CN114535450A - Intelligent control method and system for closed fin stamping production line - Google Patents

Intelligent control method and system for closed fin stamping production line Download PDF

Info

Publication number
CN114535450A
CN114535450A CN202210424168.XA CN202210424168A CN114535450A CN 114535450 A CN114535450 A CN 114535450A CN 202210424168 A CN202210424168 A CN 202210424168A CN 114535450 A CN114535450 A CN 114535450A
Authority
CN
China
Prior art keywords
stamping
oil
pixel
blanking
sheet metal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210424168.XA
Other languages
Chinese (zh)
Other versions
CN114535450B (en
Inventor
王丹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nantong Jingfeng Intelligent Equipment Co ltd
Original Assignee
Nantong Jingfeng Intelligent Equipment Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nantong Jingfeng Intelligent Equipment Co ltd filed Critical Nantong Jingfeng Intelligent Equipment Co ltd
Priority to CN202210424168.XA priority Critical patent/CN114535450B/en
Publication of CN114535450A publication Critical patent/CN114535450A/en
Application granted granted Critical
Publication of CN114535450B publication Critical patent/CN114535450B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • B21D53/00—Making other particular articles
    • B21D53/02—Making other particular articles heat exchangers or parts thereof, e.g. radiators, condensers fins, headers
    • B21D53/022—Making the fins
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B30—PRESSES
    • B30B—PRESSES IN GENERAL
    • B30B15/00—Details of, or accessories for, presses; Auxiliary measures in connection with pressing
    • B30B15/26—Programme control arrangements
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

The invention relates to the technical field of stamping, in particular to an intelligent control method and system for a closed fin stamping production line, wherein the method comprises the following steps: acquiring a sheet metal expansion diagram of a fin, and acquiring a stamping process of each pixel in the sheet metal expansion diagram; based on the stamping characteristics of the stamping processes, calculating stamping oil requirement indexes of corresponding pixels of each stamping process; acquiring the oil supply amount of each pixel position based on the stamping oil demand index; and based on the oil feeding amount, intelligently controlling the punching production line. The invention can avoid the waste of the stamping oil, ensure the stamping effect and improve the quality of the stamping part.

Description

Intelligent control method and system for closed fin stamping production line
Technical Field
The invention relates to the field of stamping, in particular to an intelligent control method and system for a closed fin stamping production line.
Background
In the existing fin stamping process, stamping oil is often used for ensuring the processing quality of high-precision and quick stamping, and the improper use amount of the stamping oil can bring the abnormity that the shearing section roughness does not meet the requirement or a workpiece is oxidized and blackened, and the like. The existing method for roughly estimating the oil supply amount of the stamping oil based on experience is poor in accuracy, and further the quality of the stamping part can be influenced.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an intelligent control method and system for a closed fin stamping production line, and the adopted technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides an intelligent control method for a closed fin stamping production line, including the following specific steps:
acquiring a sheet metal development diagram of a fin, and acquiring a stamping process of each pixel in the sheet metal development diagram;
calculating the stamping oil requirement index of each pixel corresponding to the stamping process based on the stamping characteristic of the stamping process;
acquiring the oil supply amount of each pixel position based on the stamping oil demand index;
and based on the oil feeding amount, carrying out intelligent control on the stamping production line.
Further, the stamping process comprises blanking, bending and deep drawing.
Further, the acquisition of the stamping oil requirement index of the corresponding pixel of the blanking process is specifically as follows:
obtaining a blanking edge based on the sheet metal development diagram;
and calculating the stamping oil requirement index of the pixel corresponding to the blanking process according to the shortest distance between the pixel corresponding to each blanking process and the blanking edge, the stamping precision and the geometric complexity of the blanking edge.
Further, the acquisition of the stamping oil requirement index of the corresponding pixel of the bending process is specifically as follows:
obtaining a bending line based on the sheet metal unfolding diagram;
and calculating the stamping oil requirement index of the pixels corresponding to the bending process according to the shortest distance and the bending angle between the pixels corresponding to each bending process and the bending line.
Further, the acquisition of the stamping oil requirement index of the drawing process corresponding to the pixel specifically comprises the following steps:
acquiring a forming contour line at the middle position of the stretched area after drawing based on the sheet metal development diagram;
and calculating the stamping oil requirement index of the pixel corresponding to the drawing process according to the shortest distance between the pixel corresponding to each drawing process and the contour line and the drawing depth.
Further, the oil supply amount of each pixel position is obtained based on the stamping oil demand index, and the method specifically comprises the following steps: and acquiring the oil supply amount of each pixel position by utilizing a neural network model based on the stamping oil demand index, the equipment parameters and the operating parameters of the stamping machine.
In a second aspect, another embodiment of the present invention provides a closed fin stamping line intelligent control 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 a closed fin stamping line intelligent control method.
The embodiment of the invention at least has the following beneficial effects: the invention calculates the stamping oil requirement index of each pixel corresponding to the stamping process; acquiring the oil supply amount of each pixel position based on the stamping oil demand index; and based on the oil feeding amount, carrying out intelligent control on the stamping production line. Therefore, the invention can accurately control the oil supply amount of the stamping oil at each position on the initial steel plate, thereby not only avoiding the waste of the stamping oil, but also ensuring the stamping effect and improving the quality of the stamping part.
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 the steps of an embodiment of the method of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a method and a system for intelligently controlling a closed fin stamping line according to the present invention, and specific embodiments, structures, features and effects thereof with reference to the accompanying drawings and 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.
Metal sheets with strong thermal conductivity are usually added on the surface of the heat exchange device needing heat transfer to increase the heat exchange surface area of the heat exchange device, and the metal sheets are called fins. Common fin structures are straight fins, louvered fins, serrated fins, porous fins, and corrugated fins. The stamping information of different types of fins is different, and the required fin oil (also named as fin high-speed shearing fine blanking stamping oil) is also different.
Stamping is a forming method in which a plate, a strip, a pipe, a profile, or the like is subjected to plastic deformation or separation by a press or a die to obtain a workpiece (stamped part) having a desired shape and size, and it is often necessary to apply a stamping oil to a thin plate in order to ensure dimensional accuracy, roughness of a shear section, a geometric shape, or the like. And the subsequent treatment needs to wash away grease on the workpiece, and spray coating and other operations are carried out, so that the punching oil is more and more wasted, the subsequent grease removal difficulty is increased, the punching oil is less, and the punching temperature is high, so that the abnormal defects of blackening and the like of the metal piece are caused, so that the coating amount of the punching oil needs to be accurately controlled in order to realize intelligent, green and environment-friendly production, namely the invention mainly aims at: the information of the fins to be processed is analyzed by utilizing artificial intelligence and an image processing technology, so that the oil feeding amount of the stamping oil on a stamping production line is controlled, and intelligent production is realized.
The following describes a specific scheme of an intelligent control method and system for a closed fin stamping production line provided by the invention in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating steps of an intelligent control method for a closed fin stamping line according to an embodiment of the present invention is shown, where the method includes the following steps:
acquiring a sheet metal development diagram of a fin, and acquiring a stamping process of each pixel in the sheet metal development diagram;
calculating the stamping oil requirement index of each pixel corresponding to the stamping process based on the stamping characteristic of the stamping process;
acquiring the oil supply amount of each pixel position based on the stamping oil demand index;
and based on the oil feeding amount, carrying out intelligent control on the stamping production line.
The following is a detailed description of the above steps:
the method comprises the steps of firstly, obtaining a sheet metal development diagram of a fin, and obtaining a stamping process of each pixel in the sheet metal development diagram.
Before the fin is machined, the fin is designed through design software such as SolidWorks, and therefore a machining design drawing of the fin, namely a sheet metal development drawing of the fin can be obtained.
The invention needs to realize that the stamping production line can be adaptively adjusted according to the processing requirements of different types of fins, so that the stamping process information of each position of the fin to be processed needs to be obtained firstly, namely, the position of the fin to be processed needs to be stamped with a hole, the position of the fin to be processed needs to be stamped and bent, and the position of the fin to be processed needs to be stamped and drawn. The invention relates to a stamping process for acquiring each pixel based on a sheet metal development diagram, which specifically comprises the following steps: the invention utilizes the semantic segmentation neural network to process the sheet metal expansion map, and realizes the reasoning identification of the stamping process information of each pixel.
With respect to semantically segmenting neural networks:
the semantic segmentation neural network is of an Encoder-Decoder structure, firstly performs feature extraction on an input image, namely a metal plate expansion image, through convolution and pooling operations to obtain a feature image, and then reconstructs the feature image into a corresponding semantic segmentation image through deconvolution and anti-pooling operations, wherein the semantic segmentation image is an image obtained by performing semantic category division on each pixel.
The semantic segmentation neural network training process comprises the following steps: (1) collecting an image: collecting the sheet metal development images of the fins of various types as training images. (2) And (3) label making: according to the deformation condition of the fin machined from the initial thin steel plate, namely, according to the corresponding stamping process, pixels in the sheet metal development image are classified, and the stamping process comprises blanking, bending and deep drawing, so that in the embodiment, the background type pixel is marked as 1, the stamping process is marked as 2 for the blanking pixel, the stamping process is marked as 3 for the bending pixel, and the stamping process is marked as 4 for the deep drawing pixel. (3) The training loss function is a cross entropy loss function. Training of the semantic segmentation neural network is carried out based on the training image, the label and the loss function, and when the loss function is converged and tends to be stable after the training of the semantic segmentation neural network, the training of the neural network is finished and can be used. It should be noted that the pixels corresponding to the blanking process not only include the pixels at the blanking edge, but also include pixels in a certain range at both sides of the blanking edge, or when the blanking edge forms a closed area, the pixels corresponding to the blanking process are pixels inside the blanking edge; the pixels corresponding to the bending process not only comprise the pixels of the bending line, but also comprise pixels in a certain range at two sides of the bending line; the pixels corresponding to the drawing process are pixels in the outermost outline of the region where the steel plate undergoes the extension change.
Inputting the sheet metal development diagram of the fins into the trained semantic segmentation neural network to obtain the stamping process of each pixel in the sheet metal development diagram.
And step two, calculating the stamping oil requirement index of the corresponding pixel of each stamping process based on the stamping characteristics of the stamping processes.
The stamping process comprises blanking, bending and deep drawing, and specifically, the acquisition of stamping oil requirement indexes of corresponding pixels of each stamping process is as follows:
(1) the method specifically comprises the following steps of obtaining the punching oil requirement indexes of the corresponding pixels of the blanking process: obtaining a blanking edge based on the sheet metal development diagram; and calculating the stamping oil requirement index of the pixel corresponding to the blanking process according to the shortest distance between the pixel corresponding to each blanking process and the blanking edge, the stamping precision and the geometric complexity of the blanking edge.
(11) And obtaining a blanking edge based on the sheet metal development diagram.
In one embodiment, the sheet metal development image is processed by utilizing a blanking edge identification network, and a blanking edge is identified and extracted.
In another embodiment, a semantic segmentation image output by a semantic segmentation neural network is acquired, a single-channel image of pixels corresponding to a blanking process is extracted from the semantic segmentation image, and connected domain analysis is performed on the extracted single-channel image to acquire a blanking edge.
It should be noted that there are several blanking edges that are obtained.
(12) And calculating the stamping oil requirement index of the pixel corresponding to the blanking process according to the shortest distance between the pixel corresponding to each blanking process and the blanking edge, the stamping precision and the geometric complexity of the blanking edge.
Taking a pixel corresponding to the blanking process as an example, the method for acquiring the stamping oil requirement index of the pixel corresponding to the blanking process is described as follows:
Figure DEST_PATH_IMAGE002
Figure DEST_PATH_IMAGE004
the stamping oil requirement index value of one pixel corresponding to the blanking process is larger, and the required stamping oil is more;
Figure DEST_PATH_IMAGE006
indicating the distance of the pixel from several blanking edges,
Figure DEST_PATH_IMAGE008
representing the shortest distance of the pixel to several blanking edges,
Figure DEST_PATH_IMAGE010
is a preset reference distance;
Figure DEST_PATH_IMAGE012
the required degree of the stamping precision is shown, the higher the precision requirement is, the higher the value is, and the value range is [0,1 ]]；
Figure DEST_PATH_IMAGE014
The geometric complexity of the blanking edge is in the range of [0,1 ]]The larger the value, the higher the geometrical complexity of the blanking edge and the corresponding greater the difficulty of stamping. The stamping oil requirement index of the pixels at the blanking edge is the highest, and the stamping oil requirement indexes of the pixels at the two sides of the blanking edge areThe mark is decreased progressively; the higher the processing stamping precision is, the higher the stamping oil requirement index is; the higher the complexity of the geometry of the blanking edge, the higher the stamping oil requirement index.
The geometric complexity of the blanking edges can be artificially determined according to the shapes and sizes of the blanking edges. Or, a plurality of corresponding relation libraries of the blanking edges and the geometric complexity are established in advance, and the geometric complexity corresponding to the current blanking edge is searched in the corresponding relation libraries. Or judging the geometric complexity of each blanking edge by using a geometric complexity judging network. Furthermore, the geometric complexity of the blanking edge is obtained
Figure 835522DEST_PATH_IMAGE014
The method can also be as follows:
Figure DEST_PATH_IMAGE016
Figure DEST_PATH_IMAGE018
Figure DEST_PATH_IMAGE020
the geometric complexity of the blanking edge before normalization is obtained after normalization
Figure 316444DEST_PATH_IMAGE014
；
Figure DEST_PATH_IMAGE022
Indicating on the blanking edge
Figure DEST_PATH_IMAGE024
The degree of linear mutation of each pixel point,
Figure DEST_PATH_IMAGE026
indicating common on the blanking edge
Figure 220815DEST_PATH_IMAGE026
Each pixel point;
Figure DEST_PATH_IMAGE028
indicating the distance between the pixel point and the center point of the area formed by the blanking edge, wherein,
Figure DEST_PATH_IMAGE030
is shown as
Figure 773281DEST_PATH_IMAGE024
One side of each pixel point is adjacent to the first
Figure DEST_PATH_IMAGE032
Each pixel point represents the first
Figure 525337DEST_PATH_IMAGE024
The other side of each pixel point is adjacent to the first pixel point
Figure 65908DEST_PATH_IMAGE032
Each pixel point;
Figure DEST_PATH_IMAGE034
is shown in
Figure 5045DEST_PATH_IMAGE024
Each selection at both sides of each pixel point
Figure 938366DEST_PATH_IMAGE034
The number of adjacent pixel points is preferably, but not necessarily,
Figure 826819DEST_PATH_IMAGE034
the value is 3. With pixel point labels as abscissa, pixel points correspond
Figure 289024DEST_PATH_IMAGE028
The value is the ordinate, then
Figure DEST_PATH_IMAGE036
And
Figure DEST_PATH_IMAGE038
representing the slope, in the denominator
Figure 433567DEST_PATH_IMAGE024
After mutually offsetting, the denominator is
Figure 639420DEST_PATH_IMAGE032
I.e. by
Figure DEST_PATH_IMAGE040
And
Figure DEST_PATH_IMAGE042
。
(2) the method specifically comprises the following steps of obtaining stamping oil requirement indexes of pixels corresponding to the bending process: obtaining a bending line based on the sheet metal unfolding diagram; and calculating the stamping oil requirement index of the pixels corresponding to the bending process according to the shortest distance and the bending angle between the pixels corresponding to each bending process and the bending line.
(21) And obtaining a bending line based on the sheet metal unfolded drawing.
In one embodiment, the bending lines are marked artificially in the sheet metal development diagram.
In another embodiment, the sheet metal unfolded image is processed by using a bending line identification network to identify and extract bending lines.
(22) And calculating the stamping oil requirement index of the pixels corresponding to the bending process according to the shortest distance and the bending angle between the pixels corresponding to each bending process and the bending line.
Taking a pixel corresponding to the bending process as an example, the method for acquiring the stamping oil requirement index of the pixel corresponding to the bending process is described as follows:
Figure DEST_PATH_IMAGE044
Figure 246027DEST_PATH_IMAGE004
the stamping oil requirement index of one pixel corresponding to the bending process;
Figure DEST_PATH_IMAGE046
the distance between the pixel and a plurality of bending lines is shown,
Figure DEST_PATH_IMAGE048
the shortest distance between the pixel and a plurality of bending lines is shown,
Figure DEST_PATH_IMAGE050
is a preset reference distance;
Figure DEST_PATH_IMAGE052
indicating the bending angle corresponding to the pixel. The punching press oil demand index value of the pixels on the bending line is maximum, the punching press oil demand indexes of the pixels on two sides of the bending line are decreased progressively, and meanwhile, the bending angle is larger, and the value of the punching press oil demand index of the pixels is larger.
(3) The acquisition of the stamping oil requirement index of the drawing process corresponding to the pixel specifically comprises the following steps: acquiring a forming contour line at the middle position of the stretched area after drawing based on the sheet metal development diagram; and calculating the stamping oil requirement index of the pixel corresponding to the drawing process according to the shortest distance between the pixel corresponding to each drawing process and the contour line and the drawing depth.
(31) And acquiring a forming contour line at the middle position of the stretched area after drawing based on the sheet metal development diagram.
The deep drawing process can be used for manufacturing thin-wall stamping parts with irregular shapes such as cylinders, rectangles, trapezoids, spheres, cones, polishing lines and the like. Regarding the drawing area, there are lines constituting the extension area in the sheet metal development diagram, for example, if a cylindrical stamping part is obtained after drawing, the extension area in the sheet metal development diagram is a circular ring area formed by two concentric circles, and the obtained forming contour line is a circular contour line located in the middle of the circular ring area, that is, the circular contour line is equidistant to the two concentric circles; if a rectangular stamping part is obtained after drawing, the extension area in the sheet metal development figure is a rectangular ring area formed by two concentric rectangles, and the obtained forming contour line is a rectangular contour line positioned in the middle of the rectangular ring area, namely the rectangular contour line is equidistant to the two concentric rectangles; if a strip-shaped region is obtained after drawing, the major axis of the region needs to be obtained, the extension deformation degree on the axis is the maximum, and the major axis is a forming contour line.
Alternatively, as another embodiment, the forming contour line may be acquired at another position of the after-drawing extension region from the drawing shape and depth.
(32) And calculating the stamping oil requirement index of the pixel corresponding to the drawing process according to the shortest distance between the pixel corresponding to each drawing process and the contour line and the drawing depth.
Taking a pixel corresponding to the drawing process as an example, the method for acquiring the stamping oil requirement index of the pixel corresponding to the drawing process is described as follows:
Figure DEST_PATH_IMAGE054
Figure 957762DEST_PATH_IMAGE004
the stamping oil requirement index of one pixel corresponding to the drawing process;
Figure DEST_PATH_IMAGE056
representing the shortest distance of the pixel from the plurality of contoured contours,
Figure DEST_PATH_IMAGE058
is a preset reference distance;
Figure DEST_PATH_IMAGE060
the drawing depth characteristic value is obtained according to the drawing depth, and the value range is [0,1 ]]。
And thirdly, acquiring the oil supply amount of each pixel position based on the stamping oil demand index.
The method comprises the following steps of obtaining the oil supply amount of each pixel position based on the stamping oil demand index, specifically: and acquiring the oil supply amount of each pixel position by utilizing a neural network model based on the stamping oil demand index, the equipment parameters and the operating parameters of the stamping machine.
In one embodiment, the punching oil demand index of each pixel, the equipment parameters and the operation parameters of the punching machine are input into the oil supply amount prediction network, and the oil supply amount of each pixel position is obtained. The equipment parameters and the operation parameters of the punching machine are respectively the tonnage of the punching machine and the working speed of the punching machine.
In another embodiment, the stamping effect of the closed stamping machine with different parameter states is different, so that the basic oil supply amount of the three types of stamping is obtained by combining the stamping oil requirement index, the equipment parameters and the operating parameters of the stamping machine. Specifically, the oil supply amount prediction network is a fully-connected network, the maximum value and the minimum value of the stamping oil demand index of a corresponding pixel of each stamping process and equipment parameters and operation parameters of a stamping machine are input, the basic oil supply amount of each stamping process is output, in the embodiment, the number of input data is 8, correspondingly, the input layer of the oil supply amount prediction network is provided with 8 neurons, the number of output data is 3, and correspondingly, the output layer of the oil supply amount prediction network is provided with 3 neurons. And specifically, multiplying the stamping oil demand index of the pixel corresponding to each stamping process by the corresponding basic oil supply amount to obtain the oil supply amount corresponding to each pixel, and further obtaining the oil supply amount of each pixel position. Therein, the training process of fully connected networks is well known and the invention is not described in detail.
And fourthly, based on the oil supply amount, intelligently controlling the punching production line.
And controlling the air pressure of each corresponding oil supply pipe based on the obtained oil supply amount of each pixel position, so that the flowing stamping oil amount meets the requirement.
Based on the same inventive concept as the method embodiment, an embodiment of the present invention provides an intelligent control system for a closed fin stamping line, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the steps of the intelligent control method for the closed fin stamping line are implemented.
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 specific embodiments thereof 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.
All 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 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 (7)

1. An intelligent control method for a closed fin stamping production line is characterized by comprising the following steps:
acquiring a sheet metal development diagram of a fin, and acquiring a stamping process of each pixel in the sheet metal development diagram;
calculating the stamping oil requirement index of each pixel corresponding to the stamping process based on the stamping characteristic of the stamping process;
acquiring the oil supply amount of each pixel position based on the stamping oil demand index;
and based on the oil feeding amount, carrying out intelligent control on the stamping production line.
2. The method of claim 1, wherein the stamping process comprises blanking, bending, and deep drawing.
3. The method of claim 2, wherein the obtaining of the punching oil requirement index of the corresponding pixel of the blanking process is specifically as follows:
obtaining a blanking edge based on the sheet metal development diagram;
and calculating the stamping oil requirement index of the pixel corresponding to the blanking process according to the shortest distance between the pixel corresponding to each blanking process and the blanking edge, the stamping precision and the geometric complexity of the blanking edge.
4. The method according to claim 3, wherein the obtaining of the stamping oil requirement index of the pixel corresponding to the bending process is specifically as follows:
obtaining a bending line based on the sheet metal unfolding diagram;
and calculating the stamping oil requirement index of the pixels corresponding to the bending process according to the shortest distance and the bending angle between the pixels corresponding to each bending process and the bending line.
5. The method of claim 4, wherein the acquisition of stamping oil requirement indicators for the drawing process corresponding pixels is specifically:
acquiring a forming contour line at the middle position of the stretched area after drawing based on the sheet metal development diagram;
and calculating the stamping oil requirement index of the pixel corresponding to the drawing process according to the shortest distance between the pixel corresponding to each drawing process and the contour line and the drawing depth.
6. The method according to claim 5, wherein the oil supply amount of each pixel position is obtained based on the stamping oil demand index, and specifically comprises: and acquiring the oil supply amount of each pixel position by utilizing a neural network model based on the stamping oil demand index, the equipment parameters and the operating parameters of the stamping machine.
7. A closed fin stamping line intelligent control 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 implements the steps of the method as claimed in any one of claims 1 to 6.
CN202210424168.XA 2022-04-22 2022-04-22 Intelligent control method and system for closed fin stamping production line Active CN114535450B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210424168.XA CN114535450B (en) 2022-04-22 2022-04-22 Intelligent control method and system for closed fin stamping production line

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210424168.XA CN114535450B (en) 2022-04-22 2022-04-22 Intelligent control method and system for closed fin stamping production line

Publications (2)

Publication Number Publication Date
CN114535450A true CN114535450A (en) 2022-05-27
CN114535450B CN114535450B (en) 2022-06-28

Family

ID=81667280

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210424168.XA Active CN114535450B (en) 2022-04-22 2022-04-22 Intelligent control method and system for closed fin stamping production line

Country Status (1)

Country Link
CN (1) CN114535450B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000155100A (en) * 1998-11-18 2000-06-06 Daiwa Can Co Ltd Inner face inspecting method for three-piece can
CN101704047A (en) * 2009-10-14 2010-05-12 皇裕精密冲件(昆山)有限公司 Selective oiling mechanism in stamping operation
JP2012050998A (en) * 2010-08-31 2012-03-15 Toyota Motor Kyushu Inc Device and method for automatically measuring press component inflow amount
CN105344842A (en) * 2015-07-20 2016-02-24 无锡鹏德汽车配件有限公司 Automatic lubricating oil feeding device capable of saving lubricating oil for precision stamping
CN106552871A (en) * 2016-08-05 2017-04-05 浙江吉利控股集团有限公司 A kind of punching press plate oiling frequency adjusting means
CN209830046U (en) * 2019-04-19 2019-12-24 苏州宝成汽车冲压有限公司 Adjustable punching oil adding device
CN111299448A (en) * 2019-12-17 2020-06-19 南通精丰智能设备有限公司 Closed fin stamping production line
CN113643074A (en) * 2021-09-24 2021-11-12 金成技术有限公司 Metal plate structure production quotation rapid assessment method and system based on artificial intelligence
CN215088193U (en) * 2021-05-06 2021-12-10 成都日晗精密机械有限公司 Automatic oil spraying device for feeding of punch press
CN114178122A (en) * 2021-12-13 2022-03-15 无锡微研股份有限公司 Fin oil spraying mechanism for air conditioner fin die

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000155100A (en) * 1998-11-18 2000-06-06 Daiwa Can Co Ltd Inner face inspecting method for three-piece can
CN101704047A (en) * 2009-10-14 2010-05-12 皇裕精密冲件(昆山)有限公司 Selective oiling mechanism in stamping operation
JP2012050998A (en) * 2010-08-31 2012-03-15 Toyota Motor Kyushu Inc Device and method for automatically measuring press component inflow amount
CN105344842A (en) * 2015-07-20 2016-02-24 无锡鹏德汽车配件有限公司 Automatic lubricating oil feeding device capable of saving lubricating oil for precision stamping
CN106552871A (en) * 2016-08-05 2017-04-05 浙江吉利控股集团有限公司 A kind of punching press plate oiling frequency adjusting means
CN209830046U (en) * 2019-04-19 2019-12-24 苏州宝成汽车冲压有限公司 Adjustable punching oil adding device
CN111299448A (en) * 2019-12-17 2020-06-19 南通精丰智能设备有限公司 Closed fin stamping production line
CN215088193U (en) * 2021-05-06 2021-12-10 成都日晗精密机械有限公司 Automatic oil spraying device for feeding of punch press
CN113643074A (en) * 2021-09-24 2021-11-12 金成技术有限公司 Metal plate structure production quotation rapid assessment method and system based on artificial intelligence
CN114178122A (en) * 2021-12-13 2022-03-15 无锡微研股份有限公司 Fin oil spraying mechanism for air conditioner fin die

Also Published As

Publication number Publication date
CN114535450B (en) 2022-06-28

Similar Documents

Publication Publication Date Title
CN107507208B (en) Image feature point extraction method based on curvature estimation on contour
CN107705314B (en) Multi-object image segmentation method based on gray level distribution
CN114943736B (en) Production quality detection method and system for automobile radiating fins
CN110321844B (en) Fast iris detection method based on convolutional neural network
CN113239954B (en) Attention mechanism-based image semantic segmentation feature fusion method
CN115578374A (en) Mechanical part casting quality evaluation method and system
CN115008818B (en) Stamping process optimization method capable of promoting production efficiency of sheet metal structural part
CN111598856A (en) Chip surface defect automatic detection method and system based on defect-oriented multi-point positioning neural network
CN113298809B (en) Composite material ultrasonic image defect detection method based on deep learning and superpixel segmentation
CN115082427B (en) Aluminum material calendering process parameter control method based on artificial intelligence
CN115082488B (en) Surface feather mark control method and device in automobile part galvanizing process
CN113935953A (en) Steel coil defect detection method based on image processing
CN114535450B (en) Intelligent control method and system for closed fin stamping production line
CN112906833A (en) Plasma energy deposition image identification method based on full convolution neural network
CN114239810A (en) Milling cutter wear prediction method based on improved PCANet model
CN111444903B (en) Method, device and equipment for positioning characters in cartoon bubbles and readable storage medium
CN111129400B (en) Preparation process of porous lithium battery diaphragm
CN111275732A (en) Foreground object image segmentation method based on deep convolutional neural network
CN115810106A (en) Tea tender shoot grade accurate identification method in complex environment
CN113610888B (en) Twin network target tracking method based on Gaussian smoothing
CN111797547A (en) Method for calculating temperature field of mold
CN111833305B (en) Online inspection method for fin processing quality of plate-fin heat exchanger based on machine vision
CN115049611A (en) Continuous casting billet crack defect identification method based on improved yolov5
CN116188461B (en) Sheet metal machining system based on intelligent design drawing recognition
CN107491761B (en) Target tracking method based on deep learning characteristics and point-to-set distance metric learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant