the boundary pixels is: in, Indicates The degree of temperature difference between the boundary pixels; Indicates The temperature of the boundary pixel; Indicates The window of the boundary pixels The temperature of adjacent pixels; Indicates the number of pixels in the window except the central pixel; Indicates The first part of the window of the boundary pixel The pixel points in the second part The absolute value of the temperature difference of each pixel (the traversal order of the pixels starts from the upper left corner of each part); Indicates the number of pixels in the first and second parts of the window; Represents a linear normalization function, and the normalized object is all the boundary pixels. ; represents the absolute value function.

[0034] It should be noted that Represents the average temperature of all adjacent pixels in the window, Indicates The greater the deviation, the greater the deviation. The greater the temperature difference between a boundary pixel and the pixels on both sides of it, the greater the corresponding temperature difference. Indicates The average absolute value of the difference between the temperature of the corresponding pixel points in the first part and the second part of the window of the boundary pixel points. The larger the value, the The more normal the temperature difference between the two sides of the first boundary pixel, the The smaller the possibility that the temperature of the first boundary pixel point is abnormal, the The greater the temperature difference between the boundary pixels.

[0035] It should be further explained that the thickness of different areas of the thermal image of the casting is different, and there are significant differences in temperature. Since the metal mass in the thicker area is large and the heat is evenly distributed, the temperature is higher and evenly distributed, and there is no obvious temperature anomaly or change; since the metal thickness in the thinner area is thinner, the heat conduction speed is faster, the temperature changes rapidly, and there are obvious temperature anomalies or changes. When there is no bubble area at the junction of areas of different thicknesses, due to the thermal conductivity of the metal, the temperature of the thicker area will quickly conduct to the thinner area, so that the temperature difference of the pixels in the areas of different thicknesses is small; when the bubbles generated in the junction of areas of different thicknesses will form a thermal bridge or thermal resistance, affecting the conduction of heat, resulting in the temperature of the thicker area cannot be quickly conducted to the thinner area, bypassing the bubbles and conducting from the edges of the bubbles to the thinner area, so that the temperature of the pixels on both sides of the thinner area is higher, and the temperature of the pixels in the middle is lower. The temperature difference of the pixels in the areas of different thicknesses is large, and the temperature is faulted.

[0036] Furthermore, The two different regions corresponding to the boundary area where the boundary pixel points are located are recorded as Two different thickness areas corresponding to the intersection pixel points; in order to determine the The temperature fault degree of the pixel points of two different thickness areas corresponding to the boundary pixel points is calculated by The temperature of the pixels in the two different thickness regions corresponding to the boundary pixels is quantified. In the two different thickness areas corresponding to the boundary pixel points, the thickness area with the largest pixel point temperature average is recorded as the thicker area, and the area with the smallest pixel point temperature average is recorded as the thinner area. The traversal order is from left to right for the boundary pixels. For each pixel point on the edge line where the boundary pixel points are located, the pixel points closest to each pixel point in the thicker area and the thinner area are respectively selected, that is, the pixel points adjacent to each pixel point in the two areas of different thicknesses are obtained for each pixel point in the traversal order, and are used as the pixel points corresponding to each pixel point on the edge line in the thicker area and the thinner area.

[0037] Further, The two regions of different thicknesses corresponding to the boundary pixels are in The specific calculation formula for the temperature change of a pixel point at a position is: in, Indicates The two regions of different thicknesses corresponding to the boundary pixels are in The temperature change of the pixel at each position; Indicates The thinner area corresponding to the boundary pixel The temperature of the pixel at the location; Indicates The thicker area corresponding to the boundary pixel The temperature of the pixel at the location; represents the absolute value function.

[0038] Further, according to the above method, the The two regions of different thicknesses corresponding to the boundary pixels are in The temperature changes of all pixels at the edge line where the boundary pixels are located form a temperature sequence in the traversal order. ; Obtain the curvature of the temperature series according to the finite difference method, normalize the curvature of the temperature series, and record the normalized result as The greater the curvature, the greater the degree of fault. The finite difference method is a well-known technology, and the specific method will not be introduced here.

[0039] It should be noted that when The greater the temperature difference between the first and second boundary pixels, the The greater the degree of temperature fault of the pixels in the two different thickness areas corresponding to the boundary pixels, the greater the The temperature of the boundary pixels may be abnormal.

[0040] Specifically, The specific calculation formula for the temperature anomaly expression of the boundary pixel point is: in, Indicates The temperature anomaly expression of each boundary pixel; Indicates The degree of temperature difference between the boundary pixels; Indicates The temperature fault degree of the pixels in the two different thickness areas corresponding to the boundary pixels.

[0041] It should be noted that The larger the value, the The more abnormal the temperature performance of the boundary pixels is, the more abnormal it is.

[0042] Step S004: Obtain the temperature anomaly degree of each boundary pixel point according to the temperature anomaly expression degree and edge fluctuation degree of each boundary pixel point.

