CN115753796A - Scrap steel grading method and system - Google Patents
Scrap steel grading method and system Download PDFInfo
- Publication number
- CN115753796A CN115753796A CN202211449492.3A CN202211449492A CN115753796A CN 115753796 A CN115753796 A CN 115753796A CN 202211449492 A CN202211449492 A CN 202211449492A CN 115753796 A CN115753796 A CN 115753796A
- Authority
- CN
- China
- Prior art keywords
- scrap
- steel
- scrap steel
- target
- identified
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 182
- 239000010959 steel Substances 0.000 title claims abstract description 182
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000005260 corrosion Methods 0.000 claims abstract description 18
- 230000007797 corrosion Effects 0.000 claims abstract description 18
- 238000011156 evaluation Methods 0.000 claims description 22
- 239000003086 colorant Substances 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 9
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 7
- 239000012535 impurity Substances 0.000 claims description 5
- 238000009432 framing Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 239000000463 material Substances 0.000 description 5
- 239000002699 waste material Substances 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010008 shearing Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000009628 steelmaking Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a scrap steel grading method and a scrap steel grading system, wherein the method comprises the following steps: collecting a scrap steel image; segmenting the scrap steel image, and extracting a target to be identified in the scrap steel image; calculating the size of each target to be identified, and classifying and grading the scrap steel according to the size of the target to be identified; extracting the surface characteristics of the target to be identified in the scrap steel image, and judging the corrosion degree of the scrap steel through the surface attachment of the target to be identified; and carrying out comprehensive classification grading on the steel scraps on the target to be recognized through classification grading and corrosion degree of the target to be recognized. The deep learning is used for replacing manual work to grade the scrap steel, the efficiency is high, the accuracy is high, and the labor intensity of workers is reduced.
Description
Technical Field
The invention relates to a method and a system for automatically identifying the grade of scrap steel.
Background
The method of processing scrap varies depending on the material and shape. Fragile and irregularly shaped large materials are crushed by a heavy hammer. And cutting the extra-thick and extra-long large steel scraps into qualified sizes by using a cutter. Shearing thick waste steel plates, section steel and bar steel by a shearing machine. And light materials with smaller volume and specific gravity, such as waste thin plate leftover materials, waste steel wires, waste automobile shells and the like, are compressed into blocks by a packing machine, and are bundled to be used as steelmaking raw materials. The different grades of steel scraps are very different, and the mixing of the low grade steel scraps in the steel scraps can bring huge loss to steel mills.
In the prior art, the grade of the scrap steel is generally distinguished by adopting a manual identification mode. However, the artificial subjective factors have a large influence, and the evaluation result may be influenced by fatigue, mood and the like. Secondly, every person judges that the difference exists and cannot be unified. In addition, the identification time is long, and the detection needs to be carefully checked one by one after being drawn close.
Disclosure of Invention
In view of the above, the present invention provides a scrap steel rating method for automatically identifying scrap steel grades.
In order to solve the technical problems, the technical scheme of the invention is a scrap steel rating method, which is characterized by comprising the following steps:
collecting a scrap steel image;
segmenting the scrap steel image, and extracting a target to be identified in the scrap steel image;
calculating the size of each target to be identified, and classifying and grading the scrap steel according to the size of the target to be identified;
extracting the surface characteristics of the target to be identified in the scrap steel image, and judging the corrosion degree of the scrap steel through the surface attachment of the target to be identified;
and carrying out comprehensive classification grading on the steel scraps on the target to be recognized through classification grading and corrosion degree of the target to be recognized.
As an improvement, the method for extracting the target to be identified in the scrap steel image comprises the following steps: and identifying and then framing the target to be identified in the image by using the example segmentation artificial intelligence neural network model.
As an improvement, the method for classifying and grading the scrap steel comprises the following steps:
setting size indexes of different types of scrap steel;
setting different colors for different types of scrap steel;
carrying out type recognition on the segmented target to be recognized according to the size index of the scrap steel by utilizing a scrap steel grading artificial intelligent neural network model, and predicting the recognition accuracy;
if the identification accuracy is greater than or equal to the threshold value, confirming the identification result and marking the target to be identified with the color corresponding to the grade of the target to be identified; if the identification accuracy is smaller than the threshold, acquiring a scrap steel image with higher resolution and then identifying until the identification accuracy is larger than or equal to the threshold or the scrap steel image with higher resolution cannot be acquired;
the proportions of the respective scraps were calculated from the proportions of the colors represented by the respective scraps in the image, and the overall evaluation was performed on all the scraps based on the proportions of the respective scraps.
