CN116503365A - Machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method - Google Patents
Machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method Download PDFInfo
- Publication number
- CN116503365A CN116503365A CN202310489033.6A CN202310489033A CN116503365A CN 116503365 A CN116503365 A CN 116503365A CN 202310489033 A CN202310489033 A CN 202310489033A CN 116503365 A CN116503365 A CN 116503365A
- Authority
- CN
- China
- Prior art keywords
- acquired image
- quality
- evaluation coefficient
- finned tube
- quality evaluation
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000009785 tube rolling Methods 0.000 title claims abstract description 19
- 238000012544 monitoring process Methods 0.000 title claims abstract description 17
- 238000013441 quality evaluation Methods 0.000 claims abstract description 38
- 238000005096 rolling process Methods 0.000 claims abstract description 6
- 238000010191 image analysis Methods 0.000 claims abstract description 4
- 230000007547 defect Effects 0.000 abstract description 11
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000002950 deficient Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000001125 extrusion Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000000641 cold extrusion Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 210000004262 dental pulp cavity Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method, which can effectively monitor the surface quality problems of the fin surface in the conditions of burrs, fin deformation, local damage of the fin, whole fin damage and the like in the rolling production process of the finned tube, realize the real-time identification of the surface defects of the three-dimensional condensing finned tube, effectively save resources and save labor time cost; the method comprises the following steps: s1, acquiring images of the rolling surface of a three-dimensional condensing finned tube in real time; s2, carrying out image analysis on the acquired image based on an improved YOLOv7 algorithm to obtain a quality evaluation coefficient corresponding to the acquired image; s3, comparing the quality evaluation coefficient corresponding to the acquired image with a set quality evaluation coefficient threshold, if the quality evaluation coefficient is larger than the set threshold, judging the quality state of the acquired image to be qualified, and returning to the step S1 to continuously acquire the next image; if the acquired image quality state is smaller than the set threshold value, judging that the acquired image quality state is unqualified, and giving an alarm.
Description
Technical Field
The invention relates to the technical field of three-dimensional condensing finned tube rolling, in particular to a machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method.
Background
In the refrigeration, heating and petrochemical industries, three-dimensional finned tubes based on the third-generation heat transfer technology are regarded as important energy-saving and emission-reducing technologies for reducing industrial energy consumption due to excellent heat transfer enhancement effects. At present, a three-dimensional condensing finned tube is rolled, particularly by a three-roller cutting cold extrusion molding technology, wherein the outer surface of a metal base tube is directly manufactured into a fin structure by extrusion molding, but the outer surface of the rolled finned tube often causes the surface quality problems of curling, fracture and the like of fins due to various reasons such as no alignment of the position of the finned tube in the cutter extrusion process; the related research on the surface quality problem of the finned tube is widely paid attention to by enterprises and scientific research fields, so that the surface quality problem of the finned tube needs to be monitored in real time, the processing is stopped in time, and resources are saved.
However, the current main current fin tube surface quality problem monitoring generally detects related defects such as surface curling and breakage through an independent quality detection process after the fin tube rolling is completed, and the post-inspection method needs to be performed after the rolling is completed, and once the situation such as fin breakage is inspected, scrapping treatment is usually performed, so that a great deal of resources and labor time cost are wasted.
Disclosure of Invention
Aiming at the defects of the existing three-dimensional condensing finned tube rolling technology, the invention provides a machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method, which can effectively monitor the surface quality problems of the finned tube in the conditions of burrs, fin deformation, local damage of fins, whole fin damage and the like on the surface of the finned tube in the rolling production process, realizes the real-time identification of the surface defects of the three-dimensional condensing finned tube, can effectively save resources and save labor time cost.
The aim of the invention can be achieved by the following technical scheme:
a machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method comprises the following steps:
s1, acquiring images of the rolling surface of a three-dimensional condensing finned tube in real time;
s2, carrying out image analysis on the acquired image based on an improved YOLOv7 algorithm to obtain a quality evaluation coefficient corresponding to the acquired image;
s3, comparing the quality evaluation coefficient corresponding to the acquired image with a set quality evaluation coefficient threshold, if the quality evaluation coefficient is larger than the set threshold, judging the quality state of the acquired image to be qualified, and returning to the step S1 to continuously acquire the next image; if the acquired image quality state is smaller than the set threshold value, judging that the acquired image quality state is unqualified, and giving an alarm.
Further, in the step S2, the quality evaluation coefficient corresponding to the defect-free image is 1, and the quality evaluation coefficient corresponding to the damaged image in the whole area is 0;
further, in the step S3, the set quality evaluation coefficient threshold is divided into a first threshold and a second threshold, where the value of the first threshold is smaller than the value of the second threshold;
further, if the quality evaluation coefficient corresponding to the acquired image is larger than the value of the second threshold value, judging that the quality state of the acquired image is qualified; if the quality evaluation coefficient corresponding to the acquired image is smaller than the value of the second threshold value, judging that the quality state of the acquired image is unqualified;
further, when the quality state of the acquired image is unqualified, if the quality evaluation coefficient corresponding to the acquired image is smaller than the second threshold and larger than the numerical value of the first threshold, judging that the quality of the unqualified acquired image is in a non-serious state; if the quality evaluation coefficient corresponding to the acquired image is smaller than the value of the first threshold value, judging that the quality of the unqualified acquired image is in a serious state;
further, when the quality of the unqualified acquired image is judged to be in a non-serious state, alarming by using a normally-on and intermittent peaked indicator lamp; when the quality of the unqualified acquired image is judged to be in a serious state, the alarm is given by the continuous ringing and the normally-on indication lamp.
The invention has the advantages that the invention can collect images in the three-dimensional condensing finned tube rolling process, judge whether defects occur in the production process in real time, alarm and process the defective finned tube in time, avoid scrapping the whole finned tube because of excessive surface quality defects after the subsequent processing is finished, eliminate the waste of materials, save a great deal of labor cost, have high processing speed, and have stable and reliable method, avoid subjectivity of the existing manual detection analysis, further improve the accuracy of the surface quality analysis of the finned tube, and have better economic use value.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
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 three-dimensional condensing finned tube rolling real-time monitoring method, which comprises the following steps:
s1, acquiring a three-dimensional condensing finned tube rolling surface image in real time in a processing process by using an HF868-2 high-definition camera, and transmitting the image to a man-machine interaction interface written based on PyQt 5;
s2, carrying out image analysis on the acquired image based on an improved YOLOv7 algorithm (which is an existing algorithm) according to the defect types (fuzzing, fin deformation, fin local damage and whole fin damage) and defect areas (points, local parts and whole sheets) corresponding to the fin tube so as to obtain a quality evaluation coefficient corresponding to the acquired image;
wherein the value of the quality evaluation coefficient is between 0 and 1;
the quality evaluation coefficient corresponding to the defect-free image is 1, and the quality evaluation coefficient corresponding to the whole area damaged image is 0;
s3, comparing the quality evaluation coefficient corresponding to the acquired image with a set quality evaluation coefficient threshold, if the quality evaluation coefficient is larger than the set threshold, judging the quality state of the acquired image to be qualified, and returning to the step S1 to continuously acquire the next image; if the acquired image quality state is judged to be unqualified if the acquired image quality state is smaller than the set threshold value, real-time prompt and alarm are realized through an alarm system of the developed human-computer interaction interface.
Specifically, in step S3, the set quality evaluation coefficient threshold is divided into a first threshold and a second threshold, and the value of the first threshold is smaller than the value of the second threshold;
if the quality evaluation coefficient corresponding to the acquired image is larger than the value of the second threshold value, judging that the quality state of the acquired image is qualified; if the quality evaluation coefficient corresponding to the acquired image is smaller than the value of the second threshold value, judging that the quality state of the acquired image is unqualified;
particularly, when the quality state of the collected image is unqualified, if the quality evaluation coefficient corresponding to the collected image is smaller than a second threshold value and larger than a numerical value of a first threshold value, judging that the quality of the unqualified collected image is in a non-serious state, and alarming by using an indicator lamp which is normally on and intermittently sounds for 2 minutes; if the quality evaluation coefficient corresponding to the acquired image is smaller than the value of the first threshold, judging that the quality of the unqualified acquired image is in a serious state, and alarming by using an indicator lamp which is always on and continuously sounds for 5 minutes.
In summary, after the image quality state is obtained, the man-machine interaction interface can transmit an abnormal signal to the existing control system, and the control system can judge whether to immediately stop cutter processing or to process the whole root canal and then replace the cutter according to the severity.
The method can monitor defects of burrs, fin deformation, local damage of fins, whole fin damage and the like on the surface of the fin tube caused by cutter damage in the three-dimensional condensing fin tube rolling process in real time, judges whether the defects are generated in the production process in real time, has high processing speed, and is stable and reliable; on the other hand, the limitation that the monitoring analysis is still carried out manually at present is broken, the monitoring force is enhanced, subjectivity of manual monitoring analysis is avoided, the accuracy of the surface quality analysis of the finned tube is further improved, the defective finned tube can be timely alarmed and treated, the fact that the whole finned tube is scrapped due to excessive surface quality defects after the follow-up processing is finished is avoided, the waste of materials is avoided, and a large amount of labor cost is saved.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (6)
1. A machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method is characterized by comprising the following steps of: the method comprises the following steps:
s1, acquiring images of the rolling surface of a three-dimensional condensing finned tube in real time;
s2, carrying out image analysis on the acquired image based on an improved YOLOv7 algorithm to obtain a quality evaluation coefficient corresponding to the acquired image;
s3, comparing the quality evaluation coefficient corresponding to the acquired image with a set quality evaluation coefficient threshold, if the quality evaluation coefficient is larger than the set threshold, judging the quality state of the acquired image to be qualified, and returning to the step S1 to continuously acquire the next image; if the acquired image quality state is smaller than the set threshold value, judging that the acquired image quality state is unqualified, and giving an alarm.
2. The machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method is characterized by comprising the following steps of: in the step S2, the quality evaluation coefficient corresponding to the defect-free image is 1, and the quality evaluation coefficient corresponding to the damaged image in the whole area is 0.
3. The machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method is characterized by comprising the following steps of: in the step S3, the set quality evaluation coefficient threshold is divided into a first threshold and a second threshold, and the value of the first threshold is smaller than the value of the second threshold.
4. A machine vision based three-dimensional condensing finned tube rolling real-time monitoring method according to claim 3, wherein the method comprises the following steps: if the quality evaluation coefficient corresponding to the acquired image is larger than the value of the second threshold value, judging that the quality state of the acquired image is qualified; and if the quality evaluation coefficient corresponding to the acquired image is smaller than the value of the second threshold value, judging that the quality state of the acquired image is unqualified.
5. The machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method is characterized by comprising the following steps of: when the quality state of the acquired image is unqualified, if the quality evaluation coefficient corresponding to the acquired image is smaller than the second threshold value and larger than the numerical value of the first threshold value, judging that the quality of the unqualified acquired image is in a non-serious state; and if the quality evaluation coefficient corresponding to the acquired image is smaller than the value of the first threshold value, judging that the quality of the unqualified acquired image is in a serious state.
6. The machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method is characterized by comprising the following steps of: when the quality of the unqualified acquired image is judged to be in a non-serious state, alarming by using a normally-on and intermittent alarm of an indicator lamp; when the quality of the unqualified acquired image is judged to be in a serious state, the alarm is given by the continuous ringing and the normally-on indication lamp.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310489033.6A CN116503365A (en) | 2023-05-04 | 2023-05-04 | Machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310489033.6A CN116503365A (en) | 2023-05-04 | 2023-05-04 | Machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116503365A true CN116503365A (en) | 2023-07-28 |
Family
ID=87328070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310489033.6A Pending CN116503365A (en) | 2023-05-04 | 2023-05-04 | Machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503365A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889837A (en) * | 2019-11-25 | 2020-03-17 | 东华大学 | Cloth flaw detection method with flaw classification function |
| CN112258470A (en) * | 2020-10-20 | 2021-01-22 | 上海大学 | Intelligent industrial image critical compression rate analysis system and method based on defect detection |
| CN112767327A (en) * | 2021-01-08 | 2021-05-07 | 上海大学 | Image quality management system and method based on neural network |
| CN115588000A (en) * | 2022-10-28 | 2023-01-10 | 上海恺皓科技有限公司 | Method and system for evaluating hot press molding process quality of shell-shaped dental instrument |
| CN115791800A (en) * | 2022-12-07 | 2023-03-14 | 北京科技大学 | Concrete surface crack angle monitoring method based on infinitesimal method |
| CN115857520A (en) * | 2023-02-15 | 2023-03-28 | 北京航空航天大学 | Unmanned aerial vehicle carrier landing state monitoring method based on combination of vision and ship state |
| CN115983687A (en) * | 2022-12-22 | 2023-04-18 | 广州海秀敏网络科技有限公司 | Intelligent detection management system and method for quality of cold-rolled strip steel |
-
2023
- 2023-05-04 CN CN202310489033.6A patent/CN116503365A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889837A (en) * | 2019-11-25 | 2020-03-17 | 东华大学 | Cloth flaw detection method with flaw classification function |
| CN112258470A (en) * | 2020-10-20 | 2021-01-22 | 上海大学 | Intelligent industrial image critical compression rate analysis system and method based on defect detection |
| CN112767327A (en) * | 2021-01-08 | 2021-05-07 | 上海大学 | Image quality management system and method based on neural network |
| CN115588000A (en) * | 2022-10-28 | 2023-01-10 | 上海恺皓科技有限公司 | Method and system for evaluating hot press molding process quality of shell-shaped dental instrument |
| CN115791800A (en) * | 2022-12-07 | 2023-03-14 | 北京科技大学 | Concrete surface crack angle monitoring method based on infinitesimal method |
| CN115983687A (en) * | 2022-12-22 | 2023-04-18 | 广州海秀敏网络科技有限公司 | Intelligent detection management system and method for quality of cold-rolled strip steel |
| CN115857520A (en) * | 2023-02-15 | 2023-03-28 | 北京航空航天大学 | Unmanned aerial vehicle carrier landing state monitoring method based on combination of vision and ship state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TW200951752A (en) | A method for prognostic maintenance in semiconductor manufacturing | |
| CN111783672A (en) | Image feature identification method for improving bridge dynamic displacement precision | |
| JP5441824B2 (en) | Manufacturing condition determination system for metal strip materials | |
| CN114571285A (en) | Method for intelligently identifying micro-tipping of extrusion tap | |
| CN116503365A (en) | Machine vision-based three-dimensional condensing finned tube rolling real-time monitoring method | |
| CN114993229A (en) | Multi-sensor data fusion-based ovality online detection method | |
| CN114742798A (en) | Disc shear tool changing time prediction system and method based on shear blade wear detection | |
| Wu et al. | Design of online surface inspection system of hot rolled strips | |
| AU2019320328A1 (en) | Optoelectronic solar cell test system for an in-line solar cell production plant, and method for optimising the in-line production of solar cells using an optoelectronic solar cell test system of this type | |
| CN117333727A (en) | Conveyer belt wearing and tearing area discernment analysis system based on visual image processing technique | |
| CN116346870B (en) | Industrial Internet of things system based on real-time monitoring of processing quality and control method | |
| CN116664916A (en) | Image-based pipe welding defect detection method | |
| CN118122785B (en) | Intelligent monitoring system for wire rod rolling production and manufacturing | |
| CN115338693B (en) | Machining loss avoiding method and system of automatic lathe | |
| CN118395741B (en) | AI intelligent terminal data processing system for intelligent pipe network leakage monitoring | |
| CN112404987B (en) | Manufacturing system and process of automobile wheel steel ring | |
| CN118095663B (en) | Intelligent safety lamp system for production workshop management | |
| CN117762095B (en) | Petroleum refining process monitoring system based on Internet of things | |
| TWI814677B (en) | Defect detection method and defect detection system using the same | |
| CN117250209A (en) | Automatic optical screening image processing system and method for pipeline connecting ring | |
| CN117474332A (en) | Production line spot welding operation diagnosis and detection system | |
| CN116720770A (en) | Quality monitoring management method | |
| CN115859130A (en) | Intelligent early warning method and early warning system for typical faults of hot rolled strip steel layer cooling section | |
| CN114653784A (en) | Straightening machine roller system online fault diagnosis system and method | |
| Ortega | Metal Forming Process Efficiency Improvement Based on AI Services |
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 |