CN112801391A - Artificial intelligent scrap steel impurity deduction rating method and system - Google Patents
Artificial intelligent scrap steel impurity deduction rating method and system Download PDFInfo
- Publication number
- CN112801391A CN112801391A CN202110155709.9A CN202110155709A CN112801391A CN 112801391 A CN112801391 A CN 112801391A CN 202110155709 A CN202110155709 A CN 202110155709A CN 112801391 A CN112801391 A CN 112801391A
- Authority
- CN
- China
- Prior art keywords
- scrap
- image
- scrap steel
- steel
- layered
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 104
- 239000010959 steel Substances 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000012535 impurity Substances 0.000 title claims abstract description 22
- 239000000463 material Substances 0.000 claims abstract description 43
- 238000007689 inspection Methods 0.000 claims abstract description 18
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 15
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 238000013145 classification model Methods 0.000 claims abstract description 9
- 230000011218 segmentation Effects 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000007635 classification algorithm Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012372 quality testing Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 241000252254 Catostomidae Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 239000002436 steel type Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Manufacturing & Machinery (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Factory Administration (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an artificial intelligence scrap steel impurity-deducting rating method and system, which comprises the steps of obtaining scrap steel and confirming the material type of the scrap steel; classifying through a whole image classification model to obtain different material types and image ratios thereof; sampling layered images by using an intelligent camera module to obtain layered images of different material types; utilizing a semantic segmentation model to carry out image component proportion division on the layered image; and analyzing the grade and the deduction amount of the image component according to the proportion of the image component by using an information statistical module, and counting the summary result. The invention can realize intelligent scheduling to scrap steel grade judgment after the truck enters the field, has intelligent and automatic impurity deduction full flow, can remotely and simultaneously monitor a plurality of unloading areas, improves the working environment, reduces the labor intensity and improves the quality inspection efficiency. Unnecessary losses due to human factors are also avoided.
Description
Technical Field
The invention relates to the technical field of scrap steel impurity deduction rating, in particular to an artificial intelligent scrap steel impurity deduction rating method and system.
Background
At present, the total amount of the steel scrap generated in the world every year is 3-4 hundred million tons, which accounts for about 45-50% of the total steel production, and statistical data show that the steel production in China is leading globally, but the steel scrap utilization rate is only 21.2%, which is far lower than 72.1% in the United states, and is also lower than the average level in the world. The energy consumption and the cost can be reduced by recycling the steel scrap, and 860 kilograms of steel can be smelted from 1 ton of steel scrap.
The prior art has the defects that the prior scrap steel has complex sources, various types and different material types, and the fixed grade is mainly recognized by a quality inspector by naked eyes and is difficult to quantify and standardize. The problems of mixing and doping exist, the work intensity of the quality testing personnel is high, and the work risk is high.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and in order to realize the purpose, an artificial intelligent scrap steel deduction grading method and system are adopted to solve the problems in the background technology.
An artificial intelligence scrap steel impurity-deducting rating method specifically comprises the following steps:
obtaining scrap steel and confirming the material type of the scrap steel;
classifying through a whole image classification model to obtain different material types and image ratios thereof;
sampling layered images by using an intelligent camera module to obtain layered images of different material types;
utilizing a semantic segmentation model to carry out image component proportion division on the layered image;
and analyzing the grade and the deduction amount of the image component according to the proportion of the image component by using an information statistical module, and counting the summary result.
As a further aspect of the invention: the specific method for obtaining different material types and image proportions thereof by classifying through the whole image classification model comprises the following steps:
acquiring an integral image of the material type of the scrap steel;
equally dividing the whole image into a plurality of images with equal areas;
respectively inputting a plurality of images into the whole image classification model;
extracting image features in the plurality of images by using a fine-grained classification algorithm;
and then, judging the types of the scrap steel in the images by using a classifier to obtain different material types of the images.
And finally, counting the material type area ratio of the plurality of images, thereby performing more accurate pre-inspection classification.