Preferably, the target to be identified which cannot be identified is judged as a dangerous article or impurity, and manual intervention identification is carried out.
As an improvement, the scrap car is peeled from the surrounding environment prior to segmenting the scrap image.
And preferably, judging the corrosion degree of the steel scrap by using a corrosion degree artificial intelligence neural network model.
As an improvement, the color from dark to light is set from thick to thin scrap type.
The invention also provides a scrap steel rating system, which is characterized by comprising:
the image acquisition module is used for acquiring a scrap steel image;
the example segmentation module is used for segmenting the scrap steel image and extracting a target to be identified in the scrap steel image;
the scrap steel classification grading module is used for calculating the size of each target to be identified and classifying and grading the scrap steel according to the size of the target to be identified;
the rust degree evaluation module is used for extracting the surface characteristics of the target to be identified in the steel scrap image and judging the rust degree of the steel scrap according to the surface attachment of the target to be identified;
and the comprehensive evaluation module is used for comprehensively classifying and grading the steel scraps of the target to be recognized according to the classification grading and the corrosion degree of the target to be recognized.
As an improvement, the scrap classification grading module comprises:
the setting module is used for setting the size indexes of different types of steel scraps and setting different colors for the different types of steel scraps;
the identification evaluation module is used for identifying the types of the segmented targets to be identified according to the size indexes of the scrap steel and predicting the identification accuracy;
the judging module is used for confirming the type of the scrap steel according to the relation between the identification accuracy and the threshold value and marking the color corresponding to the grade of the scrap steel;
and the overall evaluation module is used for calculating the proportion of various steel scraps according to the proportion of the color represented by each steel scrap in the image and performing overall evaluation on all the steel scraps according to the proportion of the various steel scraps.
As an improvement, the method further comprises the following steps:
and the environment stripping module is used for stripping the scrap steel transport vehicle from the surrounding environment before the scrap steel image is segmented.
The invention has the advantages that:
1. the segmentation and identification of the deep learning on the scrap steel are expanded from a two-dimensional space to a three-dimensional space, and the three-dimensional freedom degree of the color representation thickness is creatively added on the basis of the original feature extraction, so that the method is more in line with the actual requirements of scrap steel classification.
2. The proportion of different types of scrap steel is calculated according to the area of the color blocks, so that the accuracy of grade inspection of the scrap steel is greatly improved.
3. According to the color of the scrap steel marked in the image, the surface characteristics of the scrap steel are enhanced, and more visual characteristics are provided for manual auxiliary classification.
4. Impurity and hazardous articles can be rapidly positioned and identified, and the working efficiency of scrap steel grade inspection is greatly improved.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a schematic diagram of the structure of the present invention.
Detailed Description
In order that those skilled in the art will better understand the technical solutions of the present invention, the present invention will be further described in detail with reference to the following embodiments.
As shown in FIG. 1, the method for grading scrap steel comprises the following specific steps:
s1, acquiring a scrap steel image.
After the scrap steel vehicle enters the designated position, the camera acquires the scrap steel image on the vehicle layer by layer, namely the image of the top layer scrap steel is acquired firstly, then the top layer scrap steel is sucked away by the sucking disc, and then the lower layer scrap steel is shot to acquire the image, and so on. The obtained scrap steel image comprises scrap steel, a scrap steel transport vehicle and a surrounding environment, and in order to improve efficiency and reduce system overhead, the scrap steel transport vehicle and the surrounding environment in the image can be peeled off firstly before the next operation is carried out, and only the scrap steel vehicle is subjected to subsequent treatment.
And S2, segmenting the scrap steel image, and extracting the target to be identified in the scrap steel image.
After the scrap steel image is collected, each piece of scrap steel in the image needs to be segmented so as to facilitate subsequent identification. In the embodiment, an example segmentation artificial intelligence neural network model such as Mask-RCNN is used for identifying and then framing the target to be identified in the image.
S3, calculating the size of each target to be identified, and classifying and grading the scrap steel according to the size of the target to be identified, wherein the method specifically comprises the following steps:
s31, setting size indexes of different types of steel scraps; inputting the type of steel mill scrap, inputting the thickness or size represented by different types of scrap, such as: the thickness of the scrap steel 1 is 8mm, the material cutting is 50cm x 50cm, the thickness of the light and thin pressed block is less than 2mm, and the diameter of the steel bar is 6mm \8230 \
S32, setting different colors for different types of steel scraps; inputting the type and color of the steel scraps, and using different colors for different steel scraps. In the present embodiment, the color from dark to light is set from the thick to thin scrap type.
And S33, carrying out type identification on the segmented target to be identified according to the size index of the scrap steel by utilizing the scrap steel grading artificial intelligent neural network model, and meanwhile predicting the identification accuracy. After the model is trained, classifying each piece of the segmented steel scrap according to the extracted features, calculating the minimum external rectangle of each piece of the segmented steel scrap, positioning the position of the steel scrap according to the minimum external rectangle, and displaying the accuracy of classification of each piece of the steel scrap.
Because the angle and the exposed area of the scrap steel are different, the identification accuracy rate is different. For example, the identification accuracy of the scrap steel which faces the lens and is completely exposed can reach more than 95%, and the identification accuracy of the scrap steel which is slightly more exposed than the lens can only reach 60%.
S34, if the identification accuracy is larger than or equal to the threshold value, confirming the identification result and marking the color corresponding to the grade of the target to be identified; and if the identification accuracy is smaller than the threshold, acquiring the scrap steel image with higher resolution and then identifying until the identification accuracy is larger than or equal to the threshold or the scrap steel image with higher resolution cannot be acquired.
In this embodiment, the threshold is set to 80%. And when the accuracy rate is greater than or equal to 80%, the identification result is considered to be acceptable and the color corresponding to the grade of the scrap steel is marked. If the accuracy rate is less than 80%, the camera is pushed to acquire an image with higher resolution for recognition, and certainly, if the original image is clear enough, the image can be directly amplified for recognition again until the recognition accuracy rate is greater than or equal to 80% to confirm the recognition result or the image with higher resolution cannot be acquired any more. The steel scraps with the identification accuracy rate of less than 80 percent are considered as dangerous goods or impurities, and manual intervention identification is needed. At the moment, the images are mostly standardized with different colors, and dangerous goods and impurities are easily distinguished from the images by manpower, so that the labor intensity of the manpower is reduced.
S35, calculating the proportion of each steel scrap according to the proportion of the color represented by each steel scrap in the image, and performing overall evaluation on all the steel scrap according to the proportion of each steel scrap.
And counting the color of each pixel in the area where the scrap steel is located in the image so as to obtain the proportion of each grade in the scrap steel of the whole vehicle, thereby carrying out grade evaluation on the scrap steel of the whole vehicle.
S4, extracting the surface characteristics of the target to be identified in the scrap steel image, and judging the corrosion degree of the scrap steel through the surface attachment of the target to be identified.
In the embodiment, the rust degree of the scrap steel is judged by using the artificial intelligent neural network model of the rust degree. After the model is trained, inputting the surface characteristics of the recognition target in the extracted steel scrap image into the model, and matching the model according to the trained characteristic library so as to judge the corrosion degree of the steel scrap.
It should be noted that the execution of step S3 and step S4 is not sequential, and they can be executed separately or simultaneously.
And S5, carrying out comprehensive classification grading on the steel scraps on the target to be recognized through classification grading and corrosion degree of the target to be recognized.
After classification and grading of the steel scraps and judgment of the corrosion degree are finished, comprehensive evaluation can be performed according to the results of the classification and grading of the steel scraps and the corrosion degree, the evaluation standard is set according to the actual situation, and details are not repeated in the invention.
As shown in fig. 2, the present invention also provides a scrap rating system, comprising:
the image acquisition module is used for acquiring a scrap steel image;
the environment stripping module is used for stripping the scrap steel transport vehicle from the surrounding environment before the scrap steel image is segmented;
the example segmentation module is used for segmenting the scrap steel image and extracting a target to be identified in the scrap steel image;
the scrap steel classification grading module is used for calculating the size of each target to be identified and classifying and grading the scrap steel according to the size of the target to be identified;
the rust degree evaluation module is used for extracting the surface characteristics of the target to be identified in the scrap steel image and judging the rust degree of the scrap steel according to the surface attachment of the target to be identified;
and the comprehensive evaluation module is used for comprehensively classifying and grading the steel scraps of the target to be recognized according to the classification grading and the corrosion degree of the target to be recognized.
The scrap steel classification grading module specifically comprises:
the setting module is used for setting the size indexes of different types of steel scraps and setting different colors for the different types of steel scraps;
the identification evaluation module is used for identifying the types of the segmented targets to be identified according to the size indexes of the scrap steel and predicting the identification accuracy;
the judging module is used for confirming the type of the scrap steel according to the relation between the identification accuracy and the threshold value and marking the color corresponding to the grade of the scrap steel;
and the overall evaluation module is used for calculating the proportion of various steel scraps according to the proportion of the color represented by each steel scrap in the image and performing overall evaluation on all the steel scraps according to the proportion of the various steel scraps.
The above is only a preferred embodiment of the present invention, and it should be noted that the above preferred embodiment should not be considered as limiting the present invention, and the protection scope of the present invention should be subject to the scope defined by the claims. It will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the spirit and scope of the invention, and these modifications and adaptations should be considered within the scope of the invention.
Claims (10)
1. A scrap steel rating method characterized by comprising:
collecting a scrap steel image;
segmenting the scrap steel image, and extracting a target to be identified in the scrap steel image;
calculating the size of each target to be identified, and classifying and grading the scrap steel according to the size of the target to be identified;
extracting the surface characteristics of the target to be identified in the scrap steel image, and judging the corrosion degree of the scrap steel through the surface attachment of the target to be identified;
and carrying out comprehensive classification grading on the steel scraps on the target to be recognized through classification grading and corrosion degree of the target to be recognized.
2. A method for grading scrap steel according to claim 1, characterized in that the method for extracting the object to be identified in the scrap steel image is: and identifying and then framing the target to be identified in the image by using the example segmentation artificial intelligent neural network model.
3. A method as claimed in claim 2, wherein the method of classifying and grading scrap comprises:
setting size indexes of different types of scrap steel;
setting different colors for different types of scrap steel;
carrying out type recognition on the segmented target to be recognized according to the size index of the scrap steel by utilizing a scrap steel grading artificial intelligent neural network model, and meanwhile predicting the recognition accuracy;
if the identification accuracy is greater than or equal to the threshold value, confirming the identification result and marking the target to be identified with the color corresponding to the grade of the target to be identified; if the identification accuracy is smaller than the threshold, acquiring a scrap steel image with higher resolution and then identifying until the identification accuracy is larger than or equal to the threshold or the scrap steel image with higher resolution cannot be acquired;
the proportions of the respective scraps were calculated from the proportions of the colors represented by the respective scraps in the image, and the overall evaluation was performed on all the scraps based on the proportions of the respective scraps.
4. A scrap steel rating method according to claim 3, wherein: and judging the target to be identified which cannot be identified as a dangerous article or impurity, and carrying out manual intervention identification.
5. A scrap steel rating method according to claim 3, wherein: the color from dark to light is set from thick to thin steel scrap types.
6. A method of grading scrap steel according to claim 1, characterized in that: the scrap car is peeled from the surrounding environment prior to segmenting the scrap image.
7. A method of grading scrap steel according to claim 1, characterized in that: and judging the corrosion degree of the scrap steel by utilizing a corrosion degree artificial intelligent neural network model.
8. A scrap rating system, comprising:
the image acquisition module is used for acquiring a scrap steel image;
the example segmentation module is used for segmenting the scrap steel image and extracting a target to be identified in the scrap steel image;
the scrap steel classification grading module is used for calculating the size of each target to be identified and classifying and grading the scrap steel according to the size of the target to be identified;
the rust degree evaluation module is used for extracting the surface characteristics of the target to be identified in the steel scrap image and judging the rust degree of the steel scrap according to the surface attachment of the target to be identified;
and the comprehensive evaluation module is used for comprehensively classifying and grading the steel scraps of the target to be recognized according to the classification grading and the corrosion degree of the target to be recognized.
9. A scrap rating system according to claim 8, wherein the scrap classification grading module comprises:
the setting module is used for setting the size indexes of different types of steel scraps and setting different colors for the different types of steel scraps;
the identification evaluation module is used for identifying the types of the segmented targets to be identified according to the size indexes of the scrap steel and predicting the identification accuracy;
the judging module is used for confirming the type of the scrap steel according to the relation between the identification accuracy and the threshold value and marking the color corresponding to the grade of the scrap steel;
and the integral evaluation module is used for calculating the proportion of various steel scraps according to the proportion of the color represented by each steel scrap in the image and carrying out integral evaluation on all the steel scraps according to the proportion of the various steel scraps.
