CN116930196B - Machine vision-based aluminum profile production defect analysis processing method - Google Patents
Machine vision-based aluminum profile production defect analysis processing method Download PDFInfo
- Publication number
- CN116930196B CN116930196B CN202311196709.9A CN202311196709A CN116930196B CN 116930196 B CN116930196 B CN 116930196B CN 202311196709 A CN202311196709 A CN 202311196709A CN 116930196 B CN116930196 B CN 116930196B
- Authority
- CN
- China
- Prior art keywords
- tubular aluminum
- aluminum radiator
- defect
- radiator
- tubular
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 title claims abstract description 299
- 229910052782 aluminium Inorganic materials 0.000 title claims abstract description 298
- 230000007547 defect Effects 0.000 title claims abstract description 156
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 86
- 238000004458 analytical method Methods 0.000 title claims abstract description 63
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 230000007847 structural defect Effects 0.000 claims abstract description 47
- 238000011156 evaluation Methods 0.000 claims abstract description 40
- 230000017525 heat dissipation Effects 0.000 claims abstract description 17
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 239000011248 coating agent Substances 0.000 claims description 36
- 238000000576 coating method Methods 0.000 claims description 36
- 238000000034 method Methods 0.000 claims description 32
- 230000005855 radiation Effects 0.000 claims description 30
- 238000001816 cooling Methods 0.000 claims description 22
- 238000007373 indentation Methods 0.000 claims description 22
- 239000012535 impurity Substances 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000011077 uniformity evaluation Methods 0.000 claims description 5
- 239000004411 aluminium Substances 0.000 claims 1
- 238000012797 qualification Methods 0.000 abstract description 5
- 238000004141 dimensional analysis Methods 0.000 abstract description 3
- 238000009434 installation Methods 0.000 description 4
- 238000011835 investigation Methods 0.000 description 4
- 238000011056 performance test Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000011148 porous material Substances 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention relates to the technical field of aluminum profile production defect analysis, and particularly discloses a machine vision-based aluminum profile production defect analysis processing method, which comprises aluminum profile structure information acquisition and analysis, aluminum profile size information acquisition and analysis, aluminum profile performance monitoring and analysis and aluminum profile production defect feedback; according to the invention, the structural defect degree, the dimensional defect degree and the performance defect degree of the tubular aluminum radiator are analyzed, so that the quality qualification condition of the tubular aluminum radiator in a target production batch is fed back, the multi-dimensional analysis of the production defects of the tubular aluminum radiator is realized, the error in the analysis of the production defects of the tubular aluminum radiator is reduced, the comprehensiveness and convincing of the analysis of the production defects are improved, the production cost of the tubular aluminum radiator is reduced, the reference property of the production defect evaluation data of the tubular aluminum radiator is improved, and the stability of the heat dissipation performance in subsequent use is ensured.
Description
Technical Field
The invention relates to the technical field of aluminum profile production defect analysis, in particular to a machine vision-based aluminum profile production defect analysis processing method.
Background
The aluminum profile is mostly used as a raw material for producing heat dissipation structure articles, and the tubular aluminum radiator is most common in daily life, plays a key role in absorbing, conducting and radiating heat, improves the efficiency and stability of equipment and reduces the damage risk of the equipment, so that the production defect of the tubular aluminum radiator needs to be analyzed in order to ensure the heat dissipation effect of the tubular aluminum radiator.
The existing production mode of the tubular aluminum radiator mainly comprises two modes of casting and a die, wherein the die production mainly carries out production defect analysis through an apparent layer surface and a dimension layer surface, and obviously, the analysis mode has the following problems: 1. whether the surface coating is complete is only judged on the apparent layer surface, and the uniformity of the coating is not subjected to deep analysis, so that negative effects on the appearance quality, corrosion resistance, coating durability and the like of a product caused by uneven thickness of the coating are caused, and meanwhile, the air hole condition and the impurity condition in the internal structure are not analyzed, so that the coverage of the structural defect analysis of the tubular aluminum radiator cannot be improved.
2. And the size layer is only used for judging whether the size accords with the size and whether the size is incomplete, and the space condition and the angle deviation condition of the radiating fins in the tubular aluminum radiator are not subjected to deep analysis, so that the installation problem caused by the unqualified size is caused, the production cost and the installation loss of the tubular aluminum radiator are increased, and the accuracy of judging the size defect degree of the tubular aluminum radiator is reduced.
3. For the performance test layer, the performance test of the whole structure of the tubular aluminum radiator is only carried out at present, and each radiating fin is not examined one by one, so that the hidden danger examination precision of the tubular aluminum radiator cannot be ensured, the reference property of performance defect evaluation data of the tubular aluminum radiator is reduced, and meanwhile, the stability of the heat radiation performance during subsequent use cannot be ensured.
Disclosure of Invention
In view of this, in order to solve the problems set forth in the background art, a method for analyzing and processing defects in aluminum profile production based on machine vision is proposed.
The aim of the invention can be achieved by the following technical scheme: the invention provides a machine vision-based aluminum profile production defect analysis processing method, which comprises the following steps of: s1, aluminum profile structural information acquisition and analysis: and respectively carrying out image acquisition on the external structure and the internal structure of each tubular aluminum radiator in the target production batch to obtain image information, and acquiring the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator, so as to analyze the structural defect degree of the tubular aluminum radiator in the target production batch.
S2, aluminum profile size information acquisition and analysis: and acquiring the integral image and the end face image of each tubular aluminum radiator, so as to analyze the size defect degree of the tubular aluminum radiator in the target production batch.
S3, monitoring and analyzing the performance of the aluminum profile: and testing the hardness performance and the heat radiation performance of each tubular aluminum radiator, and monitoring the apparent images and the heat radiation information of the tests, so as to analyze the performance defect degree of the tubular aluminum radiator in the target production batch.
S4, feeding back production defects of the aluminum profile: if the structural defect degree or the dimensional defect degree or the performance defect degree of the tubular aluminum radiator in the target production batch reaches the set value, judging that the quality of the tubular aluminum radiator in the target production batch is unqualified, and feeding back the production defect.
Specifically, the image information includes external structure image information and internal structure image information. The external structure image information comprises the number of surface concave positions of each component radiating fin in each tubular aluminum radiator, the corresponding concave volume of each concave position, the number of surface scratch positions and the corresponding scratch length of each scratch position.
The internal structure image information comprises the number of internal air holes of each component radiating fin, the corresponding air hole area of each air hole, the number of internal impurity positions and the corresponding impurity area of each impurity position in each tubular aluminum radiator.
Specifically, the structural defect degree of the tubular aluminum radiator in the target production batch is analyzed, and the specific analysis process is as follows: a1, extracting the number of the surface concave parts of each component radiating fin and the concave volume corresponding to each concave part in each tubular aluminum radiator from the external structure image information, and respectively marking asAnd->Wherein->The number of the tubular aluminum type radiator is shown,,/>indicates the number of the cooling fin, ">,/>Representing the number of the concave part,/-, and>。
a2, calculating the dishing degree of each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,andthe total number of depressions and total volume of depressions for the set reference are shown respectively,andthe set total number of depressions and total volume of depressions are respectively expressed as corresponding depression evaluation duty ratio weight,representing natural constants.
A3, extracting the number of surface scratches of each component radiating fin and the corresponding scratch length of each scratch in each tubular aluminum radiator from the external structure image information, and analyzing the scratch degree of each tubular aluminum radiator in a similar way according to the analysis mode of the dent degree of each tubular aluminum radiator。
A4, calculating the coating uniformity of each tubular aluminum radiator according to the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator。
A5, calculating the defect degree of the external structure corresponding to each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,andthe set dishing, scratch, and coating uniformity assessments are shown for the external structural defect level assessment duty cycle, respectively.
A6, extracting the number of internal air holes of each component radiating fin, the air hole area corresponding to each air hole, the number of internal impurity positions and the impurity area corresponding to each impurity position in each tubular aluminum radiator from the internal structure image information, and analyzing the internal structure defect degree corresponding to each tubular aluminum radiator in a similar way according to the analysis mode of the external structure defect degree corresponding to each tubular aluminum radiator。
A7, calculating structural defect degree of each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,andrespectively representing the set structural defect degree evaluation duty ratio weight corresponding to the external structural defect evaluation and the internal structural defect evaluation.
A8, extracting the maximum structural defect degree from the structural defect degrees of the tubular aluminum heat sinks, and taking the maximum structural defect degree as the structural defect degree of the tubular aluminum heat sinks in the target production batch.
Specifically, the method for analyzing the dimensional defect degree of the tubular aluminum radiator in the target production batch comprises the following specific analysis processes: b1, analyzing the space uniformity of the corresponding radiating fins of the tubular aluminum radiator according to the integral image of each tubular aluminum radiator。
B2, analyzing the angle defect degree of the corresponding radiating fin of the tubular aluminum radiator according to the end face image of each tubular aluminum radiator。
B3, calculating the size defect degree of the tubular aluminum radiator in the target production batch,Wherein->And->Respectively representing the set interval uniformity evaluation and the corresponding size defect of the angle defect evaluationThe sinkage evaluates the duty cycle weight.
Specifically, the analyzing the space uniformity of the corresponding cooling fin of the tubular aluminum radiator includes the following steps: and C1, randomly positioning one radiating fin from the whole image of each tubular aluminum radiator, marking the radiating fin as a target radiating fin, sequentially ordering other radiating fins in a clockwise direction, and marking the radiating fins as reference radiating fins.
C2, arranging each monitoring point in the target radiating fins of each tubular aluminum radiator in turn from top to bottom, marking the target radiating fins as each target radiating fin, mapping each target radiating fin to each reference radiating fin to obtain mapping points corresponding to each target radiating fin in each reference radiating fin, further obtaining the distance between each target radiating fin in each tubular aluminum radiator and the mapping point corresponding to each target radiating fin in each reference radiating fin, marking the distance asWherein->Reference is made to the numbering of the heat sinks,,/>number representing mapping point->。
C3, calculating the space uniformity of the corresponding radiating fins of the tubular aluminum radiator,Wherein->Representing the number of tubular aluminum type heat sinks,and->Respectively represent the horizontal pitch deviation and the vertical pitch deviation of the set reference, +.>Indicate->Reference heat sink->Indicate->And mapping points.
Specifically, the analyzing the angle defect degree of the corresponding radiating fin of the tubular aluminum radiator includes the following steps: d1, locating the center point position of the end face of each radiating fin in each tubular aluminum radiator and the center point position of the end face of each tubular aluminum radiator from the end face image of each tubular aluminum radiator.
D2, taking the central point as a base point as a central line, connecting the central line with the central point, thereby obtaining the central angle corresponding to each radiating fin in each tubular aluminum radiator, and marking as。
D3, calculating the angle defect degree of the corresponding radiating fin of each tubular aluminum radiator,/>Wherein->And->Respectively show the setting parametersThe central angle of the illumination and the total deviation of the central angle.
D4, if the angle defect degree of the corresponding radiating fin of a certain tubular aluminum radiator is larger than or equal to a set value, judging that the tubular aluminum radiator is an abnormal radiator, counting the number of the abnormal radiators in the target production batch, and recording as。
D5, extracting the maximum value from the angle defect degree of the corresponding cooling fin of each tubular aluminum radiator, and marking as。
D6, calculating the angle defect degree of the corresponding radiating fin of the tubular aluminum radiator,/>Wherein->And->The number of abnormal radiators and the degree of angle defect, respectively, of the set reference are shown in the specification>And->The set number of abnormal radiators and the set angular defect evaluation duty weight corresponding to the angular defect deviation are respectively represented.
Specifically, the heat dissipation information refers to a period of time corresponding to the time when each fin in each tubular aluminum radiator is reduced from the rated bearing temperature to the initial temperature.
Specifically, the performance defect degree of the tubular aluminum radiator in the target production batch is analyzed, and the specific analysis process is as follows: e1, positioning each radiator in each tubular aluminum radiator from apparent imagesThe indentation depth and the indentation contour area of each fin under rated bearing strength are extracted from the heat fin to obtain the maximum indentation depth and the maximum indentation contour area of each fin in each tubular aluminum radiator, which are respectively marked asAnd->。
E2, extracting the reference contour area of the radiating fin in the tubular aluminum radiator from the cloud database, and marking as。
E3, calculating corresponding hardness performance defect degree of each tubular aluminum radiator,Wherein->Indicating the indentation depth of the set reference->The total indentation profile area ratio for the set reference is shown.
E4, extracting the time length of each radiating fin in each tubular aluminum radiator from the heat radiation information, which corresponds to the time length of each radiating fin in each tubular aluminum radiator from the rated bearing temperature to the initial temperature, recording the time length of each radiating fin in each tubular aluminum radiator, and calculating the defect degree of the corresponding heat radiation performance of each tubular aluminum radiator。
E5, calculating the performance defect degree of the tubular aluminum radiator in the target production batch,Wherein, the method comprises the steps of, wherein,andthe set performance defect evaluation and the corresponding performance defect degree evaluation duty ratio weight of the heat dissipation performance defect evaluation are respectively shown.
Specifically, the defect degree of the heat dissipation performance corresponding to each tubular aluminum radiator is calculated, and the specific calculation process is as follows: f1, if the cooling time of a certain radiating fin in a certain tubular aluminum radiator is less than or equal to a set value, judging the radiating fin as a normal radiating fin, counting the number of the normal radiating fins in each tubular aluminum radiator, and recording as。
F2, extracting maximum value and minimum value from cooling time of each radiating fin in each tubular aluminum radiator, and respectively marking asAnd。
f3, calculating the defect degree of the heat radiation performance corresponding to each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,indicating the number of heat sinks to be used,indicating the normal fin count ratio for the set reference,andand respectively representing the set heat radiation performance defect degree evaluation duty ratio weight corresponding to the number duty ratio of the normal heat radiation fins and the extreme value difference of the cooling time.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects: (1) According to the invention, the structural defect degree, the dimensional defect degree and the performance defect degree of the tubular aluminum radiator are analyzed, so that the quality qualification condition of the tubular aluminum radiator in a target production batch is fed back, the problem of limitation existing in the current mold production defect analysis of the tubular aluminum radiator through the apparent layer surface and the dimensional layer is effectively solved, the error existing in the production defect analysis of the tubular aluminum radiator is reduced, the comprehensiveness and convincing performance of the production defect analysis are improved, the production efficiency of the tubular aluminum radiator is improved, and the consistency of the product quality is ensured.
(2) According to the invention, external defect analysis is performed through three dimensions of the dishing degree, the scratch degree and the coating uniformity of the tubular aluminum radiator, meanwhile, internal defect analysis is performed through pores, impurities and the like, so that double defect analysis of the tubular aluminum radiator structure from inside to outside is realized, the investigation strength of structural defects is improved, the structural defect condition of the tubular aluminum radiator is intuitively displayed, the coverage of the structural defect analysis of the tubular aluminum radiator is expanded, and meanwhile, the reliability of the structural defect analysis of the tubular aluminum radiator is improved.
(3) According to the invention, the space uniformity and the angle defect degree of the corresponding radiating fins of the tubular aluminum radiator are calculated, so that the size defect degree of the tubular aluminum radiator is analyzed, the size qualification of the tubular aluminum radiator is guaranteed, the production cost and the installation loss of the tubular aluminum radiator are reduced, and meanwhile, the accuracy of judging the size defect degree of the tubular aluminum radiator is improved.
(4) According to the invention, the hardness performance and the heat radiation performance of each tubular aluminum radiator are tested, and the hardness performance defect degree and the heat radiation performance defect degree are analyzed according to the tested apparent images and the heat radiation information, so that the performance defect degree of the tubular aluminum radiator is obtained, the multi-dimensional analysis of the performance defect degree of the tubular aluminum radiator is realized, the hidden danger investigation accuracy of the tubular aluminum radiator is improved, the reference property of the performance defect degree evaluation data of the tubular aluminum radiator is improved, and the stability of the heat radiation performance in subsequent use is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of the method of the present invention.
Fig. 2 is an end view schematically showing a tube aluminum radiator according to the present invention.
Description of the drawings: 1. center point of the end face of the radiating fin, 2 center point of the end face of the tubular aluminum radiator, 3 center angle, 4 center line.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a machine vision-based aluminum profile production defect analysis processing method, which comprises the following steps: s1, aluminum profile structural information acquisition and analysis: and respectively carrying out image acquisition on the external structure and the internal structure of each tubular aluminum radiator in the target production batch to obtain image information, and acquiring the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator, so as to analyze the structural defect degree of the tubular aluminum radiator in the target production batch.
The external structure image, the whole image, the end face image and the apparent image which are mentioned later are all acquired through a camera arranged in a test area of the tubular aluminum radiator, the internal structure image is acquired through scanning of an x-ray machine, and the coating thickness is acquired through a coating thickness meter.
In a specific embodiment of the present invention, the image information includes external structure image information and internal structure image information.
The external structure image information comprises the number of surface concave positions of each component radiating fin in each tubular aluminum radiator, the corresponding concave volume of each concave position, the number of surface scratch positions and the corresponding scratch length of each scratch position.
The internal structure image information comprises the number of internal air holes of each component radiating fin, the corresponding air hole area of each air hole, the number of internal impurity positions and the corresponding impurity area of each impurity position in each tubular aluminum radiator.
In a specific embodiment of the present invention, the analyzing the structural defect of the tubular aluminum radiator in the target production lot includes: a1, extracting the number of the surface concave parts of each component radiating fin and the concave volume corresponding to each concave part in each tubular aluminum radiator from the external structure image information, and respectively marking asAnd->Wherein->Indicates the number of the tubular aluminum radiator, +.>,/>Indicates the number of the cooling fin, ">,/>The number of the concave part is indicated,。
a2, calculating the dishing degree of each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,andthe total number of depressions and total volume of depressions for the set reference are shown respectively,andthe set total number of depressions and total volume of depressions are respectively expressed as corresponding depression evaluation duty ratio weight,representing natural constants.
A3, extracting the number of surface scratches of each component radiating fin and the corresponding scratch length of each scratch in each tubular aluminum radiator from the external structure image information, and analyzing the scratch degree of each tubular aluminum radiator in a similar way according to the analysis mode of the dent degree of each tubular aluminum radiator。
A4, calculating the coating uniformity of each tubular aluminum radiator according to the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator。
It should be noted that, the coating uniformity of each tubular aluminum radiator is calculated, and the specific calculation process is as follows: g1, recording the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator asWherein, the method comprises the steps of, wherein,the number of the sampling point is indicated,。
g2, calculating the uniformity of the coating of each radiating fin in each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,coating thickness deviation for the set reference is shown.
And G3, carrying out average calculation on the coating uniformity of each component radiating fin in each tubular aluminum radiator to obtain the average coating uniformity of each tubular aluminum radiator, and taking the average coating uniformity as the coating uniformity of each tubular aluminum radiator.
A5, calculating the defect degree of the external structure corresponding to each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,andrespectively represent the set pitsThe trap evaluation, scratch evaluation and coating uniformity evaluation correspond to the external structural defect level evaluation duty cycle.
A6, extracting the number of internal air holes of each component radiating fin, the air hole area corresponding to each air hole, the number of internal impurity positions and the impurity area corresponding to each impurity position in each tubular aluminum radiator from the internal structure image information, and analyzing the internal structure defect degree corresponding to each tubular aluminum radiator in a similar way according to the analysis mode of the external structure defect degree corresponding to each tubular aluminum radiator。
A7, calculating structural defect degree of each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,andrespectively representing the set structural defect degree evaluation duty ratio weight corresponding to the external structural defect evaluation and the internal structural defect evaluation.
A8, extracting the maximum structural defect degree from the structural defect degrees of the tubular aluminum heat sinks, and taking the maximum structural defect degree as the structural defect degree of the tubular aluminum heat sinks in the target production batch.
According to the embodiment of the invention, the external defect degree analysis is performed through three dimensions of the dishing degree, the scratch degree and the coating uniformity of the tubular aluminum radiator, meanwhile, the internal defect degree analysis is performed through pores, impurities and the like, so that the dual defect analysis of the tubular aluminum radiator structure from inside to outside is realized, the investigation strength of structural defects is improved, the structural defect condition of the tubular aluminum radiator is intuitively displayed, the coverage of the structural defect degree analysis of the tubular aluminum radiator is expanded, and the reliability of the structural defect degree analysis of the tubular aluminum radiator is improved.
S2, aluminum profile size information acquisition and analysis: and acquiring the integral image and the end face image of each tubular aluminum radiator, so as to analyze the size defect degree of the tubular aluminum radiator in the target production batch.
The whole image is an image of a fin layout surface, and the end surface image is an image of a surface perpendicular to the fin layout surface.
In a specific embodiment of the present invention, the analyzing the dimensional defect of the tubular aluminum radiator in the target production lot includes: b1, analyzing the space uniformity of the corresponding radiating fins of the tubular aluminum radiator according to the integral image of each tubular aluminum radiator。
In a specific embodiment of the present invention, the analyzing the space uniformity of the corresponding fin of the tubular aluminum radiator specifically includes: and C1, randomly positioning one radiating fin from the whole image of each tubular aluminum radiator, marking the radiating fin as a target radiating fin, sequentially ordering other radiating fins in a clockwise direction, and marking the radiating fins as reference radiating fins.
C2, arranging each monitoring point in the target radiating fins of each tubular aluminum radiator in turn from top to bottom, marking the target radiating fins as each target radiating fin, mapping each target radiating fin to each reference radiating fin to obtain mapping points corresponding to each target radiating fin in each reference radiating fin, further obtaining the distance between each target radiating fin in each tubular aluminum radiator and the mapping point corresponding to each target radiating fin in each reference radiating fin, marking the distance asWherein->Reference is made to the numbering of the heat sinks,,/>number representing mapping point->。
C3, calculating the space uniformity of the corresponding radiating fins of the tubular aluminum radiator,Wherein->Indicates the number of tubular aluminum type heat sinks, +.>And->Respectively represent the horizontal pitch deviation and the vertical pitch deviation of the set reference, +.>Represent the firstReference heat sink->Indicate->And mapping points.
B2, analyzing the angle defect degree of the corresponding radiating fin of the tubular aluminum radiator according to the end face image of each tubular aluminum radiator。
In a specific embodiment of the present invention, the analyzing the angle defect degree of the corresponding fin of the tubular aluminum radiator specifically includes: d1, locating the center point position of the end face of each radiating fin in each tubular aluminum radiator and the center point position of the end face of each tubular aluminum radiator from the end face image of each tubular aluminum radiator.
D2, taking the central point as a base point as a central line, connecting the central line with the central point, thereby obtaining the central angle corresponding to each radiating fin in each tubular aluminum radiator, and marking as。
D3, calculating the angle defect degree of the corresponding radiating fin of each tubular aluminum radiator,/>Wherein->And->The central angle and the total deviation of the central angle of the set reference are respectively indicated.
D4, if the angle defect degree of the corresponding radiating fin of a certain tubular aluminum radiator is larger than or equal to a set value, judging that the tubular aluminum radiator is an abnormal radiator, counting the number of the abnormal radiators in the target production batch, and recording as。
D5, extracting the maximum value from the angle defect degree of the corresponding cooling fin of each tubular aluminum radiator, and marking as。
D6, calculating the angle defect degree of the corresponding radiating fin of the tubular aluminum radiator,/>Wherein->And->The number of abnormal radiators and the degree of angle defect, respectively, of the set reference are shown in the specification>And->The set number of abnormal radiators and the set angular defect evaluation duty weight corresponding to the angular defect deviation are respectively represented.
B3, calculating the size defect degree of the tubular aluminum radiator in the target production batch,Wherein->And->And respectively representing the set size defect degree evaluation duty ratio weight corresponding to the space uniformity evaluation and the angle defect evaluation.
According to the embodiment of the invention, the dimensional defect degree of the tubular aluminum radiator is analyzed by calculating the space uniformity and the angle defect degree of the corresponding radiating fins of the tubular aluminum radiator, so that the dimensional qualification of the tubular aluminum radiator is ensured, the production cost and the installation loss of the tubular aluminum radiator are reduced, and meanwhile, the accuracy of judging the dimensional defect degree of the tubular aluminum radiator is improved.
S3, monitoring and analyzing the performance of the aluminum profile: and testing the hardness performance and the heat radiation performance of each tubular aluminum radiator, and monitoring the apparent images and the heat radiation information of the tests, so as to analyze the performance defect degree of the tubular aluminum radiator in the target production batch.
In a specific embodiment of the present invention, the heat dissipation information refers to a period of time corresponding to a period of time when each fin in each tubular aluminum radiator is reduced from a rated load temperature to an initial temperature.
The time length is obtained through background extraction of the set heat radiation performance test.
In a specific embodiment of the present invention, the analyzing the performance defect degree of the tubular aluminum radiator in the target production lot includes: e1, locating the indentation depth and the indentation contour area of each fin in each tubular aluminum radiator under the rated bearing strength from the apparent image, and extracting the maximum value from the indentation depth and the indentation contour area to obtain the maximum indentation depth and the maximum indentation contour area of each fin in each tubular aluminum radiator, which are respectively recorded asAnd->。
E2, extracting the reference contour area of the radiating fin in the tubular aluminum radiator from the cloud database, and marking as。
E3, calculating corresponding hardness performance defect degree of each tubular aluminum radiator,Wherein->Indicating the indentation depth of the set reference->The total indentation profile area ratio for the set reference is shown.
E4, extracting each tubular aluminum powder from heat dissipation informationThe cooling time length of each cooling fin in the heat radiator from the rated bearing temperature to the initial temperature is recorded as the cooling time length of each cooling fin in each tubular aluminum radiator, and the corresponding heat radiation performance defect degree of each tubular aluminum radiator is calculated。
In a specific embodiment of the present invention, the calculating the defect degree of the heat dissipation performance corresponding to each tubular aluminum radiator specifically includes: f1, if the cooling time of a certain radiating fin in a certain tubular aluminum radiator is less than or equal to a set value, judging the radiating fin as a normal radiating fin, counting the number of the normal radiating fins in each tubular aluminum radiator, and recording as。
F2, extracting maximum value and minimum value from cooling time of each radiating fin in each tubular aluminum radiator, and respectively marking asAnd。
f3, calculating the defect degree of the heat radiation performance corresponding to each tubular aluminum radiator,Wherein, the method comprises the steps of, wherein,indicating the number of heat sinks to be used,indicating the normal fin count ratio for the set reference,andand respectively representing the set heat radiation performance defect degree evaluation duty ratio weight corresponding to the number duty ratio of the normal heat radiation fins and the extreme value difference of the cooling time.
E5, calculating the performance defect degree of the tubular aluminum radiator in the target production batch,Wherein, the method comprises the steps of, wherein,andthe set performance defect evaluation and the corresponding performance defect degree evaluation duty ratio weight of the heat dissipation performance defect evaluation are respectively shown.
According to the embodiment of the invention, the hardness performance and the heat radiation performance of each tubular aluminum radiator are tested, and the hardness performance defect degree and the heat radiation performance defect degree are analyzed according to the tested apparent images and the heat radiation information, so that the performance defect degree of the tubular aluminum radiator is obtained, the multi-dimensional analysis of the performance defect degree of the tubular aluminum radiator is realized, the hidden trouble investigation accuracy of the tubular aluminum radiator is improved, the performance defect degree evaluation data referential property of the tubular aluminum radiator is improved, and the stability of the heat radiation performance in subsequent use is ensured.
S4, feeding back production defects of the aluminum profile: if the structural defect degree or the dimensional defect degree or the performance defect degree of the tubular aluminum radiator in the target production batch reaches the set value, judging that the quality of the tubular aluminum radiator in the target production batch is unqualified, and feeding back the production defect.
According to the embodiment of the invention, the structural defect degree, the dimensional defect degree and the performance defect degree of the tubular aluminum radiator are analyzed, so that the quality qualification condition of the tubular aluminum radiator in a target production batch is fed back, the problem of limitation existing in the current mold production defect analysis of the tubular aluminum radiator through the apparent layer surface and the dimensional layer is effectively solved, the error existing in the production defect analysis of the tubular aluminum radiator is reduced, the comprehensiveness and the convincing degree of the production defect analysis are improved, the production efficiency of the tubular aluminum radiator is improved, and the consistency of the product quality is ensured.
The foregoing is merely illustrative and explanatory of the principles of this invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of this invention or beyond the scope of this invention as defined in the claims.
Claims (8)
1. The analysis processing method for the production defects of the aluminum profile based on machine vision is characterized by comprising the following steps of:
s1, aluminum profile structural information acquisition and analysis: respectively carrying out image acquisition on the external structure and the internal structure of each tubular aluminum radiator in the target production batch to obtain image information, and acquiring the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator so as to analyze the structural defect degree of the tubular aluminum radiator in the target production batch;
the structural defect degree of the tubular aluminum radiator in the target production batch is analyzed, and the specific analysis process is as follows:
a1, extracting the number of the surface concave parts of each component radiating fin and the concave volume corresponding to each concave part in each tubular aluminum radiator from the external structure image information, and respectively marking asAnd->Wherein->The number of the tubular aluminum type radiator is shown,,/>indicates the number of the cooling fin, ">,/>Representing the number of the concave part,/-, and>;
a2, calculating the dishing degree of each tubular aluminum radiator,/>Wherein->And->Representing the total number of recesses and total volume of recesses, respectively, for the set reference, +.>And->The total number of the set depressions and the total volume of the depressions are respectively represented by the estimated depression ratio weight,/for the total volume of the depressions>Representing natural constants;
a3, extracting the number of surface scratches of each component radiating fin and the corresponding scratch length of each scratch in each tubular aluminum radiator from the external structure image information, and according to each tubular aluminumAnalysis method of dishing degree of radiator and analysis method of scratch degree of each tubular aluminum radiator;
A4, calculating the coating uniformity of each tubular aluminum radiator according to the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator;
The coating uniformity of each tubular aluminum radiator is calculated, and the specific calculation process is as follows: g1, recording the coating thickness of each sampling point on the surface of each component radiating fin in each tubular aluminum radiator asWherein->The number of the sampling point is indicated,;
g2, calculating the uniformity of the coating of each radiating fin in each tubular aluminum radiator,Wherein->Coating thickness deviation indicating a set reference;
g3, calculating the average value of the coating uniformity of each component radiating fin in each tubular aluminum radiator to obtain the average coating uniformity of each tubular aluminum radiator, and taking the average coating uniformity as the coating uniformity of each tubular aluminum radiator;
a5, calculating each tubular aluminum type heat dissipationCorresponding to the defect degree of the external structure,Wherein->And->Respectively representing the set duty ratio weights of the dent evaluation, scratch evaluation and coating uniformity evaluation corresponding to the defect degree evaluation of the external structure;
a6, extracting the number of internal air holes of each component radiating fin, the air hole area corresponding to each air hole, the number of internal impurity positions and the impurity area corresponding to each impurity position in each tubular aluminum radiator from the internal structure image information, and analyzing the internal structure defect degree corresponding to each tubular aluminum radiator in a similar way according to the analysis mode of the external structure defect degree corresponding to each tubular aluminum radiator;
A7, calculating structural defect degree of each tubular aluminum radiator,/>Wherein->Andrespectively representing the set structural defect degree evaluation duty ratio weights corresponding to the external structural defect evaluation and the internal structural defect evaluation;
a8, extracting the maximum structural defect degree from the structural defect degrees of the tubular aluminum radiators, and taking the maximum structural defect degree as the structural defect degree of the tubular aluminum radiators in the target production batch;
s2, aluminum profile size information acquisition and analysis: acquiring the integral image and the end face image of each tubular aluminum radiator, so as to analyze the size defect degree of the tubular aluminum radiator in the target production batch;
s3, monitoring and analyzing the performance of the aluminum profile: testing the hardness performance and the heat radiation performance of each tubular aluminum radiator, and monitoring the apparent images and the heat radiation information of the tests, so as to analyze the performance defect degree of the tubular aluminum radiator in the target production batch;
s4, feeding back production defects of the aluminum profile: if the structural defect degree or the dimensional defect degree or the performance defect degree of the tubular aluminum radiator in the target production batch reaches the set value, judging that the quality of the tubular aluminum radiator in the target production batch is unqualified, and feeding back the production defect.
2. The machine vision-based aluminum profile production defect analysis processing method as claimed in claim 1, wherein the method comprises the following steps of: the image information includes external structure image information and internal structure image information;
the external structure image information comprises the number of surface concave positions of each component radiating fin in each tubular aluminum radiator, the corresponding concave volume of each concave position, the number of surface scratch positions and the corresponding scratch length of each scratch position;
the internal structure image information comprises the number of internal air holes of each component radiating fin, the corresponding air hole area of each air hole, the number of internal impurity positions and the corresponding impurity area of each impurity position in each tubular aluminum radiator.
3. The machine vision-based aluminum profile production defect analysis processing method as claimed in claim 1, wherein the method comprises the following steps of: the dimensional defect degree of the tubular aluminum radiator in the target production batch is analyzed, and the specific analysis process is as follows:
b1, according to the whole picture of each tubular aluminum radiatorLike, analyze the interval uniformity degree of the corresponding fin of tubular aluminium type radiator;
B2, analyzing the angle defect degree of the corresponding radiating fin of the tubular aluminum radiator according to the end face image of each tubular aluminum radiator;
B3, calculating the size defect degree of the tubular aluminum radiator in the target production batch,/>Wherein->And->And respectively representing the set size defect degree evaluation duty ratio weight corresponding to the space uniformity evaluation and the angle defect evaluation.
4. A machine vision-based aluminum profile production defect analysis processing method as claimed in claim 3, wherein: the space uniformity of the corresponding radiating fins of the analysis tubular aluminum radiator is as follows:
c1, randomly positioning one radiating fin from the whole image of each tubular aluminum radiator, marking the radiating fin as a target radiating fin, sequentially ordering other radiating fins in a clockwise direction, and marking the radiating fins as reference radiating fins;
c2, arranging each monitoring point in the target radiating fins of each tubular aluminum radiator in turn from top to bottom, marking the monitoring points as each target radiating point, mapping each target radiating point to each reference radiating fin, and obtaining a mapping corresponding to each target radiating point in each reference radiating finFurther, the distance between each target heat dissipation point in the target heat dissipation fins of each tubular aluminum radiator and the corresponding mapping point of each target heat dissipation point in each reference heat dissipation fin is obtained and recorded asWherein->Indicates the number of the reference fin->,/>Number representing mapping point->;
C3, calculating the space uniformity of the corresponding radiating fins of the tubular aluminum radiator,Wherein->Indicates the number of tubular aluminum type heat sinks, +.>And->Respectively represent the horizontal pitch deviation and the vertical pitch deviation of the set reference, +.>Indicate->Reference heat sink->Indicate->And mapping points.
5. A machine vision-based aluminum profile production defect analysis processing method as claimed in claim 3, wherein: the angle defect degree of the corresponding radiating fin of the analysis tubular aluminum radiator comprises the following specific analysis processes:
d1, locating the center point position of the end face of each radiating fin in each tubular aluminum radiator and the center point position of the end face of each tubular aluminum radiator from the end face image of each tubular aluminum radiator;
d2, taking the central point as a base point as a central line, connecting the central line with the central point, thereby obtaining the central angle corresponding to each radiating fin in each tubular aluminum radiator, and marking as;
D3, calculating the angle defect degree of the corresponding radiating fin of each tubular aluminum radiator,/>Wherein->And->Respectively representing the central angle of the set reference and the total deviation of the central angle;
d4, if the angle defect degree of the corresponding radiating fin of a certain tubular aluminum radiator is larger than or equal to a set value, thenJudging the tubular aluminum radiator as an abnormal radiator, counting the number of the abnormal radiators in the target production batch, and recording as;
D5, extracting the maximum value from the angle defect degree of the corresponding cooling fin of each tubular aluminum radiator, and marking as;
D6, calculating the angle defect degree of the corresponding radiating fin of the tubular aluminum radiator,/>Wherein->And->The number of abnormal radiators and the degree of angle defect, respectively, of the set reference are shown in the specification>And->The set number of abnormal radiators and the set angular defect evaluation duty weight corresponding to the angular defect deviation are respectively represented.
6. The machine vision-based aluminum profile production defect analysis processing method as claimed in claim 4, wherein the method comprises the following steps of: the heat dissipation information refers to the time period for each cooling fin in each tubular aluminum radiator to be reduced from the rated bearing temperature to the initial temperature.
7. The machine vision-based aluminum profile production defect analysis processing method as claimed in claim 6, wherein the method comprises the following steps of: the performance defect degree of the tubular aluminum radiator in the target production batch is analyzed, and the specific analysis process is as follows:
e1, locating the indentation depth and the indentation contour area of each fin in each tubular aluminum radiator under the rated bearing strength from the apparent image, and extracting the maximum value from the indentation depth and the indentation contour area to obtain the maximum indentation depth and the maximum indentation contour area of each fin in each tubular aluminum radiator, which are respectively recorded asAnd->;
E2, extracting the reference contour area of the radiating fin in the tubular aluminum radiator from the cloud database, and marking as;
E3, calculating corresponding hardness performance defect degree of each tubular aluminum radiator,Wherein->Indicating the indentation depth of the set reference->Representing the total indentation profile area ratio of the set reference;
e4, extracting the time length of each radiating fin in each tubular aluminum radiator from the heat radiation information, which corresponds to the time length of each radiating fin in each tubular aluminum radiator from the rated bearing temperature to the initial temperature, recording the time length of each radiating fin in each tubular aluminum radiator, and calculating the defect degree of the corresponding heat radiation performance of each tubular aluminum radiator;
E5, calculating the performance defect degree of the tubular aluminum radiator in the target production batch,Wherein->And->The set performance defect evaluation and the corresponding performance defect degree evaluation duty ratio weight of the heat dissipation performance defect evaluation are respectively shown.
8. The machine vision-based aluminum profile production defect analysis processing method as claimed in claim 7, wherein the method comprises the following steps of: the defect degree of the heat radiation performance corresponding to each tubular aluminum radiator is calculated, and the specific calculation process is as follows:
f1, if the cooling time of a certain radiating fin in a certain tubular aluminum radiator is less than or equal to a set value, judging the radiating fin as a normal radiating fin, counting the number of the normal radiating fins in each tubular aluminum radiator, and recording as;
F2, extracting maximum value and minimum value from cooling time of each radiating fin in each tubular aluminum radiator, and respectively marking asAnd->;
F3, calculating each tubular aluminum radiator pairDefect degree of heat dissipation performance,Wherein->Indicates the number of cooling fins->Normal fin number ratio indicating the set reference, +.>And->And respectively representing the set heat radiation performance defect degree evaluation duty ratio weight corresponding to the number duty ratio of the normal heat radiation fins and the extreme value difference of the cooling time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311196709.9A CN116930196B (en) | 2023-09-18 | 2023-09-18 | Machine vision-based aluminum profile production defect analysis processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311196709.9A CN116930196B (en) | 2023-09-18 | 2023-09-18 | Machine vision-based aluminum profile production defect analysis processing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116930196A CN116930196A (en) | 2023-10-24 |
CN116930196B true CN116930196B (en) | 2023-12-22 |
Family
ID=88381106
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311196709.9A Active CN116930196B (en) | 2023-09-18 | 2023-09-18 | Machine vision-based aluminum profile production defect analysis processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116930196B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117288099B (en) * | 2023-11-27 | 2024-01-30 | 江苏海德曼新材料股份有限公司 | Machine vision-based aluminum-plastic composite board production quality detection and analysis method |
CN117367516B (en) * | 2023-12-04 | 2024-02-23 | 江苏海德曼新材料股份有限公司 | Aluminum-plastic composite board performance detection system based on multidimensional test |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR19980075602A (en) * | 1997-03-31 | 1998-11-16 | 윤종용 | How to design the heatsink |
US6330354B1 (en) * | 1997-05-01 | 2001-12-11 | International Business Machines Corporation | Method of analyzing visual inspection image data to find defects on a device |
JP2004038885A (en) * | 2002-07-08 | 2004-02-05 | Adoin Kenkyusho:Kk | Image feature learning type defect detection method, defect detection device and defect detection program |
CN101504689A (en) * | 2009-03-26 | 2009-08-12 | 北京航空航天大学 | Radiator optimizing parameter confirming method and radiator with optimizing parameter |
WO2010061263A1 (en) * | 2008-11-28 | 2010-06-03 | Rag-All S.P.A. | Fin radiator made of mechanically connected aluminium section bars |
WO2012117468A1 (en) * | 2011-02-28 | 2012-09-07 | 日本精工株式会社 | Method for evaluating strength of aluminum die-cast part, aluminum die-cast part, and method for detecting defect of aluminum die-cast part |
CN104458748A (en) * | 2013-09-25 | 2015-03-25 | 中国科学院沈阳自动化研究所 | Aluminum profile surface defect detecting method based on machine vision |
CN106290394A (en) * | 2016-09-30 | 2017-01-04 | 华南理工大学 | A kind of cpu heat aluminium extruded forming defect detecting system and detection method |
CN108759678A (en) * | 2018-07-19 | 2018-11-06 | 广州富唯电子科技有限公司 | Automatic measuring equipment and its measurement method in heat sink sizes and flatness line |
CN111174719A (en) * | 2020-02-02 | 2020-05-19 | 肖正富 | Cooling fin size detection system and method |
CN112345539A (en) * | 2020-11-05 | 2021-02-09 | 菲特(天津)检测技术有限公司 | Aluminum die casting surface defect detection method based on deep learning |
CN112945777A (en) * | 2021-03-10 | 2021-06-11 | 辽宁忠旺集团有限公司 | Online automatic detection system and method for hardness of aluminum alloy profile |
CN114923525A (en) * | 2022-05-27 | 2022-08-19 | 四川具斯德科技有限责任公司 | Online detection, analysis and management system for defects of wires and cables based on artificial intelligence |
CN115876288A (en) * | 2023-02-27 | 2023-03-31 | 泰安奇正电子科技有限公司 | Electronic instrument fault analysis method and system based on big data |
CN116563280A (en) * | 2023-07-07 | 2023-08-08 | 深圳市鑫典金光电科技有限公司 | Composite copper heat dissipation bottom plate processing detection method and system based on data analysis |
CN116703275A (en) * | 2023-06-07 | 2023-09-05 | 荆州市到乐物流有限公司 | Logistics vehicle scheduling method based on waybill data analysis |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109883857B (en) * | 2019-03-19 | 2021-10-26 | 松下压缩机(大连)有限公司 | Method for rapidly detecting internal defects of die-casting aluminum alloy |
-
2023
- 2023-09-18 CN CN202311196709.9A patent/CN116930196B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR19980075602A (en) * | 1997-03-31 | 1998-11-16 | 윤종용 | How to design the heatsink |
US6330354B1 (en) * | 1997-05-01 | 2001-12-11 | International Business Machines Corporation | Method of analyzing visual inspection image data to find defects on a device |
JP2004038885A (en) * | 2002-07-08 | 2004-02-05 | Adoin Kenkyusho:Kk | Image feature learning type defect detection method, defect detection device and defect detection program |
WO2010061263A1 (en) * | 2008-11-28 | 2010-06-03 | Rag-All S.P.A. | Fin radiator made of mechanically connected aluminium section bars |
CN101504689A (en) * | 2009-03-26 | 2009-08-12 | 北京航空航天大学 | Radiator optimizing parameter confirming method and radiator with optimizing parameter |
WO2012117468A1 (en) * | 2011-02-28 | 2012-09-07 | 日本精工株式会社 | Method for evaluating strength of aluminum die-cast part, aluminum die-cast part, and method for detecting defect of aluminum die-cast part |
CN104458748A (en) * | 2013-09-25 | 2015-03-25 | 中国科学院沈阳自动化研究所 | Aluminum profile surface defect detecting method based on machine vision |
CN106290394A (en) * | 2016-09-30 | 2017-01-04 | 华南理工大学 | A kind of cpu heat aluminium extruded forming defect detecting system and detection method |
CN108759678A (en) * | 2018-07-19 | 2018-11-06 | 广州富唯电子科技有限公司 | Automatic measuring equipment and its measurement method in heat sink sizes and flatness line |
CN111174719A (en) * | 2020-02-02 | 2020-05-19 | 肖正富 | Cooling fin size detection system and method |
CN112345539A (en) * | 2020-11-05 | 2021-02-09 | 菲特(天津)检测技术有限公司 | Aluminum die casting surface defect detection method based on deep learning |
CN112945777A (en) * | 2021-03-10 | 2021-06-11 | 辽宁忠旺集团有限公司 | Online automatic detection system and method for hardness of aluminum alloy profile |
CN114923525A (en) * | 2022-05-27 | 2022-08-19 | 四川具斯德科技有限责任公司 | Online detection, analysis and management system for defects of wires and cables based on artificial intelligence |
CN115876288A (en) * | 2023-02-27 | 2023-03-31 | 泰安奇正电子科技有限公司 | Electronic instrument fault analysis method and system based on big data |
CN116703275A (en) * | 2023-06-07 | 2023-09-05 | 荆州市到乐物流有限公司 | Logistics vehicle scheduling method based on waybill data analysis |
CN116563280A (en) * | 2023-07-07 | 2023-08-08 | 深圳市鑫典金光电科技有限公司 | Composite copper heat dissipation bottom plate processing detection method and system based on data analysis |
Non-Patent Citations (3)
Title |
---|
Application of Shearlet transform to classification of surface defects for metals;Ke Xu 等;Image and Vision Computing;第35卷;23-30 * |
基于计算机视觉的管壳表面划痕检测技术研究;李哲毓;高明;马卫红;;应用光学(第06期);802-805 * |
硬质相对6061铝合金异型散热型材表面质量的影响;罗淞;林高用;曾菊花;孙利平;邹艳明;周玉雄;;中国有色金属学报(第07期);1521-1526 * |
Also Published As
Publication number | Publication date |
---|---|
CN116930196A (en) | 2023-10-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116930196B (en) | Machine vision-based aluminum profile production defect analysis processing method | |
US20210063376A1 (en) | Method for automatic quantitative statistical distribution characterization of dendrite structures in a full view field of metal materials | |
CN115184368B (en) | Casting defect detection control system | |
CN111220077A (en) | Visual detection device and method for installation size of threaded hole of radiator | |
CN109990711B (en) | Appearance quality detection method for punched nickel-plated steel strip | |
CN116758067B (en) | Metal structural member detection method based on feature matching | |
CN112001880B (en) | Method and device for detecting characteristic parameters of planar member | |
CN113240667A (en) | Automobile mold plane crack detection method based on image processing | |
CN116188458A (en) | Intelligent recognition method for abnormal deformation of surface of die-casting die of automobile part | |
CN110544276A (en) | Least square method ellipse fitting piston skirt maximum point size measurement method | |
CN116645364A (en) | Alloy steel casting air hole defect detection method based on image data | |
CN108827197B (en) | Linear array industrial CT homogeneous material size measurement method capable of reducing edge degradation influence | |
CN117367516B (en) | Aluminum-plastic composite board performance detection system based on multidimensional test | |
CN111815580B (en) | Image edge recognition method and small module gear module detection method | |
CN116432052B (en) | Quality detection method for clamp for new energy automobile die | |
CN116740053A (en) | Management system of intelligent forging processing production line | |
CN117781882A (en) | Industrial hardware detects MES data acquisition analysis system | |
CN117173177A (en) | Image-based metal shell optical size detection method and system | |
CN114998329B (en) | Precision stamping quality analysis system of radio frequency shielding case of electronic communication equipment | |
CN114862816A (en) | Glitch detection method, system, and computer-readable storage medium | |
CN114881952A (en) | Casting defect area detection and edge accurate segmentation method | |
CN110411380B (en) | Non-contact surface roughness measurement method based on wavelet packet texture analysis | |
WO2018070710A1 (en) | Method for detecting defect in carbide insert by using product symmetry and image similarity | |
CN107462221B (en) | Automatic measuring method for fisheye characteristics | |
CN117741090B (en) | Quality defect detection method for precision casting of gearbox |
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 |