[0043] It should be noted that The temperature anomaly performance of the first boundary pixel is The edge fluctuation degree of the first and second boundary pixels shows the same The temperature anomaly of the junction pixels is closely related to each other, which fully reflects the relationship between the temperature anomalies of the junction pixels of different regions. The temperature anomaly of the boundary pixel point, The greater the temperature anomaly of the first boundary pixel, the The greater the edge fluctuation of the first boundary pixel, the The more pixels at the intersection, the greater the possibility that the temperature of the pixel will be abnormal. The temperature anomaly performance of the first boundary pixel is The edge fluctuation degree of the boundary pixel is taken as the The weight of the temperature of the boundary pixel is used to determine the The temperature anomaly degree of the boundary pixel.

[0044] No. The specific calculation formula for the temperature anomaly degree of each boundary pixel is: in, Indicates The degree of temperature anomaly at each boundary pixel; Indicates The temperature anomaly expression of each boundary pixel; Indicates The degree of edge fluctuation of the boundary pixels; Indicates The temperature of the boundary pixel.

[0045] It should be noted that The larger the value, the The greater the temperature anomaly of the boundary pixel, the greater the temperature anomaly of the boundary pixel.

[0046] Similarly, the temperature anomaly degree of each boundary pixel is obtained according to the above steps.

[0047] Step S005: performing a threshold judgment on the temperature anomaly degree of each boundary pixel point, obtaining the temperature anomaly boundary pixel points and determining the abnormal temperature area.

[0048] The temperature anomaly degree of each boundary pixel point is determined by a threshold value. The abnormal threshold value preset in this embodiment is , which is described as an example, can be set to other values ​​in other implementations, and this embodiment does not limit it. The temperature anomaly of the boundary pixel is greater than or equal to the anomaly threshold When The boundary pixel point is recorded as the temperature anomaly boundary pixel point; The temperature anomaly of the boundary pixel is less than the anomaly threshold When The boundary pixel point is recorded as the normal temperature boundary pixel point.

[0049] According to the temperature abnormality boundary pixel points, a number of abnormal temperature regions are obtained through the regional growing algorithm. Each abnormal temperature region is a small bubble defect detected at the boundary of different thicknesses, and the real-time monitoring of the die-casting machine data in the digital factory production equipment is completed. Among them, the regional growing algorithm is a well-known technology, and the specific method is not introduced here.

[0050] At this point, this embodiment is completed.

[0051] The present invention also provides a real-time monitoring system for digital factory production equipment data, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the aforementioned real-time monitoring method for digital factory production equipment data.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for real-time monitoring of production equipment data in a digital factory, characterized in that: The method comprises the following steps: Collect thermal images of the casting, cluster the thermal images, and obtain several regions of the casting; Obtaining the edge line where each boundary pixel point in the boundary zone of different regions of the casting is located, and obtaining the edge fluctuation degree of each boundary pixel point according to the temperature difference of the pixel points on the edge line where each boundary pixel point is located; According to the temperature changes on both sides of the edge line where each boundary pixel point is located, the temperature difference degree of each boundary pixel point is obtained; through the edge line where the boundary pixel point is located, two different thickness areas corresponding to each boundary pixel point are obtained, and the temperature changes of the pixels in the two different thickness areas are analyzed to obtain the temperature fault degree of the pixels in the two different thickness areas corresponding to each boundary pixel point; according to the temperature difference degree of each boundary pixel point and the temperature fault degree of the corresponding pixels in the two different thickness areas, the temperature anomaly expression degree of each boundary pixel point is obtained; According to the temperature anomaly expression degree and edge fluctuation degree of each boundary pixel point, the temperature anomaly degree of each boundary pixel point is obtained; A threshold is determined for the temperature anomaly degree of each boundary pixel, the temperature anomaly boundary pixels are obtained, and the abnormal temperature area is determined.

2. According to claim 1, a method for real-time monitoring of digital factory production equipment data is characterized in that: The specific method of obtaining the edge line where each boundary pixel point is located is: In the boundary area between any two different regions, the boundary area is the common edge of the two different regions. The boundary pixel point is recorded as The edge line where the intersection pixels are located.

3. According to claim 1, a method for real-time monitoring of digital factory production equipment data is characterized in that: The step of obtaining the edge fluctuation degree of each boundary pixel point comprises: The first The edge line where the boundary pixel points are located is All pixels outside the boundary pixels are recorded as The adjacent pixel points on the edge line where the first boundary pixel point is located; The specific calculation formula for the edge fluctuation degree of the boundary pixel point is: in, Indicates The degree of edge fluctuation of the boundary pixels; Indicates The temperature of the boundary pixel; Indicates The boundary pixel point is located on the edge line The temperature of adjacent pixels; Indicates The number of adjacent pixels on the edge line where the boundary pixel is located; represents the linear normalization function.

4. According to claim 1, a method for real-time monitoring of digital factory production equipment data is characterized in that: The specific method for obtaining the temperature difference degree of each boundary pixel point is: Based on the edge line where each intersection pixel point is located, a window is constructed for each intersection pixel point to obtain the first part and the second part of the window of each intersection pixel point, as well as several adjacent pixels in the window of each intersection pixel point; The specific calculation formula for the temperature difference between the boundary pixels is: in, Indicates The degree of temperature difference between the boundary pixels; Indicates The temperature of the boundary pixel; Indicates The window of the boundary pixels The temperature of adjacent pixels; Indicates the number of pixels in the window except the central pixel; Indicates The first part of the window of the boundary pixel The pixel points in the second part The absolute value of the temperature difference of each pixel; Indicates the number of pixels in the first and second parts of the window; represents the linear normalization function; represents the absolute value function.

5. According to claim 4, a method for real-time monitoring of digital factory production equipment data is characterized in that: The window is constructed for each intersection pixel point respectively, and the first part and the second part in the window of each intersection pixel point are obtained, and a plurality of adjacent pixel points in the window of each intersection pixel point include: First The intersection pixel is the center pixel, and the The edge line where the boundary pixel point is located is In the vertical direction of the tangent line at the intersection pixel points, a through the window The edge line where the boundary pixel point is located is The tangent line at the boundary pixel point divides the window into the first part and the second part, and all the pixels in the window are recorded as the The adjacent pixels of the window of the intersection pixels.

6. According to claim 1, a method for real-time monitoring of digital factory production equipment data is characterized in that: The step of obtaining two different thickness regions corresponding to each boundary pixel point through the edge line where the boundary pixel point is located, analyzing the temperature changes of the pixels in the two different thickness regions, and obtaining the temperature fault degree of the pixels in the two different thickness regions corresponding to each boundary pixel point includes: The first The two different regions corresponding to the boundary area where the boundary pixel points are located are recorded as Two areas of different thicknesses corresponding to the intersection pixels; In the two different thickness areas corresponding to the boundary pixel points, the thickness area with the largest pixel point temperature average is recorded as the thicker area, and the area with the smallest pixel point temperature average is recorded as the thinner area. The traversal order is from left to right for the boundary pixels. For each pixel point on the edge line where the boundary pixel points are located, the pixel points closest to each pixel point in the thicker area and the thinner area are selected respectively, and the pixels are used as the pixel points at the corresponding positions of each pixel point on the edge line of the thicker area and the thinner area; The first The thinner area corresponding to the boundary pixel The temperature of the pixel at the position is related to the temperature of the thicker area. The absolute value of the temperature difference of the pixel point at the position is recorded as The two regions of different thicknesses corresponding to the boundary pixels are in The temperature change of the pixel at the position; Get the The two regions of different thicknesses corresponding to the boundary pixels are in The temperature changes of the pixels at all positions on the edge line where the boundary pixels are located form a temperature sequence according to the traversal order; The curvature of the temperature series is obtained by the finite difference method, and the curvature of the temperature series is normalized. The normalized result is recorded as The temperature fault degree of the pixels in the two different thickness areas corresponding to the boundary pixels.

7. According to claim 1, a method for real-time monitoring of digital factory production equipment data is characterized in that: The step of obtaining the temperature anomaly expression degree of each boundary pixel point includes: The first The temperature difference between the first and second boundary pixels is The product of the temperature fault degree of the pixels of the two different thickness areas corresponding to the boundary pixels is recorded as The temperature anomaly expression of the boundary pixels.

8. According to claim 1, a method for real-time monitoring of digital factory production equipment data is characterized in that: The step of obtaining the temperature anomaly degree of each boundary pixel point includes: The first The product of the temperature of the boundary pixel, the temperature anomaly expression and the edge fluctuation degree is recorded as The temperature anomaly degree of the boundary pixel.

9. The method for real-time monitoring of production equipment data in a digital factory according to claim 1, characterized in that: The step of obtaining the temperature anomaly boundary pixel point comprises: When When the temperature anomaly of the first boundary pixel is greater than or equal to the preset anomaly threshold, the The boundary pixel points are recorded as temperature anomaly boundary pixels; When When the temperature anomaly of the first boundary pixel is less than the preset anomaly threshold, The boundary pixel point is recorded as the normal temperature boundary pixel point.

10. A digital factory production equipment data real-time monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the computer program is executed by a processor, the steps of a method for real-time monitoring of digital factory production equipment data as described in any one of claims 1 to 9 are implemented.

Citation Information

Patent Citations

  • Infrared detection method for metal component defects based on pulse-current electromagnetic heat effect

    CN103558249A

  • Cable detection method based on image processing

    CN115841493A

  • Image detection method for cable insulation layer

    CN116543238A

  • Fault detection method and system for air pressure sintering furnace

    CN117168630A

  • Edge detection method and system based on cellular automaton

    CN117314947A

Cited By

  • Temperature control method for die-casting die for metal casting

    CN120205774A

  • Temperature determination method and device for die casting, electronic equipment and storage medium

    CN121755681A