As a further aspect of the invention: the specific method for acquiring the layered images of different material types by using the layered image sampling of the intelligent camera module comprises the following steps:
according to the steel scraps of different material types, the intelligent camera module is utilized to carry out layered image sampling on the unloaded steel scraps.
As a further aspect of the invention: the specific method for sampling the layered image comprises the following steps:
driving the vehicle loaded with the scrap steel into a parking space for positioning through a vehicle positioning algorithm;
then, the position of the sucker is adjusted through a sucker positioning algorithm, and the loaded scrap steel is unloaded after being grabbed in a uniform layering manner;
controlling the intelligent camera module to shoot and collect layered images by utilizing a camera tracking algorithm;
and meanwhile, judging whether the purity of the scrap steel of the layered image is consistent with that of the scrap steel classified by pre-inspection, and prompting manual treatment if the purity difference is large.
As a further aspect of the invention: the specific method for carrying out image component proportion division on the layered image by utilizing the semantic segmentation model comprises the following steps:
firstly, acquiring a layered image;
obtaining the characteristics of the same material type of the layered images by utilizing a semantic separation model;
and then counting and determining the proportion of the characteristics of the same material type of each layered image, and analyzing the grade and the impurity deduction amount of the scrap steel.
As a further aspect of the invention: the specific method for analyzing the grade and the deduction amount of the image components and counting the summary result by using the information statistical module according to the image component proportion condition comprises the following steps:
obtaining the volume and density curves of different steel scrap types;
respectively obtaining the volume under unit weight and the density of the steel scrap according to the area ratio, the corresponding steel scrap volume curve and the steel scrap density curve, and calculating to obtain the weight ratio;
and after the calculation is finished, mapping once through softmax to obtain the weight ratio of each steel scrap.
As a further aspect of the invention: the softmax multi-classifier is used for calculating the probability that the predicted object belongs to each category:
wherein, yiTo predict the probability of the object belonging to class C, Zi represents the weight of class C scrap, eZiIs an exponential function mapping of the weight of the C-type scrap steel through the base number e of the natural logarithm,
all scrap weights are summed after being mapped by an exponential function of the base e of the natural logarithm.
A system adopting the artificial intelligent scrap steel impurity-deducting rating method comprises
The intelligent camera module is used for shooting scrap steel images of pre-inspection classification and re-inspection layered classification;
the intelligent algorithm module is used for processing the acquired images of different material types by using different algorithms;
and the information statistical module is used for carrying out statistical analysis according to the image data obtained by the processing of the intelligent algorithm module to obtain a result.
Compared with the prior art, the invention has the following technical effects:
by adopting the technical scheme, the artificial intelligence technology is utilized, the image characteristic classification is carried out by utilizing a fine-grained image classification algorithm, the same image characteristic is processed by utilizing image semantic segmentation, algorithms such as target detection, target tracking, vehicle positioning and big data mining are utilized, the experience skills of quality inspectors are learned by a neural network, the migration of the artificial quality inspection technology is realized, and the quality inspection level of general quality inspectors is reached or even surpassed under the condition of adding big data. Therefore, intelligent scheduling to scrap steel grade judgment after the truck enters the field is realized, and the full-flow process of impurity deduction is intelligent and automatic. The working environment is improved, and the labor intensity and the quality inspection efficiency of quality inspection personnel are reduced. Unnecessary loss caused by the defects of the workflow can be avoided.
Drawings
The following detailed description of embodiments of the invention refers to the accompanying drawings in which:
FIG. 1 is a block flow diagram of an artificial intelligence scrap withholding rating method according to some embodiments disclosed herein;
FIG. 2 is a scrap volume plot of an artificial intelligence scrap withholding rating method of some embodiments disclosed herein;
FIG. 3 is a scrap density profile for an artificial intelligence scrap withholding rating method according to some embodiments of the disclosure.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The grading and impurity deduction inspection process of the existing scrap steel is as follows:
firstly, after the vehicle enters a factory, a scrap steel supplier declares the current scrap steel grade, and the gross weight of the truck is weighed by a platform scale.
Then, quality testing personnel check at a pre-testing station, preliminarily judge the grade and the type of the scrap steel, and make a truck to drive into a corresponding unloading area.
