CN113718082A - Prediction system and method for judging steelmaking end point temperature of converter based on flame image - Google Patents
Prediction system and method for judging steelmaking end point temperature of converter based on flame image Download PDFInfo
- Publication number
- CN113718082A CN113718082A CN202110944596.0A CN202110944596A CN113718082A CN 113718082 A CN113718082 A CN 113718082A CN 202110944596 A CN202110944596 A CN 202110944596A CN 113718082 A CN113718082 A CN 113718082A
- Authority
- CN
- China
- Prior art keywords
- flame
- temperature
- end point
- characteristic data
- image
- 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
- 238000009628 steelmaking Methods 0.000 title claims abstract description 14
- 238000003723 Smelting Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 15
- 238000007664 blowing Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 3
- 229910000831 Steel Inorganic materials 0.000 description 7
- 239000010959 steel Substances 0.000 description 7
- 238000009529 body temperature measurement Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000005070 sampling Methods 0.000 description 4
- 230000001681 protective effect Effects 0.000 description 2
- 238000010079 rubber tapping Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 241001062472 Stokellia anisodon Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 239000002436 steel type Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C5/00—Manufacture of carbon-steel, e.g. plain mild steel, medium carbon steel or cast steel or stainless steel
- C21C5/28—Manufacture of steel in the converter
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21C—PROCESSING OF PIG-IRON, e.g. REFINING, MANUFACTURE OF WROUGHT-IRON OR STEEL; TREATMENT IN MOLTEN STATE OF FERROUS ALLOYS
- C21C2300/00—Process aspects
- C21C2300/06—Modeling of the process, e.g. for control purposes; CII
-
- 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
- Y02P10/00—Technologies related to metal processing
- Y02P10/25—Process efficiency
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention provides a system and a method for predicting converter steelmaking endpoint temperature based on flame images, wherein the prediction system comprises: the invention adopts a flame image recognition mode to predict the temperature, is safe and convenient, can realize continuous temperature detection and real-time prediction of a temperature curve, improves the accuracy of the converter end point temperature by using the flame image recognition mode, and compared with the method of judging the smelting end point only by depending on manual experience, the invention has the advantages that the temperature precision is +/-15 ℃, and the secondary converting proportion is reduced by 30 percent.
Description
Technical Field
The invention relates to the field of automatic control of steelmaking, in particular to a system and a method for predicting converter steelmaking endpoint temperature based on flame images.
Background
The development of the steel industry requires that the individual production processes must be more tightly controlled to meet high demands on product quality, production efficiency, and at the same time, production costs are constantly minimized. At present, a converter is required to be adopted in a long-flow steelmaking process to smelt molten steel, the temperature of the molten steel is an important parameter for judging whether the molten steel is qualified, different steel types have strict tapping temperature requirements, and secondary or even multiple blowing is required when the judgment on smelting end point temperature is inappropriate, so that the production efficiency is influenced.
Generally, most of converters with more than 200t are provided with sublance systems, the sublance is adopted for temperature measurement and sampling without the need of converter reversal, and for converters without the sublance systems, the converter reversal is carried out after molten steel smelting is finished, namely, the converter is rotated from a vertical state to an included angle of 15-35 degrees between the axis of the converter and the ground plane, so that the molten steel surface is inclined, the temperature measurement operation is convenient, and temperature measurement can be carried out by inserting a temperature measurement gun into a converter mouth by manpower or a manipulator. And (3) after the temperature of the molten steel is detected successfully, pulling out the temperature measuring gun, wherein the heat with qualified temperature and components can be directly tapped, and the heat with improper temperature and components needs to be continuously blown with oxygen for smelting, and temperature measurement and sampling are carried out again until the tapping process requirement is met.
However, the existing smelting end point judgment is to judge the end point temperature by manually judging the color, the shape, the transparency and the like of the flame of the converter, and then carry out converter reversing temperature measurement, generally, operations such as manual installation of a probe, manual insertion of a temperature measuring gun and the like are needed, the labor intensity is high, the converter needs to be turned back again for reblowing when the furnace temperature is not proper, the production efficiency is reduced, and meanwhile, the risk of safety accidents is increased by manual multiple measurements.
Disclosure of Invention
In view of the above, the present invention provides a system and a method for predicting a steelmaking end point temperature of a converter based on a flame image.
In order to achieve the purpose, the invention adopts the technical scheme that: the prediction system for judging the steelmaking end point temperature of the converter based on the flame image comprises:
the image acquisition unit is used for continuously acquiring original flame images of the furnace mouth;
the image processing module is used for respectively processing the continuously acquired original furnace mouth flame images to obtain the current furnace mouth flame characteristics corresponding to each original furnace mouth flame image, and the current furnace mouth flame characteristic data set is obtained after the current furnace mouth flame characteristics are summarized;
the temperature prediction module is used for predicting the smelting temperature in the furnace corresponding to each characteristic data in the current furnace mouth flame characteristic data set to obtain a temperature change curve based on time;
and the end point prediction module is used for predicting the blowing end point based on the smelting end point temperature corresponding to the temperature change curve.
Further, the image processing module adopts HSI color space parameters to establish a color space model for the original fire door flame image to obtain the current fire door flame characteristics, and the current fire door flame characteristics include but are not limited to the profile characteristics and the gray value parameters of the fire door flames.
Further, the prediction system further comprises a preprocessing module for preprocessing the original fire door flame image, and the preprocessing step at least comprises graying processing.
Furthermore, the image acquisition unit is a camera, the image processing module, the temperature prediction module and the end point prediction module jointly form a computer system, and the camera and the computer system are connected in a network, USB (universal serial bus) line or serial port mode.
Further, the lens of the camera is over against the position of the observation hole in the converter blowing process, and the acquisition frequency of the camera on the original fire hole flame image is 2 times/s.
The invention relates to a method for predicting the steelmaking end point temperature of a converter based on a flame image, which comprises the following steps:
s1, continuously acquiring original flame images of the fire door;
s2, respectively processing the continuously acquired original fire door flame images to obtain current fire door flame characteristics corresponding to each original fire door flame image, and summarizing to obtain a current fire door flame characteristic data set;
s3, respectively predicting the smelting temperature in the furnace corresponding to each characteristic data in the current furnace mouth flame characteristic data set to obtain a temperature change curve based on time;
and S4, predicting the blowing end point based on the smelting end point temperature corresponding to the temperature change curve.
Furthermore, in the third step, when the temperature change curve is generated, obviously wrong data needs to be removed.
Further, when predicting the smelting temperature in the furnace corresponding to the characteristic data in the current fire hole flame characteristic data set, the method comprises the following steps:
s3.1, extracting a plurality of fire hole flame characteristic vectors;
s3.2, normalizing the input variables of the LSTM prediction model, specifically converting a data set by using a series _ to _ superimposed () function, and converting data into a plurality of input variables and 1 output variable;
s3.3, randomly dividing the data set into a training set and a testing set, wherein the training set is used for training and learning of the LSTM prediction model, and the testing set is used for evaluating and testing the LSTM prediction model to obtain a corrected LSTM prediction model;
and S3.4, predicting the smelting temperature in the furnace corresponding to the characteristic data in the flame characteristic data set of the current furnace mouth through the corrected LSTM prediction model.
Further, in step S3.1, the extracted fire hole flame feature vector includes, but is not limited to, a luminance value, a rotation-invariant LBP feature value, and a HOG feature value.
Further, in step S3.3, the ratio of the training set to the test set generated randomly is 9: 1.
Compared with the prior art, the invention has the beneficial effects that: the method adopts a flame image recognition mode to predict the temperature, is safe and convenient, can realize continuous temperature detection and real-time prediction of a temperature curve, improves the accuracy of the end point temperature of the converter by using the flame image recognition mode, and reduces the secondary blowing proportion by 30 percent compared with the method of judging the smelting end point only by depending on manual experience, wherein the temperature precision is +/-15 ℃.
Drawings
FIG. 1 is a schematic block diagram of a system for predicting the steelmaking end point temperature of a converter based on flame images.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the protection scope of the present invention.
A prediction system for judging the steelmaking end point temperature of a converter based on a flame image comprises:
the image acquisition unit is used for continuously acquiring original flame images of the furnace mouth; in this embodiment, the image obtaining unit is preferably a camera, the image processing module, the temperature prediction module and the endpoint prediction module together form a computer system, where it should be noted that the computer system further includes other modules, such as a storage module, and the camera and the computer system are connected by a network, a USB cable or a serial port.
The camera is arranged right above the converter mouth of the converter, the lens of the camera is over against the position of the observation hole in the converter blowing process, the visual angle of the lens is-45-45 degrees, in the embodiment, the visual angle of the lens is 40 degrees, and the distance between the camera and the converter is 20 meters, so that the camera can collect flame in the smelting process.
After the blowing starts, a video camera starts to capture and acquire images, images of flames are directly acquired at the speed of 2 times/s, the focal distance of the video camera is adjusted to be directly aligned to the central area of the flames during shooting, 5 images of 64 pixels by 64 pixels near the central area are extracted from each flame image, and the images with the size of 64 are input uniformly to be used as extracted image features.
The digital camera is fixed by a special bracket additionally provided with a heat insulation protective cover, the protective cover is made of high-temperature-resistant quartz glass, the height of the camera can be adjusted by the bracket, and the shooting angle can be rotatably adjusted. The special bracket is arranged in a region where people see fire, and the height and the angle are adjusted to ensure that the camera can shoot the flame at the converter mouth.
The image processing module is used for respectively processing the continuously acquired original furnace mouth flame images to obtain the current furnace mouth flame characteristics corresponding to each original furnace mouth flame image, and the current furnace mouth flame characteristic data set is obtained after the current furnace mouth flame characteristics are summarized; in the invention, the image processing module adopts HSI color space parameters to establish a color space model for an original fire hole flame image to obtain the current fire hole flame characteristics, wherein the current fire hole flame characteristics comprise but are not limited to the profile characteristics and the gray value parameters of the fire hole flame.
The temperature prediction module is used for predicting the smelting temperature in the furnace corresponding to each characteristic data in the current furnace mouth flame characteristic data set to obtain a temperature change curve based on time;
and the end point prediction module is used for predicting the blowing end point based on the smelting end point temperature corresponding to the temperature change curve.
Further, the prediction system further comprises a preprocessing module for preprocessing the original fire door flame image, and the preprocessing step at least comprises graying processing.
The invention relates to a method for predicting the steelmaking end point temperature of a converter based on a flame image, which comprises the following steps:
s1, continuously acquiring original flame images of the fire door;
s2, respectively processing the continuously acquired original fire door flame images to obtain current fire door flame characteristics corresponding to each original fire door flame image, and summarizing to obtain a current fire door flame characteristic data set;
s3, respectively predicting the smelting temperature in the furnace corresponding to each characteristic data in the current furnace mouth flame characteristic data set to obtain a temperature change curve based on time, and removing obviously wrong data when generating the temperature change curve;
and S4, predicting the blowing end point based on the smelting end point temperature corresponding to the temperature change curve.
And step three, when the furnace smelting temperature corresponding to the characteristic data in the current furnace mouth flame characteristic data set is predicted, the method comprises the following steps:
s3.1, extracting a plurality of fire door flame characteristic vectors, wherein the extracted fire door flame characteristic vectors include but are not limited to a brightness value, a rotation invariant LBP characteristic value and an HOG characteristic value;
the specific extraction method comprises the following steps:
1. extracting a brightness value: acquiring the brightness value of a picture by adopting a PIL module in python;
2. extracting a rotation invariant Local Binary Pattern (LBP) characteristic value: the LBP is used to extract image texture features. After the radius and the number of the sampling points are determined, the positions of the sampling points in the circular neighborhood are continuously rotated to obtain a series of LBP characteristic values, and the minimum value is selected to serve as the LBP characteristic value of an LBP center pixel point;
3. extracting directional gradient Histogram (HOG) feature values: the HOG operates on local grid cells of the image and remains well invariant to both geometric and optical distortions of the image.
S3.2, the LSTM is a time-recursive neural network, can perfectly solve the problem of a plurality of input variables, and aims to develop an LSTM model for multivariate time series prediction in a Keras deep learning library. This step S3.2 aims at preparing a temperature prediction data set for the LSTM prediction model, treating the data set as a supervised learning problem and normalizing the input variables, specifically using a series _ to _ superimposed () function to convert the data set, converting the data into 3 input variables (luminance values, LBP, HOG) and 1 output variable (temperature);
s3.3, randomly dividing the data set into a training set and a testing set, wherein in the embodiment, the proportion of the randomly generated training set and the testing set is 9: 1, the training set is used for training and learning of the LSTM prediction model, the testing set is used for evaluating and testing the LSTM prediction model, and the input (X) is reconstructed into a 3D format expected by the LSTM prediction model, namely [ sample, time step length, characteristics ] to obtain the corrected LSTM prediction model;
further: (1) the number of the hidden layers and the number of the nerve units of the hidden layers can be adjusted according to the actual needs of the users;
(2) using a Mean Absolute Error (MAE) loss function in an LSTM prediction model, then tracking the training and testing failures in the training process by setting a validation _ data parameter in a fit () function, and drawing the training and testing losses when the operation is finished;
(3) combining the prediction set with the test set, and performing inverse scaling, wherein the scaling of the test data set can also be performed by using expected pollution figures;
(4) using the predicted and actual values, the error fraction of the model can be calculated, and the Root Mean Square Error (RMSE) of the error in the same units as the variables themselves can also be calculated.
And S3.4, predicting the smelting temperature in the furnace corresponding to the characteristic data in the flame characteristic data set of the current furnace mouth through the corrected LSTM prediction model.
The method adopts a flame image recognition mode to predict the temperature, is safe and convenient, can realize continuous temperature detection and real-time prediction of a temperature curve, improves the accuracy of the end point temperature of the converter by using the flame image recognition mode, and reduces the secondary blowing proportion by 30 percent compared with the method of judging the smelting end point only by depending on manual experience, wherein the temperature precision is +/-15 ℃.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A prediction system for judging the steelmaking end point temperature of a converter based on a flame image is characterized by comprising:
the image acquisition unit is used for continuously acquiring original flame images of the furnace mouth;
the image processing module is used for respectively processing the continuously acquired original furnace mouth flame images to obtain the current furnace mouth flame characteristics corresponding to each original furnace mouth flame image, and the current furnace mouth flame characteristic data set is obtained after the current furnace mouth flame characteristics are summarized;
the temperature prediction module is used for predicting the smelting temperature in the furnace corresponding to each characteristic data in the current furnace mouth flame characteristic data set to obtain a temperature change curve based on time;
and the end point prediction module is used for predicting the blowing end point based on the smelting end point temperature corresponding to the temperature change curve.
2. The system of claim 1, wherein the image processing module uses HSI color space parameters to build a color space model for the original fire hole flame image to obtain the current fire hole flame characteristics, and the current fire hole flame characteristics include but are not limited to the profile characteristics and the gray value parameters of the fire hole flame.
3. The system of claim 1, further comprising a preprocessing module for preprocessing the original fire door flame image, wherein the preprocessing step comprises at least graying.
4. The system of claim 1, wherein the image acquisition unit is a camera, the image processing module, the temperature prediction module and the endpoint prediction module together form a computer system, and the camera is connected to the computer system via a network, a USB (universal serial bus) cable or a serial port.
5. The system of claim 4, wherein the camera has a lens facing the position of the observation hole during the blowing process of the converter, and the camera acquires the original flame image at the furnace mouth at a frequency of 2 times/s.
6. A prediction method for judging the steelmaking end point temperature of a converter based on a flame image is characterized by comprising the following steps:
s1, continuously acquiring original flame images of the fire door;
s2, respectively processing the continuously acquired original fire door flame images to obtain current fire door flame characteristics corresponding to each original fire door flame image, and summarizing to obtain a current fire door flame characteristic data set;
s3, respectively predicting the smelting temperature in the furnace corresponding to each characteristic data in the current furnace mouth flame characteristic data set to obtain a temperature change curve based on time;
and S4, predicting the blowing end point based on the smelting end point temperature corresponding to the temperature change curve.
7. The prediction method according to claim 6, wherein: and step three, when the temperature change curve is generated, obviously wrong data needs to be removed.
8. The prediction method according to claim 6, wherein: and step three, when the furnace smelting temperature corresponding to the characteristic data in the current furnace mouth flame characteristic data set is predicted, the method comprises the following steps:
s3.1, extracting a plurality of fire hole flame characteristic vectors;
s3.2, normalizing the input variables of the LSTM prediction model, specifically converting a data set by using a series _ to _ superimposed () function, and converting data into a plurality of input variables and 1 output variable;
s3.3, randomly dividing the data set into a training set and a testing set, wherein the training set is used for training and learning of the LSTM prediction model, and the testing set is used for evaluating and testing the LSTM prediction model to obtain a corrected LSTM prediction model;
and S3.4, predicting the smelting temperature in the furnace corresponding to the characteristic data in the flame characteristic data set of the current furnace mouth through the corrected LSTM prediction model.
9. The prediction method according to claim 8, wherein: in step S3.1, the extracted fire hole flame feature vector includes, but is not limited to, a luminance value, a rotation-invariant LBP feature value, and a HOG feature value.
10. The prediction method according to claim 8, wherein: in step S3.3, the ratio of the training set to the test set generated randomly is 9: 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110944596.0A CN113718082A (en) | 2021-08-17 | 2021-08-17 | Prediction system and method for judging steelmaking end point temperature of converter based on flame image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110944596.0A CN113718082A (en) | 2021-08-17 | 2021-08-17 | Prediction system and method for judging steelmaking end point temperature of converter based on flame image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113718082A true CN113718082A (en) | 2021-11-30 |
Family
ID=78676135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110944596.0A Pending CN113718082A (en) | 2021-08-17 | 2021-08-17 | Prediction system and method for judging steelmaking end point temperature of converter based on flame image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113718082A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132667A (en) * | 2023-10-26 | 2023-11-28 | 湖南半岛医疗科技有限公司 | Thermal image processing method and related device based on environmental temperature feedback |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101698896A (en) * | 2009-09-28 | 2010-04-28 | 南京理工大学 | System and method for steel-making online end-point control through furnace mouth radiation information fusion |
| CN102206727A (en) * | 2011-05-31 | 2011-10-05 | 湖南镭目科技有限公司 | Converter steelmaking endpoint determination method and system, control method and control system |
| CN102876838A (en) * | 2012-10-30 | 2013-01-16 | 湖南镭目科技有限公司 | System for detecting carbon content and temperature in converter |
-
2021
- 2021-08-17 CN CN202110944596.0A patent/CN113718082A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101698896A (en) * | 2009-09-28 | 2010-04-28 | 南京理工大学 | System and method for steel-making online end-point control through furnace mouth radiation information fusion |
| CN102206727A (en) * | 2011-05-31 | 2011-10-05 | 湖南镭目科技有限公司 | Converter steelmaking endpoint determination method and system, control method and control system |
| CN102876838A (en) * | 2012-10-30 | 2013-01-16 | 湖南镭目科技有限公司 | System for detecting carbon content and temperature in converter |
Non-Patent Citations (3)
| Title |
|---|
| 何涛焘等: "基于炉口火焰信息的转炉炼钢终点预报系统", 《中国冶金》 * |
| 曾鹏飞 等: "基于二次相似性度量的即时学习转炉炼钢终点碳温软测量方法", 《计算机集成制造系统》 * |
| 江帆等: "基于火焰图像CNN的转炉炼钢吹炼终点判断方法", 《计算机工程》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132667A (en) * | 2023-10-26 | 2023-11-28 | 湖南半岛医疗科技有限公司 | Thermal image processing method and related device based on environmental temperature feedback |
| CN117132667B (en) * | 2023-10-26 | 2024-02-06 | 湖南半岛医疗科技有限公司 | Thermal image processing method and related device based on environmental temperature feedback |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
| CN110438284B (en) | Intelligent tapping device of converter and control method | |
| CN109271844B (en) | Electrical cabinet electrical symbol recognition method based on OpenCV | |
| CN109993154B (en) | Intelligent identification method for single-pointer sulfur hexafluoride instrument of transformer substation | |
| CN111598889B (en) | Identification method and device for inclination fault of equalizing ring and computer equipment | |
| CN106096603A (en) | A kind of dynamic flame detection method merging multiple features and device | |
| CN109196553B (en) | Photovoltaic panel identification method, ground station, control equipment and unmanned aerial vehicle | |
| CN116721107B (en) | Intelligent monitoring system for cable production quality | |
| CN110726725A (en) | Transmission line hardware corrosion detection method and device | |
| CN113718082A (en) | Prediction system and method for judging steelmaking end point temperature of converter based on flame image | |
| CN111047598B (en) | Deep learning-based ultraviolet discharge light spot segmentation method and device for power transmission and transformation equipment | |
| CN112828275B (en) | Automatic slag skimming method, device and system | |
| CN111626104B (en) | Cable hidden trouble point detection method and device based on unmanned aerial vehicle infrared thermal image | |
| Wu et al. | Experimental analysis of image dehazing algorithms for pelletization process images | |
| CN111222360A (en) | Method and device for detecting melting state of silicon material and storage medium | |
| CN111931785A (en) | Edge detection method for infrared image target of power equipment | |
| CN112560574A (en) | River black water discharge detection method and recognition system applying same | |
| CN109784257B (en) | Transformer thermometer detection and identification method | |
| CN108830834B (en) | Automatic extraction method for video defect information of cable climbing robot | |
| CN108492292B (en) | Infrared image processing-based wire strand scattering detection method | |
| CN115147349A (en) | Method and device for determining smelting end point of converter, electronic equipment and storage medium | |
| CN114332069B (en) | Connector detection method and device based on machine vision | |
| Yang et al. | An intelligent identification algorithm for obtaining the state of power equipment in SIFT-based environments | |
| CN111429411B (en) | X-ray defect image sample generation method for carbon fiber composite core wire | |
| CN114187282A (en) | Grate cooler bed thickness measuring method based on image segmentation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211130 |