10. A scrap rating system in accordance with claim 8 further comprising:
and the environment stripping module is used for stripping the scrap steel transport vehicle from the surrounding environment before the scrap steel image is segmented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211449492.3A CN115753796A (en) | 2022-11-18 | 2022-11-18 | Scrap steel grading method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211449492.3A CN115753796A (en) | 2022-11-18 | 2022-11-18 | Scrap steel grading method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115753796A true CN115753796A (en) | 2023-03-07 |
Family
ID=85373668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211449492.3A Pending CN115753796A (en) | 2022-11-18 | 2022-11-18 | Scrap steel grading method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115753796A (en) |
Citations (5)
| 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 |
| 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 |
| CN114155224A (en) * | 2021-12-06 | 2022-03-08 | 用友网络科技股份有限公司 | Method and device for acquiring scrap settlement data, scrap settlement system and recycling site |
| CN114387526A (en) * | 2021-11-30 | 2022-04-22 | 阿里巴巴达摩院(杭州)科技有限公司 | Image processing method, storage medium, and computer terminal |
| CN114511046A (en) * | 2022-04-19 | 2022-05-17 | 阿里巴巴（中国）有限公司 | Object recognition method and device |
-
2022
- 2022-11-18 CN CN202211449492.3A patent/CN115753796A/en active Pending
Patent Citations (5)
| 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 |
| 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 |
| CN114387526A (en) * | 2021-11-30 | 2022-04-22 | 阿里巴巴达摩院(杭州)科技有限公司 | Image processing method, storage medium, and computer terminal |
| CN114155224A (en) * | 2021-12-06 | 2022-03-08 | 用友网络科技股份有限公司 | Method and device for acquiring scrap settlement data, scrap settlement system and recycling site |
| CN114511046A (en) * | 2022-04-19 | 2022-05-17 | 阿里巴巴（中国）有限公司 | Object recognition method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110717455B (en) | Method for classifying and detecting grades of scrap steel in storage | |
| CN111951237B (en) | Visual appearance detection method | |
| CN110414320B (en) | Method and system for safety production supervision | |
| CN105551064B (en) | A kind of method based on characteristics of image estimation windrow volume change | |
| CN117152161B (en) | Shaving board quality detection method and system based on image recognition | |
| CN106778779A (en) | A kind of electric injection molding machine mould detection method | |
| CN107153067A (en) | A kind of surface defects of parts detection method based on MATLAB | |
| CN112881412B (en) | Method for detecting non-metal foreign matters in scrap steel products | |
| JP7301783B2 (en) | Composition analysis method for electronic/electrical equipment parts scrap, electronic/electrical equipment parts scrap processing method, electronic/electrical equipment parts scrap composition analysis device, and electronic/electrical equipment parts scrap processing equipment | |
| CN112734702A (en) | Bridge safety monitoring method based on big data analysis and machine vision and cloud platform | |
| CN113177605A (en) | Scrap steel carriage grade judgment method based on video monitoring | |
| CN113610185B (en) | Wood color sorting method based on dominant hue identification | |
| EP4197656A1 (en) | Scrap discrimination system and scrap discrimination method | |
| CN113281115B (en) | Control method for intelligent tobacco leaf shearing | |
| CN102496030B (en) | Identification method and identification device for dangerous targets in power monitoring system | |
| CN113936291A (en) | Aluminum template quality inspection and recovery method based on machine vision | |
| CN115753796A (en) | Scrap steel grading method and system | |
| CN117409005A (en) | Defective product detection system and method for plate receiving machine based on image | |
| CN105512633A (en) | Power system dangerous object identification method and apparatus | |
| CN114782808A (en) | Scrap steel grading identification method and system based on machine vision algorithm | |
| CN111723861B (en) | Gangue percentage identification method for coal mine control baffle | |
| CN115810161A (en) | Transformer substation fire identification method and system | |
| CN113369155B (en) | Renewable waste product identification detection and automatic recovery system and method | |
| CN112808782A (en) | Automatic detection method for rust removal grade of hot rolled plate | |
| CN103714352A (en) | Halation inhibition method based on image cognition region |
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 |