CN113409343A - Real-time solid fuel material layer thickness measuring method - Google Patents
Real-time solid fuel material layer thickness measuring method Download PDFInfo
- Publication number
- CN113409343A CN113409343A CN202110664020.9A CN202110664020A CN113409343A CN 113409343 A CN113409343 A CN 113409343A CN 202110664020 A CN202110664020 A CN 202110664020A CN 113409343 A CN113409343 A CN 113409343A
- Authority
- CN
- China
- Prior art keywords
- image
- thickness
- combustion
- solid fuel
- material layer
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to the technical field of combustion measurement, and particularly discloses a method for measuring the thickness of a solid fuel material layer in real time, which comprises the following steps: (1) shooting a solid fuel combustion image to obtain a combustion image; (2) converting the combustion image into a characteristic image; (3) segmenting the characteristic image to obtain a binary image; (4) identifying the position of a burning live wire in the binary image; and calculating the thickness of the fuel material layer according to the position of the fire line. The measuring method is a non-contact real-time solid fuel thickness measuring method, has no influence on the combustion process, has low equipment cost, can be used for shooting flame by adopting a common camera, is not influenced by the porosity of a fuel layer, directly measures the thickness, has smaller error and better robustness, can obtain the height spatial distribution condition of the fuel layer, and has important significance on the application in the field of high-temperature combustion.
Description
Technical Field
The invention relates to the technical field of combustion measurement, in particular to a method for measuring the thickness of a solid fuel material layer in real time.
Background
In the process of burning the solid fuel, due to the influences of the spatial characteristics of flame temperature, turbulence, burning conditions and the like, the burning of all parts of the material layer is not uniform. The uneven burning results in inconsistent thickness of the material layers of the solid fuel. Under the scene that solid fuel needs to be continuously supplemented and the combustion stability is kept, such as thermal power generation, waste incineration power generation and the like, the measurement of the thickness of a solid material layer is very important. If the distribution condition of the thickness of each part of the material layer can be measured, corresponding adjustment can be made according to the thickness condition of each part, so that the solid fuel is uniformly combusted, which has very important significance for the actual production process
In the existing combustion state monitoring technology and combustion diagnosis technology, no technology capable of measuring the thickness of a fuel material layer exists. At present, relevant researches only stay in the field of theoretical calculation, and a combustion model is established by a method of calculating fluid mechanics, so that the thickness variation condition of the fuel under various conditions is predicted (Alobaid F, Al-Maliki W A K, Lanz T, et Al. dynamic simulation of a mechanical solid water intake [ J ]. Energy,2018,149: 230-. And because the calculation process needs to consume a large amount of calculation power, the calculation time is very long, and the method cannot be applied to an actual detection scene.
CN211317391U and CN102865582A disclose a device for measuring the differential pressure and thickness of a garbage layer in a garbage incinerator, which respectively provide a method for estimating the thickness of a solid fuel material layer by measuring the differential pressure above and below the bed layer, and the conversion relationship between the pressure measurement position and the pressure thickness is different. The essence of the method is that the pressure difference is used for reflecting the change condition of the thickness of the material layer, the change condition is influenced by factors such as porosity, viscosity and the like of the material layer, the change of the thickness can only be reflected indirectly, and larger errors exist. Meanwhile, because the pressure measurement belongs to point measurement, the spatial distribution information about the fuel thickness cannot be obtained, and the thickness difference of the solid fuel material layer in each region cannot be distinguished. Therefore, the method has great limitation in the practical application process.
Disclosure of Invention
Aiming at the problem that the fuel thickness cannot be accurately measured in the prior art, the invention provides the image-based real-time solid fuel layer thickness measuring method, the fuel layer thickness is directly obtained in real time by utilizing image information, the method is simple and convenient, the measuring result is more accurate, and the method has important significance for the high-temperature combustion industry.
In order to achieve the purpose, the invention adopts the technical scheme that:
a real-time solid fuel layer thickness measuring method comprises the following steps:
(1) taking a solid fuel combustion image: shooting the solid fuel in the fuel chamber by using a common camera to obtain a combustion image;
(2) converting the combustion image into a characteristic image: projecting the combustion image to a characteristic space to obtain a characteristic image F, wherein the formula of the characteristic change process is as follows:
F＝f(I)
wherein f (.) represents the mapping of the original image space to the feature space, and I represents the original image;
(3) segmenting the characteristic image: selecting a proper threshold value xi to segment the characteristic image F obtained in the step (2), wherein the value which is greater than or equal to the threshold value is marked as 1, the value which is lower than the threshold value is marked as 0, and a binary image is obtained, wherein the segmentation formula is as follows:
b represents a binary image, I represents an original image, I and j represent the ith row and the jth column of pixel points in the image; ξ represents a selected threshold;
(4) identifying the position of a burning live wire in a binary image: carrying out contour detection on the binary image by adopting a selected threshold value, wherein the upper edge of the contour is a burning live wire position;
(5) calculating the thickness of the fuel material layer: and (4) calculating the thickness of the solid fuel material layer in real time by taking the bottom position of the fuel as a reference position according to the position of the firing line in the step (4), wherein a specific calculation formula is as follows:
hm＝ym，b-ym，f
wherein h ismDenotes the thickness of the bed at position m, ym，fIndicating the position of the fire line at position m, ym，bIndicating the fuel reference position at position m.
Preferably, in step (2), when the boundary between the flame region and the non-flame region in the combustion image is obvious, the characteristic change process is to convert the combustion image into a gradient image, the threshold value calculated in the gradient image has a more ideal effect, and the calculation result is more accurate, and the formula converted into the gradient image is as follows:
wherein I represents the original image, GyRepresented as a gradient image in the y-direction.
Preferably, in the step (2), when the boundary between the flame region and the non-flame region in the combustion image is not obvious, the characteristic change process is to convert the combustion image into a gray scale space, and the conversion formula is specifically as follows:
Gray＝0.299R+0.578G+0.114B
where Gray represents a Gray scale image and R, G, B represents the intensity values of the red, green, and blue channels in the combustion image, respectively.
Preferably, according to the histogram characteristics of the feature image, the initial threshold is calculated by a triangular threshold method for a unimodal distribution, and the initial threshold is calculated by an Otsu method for a bimodal distribution, so as to obtain a suitable threshold.
Further preferably, because the triangle threshold method and the Otsu method are influenced by the bandwidth precision of histogram selection of the feature image, after the initial threshold value is calculated based on the histogram threshold value selection triangle and the Otsu method, a more accurate threshold value is selected by adopting a manual fine adjustment mode according to the material layer segmentation effect.
Preferably, when the acquired combustion image has large noise, a low-pass filter is adopted to smooth the image, so that noise interference is reduced, and the accuracy of measurement is improved.
Preferably, a series of images are obtained by adopting a continuous multi-time shooting method, and an average value obtained according to the threshold values of the series of images is used as a final threshold value, so that the robustness in the practical application process is improved; the calculation formula of the threshold is as follows:
where n is the number of images used, ξkThe threshold value of the k-th graph is shown.
Preferably, a series of continuous images are obtained by adopting a video shooting method, and an average value obtained according to threshold values of the series of images is used as a final threshold value; the calculation formula of the threshold is as follows:
where n is the number of images used, ξkThe threshold value of the k-th graph is shown.
Preferably, when a fixed and unchanging region exists in the shot combustion image, the threshold value is calculated by cutting the image into a plurality of sub-images according to the region of interest. For example, when the furnace wall or two combustion areas exist, the method can be adopted to cut the image and respectively calculate the threshold value, thereby improving the accuracy of the measurement result.
Preferably, when a fixed area exists in the shot combustion image, the image is divided into a plurality of areas with the same size by adopting an adaptive threshold algorithm, the threshold values are respectively calculated, and then the final threshold value is calculated by adopting an averaging method or a Gaussian weighted averaging method according to the threshold values of the adjacent areas. The accuracy of the measurement result obtained in this way is higher, and the situation in practical application is better met.
Regarding the determination of the position of the fire line, the contour is the boundary between 0 and 1 in the binary image, and since the intensity of the combustion image is high when the material and the flame exist simultaneously, the upper edge of the selected contour is the position of the fire line, and is usually the height position of the remaining fuel.
Compared with the prior art, the invention has the following beneficial effects:
the measuring method is a non-contact real-time solid fuel thickness measuring method, has no influence on the combustion process, has low equipment cost compared with other thickness measuring methods, can be used for shooting flame by adopting a common camera, is not influenced by the porosity of a fuel layer, directly measures the thickness, has smaller error and better robustness, can obtain the height spatial distribution condition of the fuel layer, is more reliable in theory, and has important significance on the application in the field of high-temperature combustion.
Drawings
FIG. 1 is a schematic view of the measurement method of the present invention.
Fig. 2 is a schematic view of the structure of the apparatus in example 1, in which 1 is a burning solid fuel, 2 is an infrared camera, and 3 is a computer.
Fig. 3 is a combustion image taken by a general camera in example 1.
Fig. 4 is a characteristic image obtained by conversion in example 1.
Fig. 5 is a binarized image calculated in example 1.
FIG. 6 shows the position of the fire line of the combustion image in example 1.
Fig. 7 is the results of the calculated measured thickness of the solid fuel layer in example 1.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Those skilled in the art should understand that they can make modifications and equivalents without departing from the spirit and scope of the present invention, and all such modifications and equivalents are intended to be included within the scope of the present invention.
FIG. 1 is a schematic view of the measurement method of the present invention, which includes acquiring an image by a camera, converting the image into a characteristic image, segmenting the image by using a threshold value to obtain a binarized image, identifying a fire line, and finally calculating the thickness of a bed of solid fuel.
Example 1
The schematic structural diagram of the combustion testing device in the present embodiment is shown in fig. 2, and includes a solid fuel 1, a general camera 2 and a computer 3, where the computer 3 may also be a computing device with an image processing function integrated with the camera.
The application scenario in this embodiment is measurement of the thickness of a garbage material layer in a garbage incinerator, a grate-type household garbage incineration power plant with a daily throughput of 400 tons is used as a specific application scenario, a burning solid fuel 1 is household garbage which is burning in a hearth, a common camera 2 is a hearth monitoring camera to shoot solid comburent in the hearth, and a computer 3 can access pictures shot in the common camera 2 and perform calculation processing on the pictures. When the incinerator is in operation, the monitoring camera is normally operated, the picture of the monitoring camera faces to the burning tail end of the garbage incinerator, and the ordinary camera 2 obtains the burning tail end image, as shown in fig. 3, which is the obtained original burning image.
Since there is no obvious feature in the flame region and the boundary of the non-flame region in the combustion image in this embodiment, the combustion image is converted into a Gray space, and R, G, B channel values of combustion I are substituted into Gray 0.299R +0.578G +0.114B, so as to obtain a feature image as shown in fig. 4, where some fixed pictures in the combustion image have been cut and removed, and the selected region range is [ 100: 1000, 80: 600 ].
Because the monitoring pictures in the camera are continuous video signals, according to the histogram characteristics of the characteristic images, the Otsu method is adopted to calculate the gray level image threshold of each frame of picture in a continuous period of time, the average 167 is taken as the threshold, the video which normally runs for 8 hours is selected, and the average threshold is calculated by totaling the threshold calculated by 576000 frames of pictures.
The image is segmented by using the threshold value, the intensity value of the image is greater than or equal to the threshold value and is marked as 1, the intensity value of the image is lower than the threshold value and is marked as 0, a binary image is obtained, and the segmentation formula is as follows:
b represents a binary image, I represents an original image, I and j represent the ith row and the jth column of pixel points in the image; ξ represents a selected threshold; the obtained binary image is subjected to contour detection as shown in fig. 5, a boundary between 0 and 1 is found, and an upper edge of the contour is obtained as a position of a burning fire line, so that a position of the fire line as shown in fig. 6 is obtained. Selecting a fuel bottom position 0 as a reference position, and calculating the thickness of a solid fuel material layer in real time, wherein the specific calculation formula is as follows:
h0＝y0，b-y0，f
wherein h is0Denotes the thickness of the bed at position 0, y0，fIndicating the fire line position at position 0, y0，bIndicating the fuel reference position at position 0. Live line position y at position 00，f165, fuel bottom position y at position 00，b180 to obtain h0180-165, so that the fuel layer thickness at position 0 is known to be 15, the layer thicknesses at other positions are calculated in the same manner, resulting in the thickness measurement shown in fig. 7.
Claims (10)
1. A real-time measurement method for the thickness of a solid fuel material layer is characterized by comprising the following steps:
(1) taking a solid fuel combustion image: shooting the solid fuel in the fuel chamber by using a common camera to obtain a combustion image;
(2) converting the combustion image into a characteristic image: projecting the combustion image to a characteristic space to obtain a characteristic image F, wherein the formula of the characteristic change process is as follows:
F＝f(I)
wherein f (.) represents the mapping of the original image space to the feature space, and I represents the original image;
(3) segmenting the characteristic image: selecting a proper threshold value xi to segment the characteristic image F obtained in the step (2), wherein the value which is greater than or equal to the threshold value is marked as 1, the value which is lower than the threshold value is marked as 0, and a binary image is obtained, wherein the segmentation formula is as follows:
b represents a binary image, I represents an original image, I and j represent the ith row and the jth column of pixel points in the image; ξ represents a selected threshold;
(4) identifying the position of a burning live wire in a binary image: carrying out contour detection on the binary image by adopting a selected threshold value, wherein the upper edge of the contour is a burning live wire position;
(5) calculating the thickness of the fuel material layer: and (4) calculating the thickness of the solid fuel material layer in real time by taking the bottom position of the fuel as a reference position according to the position of the firing line in the step (4), wherein a specific calculation formula is as follows:
hm＝ym,b-ym,f
wherein h ismDenotes the thickness of the bed at position m, ym,fIndicating the position of the fire line at position m, ym,bIndicating the fuel reference position at position m.
2. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1, wherein in the step (2), when the boundary between the flame region and the non-flame region in the combustion image is obvious, the characteristic change process is to convert the combustion image into a gradient image, and the formula for converting the gradient image is as follows:
wherein I represents the original image, GyRepresented as a gradient image in the y-direction.
3. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1, wherein in the step (2), when the boundary between the flame region and the non-flame region in the combustion image is not obvious, the characteristic change process is to convert the combustion image into a gray space, and the conversion formula is specifically as follows:
Gray＝0.299R+0.578G+0.114B
where Gray represents a Gray scale image and R, G, B represents the intensity values of the red, green, and blue channels in the combustion image, respectively.
4. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1, wherein according to the histogram characteristics of the characteristic image, the initial threshold value is calculated by a triangular threshold method for a unimodal distribution, and the initial threshold value is calculated by an Otsu method for a bimodal distribution, so that a proper threshold value is obtained.
5. The method according to claim 1, wherein after the initial threshold is calculated by using a triangle and/or Otsu method based on the histogram threshold, a more accurate threshold is selected by using a manual fine adjustment method according to the bed segmentation effect.
6. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1, wherein when the acquired combustion image has large noise, the image is smoothed by a low-pass filter, so that noise interference is reduced.
7. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1 is characterized in that a series of images are obtained by adopting a method of continuously shooting for multiple times, and an average value obtained according to threshold values of the series of images is used as a final threshold value; the calculation formula of the threshold is as follows:
where n is the number of images used, ζkThe threshold value of the k-th graph is shown.
8. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1 is characterized in that a series of continuous images are obtained by adopting a video shooting method, and an average value obtained according to a threshold value of the series of images is used as a final threshold value; the calculation formula of the threshold is as follows:
where n is the number of images used, ζkThe threshold value of the k-th graph is shown.
9. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1, wherein when a fixed and invariable area exists in a shot combustion image, the threshold value is calculated by cutting the image into a plurality of sub-images according to the area of interest.
10. The method for measuring the thickness of the solid fuel material layer in real time according to claim 1, wherein when a fixed area exists in a shot combustion image, an adaptive threshold algorithm is adopted to divide the image into a plurality of areas with the same size, the threshold values are respectively calculated, and then an averaging method or a Gaussian weighted averaging method is adopted to calculate the final threshold value according to the threshold values of the adjacent areas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110664020.9A CN113409343B (en) | 2021-06-16 | 2021-06-16 | Real-time solid fuel material layer thickness measuring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110664020.9A CN113409343B (en) | 2021-06-16 | 2021-06-16 | Real-time solid fuel material layer thickness measuring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113409343A true CN113409343A (en) | 2021-09-17 |
| CN113409343B CN113409343B (en) | 2022-03-15 |
Family
ID=77684012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110664020.9A Active CN113409343B (en) | 2021-06-16 | 2021-06-16 | Real-time solid fuel material layer thickness measuring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113409343B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2073147A1 (en) * | 2007-12-21 | 2009-06-24 | Daon Holdings Limited | Generic biometric filter |
| US20160128661A1 (en) * | 2010-08-12 | 2016-05-12 | Heartflow, Inc. | Method and system for image processing to determine patient-specific blood flow characteristics |
| CN106767458A (en) * | 2016-12-29 | 2017-05-31 | 中核北方核燃料元件有限公司 | Each thickness degree method for automatic measurement of coated fuel particles |
| CN107730548A (en) * | 2017-10-23 | 2018-02-23 | 厦门诺银科技有限公司 | It is a kind of based on average gray and area towards heating furnace flame real-time detection method |
| CN108759664A (en) * | 2018-05-22 | 2018-11-06 | 湖南瑞智健科技有限公司 | A kind of nuclear fuel rod size detecting method and system based on telecentric optics |
| US20180361588A1 (en) * | 2016-01-27 | 2018-12-20 | South China University Of Technology | Multiple Lens-Based Smart Mechanical Arm and Positioning and Assembly Method Thereof |
| CN109145689A (en) * | 2017-06-28 | 2019-01-04 | 南京理工大学 | A kind of robot fire detection method |
-
2021
- 2021-06-16 CN CN202110664020.9A patent/CN113409343B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2073147A1 (en) * | 2007-12-21 | 2009-06-24 | Daon Holdings Limited | Generic biometric filter |
| US20160128661A1 (en) * | 2010-08-12 | 2016-05-12 | Heartflow, Inc. | Method and system for image processing to determine patient-specific blood flow characteristics |
| US20180361588A1 (en) * | 2016-01-27 | 2018-12-20 | South China University Of Technology | Multiple Lens-Based Smart Mechanical Arm and Positioning and Assembly Method Thereof |
| CN106767458A (en) * | 2016-12-29 | 2017-05-31 | 中核北方核燃料元件有限公司 | Each thickness degree method for automatic measurement of coated fuel particles |
| CN109145689A (en) * | 2017-06-28 | 2019-01-04 | 南京理工大学 | A kind of robot fire detection method |
| CN107730548A (en) * | 2017-10-23 | 2018-02-23 | 厦门诺银科技有限公司 | It is a kind of based on average gray and area towards heating furnace flame real-time detection method |
| CN108759664A (en) * | 2018-05-22 | 2018-11-06 | 湖南瑞智健科技有限公司 | A kind of nuclear fuel rod size detecting method and system based on telecentric optics |
Non-Patent Citations (1)
| Title |
|---|
| 张学宏: "倒转炉排抛煤机链条炉燃烧过程的初步分析", 《浙江大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113409343B (en) | 2022-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105956618B (en) | Converter steelmaking blowing state identification system and method based on image dynamic and static characteristics | |
| CN108428231B (en) | Multi-parameter part surface roughness learning method based on random forest | |
| US11636584B2 (en) | Real-time traceability method of width of defect based on divide-and-conquer | |
| CN110906875B (en) | Visual processing method for aperture measurement | |
| CN110926339A (en) | Real-time three-dimensional measurement method based on one-time projection structured light parallel stripe pattern | |
| CN109754019B (en) | Method for continuously monitoring combustion condition of boiler | |
| CN112651968A (en) | Wood board deformation and pit detection method based on depth information | |
| JP2014228357A (en) | Crack detecting method | |
| KR101868483B1 (en) | Prediction of two blur parameters of edges in varying contrast | |
| CN113674280A (en) | Method for measuring temperature of hearth of power station boiler | |
| CN112561875A (en) | Photovoltaic cell panel coarse grid detection method based on artificial intelligence | |
| CN112241970A (en) | Schlieren imaging-based gas-liquid two-phase gas-liquid flow field velocity measuring method and system | |
| CN110160661B (en) | Object surface temperature measuring method and device based on visible light photo | |
| CN116843682A (en) | Boiler thermal efficiency on-line detection and analysis system using thermal infrared imager | |
| CN117522864B (en) | European pine plate surface flaw detection method based on machine vision | |
| CN114973010A (en) | Remote sensing water depth inversion model migration method based on no prior data | |
| CN117195439B (en) | Intelligent optimization method for large-shaft-diameter full-section mechanical sealing performance | |
| CN113409343B (en) | Real-time solid fuel material layer thickness measuring method | |
| CN117910073A (en) | Artwork package design optimization system and method based on 3D printing technology | |
| CN112053341A (en) | Surface temperature measurement method of alloy material based on light reflectivity and artificial intelligence | |
| CN115205317B (en) | Bridge monitoring photoelectric target image light spot center point extraction method | |
| CN117593499A (en) | Hydropower station electromechanical equipment fault identification method based on distributed routing inspection strategy | |
| CN115880683B (en) | Urban waterlogging ponding intelligent water level detection method based on deep learning | |
| CN117146733A (en) | Comprehensive measurement method for high Wen Mubiao three-dimensional morphology and temperature field | |
| CN115423807A (en) | Cloth defect detection method based on outlier detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |