CN113643074B - Metal plate structure production quotation rapid assessment method and system based on artificial intelligence - Google Patents

Metal plate structure production quotation rapid assessment method and system based on artificial intelligence Download PDF

Info

Publication number
CN113643074B
CN113643074B CN202111118283.6A CN202111118283A CN113643074B CN 113643074 B CN113643074 B CN 113643074B CN 202111118283 A CN202111118283 A CN 202111118283A CN 113643074 B CN113643074 B CN 113643074B
Authority
CN
China
Prior art keywords
difficulty
welding
bending
edge
difference
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
Application number
CN202111118283.6A
Other languages
Chinese (zh)
Other versions
CN113643074A (en
Inventor
姬蕾
郑代顺
路秋媛
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.)
Jincheng Technology Co ltd
Original Assignee
Jincheng Technology 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 Jincheng Technology Co ltd filed Critical Jincheng Technology Co ltd
Priority to CN202111118283.6A priority Critical patent/CN113643074B/en
Publication of CN113643074A publication Critical patent/CN113643074A/en
Application granted granted Critical
Publication of CN113643074B publication Critical patent/CN113643074B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201Market modelling; Market analysis; Collecting market data
    • G06Q30/0206Price or cost determination based on market factors
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/68Analysis of geometric attributes of symmetry

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Geometry (AREA)
  • Bending Of Plates, Rods, And Pipes (AREA)

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a method and a system for quickly evaluating sheet metal structure production quotation based on artificial intelligence. The method acquires an edge image of the planar design drawing. And analyzing blanking process data, welding process data, stamping process data and bending process data through edge information in the edge image. The process difficulty of various processes is obtained through the analysis of various process data. Further obtaining the integral production difficulty, and obtaining the defective rate according to the integral production difficulty and various process difficulties combined with batch quantity. The process cost is obtained by analyzing various process data, and the final quote is obtained by combining the material cost, the production batch quantity and the defective rate. According to the embodiment of the invention, the production quotation of the sheet metal structural part is rapidly and accurately obtained through image processing.

Description

Metal plate structure production quotation rapid assessment method and system based on artificial intelligence
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a system for quickly evaluating sheet metal structure production quotation based on artificial intelligence.
Background
The metal plate is also called as sheet metal, and the sheet metal structural member is a product after processes of stretching, stamping, welding, bending and the like. The sheet metal structural part can be used for manufacturing components in various forms by a simple processing technology, has small processing amount, high efficiency and standard shape, and is convenient for automatic processing. Therefore, the demand of the sheet metal structural part in the production process pays attention to the production quantity according to the required batch.
When the sheet metal structural member is produced and processed, an accurate price is often required to be provided according to the pattern of the sheet metal structural member, and the production operation is convenient. In the prior art, the quotation for the sheet metal structural part needs to be judged manually on the content and the process of the structural part, and the method is time-consuming, labor-consuming, low in efficiency and incapable of obtaining the quotation content quickly and accurately.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a sheet metal structure production quotation rapid evaluation method and system based on artificial intelligence, and the adopted technical scheme is as follows:
the invention provides a rapid evaluation method for sheet metal structure production quotation based on artificial intelligence, which comprises the following steps:
acquiring a planar design drawing of a sheet metal structural part; acquiring an edge image of the planar design drawing;
obtaining an outer contour edge and an inner edge in the edge image; acquiring a difference pixel point of the minimum circumscribed rectangle of the outer contour edge and the outer contour edge; taking the difference edges corresponding to the symmetrical difference pixel points as welding edges to obtain symmetrical lines of the welding edges; the two end points of the symmetry line are on the minimum circumscribed rectangle and the welding edge; taking the communication area of the inner edge as a stamping area; detecting a dotted line of the inner edge after the punching area is removed, and taking a line segment in the dotted line as a bending line;
acquiring an included angle of the difference edges, and determining blanking difficulty according to the number of the difference edges and the included angle; obtaining the stamping difficulty according to the area of the stamping area; forming parallel symmetrical bending lines into a parallel symmetrical bending line set, and obtaining bending difficulty according to the number of the parallel bending line set and the distance between the bending lines; obtaining the welding difficulty according to the number of the welding edges, the length of the symmetrical line and the number of the intersection points of the welding edges and the bending lines;
weighting and summing the blanking difficulty, the welding difficulty, the stamping difficulty and the bending difficulty to obtain the overall production difficulty; sending the blanking difficulty, the welding difficulty, the stamping difficulty, the bending difficulty, the overall production difficulty and a preset production batch quantity into a pre-trained full-connection network to obtain a defective rate;
obtaining the process cost according to the number of the difference edges, the number of the welding edges, the number of the stamping edges and the number of the bending lines; and obtaining a final quote according to the preset material cost, the process cost, the production batch quantity and the defective rate.
Further, the obtaining of the difference pixel point between the minimum circumscribed rectangle of the outer contour edge and the outer contour edge includes:
obtaining a connecting line from the minimum circumscribed rectangle pixel point to the central point of the edge image; and if the distance between the outline edge pixel point and the edge image central point on the connecting line is different from the length of the connecting line, the corresponding outline edge pixel point is the difference pixel point.
Further, the using the symmetrical difference edges corresponding to the difference pixel points as welding edges includes:
if the opposite angle of the minimum circumscribed rectangle has the difference edge, connecting the two difference edges point by point through the central point of the edge image to obtain a first distance sequence;
if the difference edges which are vertically and/or horizontally corresponding exist on the four sides of the minimum circumscribed rectangle, the vertical and/or horizontal distance between each pixel point of the two difference edges is obtained, and a second distance sequence is obtained;
and analyzing data difference on two sides of the peak position in the first distance sequence and the second distance sequence, analyzing the symmetry of the difference edge according to the data difference, and taking the difference edge corresponding to the symmetrical difference pixel point as a welding edge.
Further, the analyzing data differences on both sides of the peak position in the first distance sequence and the second distance sequence, and analyzing the symmetry of the difference edge according to the data differences includes: obtaining the symmetry according to a symmetry formula; the symmetry formula is:
Figure DEST_PATH_IMAGE002
Figure DEST_PATH_IMAGE004
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE006
in order for the symmetry to be such that,
Figure DEST_PATH_IMAGE008
half the number of pixels at the edge of the disparity,
Figure DEST_PATH_IMAGE010
is an index of the property of the pixel point,
Figure DEST_PATH_IMAGE012
is the peak point
Figure DEST_PATH_IMAGE014
The right side is
Figure DEST_PATH_IMAGE016
The number of the data is one,
Figure DEST_PATH_IMAGE018
is the peak point
Figure 296139DEST_PATH_IMAGE014
At the left side
Figure 682121DEST_PATH_IMAGE016
A piece of data;
if the symmetry is 1, the corresponding difference edge is the welding edge.
Further, the obtaining the included angle of the difference edges and determining the blanking difficulty according to the number of the difference edges and the included angle includes: obtaining the blanking difficulty through a blanking difficulty formula; the blanking difficulty formula comprises:
Figure DEST_PATH_IMAGE020
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE022
in order to address the difficulty of the blanking,
Figure DEST_PATH_IMAGE024
as to the number of the difference edges,
Figure DEST_PATH_IMAGE026
is as follows
Figure DEST_PATH_IMAGE028
The included angle of each of the differential edges.
Further, the obtaining of the welding difficulty according to the number of the welding edges, the length of the symmetry line, and the number of the intersection points of the welding edges and the bending line includes: obtaining the welding difficulty through a welding difficulty formula; the welding difficulty formula comprises:
Figure DEST_PATH_IMAGE030
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE032
in order to address the difficulty of the welding,
Figure DEST_PATH_IMAGE034
as to the number of the welding edges,
Figure DEST_PATH_IMAGE036
is as follows
Figure DEST_PATH_IMAGE038
The length of said line of symmetry of each of said welding edges,
Figure DEST_PATH_IMAGE040
for the welding edge toThe number of intersection points of the bending lines.
Further, the obtaining of the bending difficulty according to the number of the parallel symmetrical bending line sets and the distance between the bending lines includes: obtaining the bending difficulty through a bending difficulty formula; the bending difficulty formula comprises:
Figure DEST_PATH_IMAGE042
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE044
in order to make the bending difficult,
Figure DEST_PATH_IMAGE046
the number of the parallel symmetrical bending line sets is,
Figure DEST_PATH_IMAGE048
the number of the bending lines is equal to the number of the bending lines,
Figure DEST_PATH_IMAGE050
in order to preset the standard distance of the bending line,
Figure DEST_PATH_IMAGE052
is as follows
Figure 472310DEST_PATH_IMAGE028
The distance between each bending line and the bending line on one side,
Figure DEST_PATH_IMAGE054
is as follows
Figure 805203DEST_PATH_IMAGE028
The distance between the bending line and the other side of the bending line on one side.
Further, the obtaining of the process cost according to the number of the difference edges, the welding length of the welding edges, the number of the stamping areas and the number of the bending lines includes: obtaining the process cost according to a process cost calculation formula; the process cost calculation formula is as follows:
Figure DEST_PATH_IMAGE056
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE058
in order to be at the cost of the process,
Figure 540946DEST_PATH_IMAGE024
as to the number of the difference edges,
Figure 832250DEST_PATH_IMAGE034
as to the number of the welding edges,
Figure 820323DEST_PATH_IMAGE036
is as follows
Figure 488064DEST_PATH_IMAGE038
The length of said line of symmetry of each of said welding edges,
Figure DEST_PATH_IMAGE060
the cost is the unit price for welding,
Figure 94626DEST_PATH_IMAGE046
as to the number of the punching regions,
Figure DEST_PATH_IMAGE062
the cost of the stamping is the unit price,
Figure 274941DEST_PATH_IMAGE048
the number of the bending lines is equal to the number of the bending lines,
Figure DEST_PATH_IMAGE064
the cost is a unit price for bending.
Further, the obtaining of the final quote according to the preset material cost, the process cost, the production lot quantity and the defective rate includes: obtaining the final quotation through a final quotation formula; the final quotation formula is:
Figure DEST_PATH_IMAGE066
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE068
in order to be able to make the final quote,
Figure 622745DEST_PATH_IMAGE058
in order to be at the cost of the process,
Figure DEST_PATH_IMAGE070
in order to be able to reduce the material costs,
Figure DEST_PATH_IMAGE072
in order to be able to produce the batch size,
Figure DEST_PATH_IMAGE074
in order to achieve the defective rate described above,
Figure DEST_PATH_IMAGE076
the profit margin is preset.
The invention also provides a sheet metal structure production quotation rapid evaluation system based on artificial intelligence, which comprises a memory, a processor and a computer program which is stored in the memory and can be run on the processor, and is characterized in that the processor realizes any step of the sheet metal structure production quotation rapid evaluation method based on artificial intelligence when executing the computer program.
The invention has the following beneficial effects:
according to the embodiment of the invention, the data required by various processes are analyzed through the characteristics of various processes on the plane design drawing of the sheet metal structural part; and evaluating the processing difficulty of each process according to the process data. And outputting the defective rate by using the full-connection network according to the processing difficulty, and considering the defective rate, the final quotation can be more accurate. The process cost is analyzed by analyzing the process data, and an accurate final quote is obtained by further combining the material cost and the production batch quantity.
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 flowchart of a sheet metal structure production quotation rapid evaluation method based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a three-dimensional image of a sheet metal structure according to an embodiment of the present invention;
FIG. 3 is an edge image of a sheet metal structural member layout provided in one embodiment of the present invention; FIG. 4 is a blanking process image provided by an embodiment of the present invention;
FIG. 5 is an image of a welding process provided by one embodiment of the present invention;
FIG. 6 is a stamping process image provided by one embodiment of the present invention;
FIG. 7 is an image of a bending process provided in accordance with an embodiment of the present invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined purpose, the following detailed description, with reference to the accompanying drawings and preferred embodiments, describes a sheet metal structure production quotation rapid evaluation method and system based on artificial intelligence, and the specific implementation, structure, features and effects thereof according to the present invention. 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 a sheet metal structure production quotation rapid evaluation method and system based on artificial intelligence, which is provided by the invention, with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for rapidly evaluating a sheet metal structure production quotation based on artificial intelligence according to an embodiment of the present invention is shown, where the method includes:
step S1: acquiring a planar design drawing of a sheet metal structural part; an edge image of the floor plan is acquired.
The planar design drawing of the sheet metal structural member is generally a structural member development planar drawing which is rendered and derived by modeling software such as CAD (computer aided design). By the characteristics of each edge in the plan view, parameter information of blanking, welding, stamping and bending processes can be obtained. Referring to fig. 2, a three-dimensional image of a sheet metal structural member according to an embodiment of the present invention is shown. Referring to fig. 3, an edge image of a sheet metal structural member plan view according to an embodiment of the present invention is shown. That is, the sheet metal structure of the pattern of fig. 2 can be obtained by subjecting the sheet material to various processes according to the information in fig. 3.
In the embodiment of the invention, after the planar design drawing of the sheet metal structural part is obtained, the planar design drawing is subjected to binarization processing by using a maximum inter-class threshold method, so that the subsequent edge detection is facilitated.
And carrying out edge detection on the planar design drawing to obtain an edge image. The various edges in the plan view represent features of the respective process, such as the outer contour edges representing blanking features of the structural member, etc., as will be explained in detail in the subsequent steps. In the embodiment of the invention, the canny operator is used for carrying out edge detection on the plane design drawing to obtain an edge image.
Step S2: and acquiring process data of each process by extracting and analyzing the edge features in the edge image.
Because the flat design drawing is an electronic picture derived by software rendering, the influence of irrelevant background is avoided, and the edge information of the structural part can be completely acquired by using an edge detection technology.
The edges in the edge image are composed of edges of various forms, and because of the plan design drawing requirements of the sheet metal structural member, the edges of each form feature can be used to represent process data of a desired process. That is, the edge image can be regarded as an image formed by stitching a plurality of process images.
For the blanking process, it is required to blank the material sheet according to the required size and shape on the material sheet, so the outer contour edge in the edge image may represent the blanking process data. The acquisition of the blanking process data specifically comprises the following steps:
the outline edges in the edge image are obtained. And obtaining the minimum circumscribed rectangle of the outer contour edge according to the size information of the outer contour edge, and obtaining the difference pixel point of the outer contour edge according to the difference between the outer contour edge and the minimum circumscribed rectangle. The shape information of the current structural part is represented by the difference edge formed by the difference pixel points, and the size information of the current structural part can be represented by the size of the minimum circumscribed rectangle. And obtaining blanking process data according to the shape information and the size information. Referring to fig. 4, a blanking process image according to an embodiment of the present invention is shown. The method for acquiring the difference pixel point comprises the following steps:
and obtaining a connecting line from the minimum circumscribed rectangle pixel point to the central point of the edge image. And if the distance from the outline edge pixel point to the edge image central point on the connecting line is different from the length of the connecting line, the corresponding outline edge pixel point is a difference pixel point.
In the embodiment of the invention, the edge of the maximum closed connected domain in the edge image is taken as the outer contour edge, and the inner edge is obtained by removing the outer contour edge.
For the welding process, a splice welding is required at the notch reserved in the blanking process, which is indicated as the welding edge in the edge image. The welding edge is one of the difference edges on the outer contour, because the welding process requires that the materials are spliced and aligned to be welded, the welding edge has symmetry, the symmetric welding edge can completely align the materials, and therefore the symmetrical difference edge is used as the welding edge on the outer contour edge to obtain welding process data, which specifically comprises the following steps:
aiming at the characteristics of the welding gap, the welding gap at the diagonal position is positioned at the corner on the three-dimensional information after welding, so the symmetry of the diagonal gap needs to be considered in a plane design drawing; the notches on the four sides need to be in the same plane after welding, so the symmetry of the four sides, vertical or horizontal, needs to be considered in the plane design. If the opposite angle of the minimum circumscribed rectangle has a difference edge, the center point of the over-edge image connects the two difference edges point by point to obtain a first distance sequence. And if the four sides of the minimum circumscribed rectangle have difference edges which are vertically and/or horizontally corresponding, obtaining the vertical and/or horizontal distance between each pixel point of the two difference edges, and obtaining a second distance sequence. Analyzing data differences on two sides of the peak position in the first distance sequence and the second distance sequence, and analyzing the symmetry of a difference edge according to the data differences, specifically comprising:
and obtaining symmetry according to a symmetry formula. The symmetry formula is:
Figure DEST_PATH_IMAGE002A
Figure DEST_PATH_IMAGE004A
wherein the content of the first and second substances,
Figure 74937DEST_PATH_IMAGE006
in order to have the symmetry properties,
Figure 316431DEST_PATH_IMAGE008
the number of pixels that is half of the difference edge,
Figure 949538DEST_PATH_IMAGE010
is an index of the property of the pixel point,
Figure 925584DEST_PATH_IMAGE012
is the peak point
Figure 403970DEST_PATH_IMAGE014
The right side is
Figure 765550DEST_PATH_IMAGE016
The number of the data is one,
Figure 569558DEST_PATH_IMAGE018
is the peak point
Figure 32900DEST_PATH_IMAGE014
At the left side
Figure 580556DEST_PATH_IMAGE016
And (4) data.
If the symmetry is 1, the corresponding difference edge is the symmetrical difference edge, the corresponding notch needs to be welded, and the difference edge is reserved as the welding edge. While obtaining a symmetry line of the welding edge. The two ends of the line of symmetry are on the minimum circumscribed rectangle and the welding edge. The length of the line of symmetry represents the length of the weld that is required after subsequent alignment of the weld edges. Referring to fig. 5, an image of a welding process according to an embodiment of the present invention is shown. The welding process image only contains the welding edge and the corresponding symmetrical line length as welding process data.
For the punching process data, punching holes or punching specific shapes on the material are required according to design requirements, so that the closed connected regions in the inner contour of the edge image can be regarded as punching regions, and the area and the number of the punching regions can be regarded as the punching process data. Referring to fig. 6, a stamping process image according to an embodiment of the present invention is shown.
For the bending process data, the bending lines are distributed in the plane design drawing by dotted lines, the number of the line segments in the dotted lines represents the bending times, so that the dotted lines of the inner edge after the punching area is removed are detected, and the line segments in the dotted lines are used as the bending lines. In the embodiment of the invention, the straight line of the inner edge after the punching area is removed is detected by Hough transform to obtain a plurality of line segments. Because the distances between the line segments in the dotted line are the same, whether the line segments are the line segments in the same dotted line is judged according to the distance similarity of the line segments. And taking the bending line as bending process data. Referring to FIG. 7, an image of a bending process according to an embodiment of the present invention is shown.
Step S3: and analyzing the process data of various processes to obtain the process difficulty of each process.
The production process of the sheet metal structural part sequentially comprises the steps of blanking, stamping, bending and welding. 4 processes are carried out in sequence to complete production, so that the process difficulty is analyzed in sequence, and the method specifically comprises the following steps:
for the blanking process, the smaller the included angle of the difference edge is, the more detailed operation is required in the blanking process, that is, the greater the blanking difficulty is, so the blanking difficulty is determined according to the number of the difference edge and the included angle, which specifically includes: and obtaining the blanking difficulty through a blanking difficulty formula. The blanking difficulty formula comprises:
Figure DEST_PATH_IMAGE020A
wherein the content of the first and second substances,
Figure 734326DEST_PATH_IMAGE022
in order to make the blanking difficult,
Figure 974814DEST_PATH_IMAGE024
to be the number of the difference edges,
Figure 646492DEST_PATH_IMAGE026
is as follows
Figure 997838DEST_PATH_IMAGE028
The included angle of the differential edges.
For the stamping process, the stamping difficulty is increased when the stamping area is larger because the stamping area is often designed holes or special shapes
Figure DEST_PATH_IMAGE078
The larger. In the embodiment of the inventionAnd (3) the inverse proportional relation between the area of the stamping area and the stamping difficulty, and the ratio of the standard stamping area to the area of each stamping area is accumulated to be used as the stamping difficulty. In other embodiments, other stamping difficulty obtaining methods may be set according to a specific stamping design, which is not described herein.
For the bending process, the smaller the interval between the bending line and the bending line around the bending line is, the greater the bending process difficulty is; the more the bending times, the greater the bending process difficulty. The bending lines which are symmetrical in parallel are two edges of one surface of the structural member after being bent, so that the bending lines which are symmetrical in parallel are regarded as a type of bending line to form a set of the bending lines which are symmetrical in parallel. The quantity of parallel symmetry line set of bending has represented the number of times that the material need be bent, obtains the degree of difficulty of bending according to the quantity of parallel line set of bending and the distance between the line of bending and specifically includes: and obtaining the bending difficulty through a bending difficulty formula. The bending difficulty formula comprises:
Figure DEST_PATH_IMAGE042A
wherein the content of the first and second substances,
Figure 209377DEST_PATH_IMAGE044
in order to make the bending difficult,
Figure 620767DEST_PATH_IMAGE046
the number of the parallel symmetrical bending line sets,
Figure 527543DEST_PATH_IMAGE048
in order to increase the number of the bending lines,
Figure 931848DEST_PATH_IMAGE050
in order to preset the standard distance of the bending line,
Figure 873259DEST_PATH_IMAGE052
is as follows
Figure 455551DEST_PATH_IMAGE028
The distance between each bending line and the bending line on one side,
Figure 849623DEST_PATH_IMAGE054
is as follows
Figure 792040DEST_PATH_IMAGE028
The distance between the bending line and the other side of the bending line on one side. The bending difficulty formula analyzes the bending difficulty by analyzing the interval and the bending times of two sides of the bending line.
For the welding process, the longer the welding length is, the more the welding inflection points are, the greater the welding difficulty is. Wherein the nodical table quantity of welding inflection point accessible welding edge and the line of bending represents, consequently obtains the welding degree of difficulty according to the length of the quantity of welding edge, symmetry line and the nodical quantity of welding edge and the line of bending, specifically includes: obtaining the welding difficulty through a welding difficulty formula; the welding difficulty formula comprises:
Figure DEST_PATH_IMAGE030A
wherein the content of the first and second substances,
Figure 994482DEST_PATH_IMAGE032
in order to make the welding difficult,
Figure 17450DEST_PATH_IMAGE034
in order to weld the number of edges,
Figure 898818DEST_PATH_IMAGE036
is as follows
Figure 395659DEST_PATH_IMAGE038
The length of the line of symmetry of the individual welding edges,
Figure 46083DEST_PATH_IMAGE040
the number of the intersection points of the welding edge and the bending line is shown.
Step S4: weighting and summing various process difficulties to obtain the overall production difficulty; and sending various process difficulties, the whole production difficulty and the preset production batch quantity into a pre-trained fully-connected network to obtain the defective rate.
After all process difficulties are obtained, the various process difficulties are combined through a weighted summation method to obtain the overall production difficulty, namely:
Figure DEST_PATH_IMAGE080
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE082
in order to make the whole production difficult,
Figure 360390DEST_PATH_IMAGE022
in order to make the blanking difficult,
Figure DEST_PATH_IMAGE084
the weight corresponding to the blanking difficulty is set,
Figure 243901DEST_PATH_IMAGE032
in order to make the welding difficult,
Figure DEST_PATH_IMAGE086
the weight corresponding to the welding difficulty is set,
Figure 747694DEST_PATH_IMAGE078
in order to make the punching difficult,
Figure DEST_PATH_IMAGE088
the weight corresponding to the difficulty of stamping is,
Figure 970734DEST_PATH_IMAGE044
in order to make the bending difficult,
Figure DEST_PATH_IMAGE090
the weight is the weight corresponding to the bending difficulty. In the embodiment of the invention, considering that both blanking and stamping are to cut or cut the material plate by using a machine, the weights corresponding to the two processes should be the same, and considering that the bending process is more complicated, the material plate needs to be processed for multiple timesTherefore, the corresponding weight is larger, specifically:
Figure DEST_PATH_IMAGE092
the defective rate in the production process can be judged according to historical data by all the process difficulties and the overall production difficulty, the defective rate is the ratio of the defective amount to the production batch amount, therefore, the defective rate is obtained by analyzing all the process difficulties, the overall production difficulty and the preset production batch amount together, and all the parameters are sent into a pre-trained full-connection network to obtain the corresponding defective rate. The fully connected network is a conventional technical means, and is not described herein in detail.
Step S5: obtaining the process cost according to the number of the difference edges, the number of the welding edges, the number of the stamping edges and the number of the bending lines; and obtaining a final quoted price according to the preset material cost, the process cost, the production batch quantity and the defective rate.
The process cost of the sheet metal structural part in the production process can be obtained by combining the required unit price according to each process data, the plane size of the structural part is determined by considering that the whole frame needs to be firstly cut once when the sheet metal structural part is produced, and the essential significance of the blanking process and the stamping process is to cut materials, so that the blanking process data and the stamping process data can be jointly analyzed; further determine the process cost by combining the bending times and the welding length, and specifically comprise the following steps:
obtaining the process cost according to a process cost calculation formula; the process cost calculation formula is as follows:
Figure DEST_PATH_IMAGE094
wherein the content of the first and second substances,
Figure 724451DEST_PATH_IMAGE058
in order to reduce the cost of the process,
Figure 580412DEST_PATH_IMAGE024
to be the number of the difference edges,
Figure 419055DEST_PATH_IMAGE034
in order to weld the number of edges,
Figure 512913DEST_PATH_IMAGE036
is as follows
Figure 28077DEST_PATH_IMAGE038
The length of the line of symmetry of the individual welding edges,
Figure 105754DEST_PATH_IMAGE060
the cost is the unit price for welding,
Figure 748088DEST_PATH_IMAGE046
as to the number of the punched-out areas,
Figure 227611DEST_PATH_IMAGE062
the cost of the stamping is the unit price,
Figure 461146DEST_PATH_IMAGE048
in order to increase the number of the bending lines,
Figure 478649DEST_PATH_IMAGE064
the cost is a unit price for bending.
The cost analysis not only considers the process cost, but also analyzes the material cost, which is the material size multiplied by the material unit price.
The final quoted price can be obtained by combining the process cost, the material cost, the production batch quantity, the defective rate and the preset profit margin, and the method specifically comprises the following steps: obtaining a final quotation through a final quotation formula; the final quote formula is:
Figure DEST_PATH_IMAGE066A
wherein the content of the first and second substances,
Figure 846046DEST_PATH_IMAGE068
in order to be the final quote,
Figure 180075DEST_PATH_IMAGE058
in order to reduce the cost of the process,
Figure 787774DEST_PATH_IMAGE070
in order to be able to reduce the material costs,
Figure 840044DEST_PATH_IMAGE072
in order to produce a batch size,
Figure 355339DEST_PATH_IMAGE074
in order to obtain a defective rate,
Figure 259054DEST_PATH_IMAGE076
the profit margin is preset.
The final quoted price is rapidly and accurately acquired, the smooth proceeding of the production project is ensured, and the efficiency of the project flow is improved.
In summary, the embodiment of the present invention obtains the edge image of the floor plan. And analyzing blanking process data, welding process data, stamping process data and bending process data through edge information in the edge image. The process difficulty of various processes is obtained through the analysis of various process data. Further obtaining the integral production difficulty, and obtaining the defective rate according to the integral production difficulty and various process difficulties combined with batch quantity. The process cost is obtained by analyzing various process data, and the final quote is obtained by combining the material cost, the production batch quantity and the defective rate. According to the embodiment of the invention, the production quotation of the sheet metal structural part is rapidly and accurately obtained through image processing.
The invention also provides a sheet metal structure production quotation rapid evaluation system based on artificial intelligence, which comprises a memory, a processor and a computer program which is stored in the memory and can be operated on the processor, and is characterized in that the processor realizes any step of the sheet metal structure production quotation rapid evaluation method based on artificial intelligence when executing the computer program.
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.
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 is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (9)

1. A sheet metal structure production quotation rapid assessment method based on artificial intelligence is characterized by comprising the following steps:
acquiring a planar design drawing of a sheet metal structural part; acquiring an edge image of the planar design drawing;
taking the edge of the maximum closed connected domain in the edge image as an outer contour edge, and removing the outer contour edge to obtain an inner edge; obtaining a minimum circumscribed rectangle of the outline edge and difference pixel points of the outline edge, wherein the difference pixel points form a difference edge; taking the difference edges corresponding to the symmetrical difference pixel points as welding edges to obtain symmetrical lines of the welding edges; the two end points of the symmetry line are on the minimum circumscribed rectangle and the welding edge; taking the communication area of the inner edge as a stamping area; detecting a dotted line of the inner edge after the punching area is removed, and taking a line segment in the dotted line as a bending line;
acquiring an included angle of the difference edges, and determining blanking difficulty according to the number of the difference edges and the included angle; obtaining the stamping difficulty according to the area of the stamping area; forming parallel symmetrical bending lines into a parallel symmetrical bending line set, and obtaining bending difficulty according to the number of the parallel bending line set and the distance between the bending lines; obtaining the welding difficulty according to the number of the welding edges, the length of the symmetrical line and the number of the intersection points of the welding edges and the bending lines;
weighting and summing the blanking difficulty, the welding difficulty, the stamping difficulty and the bending difficulty to obtain the overall production difficulty; sending the blanking difficulty, the welding difficulty, the stamping difficulty, the bending difficulty, the overall production difficulty and a preset production batch quantity into a pre-trained full-connection network to obtain a defective rate;
obtaining the process cost according to the number of the difference edges, the number of the welding edges, the number of the stamping areas and the number of the bending lines; obtaining a final quote according to preset material cost, the process cost, the production batch quantity and the defective rate;
wherein the using the symmetrical difference edges corresponding to the difference pixel points as welding edges comprises:
if the opposite angle of the minimum circumscribed rectangle has the difference edge, connecting the two difference edges point by point through the central point of the edge image to obtain a first distance sequence; if the difference edges which are vertically and/or horizontally corresponding exist on the four sides of the minimum circumscribed rectangle, the vertical and/or horizontal distance between each pixel point of the two difference edges is obtained, and a second distance sequence is obtained; and analyzing data difference on two sides of the peak position in the first distance sequence and the second distance sequence, analyzing the symmetry of the difference edge according to the data difference, and taking the difference edge corresponding to the symmetrical difference pixel point as a welding edge.
2. The method for rapidly evaluating sheet metal structure production quotation based on artificial intelligence according to claim 1, wherein the step of obtaining the difference pixel points of the minimum circumscribed rectangle of the outer contour edge and the outer contour edge comprises the steps of:
obtaining a connecting line from the minimum circumscribed rectangle pixel point to the central point of the edge image; and if the distance between the outline edge pixel point and the edge image central point on the connecting line is different from the length of the connecting line, the corresponding outline edge pixel point is the difference pixel point.
3. The method for rapidly evaluating sheet metal structure production quotation based on artificial intelligence as claimed in claim 1, wherein the analyzing data differences on both sides of the peak position in the first distance sequence and the second distance sequence, and the analyzing the symmetry of the difference edge according to the data differences comprises: obtaining the symmetry according to a symmetry formula; the symmetry formula is:
Figure 624879DEST_PATH_IMAGE002
Figure 554789DEST_PATH_IMAGE004
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE005
in order for the symmetry to be such that,
Figure 451811DEST_PATH_IMAGE006
half the number of pixels at the edge of the disparity,
Figure DEST_PATH_IMAGE007
is an index of the property of the pixel point,
Figure 631120DEST_PATH_IMAGE008
is the peak point
Figure DEST_PATH_IMAGE009
The right side is
Figure 93194DEST_PATH_IMAGE010
The number of the data is one,
Figure DEST_PATH_IMAGE011
is the peak point
Figure 674348DEST_PATH_IMAGE009
At the left side
Figure 540673DEST_PATH_IMAGE010
A piece of data;
if the symmetry is 1, the corresponding difference edge is the welding edge.
4. The method for rapidly evaluating sheet metal structure production quotation based on artificial intelligence of claim 1, wherein the obtaining the included angle of the difference edges, and the determining the blanking difficulty according to the number of the difference edges and the included angle comprises: obtaining the blanking difficulty through a blanking difficulty formula; the blanking difficulty formula comprises:
Figure DEST_PATH_IMAGE013
wherein the content of the first and second substances,
Figure 456545DEST_PATH_IMAGE014
in order to address the difficulty of the blanking,
Figure DEST_PATH_IMAGE015
as to the number of the difference edges,
Figure 473043DEST_PATH_IMAGE016
is as follows
Figure DEST_PATH_IMAGE017
Each of the difference edgesThe angle of the edges.
5. The method for rapidly evaluating sheet metal structure production quotation based on artificial intelligence as claimed in claim 1, wherein the obtaining of the welding difficulty according to the number of the welding edges, the length of the symmetry line and the number of the intersection points of the welding edges and the bending line comprises: obtaining the welding difficulty through a welding difficulty formula; the welding difficulty formula comprises:
Figure DEST_PATH_IMAGE019
wherein the content of the first and second substances,
Figure 298916DEST_PATH_IMAGE020
in order to address the difficulty of the welding,
Figure DEST_PATH_IMAGE021
as to the number of the welding edges,
Figure 260444DEST_PATH_IMAGE022
is as follows
Figure DEST_PATH_IMAGE023
The length of said line of symmetry of each of said welding edges,
Figure 148765DEST_PATH_IMAGE024
the number of the intersection points of the welding edges and the bending lines is shown.
6. The method for rapidly evaluating sheet metal structure production quotation based on artificial intelligence as claimed in claim 1, wherein the obtaining of the bending difficulty according to the number of the parallel symmetrical bending line sets and the distance between the bending lines comprises: obtaining the bending difficulty through a bending difficulty formula; the bending difficulty formula comprises:
Figure 562429DEST_PATH_IMAGE026
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE027
in order to make the bending difficult,
Figure 101864DEST_PATH_IMAGE028
the number of the parallel symmetrical bending line sets is,
Figure DEST_PATH_IMAGE029
the number of the bending lines is equal to the number of the bending lines,
Figure 982095DEST_PATH_IMAGE030
in order to preset the standard distance of the bending line,
Figure DEST_PATH_IMAGE031
is as follows
Figure 341401DEST_PATH_IMAGE017
The distance between each bending line and the bending line on one side,
Figure 293176DEST_PATH_IMAGE032
is as follows
Figure 437850DEST_PATH_IMAGE017
The distance between the bending line and the other side of the bending line on one side.
7. The method for rapidly evaluating sheet metal structure production quotation based on artificial intelligence of claim 1, wherein the obtaining of the process cost according to the number of the difference edges, the number of the welding edges, the number of the punching areas and the number of the bending lines comprises: obtaining the process cost according to a process cost calculation formula; the process cost calculation formula is as follows:
Figure 207092DEST_PATH_IMAGE034
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE035
in order to be at the cost of the process,
Figure 929060DEST_PATH_IMAGE015
as to the number of the difference edges,
Figure 559893DEST_PATH_IMAGE021
as to the number of the welding edges,
Figure 152548DEST_PATH_IMAGE022
is as follows
Figure 95621DEST_PATH_IMAGE023
The length of said line of symmetry of each of said welding edges,
Figure 39306DEST_PATH_IMAGE036
the cost is the unit price for welding,
Figure 473830DEST_PATH_IMAGE028
as to the number of the punching regions,
Figure DEST_PATH_IMAGE037
the cost of the stamping is the unit price,
Figure 842363DEST_PATH_IMAGE029
the number of the bending lines is equal to the number of the bending lines,
Figure 297615DEST_PATH_IMAGE038
the cost is a unit price for bending.
8. The method for rapidly evaluating sheet metal structure production quotation based on artificial intelligence as claimed in claim 1, wherein the obtaining of the final quotation according to the preset material cost, the process cost, the production batch size and the reject rate comprises: obtaining the final quotation through a final quotation formula; the final quotation formula is:
Figure 603962DEST_PATH_IMAGE040
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE041
in order to be able to make the final quote,
Figure 357024DEST_PATH_IMAGE035
in order to be at the cost of the process,
Figure 924271DEST_PATH_IMAGE042
in order to be able to reduce the material costs,
Figure DEST_PATH_IMAGE043
in order to be able to produce the batch size,
Figure 222529DEST_PATH_IMAGE044
in order to achieve the defective rate described above,
Figure DEST_PATH_IMAGE045
the profit margin is preset.
9. An artificial intelligence based sheet metal structure production quotation rapid assessment system, comprising a memory, a processor and a computer program stored in the memory and operable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program.
CN202111118283.6A 2021-09-24 2021-09-24 Metal plate structure production quotation rapid assessment method and system based on artificial intelligence Active CN113643074B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111118283.6A CN113643074B (en) 2021-09-24 2021-09-24 Metal plate structure production quotation rapid assessment method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111118283.6A CN113643074B (en) 2021-09-24 2021-09-24 Metal plate structure production quotation rapid assessment method and system based on artificial intelligence

Publications (2)

Publication Number Publication Date
CN113643074A CN113643074A (en) 2021-11-12
CN113643074B true CN113643074B (en) 2022-03-11

Family

ID=78426184

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111118283.6A Active CN113643074B (en) 2021-09-24 2021-09-24 Metal plate structure production quotation rapid assessment method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN113643074B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114535450B (en) * 2022-04-22 2022-06-28 南通精丰智能设备有限公司 Intelligent control method and system for closed fin stamping production line

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101702225A (en) * 2009-09-11 2010-05-05 合肥锻压机床有限公司 Quick quotation system of forging machine tool and quick quotation method thereof
CN104462675A (en) * 2014-11-25 2015-03-25 英业达科技有限公司 Method for calculating material sizes
CN108320098A (en) * 2018-02-02 2018-07-24 四川爱华立康智能科技有限公司 Metal plate Intelligent Machining, production management system and the method for carrying out metal plate production with it
CN113052426A (en) * 2020-12-11 2021-06-29 朗道供应链(苏州)有限公司 Machining cost calculation method and system based on mechanical parts
CN113283946A (en) * 2021-06-16 2021-08-20 中山市爱美泰电器有限公司 Calculation method for quickly verifying product cost by defining reference array price

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103954213B (en) * 2014-04-17 2017-05-31 北京力信联合科技有限公司 A kind of method of the measured drawing for analyzing part
US9934325B2 (en) * 2014-10-20 2018-04-03 Korean Institute Of Science And Technology Information Method and apparatus for distributing graph data in distributed computing environment
CN112712512A (en) * 2021-01-05 2021-04-27 余波 Hot-rolled strip steel scab defect detection method and system based on artificial intelligence

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101702225A (en) * 2009-09-11 2010-05-05 合肥锻压机床有限公司 Quick quotation system of forging machine tool and quick quotation method thereof
CN104462675A (en) * 2014-11-25 2015-03-25 英业达科技有限公司 Method for calculating material sizes
CN108320098A (en) * 2018-02-02 2018-07-24 四川爱华立康智能科技有限公司 Metal plate Intelligent Machining, production management system and the method for carrying out metal plate production with it
CN113052426A (en) * 2020-12-11 2021-06-29 朗道供应链(苏州)有限公司 Machining cost calculation method and system based on mechanical parts
CN113283946A (en) * 2021-06-16 2021-08-20 中山市爱美泰电器有限公司 Calculation method for quickly verifying product cost by defining reference array price

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Economic evaluation of alternative process chains for the large-scale manufacturing of metal-fibre laminates;Rothe, Felix等;《2ND CIRP CONFERENCE ON COMPOSITE MATERIAL PARTS MANUFACTURING》;20191231;第85卷;全文 *
基于加工模拟技术的钣金切割成本估算模型研究;蒋麒麟等;《锻压装备与制造技术》;20070530(第5期);全文 *
基于过程的钣金成本估算;石小清等;《物流工程与管理》;20110630(第6期);全文 *

Also Published As

Publication number Publication date
CN113643074A (en) 2021-11-12

Similar Documents

Publication Publication Date Title
CN104463795B (en) A kind of dot matrix DM image in 2 D code processing method and processing device
CN102006425B (en) Method for splicing video in real time based on multiple cameras
DE602005006341T2 (en) Device, method, recording medium and information processing program
CN108197618B (en) Method and device for generating human face detection model
CN103456003B (en) Object tracking device and method and error characteristic point device for eliminating and method
CN107992871A (en) The automatic accounting method in dining room based on image recognition
US20200356800A1 (en) Polygonal region detection
CN108710916B (en) Picture classification method and device
CN113643074B (en) Metal plate structure production quotation rapid assessment method and system based on artificial intelligence
CN104487843A (en) Image processing device, program, image processing method, computer-readable medium, and image processing system
CN104881676B (en) A kind of facial image convex-concave pattern texture feature extraction and recognition methods
CN104036284A (en) Adaboost algorithm based multi-scale pedestrian detection method
CN103020993A (en) Visual saliency detection method by fusing dual-channel color contrasts
CN108846831B (en) Band steel surface defect classification method based on combination of statistical characteristics and image characteristics
CN111160284A (en) Method, system, equipment and storage medium for evaluating quality of face photo
Peng et al. Lggd+: Image retargeting quality assessment by measuring local and global geometric distortions
CN112926441B (en) Home identification method, system, device and medium based on machine vision
EP3748578A1 (en) Automatic visual detection of defects in images of via holes
CN106415606B (en) A kind of identification based on edge, system and method
CN107194310A (en) The rigid-object tracking matched based on scene change classifications and online local feature
CN111641822A (en) Method for evaluating quality of repositioning stereo image
CN108182457A (en) For generating the method and apparatus of information
Wen et al. Complex surface ROI detection for steel plate fusing the gray image and 3D depth information
CN107909565A (en) Stereo-picture Comfort Evaluation method based on convolutional neural networks
CN106056575A (en) Image matching method based on object similarity recommended algorithm

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
CB02 Change of applicant information

Address after: 272500 No. 1, Jincheng Road, economic development zone, Wenshang County, Jining City, Shandong Province

Applicant after: Jincheng Technology Co.,Ltd.

Address before: 272500 No.1 Jincheng Road, Wenshang Economic Development Zone, Jining City, Shandong Province

Applicant before: Jincheng Technology Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant