CN115338282B - Magnesium alloy forging product stamping forming system and stamping forming method - Google Patents
Magnesium alloy forging product stamping forming system and stamping forming method Download PDFInfo
- Publication number
- CN115338282B CN115338282B CN202211266968.XA CN202211266968A CN115338282B CN 115338282 B CN115338282 B CN 115338282B CN 202211266968 A CN202211266968 A CN 202211266968A CN 115338282 B CN115338282 B CN 115338282B
- Authority
- CN
- China
- Prior art keywords
- temperature
- point
- offset
- isothermal
- pixel
- 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.)
- Active
Links
- 238000005242 forging Methods 0.000 title claims abstract description 69
- 229910000861 Mg alloy Inorganic materials 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000010438 heat treatment Methods 0.000 claims abstract description 58
- 239000013598 vector Substances 0.000 claims abstract description 53
- 238000009826 distribution Methods 0.000 claims abstract description 25
- 238000004891 communication Methods 0.000 claims description 37
- 230000008859 change Effects 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000004090 dissolution Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
- 229910000859 α-Fe Inorganic materials 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21C—MANUFACTURE OF METAL SHEETS, WIRE, RODS, TUBES OR PROFILES, OTHERWISE THAN BY ROLLING; AUXILIARY OPERATIONS USED IN CONNECTION WITH METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL
- B21C51/00—Measuring, gauging, indicating, counting, or marking devices specially adapted for use in the production or manipulation of material in accordance with subclasses B21B - B21F
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D—WORKING OR PROCESSING OF SHEET METAL OR METAL TUBES, RODS OR PROFILES WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D37/00—Tools as parts of machines covered by this subclass
- B21D37/16—Heating or cooling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention relates to the technical field of control devices of forging presses, in particular to a magnesium alloy forging product stamping forming system and a stamping forming method. The method comprises the following steps: carrying out mean shift clustering on the surface temperature image to obtain an initial central point of clustering and obtain a circular area, wherein the circular area is a clustering range of the initial central point; obtaining a final offset vector according to the offset vector of each isothermal connected domain in the circular area; moving the position of the initial central point according to the final offset vector until the clustering is completed to obtain a low-temperature region and a normal region of the surface temperature image; and obtaining a heating position and a heating temperature, and heating the magnesium alloy forging with uneven temperature distribution based on the heating position and the heating temperature. The distribution condition of the surface temperature of the magnesium alloy can be accurately obtained, the heating position and the heating temperature can be accurately obtained, the surface of the magnesium alloy is heated according to the heating position and the heating temperature, so that the temperature distribution of the magnesium alloy forge piece is uniform, and the precision of a stamping product is ensured.
Description
Technical Field
The invention relates to the technical field of control devices of forging presses, in particular to a magnesium alloy forging product stamping forming system and a stamping forming method.
Background
When the magnesium alloy forging is subjected to stamping forming through a forging press, the forging needs to be subjected to heat treatment, if the temperature distribution of the forging is uneven, different parts of the forging deform differently when the forging is subjected to the same force, so that the precision error of the forging is increased, and the temperature distribution on the surface of the magnesium alloy forging is uneven mainly due to insufficient quenching heating temperature, heating and heat preservation time, insufficient austenitizing, hypoeutectoid, incomplete dissolution of congratulatory steel ferrite, too little dissolution of hypereutectoid steel carbide and the like.
In the prior art, the temperature sensor is generally additionally arranged on the forging press to measure the temperature of the magnesium alloy forging, but the temperature sensor can only carry out single-point sampling to obtain the local temperature and cannot accurately and timely analyze the temperature of the surface of the magnesium alloy forging, so that the magnesium alloy forging with uneven distribution of the surface temperature after being heated cannot be timely retreated.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a magnesium alloy forging product stamping forming system and a stamping forming method, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a method for stamping a magnesium alloy forging product, including: a magnesium alloy forging product stamping forming method comprises the following steps: obtaining a surface temperature image of the magnesium alloy forging by using an infrared thermometer, wherein each pixel point in the surface temperature image corresponds to one temperature; carrying out mean shift clustering on the surface temperature image to obtain an initial central point of clustering, and obtaining a circular area by taking one initial central point as a circle center and a preset length as a radius, wherein the circular area is a clustering range of the initial central point;
selecting a pixel point in the circular area, marking as an offset point, and obtaining the absolute value of the difference value of the temperatures of the offset point and the initial central point; obtaining an isothermal communication domain containing offset points, wherein the temperatures corresponding to pixel points in the isothermal communication domain are equal; obtaining a temperature change index of the isothermal communication domain according to the difference between the temperature corresponding to the adjacent peripheral pixel point at the edge of the isothermal communication domain and the temperature corresponding to the pixel point in the isothermal communication domain; the product of the area of the isothermal connected domain, the temperature change index and the hyperparameter is the offset weight;
obtaining a vector with a modular length which is the product of the absolute value of the difference value of the temperatures corresponding to the initial central point and the offset weight, and recording the vector as an offset vector, wherein the direction of the offset vector is determined by the difference value of the temperatures corresponding to the initial central point and the offset point; summing the offset vectors of all isothermal connected domains in the circular area to obtain a final offset vector; moving the position of the initial central point according to the final offset vector until the clustering is completed to obtain a low-temperature region and a normal region of the surface temperature image;
obtaining the central point of the low-temperature area as a heating position; obtaining the heating temperature according to the difference value of the temperature corresponding to each pixel point in the low-temperature area and the mean value of the temperatures corresponding to the pixel points in the normal area and the distance between each pixel point in the low-temperature area and the heating position; and heating the magnesium alloy forging with uneven surface temperature distribution based on the heating position and the heating temperature.
Preferably, obtaining the initial center point of the cluster comprises: there are multiple initial center points when mean-shift clustering is performed on the surface temperature images.
Preferably, obtaining an isothermal connected domain containing the offset point comprises: obtaining pixel points with the same temperature corresponding to the offset points in the circular area; setting the pixel value of the coordinate of the pixel point with the same temperature as the offset point as a first preset value, setting the pixel values of the other pixel points as second preset values, and obtaining the isothermal connected domain by using an 8-neighborhood connected domain extraction algorithm.
Preferably, obtaining an indication of the temperature change of the isothermally connected domain comprises: setting a sliding window with a preset size, wherein the sliding step length is the side length of the sliding window, and the edge pixel point of the isothermal communicating domain is the central point of the sliding window; obtaining the mean value of the temperatures corresponding to the pixel points which do not belong to the isothermal communication domain in all the sliding windows when the sliding windows slide by taking the edge of the isothermal communication domain as a sliding track; and the difference value of the mean value of the temperatures corresponding to the pixel points in the isothermal connected domain and the mean value of the temperatures corresponding to the pixel points not belonging to the isothermal connected domain in all the sliding windows is the temperature change index of the isothermal connected domain.
Preferably, the determining of the direction of the offset vector by the difference of the temperatures corresponding to the initial central point and the offset point comprises: if the difference value of the temperatures corresponding to the initial central point and the offset point is more than or equal to 0, the direction of the offset vector is that the initial central point points to the offset point; if the difference value of the temperatures corresponding to the initial central point and the offset point is less than 0, the direction of the offset vector is that the offset point points to the initial central point, and the direction of the offset vector is that the offset point points to the initial central point indicates that the initial central point does not need to move to the offset point.
Preferably, moving the position of the initial center point according to the final offset vector includes: and if the end point is between two pixel points, the distance between the two pixel points and the final offset vector is obtained, and the pixel point with the small distance is taken as the position to which the initial center point is moved.
Preferably, the heating temperature is:
wherein T represents a heating temperature in a low temperature region; m represents the number of pixel points in a low-temperature region;
expressing the difference value of the temperature value corresponding to the mth pixel point in the low-temperature area and the average value of the temperatures corresponding to the pixel points in the normal area; e represents a natural constant;
Indicating the distance between the mth pixel point in the low temperature region and the heating position.
In a second aspect, another embodiment of the present invention provides a magnesium alloy forging product stamping forming system, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the magnesium alloy forging product stamping forming method.
The embodiment of the invention at least has the following beneficial effects: according to the method, the temperature corresponding to the pixel points in the magnesium alloy forging surface temperature image is analyzed, the temperature difference of the pixel points, the temperature change of the isothermal connected domain and the area of the isothermal connected domain are used for obtaining the offset vector, a method for obtaining the mass center by using a conventional mean shift clustering algorithm is replaced, the improved mean shift clustering algorithm can better accord with the characteristics of the magnesium alloy surface temperature, the distribution condition of the magnesium alloy surface temperature can be accurately obtained, the heating position and the heating temperature can be accurately obtained, the magnesium alloy surface is heated according to the heating position and the heating temperature, the temperature distribution of the magnesium alloy forging is uniform, and the precision of a stamped product is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a magnesium alloy forging product stamping forming method.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description, the structure, the features and the effects of a magnesium alloy forging product stamping forming system and a stamping forming method according to the present invention are provided with the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 following specifically describes a specific scheme of the magnesium alloy forging product stamping forming system and the stamping forming method provided by the invention with reference to the accompanying drawings.
Example 1
The main application scenarios of the invention are as follows: when the magnesium alloy forging is stamped, the temperature of the magnesium alloy forging is detected, whether the temperature distribution of the magnesium alloy forging is uniform or not is judged, if the forging press is controlled to heat a region with lower temperature unevenly, it needs to be explained that the uneven temperature distribution of the surface of the magnesium alloy forging mainly means that the temperature of some regions of the magnesium alloy forging is too low, and the temperatures of other regions all belong to normal temperature and meet the stamping requirement.
Referring to fig. 1, a flow chart of a method for stamping a magnesium alloy forging product according to an embodiment of the present invention is shown, where the method includes the following steps:
the method comprises the following steps: obtaining a surface temperature image of the magnesium alloy forging by using an infrared thermometer, wherein each pixel point in the surface temperature image corresponds to one temperature; and performing mean shift clustering on the surface temperature image to obtain an initial central point of clustering, and obtaining a circular area by taking one initial central point as a circle center and a preset length as a radius, wherein the circular area is a clustering range of the initial central point.
Firstly, an infrared thermometer is fixed in a forging press, wherein the infrared thermometer is fixed in the forging press and is used for acquiring a surface temperature image of a magnesium alloy forging, and each pixel point in the surface temperature image corresponds to a temperature value.
Further, the conventional method is to judge the unqualified surface temperature of the current magnesium alloy forging according to the minimum temperature value, and then heat the magnesium alloy forging according to the minimum temperature value, so that the temperature at which the current magnesium alloy forging should be heated cannot be well obtained. Even if the local temperature on the surface of the magnesium alloy forging is too low, when the clustering is carried out by using the conventional mean shift algorithm to obtain the magnesium alloy forging temperature too low region, the region with too low temperature does not present an absolute circular shape to represent temperature drop, so that the conventional centroid calculation method cannot well obtain the heating position of the current magnesium alloy forging.
Therefore, the conventional mean shift clustering algorithm is improved to judge the current heating position and the corresponding heating temperature of the magnesium alloy forging, the conventional clustering algorithm is used for clustering according to the temperature value to judge a low-temperature region, and when the temperature value in the image is clustered, the conventional mean shift algorithm cannot well finish clustering due to the fact that the coordinates of pixel points in the image are continuous; however, in order to obtain the position to be heated and the temperature to be heated of the current magnesium alloy forging, the present mean shift clustering method needs to be adjusted, so that the position to be heated and the temperature to be heated of the current forging can be obtained in a clustering manner.
Finally, in the surface temperature image, the coordinates of the center points of the mean shifts are initialized randomly to obtain a plurality of initial center points, and since the temperatures are continuously changed and approximately distributed in a gaussian manner (circular distribution), a circular area is obtained by taking each initial center point as a center of a circle and the length of the radius as a preset length as a clustering range of each initial center point, preferably, the radius of the circular area in the embodiment is set to 30 pixel points, and in the actual use process, an implementer can set the coordinates according to the actual situation.
Step two: selecting a pixel point in the circular area, marking as an offset point, and obtaining the absolute value of the difference value of the temperatures of the offset point and the initial central point; obtaining an isothermal communication domain containing offset points, wherein the temperatures corresponding to pixel points in the isothermal communication domain are equal; obtaining a temperature change index of the isothermal communication domain according to the difference between the temperature corresponding to the adjacent peripheral pixel point at the edge of the isothermal communication domain and the temperature corresponding to the pixel point in the isothermal communication domain; the product of the area of the isothermal connected domain, the temperature change index and the hyperparameter is the offset weight.
Firstly, in the surface temperature image of the whole magnesium alloy forging, when clustering is performed by adopting mean shift, the offset direction of the initial central point cannot be determined according to the distribution of coordinate points, the offset direction of the initial central point should be determined by using a temperature difference, and when the offset direction of the initial central point is determined by using the temperature difference, the finally obtained area is centered on the lowest temperature value, and the heating effect cannot well improve the temperature distribution of the whole forging when the low-temperature area of the forging is heated because the morphological distribution of the local low-temperature area is not absolutely regular. Therefore, the offset vector when the mean shift clustering is adopted is determined according to the range of the isothermal distribution of the temperature difference, and the final mean shift result is obtained.
Further, an ith initial center point is selected, a pixel point is selected in a circular area of the initial center point and is recorded as an offset point j, the jth offset point is also represented, and the absolute value of the difference value between the temperature corresponding to the ith initial center point and the jth offset point is obtained
Wherein->
Indicates the temperature corresponding to the ith initial midpoint>
Indicating the temperature corresponding to the jth offset point; when/is>
Now, it is stated that the temperature corresponding to the jth offset point is lower than or equal to the temperature corresponding to the ith initial center point, so that for these two points at this time, when ^ is greater than or equal to ^ i>
When 0, the ith initial center point does not move
If the value is greater than 0, the ith initial center point should be moved to the location of the jth offset point.
Then, for the ith initial center point and the jth offset point, if the ith initial center point is offset to the jth offset point, if the moving distance is the distance between the two points, the low-temperature region finally obtained after clustering is centered on the lowest temperature value, and since the form distribution of the local low-temperature region is not absolutely regular, the heating effect cannot well improve the temperature distribution of the whole magnesium alloy forging when the low-temperature region of the magnesium alloy forging is heated.
Therefore, the distance of movement of the ith initial center point needs to be adjusted according to the distribution of the equal pixel points of the temperature corresponding to the jth offset point. Obtaining pixel points with the same temperature as that of the jth offset point in a circular area corresponding to the ith initial central point, setting pixel values of the pixel points to be first preset values, and setting pixel values of the rest other pixel points to be second preset values, preferably, the first preset value is 1 and the second preset value is 0 in the present example, completing isothermal threshold segmentation of the pixel points, and then obtaining an isothermal connected domain of the jth offset point by using an 8-neighborhood connected domain extraction algorithm, wherein the temperature corresponding to the pixel points in the isothermal connected domain is equal to the temperature corresponding to the jth offset point.
And finally, obtaining an offset weight according to the area of the isothermal communication domain corresponding to the jth offset point and the change of the temperature corresponding to the pixel point of the peripheral region of the edge line of the isothermal communication domain, and adjusting the distance of the ith initial central point relative to the jth offset point when the ith initial central point moves by using the offset weight of the isothermal communication domain corresponding to the jth offset point and the difference value between the temperature corresponding to the ith initial central point and the corresponding jth offset point.
Therefore, it is also necessary to obtain the temperature change index of the isothermal connected domain corresponding to the jth offset point
The specific obtaining method comprises the following steps: setting a sliding window with a preset size, wherein the sliding step length is the side length of the sliding window, and the edge pixel point of the isothermal connected domain is taken as the central point of the sliding window, preferably the size of the sliding window in the embodiment is 3*3; obtaining the mean value of the temperatures corresponding to the pixel points which do not belong to the isothermal communication domain in all the sliding windows when the sliding windows slide by taking the edge of the isothermal communication domain as a sliding track; the difference value between the mean value of the temperatures corresponding to the pixel points in the isothermal communication domain and the mean value of the temperatures corresponding to the pixel points not belonging to the isothermal communication domain in all the sliding windows is the temperature change index ^ of the isothermal communication domain>
。
Then the shift weight of the isothermal connected domain corresponding to the jth shift point is
Comprises the following steps:
wherein,
the area of an isothermal communication domain corresponding to the jth offset point in a circular region corresponding to the ith initial central point; the larger the value is, the current is representedThe wider the temperature distribution of the isothermal communication domain corresponding to the jth offset point is, the larger the offset weight should be when carrying out low-temperature region weighing;
And the difference value between the temperature mean value of the isothermal communication domain corresponding to the jth offset point and the temperature of the adjacent region at the edge of the isothermal communication domain is represented, the larger the temperature difference value is, the lower the temperature of the isothermal communication domain corresponding to the jth offset point is possibly, the violent temperature change is represented, and the larger the offset weight is when the current low-temperature region is measured. a is a hyper-parameter, which can be adjusted by an implementer according to a specific implementation scenario, in this embodiment, a =0.78.
Step three: obtaining a vector with a modular length which is the product of the absolute value of the difference value of the temperatures corresponding to the initial central point and the offset weight, and recording the vector as an offset vector, wherein the direction of the offset vector is determined by the difference value of the temperatures corresponding to the initial central point and the offset point; summing the offset vectors of all isothermal connected domains in the circular area to obtain a final offset vector; and moving the position of the initial central point according to the final offset vector until the clustering is completed to obtain a low-temperature region and a normal region of the surface temperature image.
First, it should be noted that the pixel points in the isothermal connected domain corresponding to the jth offset point are all continuous, and the temperatures are all the same, so that other pixel points in the connected domain do not need to participate in the same operation as the jth offset point. Meanwhile, a plurality of offset points are arranged in the circular area corresponding to the ith initial central point, a corresponding isothermal communication domain is arranged corresponding to each offset point, the operation of the second step needs to be carried out on each isothermal communication domain to obtain the offset weight of each isothermal communication domain, and only one offset point in the circular area of one initial central point is used for description here.
Meanwhile, the circular area is internally provided with a plurality of isothermal communication domains, namely, the circular area is partitioned, after the partitioning, the offset weight of each block is obtained according to the block, and then the offset vector of each block is obtained, so that the characteristics of temperature distribution can be better met, and the obtained clustering result is more reasonable. The offsetThe modular length of the vector is the product of the absolute value of the difference value of the temperature corresponding to the ith initial central point and the jth offset point and the offset weight corresponding to the isothermal connected domain corresponding to the jth offset point, namely the modular length is the product of the absolute value of the difference value of the temperature corresponding to the ith initial central point and the jth offset point and the offset weight corresponding to the isothermal connected domain corresponding to the jth offset point
The direction of the offset vector is determined by the difference value of the temperatures corresponding to the initial central point and the offset point, and if the difference value of the temperatures corresponding to the initial central point and the offset point is more than or equal to 0, the direction of the offset vector is that the initial central point points to the offset point; if the difference value of the temperatures corresponding to the initial central point and the offset point is less than 0, the direction of the offset vector is that the offset point points to the initial central point, and the direction of the offset vector is that the offset point points to the initial central point indicates that the initial central point does not need to move to the offset point.
Further, for the final offset vector of the ith initial center point, the offset vectors of all isothermal areas in the circular area of the ith initial center point are comprehensively considered, and the offset vectors of all isothermal areas in the circular area of the ith initial center point are summed to obtain the final offset vector
Where the summation of the vectors is performed according to the parallelogram rule; the ith initial center point is shifted by the final shift vector ≧>
Is moved in the direction of the final offset vector ≥>
Meanwhile, during migration, the migrated position may not happen to fall on a pixel point, and may fall between two pixel points, so as to obtain the distance between the two pixel points and the final migration vector, and use the pixel point with a small distance as the position to be migrated to the ith initial center point. />
And finally, continuously updating the position of each initial central point according to the final offset vector, stopping clustering when the position of each initial point does not need to be updated, and obtaining a low-temperature region and a normal region, wherein in the clustering process, all regions with initial central point position offset are used as the low-temperature region to be found. It should be noted that the present embodiment does not perform block partitioning and clustering first, because the block may be too large, which results in poor direct clustering result. Therefore, the present embodiment selects to perform blocking in the clustering process, and when random initialization is caused for an existing large-area uniform temperature region, part of the points do not move, so that coordinates of all initial central points after clustering is completed are compared with coordinates of all initial central points during initialization, the initial central points which do not move are removed, and clustering is completed.
Step four: obtaining the central point of the low-temperature area as a heating position; obtaining the heating temperature according to the difference value of the temperature corresponding to each pixel point in the low-temperature area and the mean value of the temperatures corresponding to the pixel points in the normal area and the distance between each pixel point in the low-temperature area and the heating position; and heating the magnesium alloy forging with uneven surface temperature distribution based on the heating position and the heating temperature.
Firstly, obtaining a central point of a low-temperature area, wherein the position of the central point is a heating position, obtaining a temperature to be heated at the moment, calculating the heating temperature by utilizing the difference value of the average value of the temperature corresponding to each pixel point in the low-temperature area and the temperature corresponding to the pixel point in a normal area and the distance between each pixel point in the low-temperature area and the heating position:
wherein T represents a heating temperature in a low temperature region; m represents the number of pixel points in a low-temperature region;
representing the difference value between the temperature value corresponding to the mth pixel point in the low-temperature area and the mean value of the temperatures corresponding to the pixel points in the normal area, if ^ is greater than or equal to>
The temperature difference is obvious, and the required temperature value is high during heating; e represents a natural constant;
Indicates the distance between the mth pixel point in the low temperature region and the heating position, and the closer the distance is, the more the temperature value to be cleared can be indicated, so the smaller the distance is, the more the temperature value is>
The larger the value of (a).
When the heating position and the heating temperature are obtained, the coordinate point of the heating position is input into the PCL control module, wherein the PCL control module can control the position and the temperature of the heating gun, the heating gun is used for heating the current magnesium alloy forging, so that the surface temperature of the magnesium alloy forging with uneven surface temperature distribution becomes even, the magnesium alloy forging after the heating is finished is subjected to stamping forming according to a preset die, and the temperature of the magnesium alloy forging obtained before the stamping is even in distribution, so that no overlarge temperature difference exists, and the precision of a stamped product is ensured.
Example 2
The embodiment provides a magnesium alloy forging product stamping forming system embodiment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program is used for realizing the steps of the magnesium alloy forging product stamping forming method when being executed by the processor. Since embodiment 1 has already described a detailed description of a magnesium alloy forging product press forming method, it will not be described more here.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And that specific embodiments have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (8)
1. A magnesium alloy forging product stamping forming method is characterized by comprising the following steps: obtaining a surface temperature image of the magnesium alloy forging by using an infrared thermometer, wherein each pixel point in the surface temperature image corresponds to one temperature; carrying out mean shift clustering on the surface temperature image to obtain an initial central point of clustering, and obtaining a circular area by taking one initial central point as a circle center and a preset length as a radius, wherein the circular area is a clustering range of the initial central point;
selecting a pixel point in the circular area, marking as an offset point, and obtaining an absolute value of a difference value of the temperature of the offset point and the temperature of the initial central point; obtaining an isothermal communication domain containing offset points, wherein the temperatures corresponding to pixel points in the isothermal communication domain are equal; obtaining a temperature change index of the isothermal communication domain according to the difference between the temperature corresponding to the adjacent peripheral pixel point at the edge of the isothermal communication domain and the temperature corresponding to the pixel point in the isothermal communication domain; the product of the area of the isothermal connected domain, the temperature change index and the hyperparameter is the offset weight;
obtaining a vector with a modular length which is the product of the absolute value of the difference value of the temperatures corresponding to the initial central point and the offset weight, and recording the vector as an offset vector, wherein the direction of the offset vector is determined by the difference value of the temperatures corresponding to the initial central point and the offset point; summing the offset vectors of all isothermal connected domains in the circular area to obtain a final offset vector; moving the position of the initial central point according to the final offset vector until the clustering is completed to obtain a low-temperature region and a normal region of the surface temperature image;
obtaining the central point of the low-temperature area as a heating position; obtaining the heating temperature according to the difference value of the temperature corresponding to each pixel point in the low-temperature area and the mean value of the temperatures corresponding to the pixel points in the normal area and the distance between each pixel point in the low-temperature area and the heating position; and heating the magnesium alloy forging with uneven surface temperature distribution based on the heating position and the heating temperature.
2. The method of claim 1, wherein the obtaining the clustered initial center points comprises: there are multiple initial center points when mean-shift clustering is performed on the surface temperature images.
3. The method of claim 1, wherein the obtaining an isothermal communication zone including an offset point comprises: obtaining pixel points with the same temperature corresponding to the offset points in the circular area; setting the pixel value of the coordinate of the pixel point with the same temperature as the offset point as a first preset value, setting the pixel values of the other pixel points as second preset values, and obtaining the isothermal connected domain by using an 8-neighborhood connected domain extraction algorithm.
4. The method of claim 1, wherein the obtaining an indication of temperature change in the isothermal connected region comprises: setting a sliding window with a preset size, wherein the sliding step length is the side length of the sliding window, and the edge pixel point of the isothermal connected domain is taken as the central point of the sliding window; obtaining the mean value of the temperatures corresponding to the pixel points which do not belong to the isothermal communication domain in all the sliding windows when the sliding windows slide by taking the edge of the isothermal communication domain as a sliding track; and the difference value of the mean value of the temperatures corresponding to the pixel points in the isothermal connected domain and the mean value of the temperatures corresponding to the pixel points not belonging to the isothermal connected domain in all the sliding windows is the temperature change index of the isothermal connected domain.
5. The method of claim 1, wherein determining the direction of the offset vector from the difference in temperature between the initial center point and the offset point comprises: if the difference value of the temperatures corresponding to the initial central point and the offset point is more than or equal to 0, the direction of the offset vector is that the initial central point points to the offset point; if the difference value of the temperature corresponding to the initial central point and the offset point is less than 0, the direction of the offset vector is that the offset point points to the initial central point, and the direction of the offset vector is that the offset point points to the initial central point, which means that the initial central point does not move to the offset point.
6. The method of claim 1, wherein moving the location of the initial center point according to the final offset vector comprises: and if the end point is between two pixel points, the distance between the two pixel points and the final offset vector is obtained, and the pixel point with small distance is taken as the position to which the initial center point is moved.
7. The method of claim 1, wherein the heating temperature is:
wherein T represents a heating temperature in a low temperature region; m represents the number of pixel points in a low-temperature region;
expressing the difference value of the temperature value corresponding to the mth pixel point in the low-temperature area and the average value of the temperatures corresponding to the pixel points in the normal area; e represents a natural constant;
indicating the distance between the mth pixel point in the low temperature region and the heating position.
8. A magnesium alloy forging product press forming system comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor performs the steps of a method of press forming a magnesium alloy forging product as claimed in any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211266968.XA CN115338282B (en) | 2022-10-17 | 2022-10-17 | Magnesium alloy forging product stamping forming system and stamping forming method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211266968.XA CN115338282B (en) | 2022-10-17 | 2022-10-17 | Magnesium alloy forging product stamping forming system and stamping forming method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115338282A CN115338282A (en) | 2022-11-15 |
| CN115338282B true CN115338282B (en) | 2023-03-24 |
Family
ID=83957538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211266968.XA Active CN115338282B (en) | 2022-10-17 | 2022-10-17 | Magnesium alloy forging product stamping forming system and stamping forming method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115338282B (en) |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3702124B2 (en) * | 1999-04-28 | 2005-10-05 | 新日本製鐵株式会社 | Submerged arc welding method for HT590 grade refractory steel |
| US7343770B2 (en) * | 2002-08-16 | 2008-03-18 | Nanoprecision Products, Inc. | Stamping system for manufacturing high tolerance parts |
| US7572643B2 (en) * | 2005-11-21 | 2009-08-11 | E. I. Du Pont De Nemours And Company | Nanoparticle composite-coated glass microspheres for use in bioassays |
| JP6537986B2 (en) * | 2016-01-26 | 2019-07-03 | 伸和コントロールズ株式会社 | Temperature control system |
| CN107745028B (en) * | 2017-11-06 | 2019-05-24 | 航天材料及工艺研究所 | High magnesium-rare earth coupling barrel deformation temperature field control tooling and control method |
| CN110116141A (en) * | 2018-02-07 | 2019-08-13 | 宝山钢铁股份有限公司 | A kind of heating system of adaptive magnesium alloy board warm-rolling process temperature distribution |
| CN109040689A (en) * | 2018-08-24 | 2018-12-18 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Pattern information processing system for the tracking of helicopter line walking process infrared heat point |
| CN111466794B (en) * | 2020-03-16 | 2021-04-20 | 珠海格力电器股份有限公司 | Tea making control method and device, terminal and computer readable medium |
| CN111899256B (en) * | 2020-08-12 | 2023-10-03 | 南京工程学院 | Retired lithium battery screening method based on infrared image hotspot feature cluster analysis |
| CN112170506B (en) * | 2020-10-14 | 2024-08-16 | 哈尔滨工业大学（威海） | Temperature compensation method and device for conveying roller way of magnesium or magnesium alloy plate strip |
-
2022
- 2022-10-17 CN CN202211266968.XA patent/CN115338282B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115338282A (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108876816B (en) | Target tracking method based on self-adaptive target response | |
| Gola et al. | Objective microstructure classification by support vector machine (SVM) using a combination of morphological parameters and textural features for low carbon steels | |
| Goyal et al. | Multi-class semantic segmentation of skin lesions via fully convolutional networks | |
| Hemanth et al. | Performance improved iteration-free artificial neural networks for abnormal magnetic resonance brain image classification | |
| CN106408594B (en) | Video multi-target tracking based on more Bernoulli Jacob's Eigen Covariances | |
| Cruz-Aceves et al. | Automatic segmentation of coronary arteries using Gabor filters and thresholding based on multiobjective optimization | |
| US10786227B2 (en) | System and method for ultrasound examination | |
| Krawczyk et al. | A hybrid classifier committee for analysing asymmetry features in breast thermograms | |
| Huang et al. | Detectability of infrared small targets | |
| CN110276784B (en) | Correlation filtering moving target tracking method based on memory mechanism and convolution characteristics | |
| CN109255304A (en) | Method for tracking target based on distribution field feature | |
| CN115338282B (en) | Magnesium alloy forging product stamping forming system and stamping forming method | |
| CN114723700A (en) | Iron furnace surface crack growth prediction method and system based on computer vision | |
| CN113327272A (en) | Robustness long-time tracking method based on correlation filtering | |
| Huang et al. | Feature selection in froth flotation for production condition recognition | |
| CN107527348B (en) | Significance detection method based on multi-scale segmentation | |
| Chaddad et al. | Deep radiomic features from MRI scans predict survival outcome of recurrent glioblastoma | |
| CN116740053B (en) | Management system of intelligent forging processing production line | |
| Bhardwaj et al. | Brain tumor image segmentation using K-means and fuzzy C-means clustering | |
| CN107657223B (en) | Face authentication method based on rapid processing multi-distance metric learning | |
| CN111723808B (en) | Infrared weak target extraction method based on maximum value background prediction | |
| Su et al. | Real-time multiple object tracking based on optical flow | |
| Hsu et al. | Detection of minimum biomarker features via bi-level optimization framework by nested hybrid differential evolution | |
| Desai et al. | Enhancing Plant Leaf Disease Classification Performance Through EfficientNetB3 and Hyperparameter Optimization | |
| Jeena et al. | A novel method for stroke prediction from retinal images using HoG approach |
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 |