Secondly, quality testing personnel observe the steel scrap grades and impurity content conditions at different depths in a layering manner along with the unloading of the suction cups at a rechecking station.
After the whole truck is unloaded, the truck is weighed through the platform scale.
And finally, summarizing the observed result and the net weight of the steel scrap (the net weight of the steel scrap is the gross weight of the truck-the tare weight of the truck), and evaluating the grade of the steel scrap and the impurity content of the whole truck by a quality inspector according to personal experience and internal control standards.
Referring to fig. 1, in an embodiment of the present invention, an artificial intelligence scrap steel impurity deduction rating method includes:
s1, obtaining scrap steel and confirming the material type of the scrap steel;
specifically, scrap steel is roughly classified into two types: the material types are uniform, and the main components of the material types are waste steel of one type, such as crushed materials, small materials and large materials. Mixed material type: there are various types of scrap steel.
S2, classifying through the whole image classification model to obtain different material types and rough image ratios thereof;
the method comprises the steps of obtaining an overall image of a scrap steel material type through image pickup equipment such as a camera, dividing the overall image into a plurality of images, inputting the images into an overall image classification model, respectively extracting image features in the images by using a fine-grained classification algorithm, and performing pre-inspection classification on the scrap steel type in the images by using a classifier to obtain different material types and image occupation ratios thereof.
Specifically, the scrap steel loading and transporting vehicle can enter a designated unloading area according to different types of scrap steel, and the unloading areas of the different types of scrap steel are different, so that the subsequent scrap steel process treatment is facilitated.
S3, sampling layered images by using an intelligent camera module to obtain layered images of different material types;
and after the vehicles loaded with the waste steel with different material types are driven into the appointed unloading area, the intelligent camera module is utilized to carry out layered image sampling on the unloaded waste steel.
Driving the vehicle loaded with the scrap steel into a parking space for positioning through a vehicle positioning algorithm;
then, the position of the sucker is adjusted through a sucker positioning algorithm, and the loaded scrap steel is unloaded after being grabbed in a uniform layering manner;
specifically, in the sucker unloading process, a unified operation process flow is followed, each layer of scrap steel is uniformly grabbed, the coverage rate reaches over 85 percent, and the coincidence rate is less than 10 percent.
Controlling the intelligent camera module to shoot and collect layered images by utilizing a camera tracking algorithm;
and meanwhile, judging whether the purity of the scrap steel of the layered image is consistent with that of the scrap steel classified by pre-inspection, and prompting manual treatment if the purity difference is large.
Vehicle positioning algorithm: and automatically identifying the contour information of the vehicle and determining whether the vehicle is parked in place by combining the positioning information of the field distance sensor. If not, the system prompts the driver to park the vehicle in place.
And (3) a sucker positioning algorithm: the suckers are uniformly unloaded layer by layer, so that the uniform distribution and the coverage rate of an image acquisition area are ensured.
The camera tracking algorithm: the automatic tracking sucker unloading area is enlarged and the inside of the car is photographed, the photographing coverage rate of the scrap steel of the whole car is high, the area of a repeated area is low, and if the coverage rate is more than 85%, the area of the repeated photographing area is less than 10%.
S4, carrying out fine image component proportion division on the layered image by utilizing a semantic segmentation model;
firstly, acquiring a layered image;
obtaining the characteristics of the same material type of the layered images by utilizing a semantic separation model;
and then counting and determining the proportion of the characteristics of the same material type of each layered image, and analyzing the grade and the impurity deduction amount of the scrap steel.
In particular, the method comprises the following steps of,
and S5, analyzing the grade and the deduction amount according to the image component proportion condition by using an information statistic module, and counting the summary result.
As shown in fig. 2 and 3, rough volume and density curves of different steel scrap types are obtained through a large amount of data training, and the weight ratio of the steel scrap with different thicknesses in the whole body is finally calculated by combining the sizes of the identified steel scrap types under the unified calibration scale.
Respectively obtaining the volume under unit weight and the density of the steel scrap according to the area ratio, the corresponding steel scrap volume curve and the steel scrap density curve, and calculating to obtain the weight under a calibration scale according to m ═ rho v;
and after the weight calculation of all types of scrap steel is finished, mapping once through softmax to obtain the weight ratio of each scrap steel.
The softmax multi-classifier is used for calculating the probability that the predicted object belongs to each category:
wherein, yiTo predict the probability of the object belonging to class C, Zi represents the weight of class C scrap, eZiIs an exponential function mapping of the weight of the C-type scrap steel through the base number e of the natural logarithm,
all scrap weights are summed after being mapped by an exponential function of the base e of the natural logarithm.
A system adopting the artificial intelligent scrap steel impurity-deducting rating method comprises
The intelligent camera module is used for shooting scrap steel images of pre-inspection classification and re-inspection layered classification;
the intelligent algorithm module is used for processing the acquired images of different material types by using different algorithms;
and the information statistical module is used for carrying out statistical analysis according to the image data obtained by the processing of the intelligent algorithm module to obtain a result.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents, which should be construed as being within the scope of the invention.
Claims (8)
1. An artificial intelligence scrap steel impurity deduction rating method is characterized by comprising the following steps:
obtaining scrap steel and confirming the material type of the scrap steel;
classifying through a whole image classification model to obtain different material types and image ratios thereof;
sampling layered images by using an intelligent camera module to obtain layered images of different material types;
utilizing a semantic segmentation model to carry out image component proportion division on the layered image;
and analyzing the grade and the deduction amount of the image component according to the proportion of the image component by using an information statistical module, and counting the summary result.
2. The artificial intelligence scrap steel impurity deduction rating method according to claim 1, wherein the specific method for obtaining different material types and image ratios thereof by classifying through a whole graph classification model comprises the following steps:
acquiring an integral image of the material type of the scrap steel;
equally dividing the whole image into a plurality of images with equal areas;
respectively inputting a plurality of images into the whole image classification model;
extracting image features in the plurality of images by using a fine-grained classification algorithm;
and then, judging the types of the scrap steel in the images by using a classifier to obtain different material types of the images.
And finally, counting the material type area ratio of the plurality of images, thereby performing more accurate pre-inspection classification.
3. The artificial intelligence scrap steel impurity deduction rating method according to claim 2, wherein the specific method for acquiring layered images of different material types by using layered image sampling of the intelligent camera module comprises the following steps:
according to the steel scraps of different material types, the intelligent camera module is utilized to carry out layered image sampling on the unloaded steel scraps.
4. The artificial intelligence scrap steel impurity deduction rating method according to claim 3, wherein the specific method of layered image sampling comprises the following steps:
driving the vehicle loaded with the scrap steel into a parking space for positioning through a vehicle positioning algorithm;
then, the position of the sucker is adjusted through a sucker positioning algorithm, and the loaded scrap steel is unloaded after being grabbed in a uniform layering manner;
controlling the intelligent camera module to shoot and collect layered images by utilizing a camera tracking algorithm;
and meanwhile, judging whether the purity of the scrap steel of the layered image is consistent with that of the scrap steel classified by pre-inspection, and prompting manual treatment if the purity difference is large.
5. The artificial intelligence scrap steel deduction and impurity rating method according to claim 4, wherein the specific method for performing image component proportion division on the layered image by using the semantic segmentation model comprises the following steps:
firstly, acquiring a layered image;
obtaining the characteristics of the same material type of the layered images by utilizing a semantic separation model;
and then counting and determining the proportion of the characteristics of the same material type of each layered image, and analyzing the grade and the impurity deduction amount of the scrap steel.
6. The artificial intelligence scrap steel deduction and impurity rating method according to claim 5, wherein the specific method for analyzing the grade and the impurity deduction amount of the scrap steel and counting the summary result according to the image component proportion by using the information statistic module comprises the following steps:
obtaining the volume and density curves of different steel scrap types;
respectively obtaining the volume under unit weight and the density of the steel scrap according to the area ratio, the corresponding steel scrap volume curve and the steel scrap density curve, and calculating to obtain the weight ratio;
and after the calculation is finished, mapping once through softmax to obtain the weight ratio of each steel scrap.
7. The artificial intelligence scrap steel deduction and impurity rating method according to claim 6, wherein the softmax multi-classifier is used for calculating the probability that the prediction object belongs to each class:
wherein, yiTo predict the probability of the object belonging to class C, Zi represents the weight of class C scrap, eZiIs an exponential function mapping of the weight of the C-type scrap steel through the base number e of the natural logarithm,
all scrap weights are summed after being mapped by an exponential function of the base e of the natural logarithm.
8. A system using the artificial intelligence scrap steel impurity deduction rating method as claimed in claims 1 to 7, comprising
The intelligent camera module is used for shooting scrap steel images of pre-inspection classification and re-inspection layered classification;
the intelligent algorithm module is used for processing the acquired images of different material types by using different algorithms;
and the information statistical module is used for carrying out statistical analysis according to the image data obtained by the processing of the intelligent algorithm module to obtain a result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155709.9A CN112801391B (en) | 2021-02-04 | 2021-02-04 | Artificial intelligent scrap steel impurity deduction rating method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110155709.9A CN112801391B (en) | 2021-02-04 | 2021-02-04 | Artificial intelligent scrap steel impurity deduction rating method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112801391A true CN112801391A (en) | 2021-05-14 |
| CN112801391B CN112801391B (en) | 2021-11-19 |
Family
ID=75814159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110155709.9A Active CN112801391B (en) | 2021-02-04 | 2021-02-04 | Artificial intelligent scrap steel impurity deduction rating method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112801391B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113627830A (en) * | 2021-09-08 | 2021-11-09 | 西安智者云集云计算有限公司 | Scrap steel grading system and method |
| CN113642539A (en) * | 2021-10-14 | 2021-11-12 | 阿里巴巴达摩院(杭州)科技有限公司 | Cargo treatment and scrap steel treatment method and device |
| CN113743210A (en) * | 2021-07-30 | 2021-12-03 | 阿里巴巴达摩院(杭州)科技有限公司 | Image recognition method and scrap grade recognition method |
| CN113810605A (en) * | 2021-08-17 | 2021-12-17 | 阿里巴巴达摩院(杭州)科技有限公司 | Target object processing method and device |
| CN114860359A (en) * | 2022-04-06 | 2022-08-05 | 阿里巴巴达摩院(杭州)科技有限公司 | Image processing method, system and storage medium |
| CN115125363A (en) * | 2022-06-09 | 2022-09-30 | 北京同创信通科技有限公司 | Intelligent identification system and method for detecting batching in scrap steel hopper |
| CN115159150A (en) * | 2022-09-07 | 2022-10-11 | 江苏金恒信息科技股份有限公司 | Scrap steel approach control method and system and computer readable storage medium |
| CN115496757A (en) * | 2022-11-17 | 2022-12-20 | 山东新普锐智能科技有限公司 | Hydraulic plate turnover surplus material amount detection method and system based on machine vision |
| CN115830008A (en) * | 2023-02-06 | 2023-03-21 | 上海爱梵达云计算有限公司 | Analysis system for judging waste degree of scrap steel based on image analysis comparison |
| CN115861304A (en) * | 2023-02-20 | 2023-03-28 | 江苏金恒信息科技股份有限公司 | Method and system for detecting steel strip-shaped structure based on image processing |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160140424A1 (en) * | 2014-11-13 | 2016-05-19 | Nec Laboratories America, Inc. | Object-centric Fine-grained Image Classification |
| CN108564271A (en) * | 2018-04-10 | 2018-09-21 | 西王金属科技有限公司 | A kind of steel scrap quality inspection statistical system |
| CN109919243A (en) * | 2019-03-15 | 2019-06-21 | 天津拾起卖科技有限公司 | A kind of scrap iron and steel type automatic identifying method and device based on CNN |
| US20190266731A1 (en) * | 2018-02-26 | 2019-08-29 | Abc Fintech Co., Ltd. | Image segmentation method and device |
| US20190286940A1 (en) * | 2018-03-13 | 2019-09-19 | Fujitsu Limited | Method and apparatus for training image model, and method and apparatus for category prediction |
| CN110660074A (en) * | 2019-10-10 | 2020-01-07 | 北京同创信通科技有限公司 | Method for establishing steel scrap grade division neural network model |
| CN110717455A (en) * | 2019-10-10 | 2020-01-21 | 北京同创信通科技有限公司 | Method for classifying and detecting grades of scrap steel in storage |
| CN111292026A (en) * | 2020-04-27 | 2020-06-16 | 江苏金恒信息科技股份有限公司 | Scrap steel grading method and device based on neural network model fusion |
| CN112016617A (en) * | 2020-08-27 | 2020-12-01 | 中国平安财产保险股份有限公司 | Fine-grained classification method and device and computer-readable storage medium |
| CN112163465A (en) * | 2020-09-11 | 2021-01-01 | 华南理工大学 | Fine-grained image classification method, fine-grained image classification system, computer equipment and storage medium |
-
2021
- 2021-02-04 CN CN202110155709.9A patent/CN112801391B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160140424A1 (en) * | 2014-11-13 | 2016-05-19 | Nec Laboratories America, Inc. | Object-centric Fine-grained Image Classification |
| US20190266731A1 (en) * | 2018-02-26 | 2019-08-29 | Abc Fintech Co., Ltd. | Image segmentation method and device |
| US20190286940A1 (en) * | 2018-03-13 | 2019-09-19 | Fujitsu Limited | Method and apparatus for training image model, and method and apparatus for category prediction |
| CN108564271A (en) * | 2018-04-10 | 2018-09-21 | 西王金属科技有限公司 | A kind of steel scrap quality inspection statistical system |
| CN109919243A (en) * | 2019-03-15 | 2019-06-21 | 天津拾起卖科技有限公司 | A kind of scrap iron and steel type automatic identifying method and device based on CNN |
| CN110660074A (en) * | 2019-10-10 | 2020-01-07 | 北京同创信通科技有限公司 | Method for establishing steel scrap grade division neural network model |
| CN110717455A (en) * | 2019-10-10 | 2020-01-21 | 北京同创信通科技有限公司 | Method for classifying and detecting grades of scrap steel in storage |
| CN111292026A (en) * | 2020-04-27 | 2020-06-16 | 江苏金恒信息科技股份有限公司 | Scrap steel grading method and device based on neural network model fusion |
| CN112016617A (en) * | 2020-08-27 | 2020-12-01 | 中国平安财产保险股份有限公司 | Fine-grained classification method and device and computer-readable storage medium |
| CN112163465A (en) * | 2020-09-11 | 2021-01-01 | 华南理工大学 | Fine-grained image classification method, fine-grained image classification system, computer equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 何荣福: "外购废钢抽样计量称杂检验实践", 《山东工业技术》 * |
| 冯语姗: "自上而下注意图分割的细粒度图像分类", 《中国图象图形学报》 * |
| 郭锋: "基于深度学习的废钢智能验质***", 《工程装备》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113743210A (en) * | 2021-07-30 | 2021-12-03 | 阿里巴巴达摩院(杭州)科技有限公司 | Image recognition method and scrap grade recognition method |
| CN113810605A (en) * | 2021-08-17 | 2021-12-17 | 阿里巴巴达摩院(杭州)科技有限公司 | Target object processing method and device |
| CN113627830A (en) * | 2021-09-08 | 2021-11-09 | 西安智者云集云计算有限公司 | Scrap steel grading system and method |
| CN113642539A (en) * | 2021-10-14 | 2021-11-12 | 阿里巴巴达摩院(杭州)科技有限公司 | Cargo treatment and scrap steel treatment method and device |
| CN114860359A (en) * | 2022-04-06 | 2022-08-05 | 阿里巴巴达摩院(杭州)科技有限公司 | Image processing method, system and storage medium |
| CN114860359B (en) * | 2022-04-06 | 2024-05-14 | 阿里巴巴达摩院(杭州)科技有限公司 | Image processing method, system and storage medium |
| CN115125363B (en) * | 2022-06-09 | 2023-10-20 | 北京同创信通科技有限公司 | Intelligent recognition system and method for detecting ingredients in scrap steel hopper |
| CN115125363A (en) * | 2022-06-09 | 2022-09-30 | 北京同创信通科技有限公司 | Intelligent identification system and method for detecting batching in scrap steel hopper |
| CN115159150A (en) * | 2022-09-07 | 2022-10-11 | 江苏金恒信息科技股份有限公司 | Scrap steel approach control method and system and computer readable storage medium |
| CN115159150B (en) * | 2022-09-07 | 2022-12-20 | 江苏金恒信息科技股份有限公司 | Scrap steel approach control method and system and computer readable storage medium |
| CN115496757B (en) * | 2022-11-17 | 2023-02-21 | 山东新普锐智能科技有限公司 | Hydraulic flap excess material amount detection method and system based on machine vision |
| CN115496757A (en) * | 2022-11-17 | 2022-12-20 | 山东新普锐智能科技有限公司 | Hydraulic plate turnover surplus material amount detection method and system based on machine vision |
| CN115830008A (en) * | 2023-02-06 | 2023-03-21 | 上海爱梵达云计算有限公司 | Analysis system for judging waste degree of scrap steel based on image analysis comparison |
| CN115861304A (en) * | 2023-02-20 | 2023-03-28 | 江苏金恒信息科技股份有限公司 | Method and system for detecting steel strip-shaped structure based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112801391B (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112801391B (en) | Artificial intelligent scrap steel impurity deduction rating method and system | |
| CN110717455B (en) | Method for classifying and detecting grades of scrap steel in storage | |
| CN110389127B (en) | System and method for identifying metal ceramic parts and detecting surface defects | |
| CN110779937B (en) | Casting product internal defect intelligent detection device | |
| CN109977808A (en) | A kind of wafer surface defects mode detection and analysis method | |
| CN110610475B (en) | Visual defect detection method of deep convolutional neural network | |
| CN108711148B (en) | Tire defect intelligent detection method based on deep learning | |
| CN112881412B (en) | Method for detecting non-metal foreign matters in scrap steel products | |
| CN110544231B (en) | Lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithm | |
| CN110660074B (en) | Method for establishing steel scrap grade division neural network model | |
| CN113743210A (en) | Image recognition method and scrap grade recognition method | |
| CN101510262A (en) | Automatic measurement method for separated-out particles in steel and morphology classification method thereof | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN111291814A (en) | Crack identification algorithm based on convolution neural network and information entropy data fusion strategy | |
| CN113177605A (en) | Scrap steel carriage grade judgment method based on video monitoring | |
| CN114078126A (en) | Scrap steel grading method and device based on machine learning | |
| CN109239073A (en) | A kind of detection method of surface flaw for body of a motor car | |
| CN116152242B (en) | Visual detection system of natural leather defect for basketball | |
| CN111598845A (en) | Pavement crack detection and positioning method based on deep learning and NEO-6M positioning module | |
| CN113810605A (en) | Target object processing method and device | |
| CN116363136B (en) | On-line screening method and system for automatic production of motor vehicle parts | |
| CN115953568A (en) | Intelligent mineral sorting method based on lightweight target detection framework | |
| CN112907651B (en) | Measuring method of oyster external form based on semantic segmentation network | |
| CN114155224A (en) | Method and device for acquiring scrap settlement data, scrap settlement system and recycling site | |
| CN114863277A (en) | Machine vision-based method for rapidly detecting irregular particle group overrun particles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 230088 No. 5111 Wangjiangxi Road, Hefei High-tech Zone, Anhui Province Applicant after: HKUST intelligent Internet of things Technology Co.,Ltd. Address before: 230088 No. 5111 Wangjiangxi Road, Hefei High-tech Zone, Anhui Province Applicant before: HKUST intelligent IOT Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |