CN113947720A - Method for judging working state of density meter - Google Patents
Method for judging working state of density meter Download PDFInfo
- Publication number
- CN113947720A CN113947720A CN202111558015.6A CN202111558015A CN113947720A CN 113947720 A CN113947720 A CN 113947720A CN 202111558015 A CN202111558015 A CN 202111558015A CN 113947720 A CN113947720 A CN 113947720A
- Authority
- CN
- China
- Prior art keywords
- picture
- area
- air pressure
- pointer
- region
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 239000000126 substance Substances 0.000 claims description 9
- 241000283984 Rodentia Species 0.000 claims description 6
- VLPFTAMPNXLGLX-UHFFFAOYSA-N trioctanoin Chemical compound CCCCCCCC(=O)OCC(OC(=O)CCCCCCC)COC(=O)CCCCCCC VLPFTAMPNXLGLX-UHFFFAOYSA-N 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 abstract description 23
- 229910018503 SF6 Inorganic materials 0.000 description 25
- SFZCNBIFKDRMGX-UHFFFAOYSA-N sulfur hexafluoride Chemical compound FS(F)(F)(F)(F)F SFZCNBIFKDRMGX-UHFFFAOYSA-N 0.000 description 25
- 229960000909 sulfur hexafluoride Drugs 0.000 description 25
- 239000003086 colorant Substances 0.000 description 3
- 241000219307 Atriplex rosea Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L19/00—Details of, or accessories for, apparatus for measuring steady or quasi-steady pressure of a fluent medium insofar as such details or accessories are not special to particular types of pressure gauges
- G01L19/08—Means for indicating or recording, e.g. for remote indication
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L19/00—Details of, or accessories for, apparatus for measuring steady or quasi-steady pressure of a fluent medium insofar as such details or accessories are not special to particular types of pressure gauges
- G01L19/08—Means for indicating or recording, e.g. for remote indication
- G01L19/10—Means for indicating or recording, e.g. for remote indication mechanical
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N9/00—Investigating density or specific gravity of materials; Analysing materials by determining density or specific gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
A method for judging the working state of a density meter comprises the following steps: collecting a density meter picture; and B: establishing a training data set; and C: obtaining a detection model based on the training data set, wherein the detection model is used for detecting an air pressure critical area and a pointer area of a density meter picture; step D: inputting a to-be-detected densitometer picture into a detection model to obtain the coordinates and category information of the position rectangular frames of the air pressure critical area and the pointer area; step E: respectively cutting out an air pressure critical area picture and a pointer area picture according to the position rectangular frame coordinates; step F: judging whether the density meter is in the critical state of the air pressure at present according to the area intersection ratio; step G: when the density meter is in a non-air pressure critical state, respectively counting the number of corresponding pixels in the pointer area picture; step H: and judging the working state of the density table according to the number of the corresponding pixels. The invention solves the problems of large workload, low inspection efficiency and potential safety hazard existing in manual field inspection.
Description
Technical Field
The invention relates to the technical field of meter state detection, in particular to a method for judging the working state of a density meter.
Background
A large number of density meters are commonly arranged in a power distribution room, the appearance of the power distribution room is simple, and the power distribution room is composed of a colored pointer, a plurality of scale value numbers and two sections of arc scales with two different colors. The density meter can visually display the density value in the circuit breaker through a pointer and scales, and is an instrument device which needs to be checked when a power inspection worker goes to a site for inspection every time. Density table one has three states to judge: the first state is a normal air pressure state, and the pointer is positioned in the arc scale with the first color; the second state is an air pressure critical state, the pointer is located at the junction of the arc scale with the first color and the arc scale with the second color, and the routing inspection personnel needs to prepare for replacing the density relay corresponding to the density meter; the third state is the state that the air pressure is too low, and the pointer is located the scale arc of second colour this moment, and the personnel of patrolling and examining need change the density relay that this density table corresponds at once to patrol and examine and report on.
Because the number of power distribution rooms or switch stations of each power supply station is large, the current power distribution rooms are mainly inspected on site manually in daily life, and the problems of large workload, low inspection efficiency, potential safety hazards and the like exist.
Disclosure of Invention
The invention aims to provide a method for judging the working state of a density meter aiming at the defects in the background technology. According to the invention, the automatic judgment of three working states of normal air pressure, critical air pressure and low air pressure is automatically carried out according to the position relation between the critical air pressure region and the pointer region and the color of the pointer region by shooting the density meter picture by the robot, so that the method has the characteristics of simplicity in realization and high accuracy, can meet the performance requirement of the inspection machine, and perfectly solves the problems of large workload, low inspection efficiency and potential safety hazard in manual field inspection.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for judging the working state of a density meter comprises the following steps:
step A: collecting density meter pictures under different illumination and different angles;
and B: marking the density table pictures, storing the marking information of each density table picture into a corresponding marking information file, and establishing a training data set containing the density table pictures and the marking information file;
and C: training a target detection network based on the training data set to obtain a detection model, wherein the detection model is used for detecting an air pressure critical area and a pointer area of a density meter picture;
step D: inputting the picture of the density meter to be detected into the detection model to obtain the coordinates and the category information of the rectangular frames of the positions of the air pressure critical area and the pointer area in the picture of the density meter to be detected;
step E: respectively cutting an air pressure critical area picture and a pointer area picture from the to-be-detected density meter picture according to the position rectangular frame coordinates;
step F: acquiring an area intersection ratio of the atmospheric pressure critical region and the pointer region based on the atmospheric pressure critical region picture and the pointer region picture, judging whether a density meter is in an atmospheric pressure critical state currently according to the area intersection ratio, and executing the step G if the density meter is in a non-atmospheric pressure critical state;
step G: respectively counting the number of corresponding pixels in the pointer region picture;
step H: and judging the working state of the density table in a non-air pressure critical state according to the number of the corresponding pixels in the pointer region picture.
Preferably, in the step B, the following steps are performed:
step B1: respectively marking the position and the type name of an air pressure critical area and a pointer area in each density table picture;
step B2: correspondingly establishing a marking information file for each density table picture, and storing the marking information of each density table picture into the corresponding marking information file;
step B3: and establishing a training data set, wherein the training data set comprises all density table pictures and marking information files.
Preferably, in the step D, the following steps are performed:
step D1: inputting the to-be-detected density chart picture into a detection model;
step D2: the detection model respectively detects an air pressure critical area and a pointer area in the picture of the density meter to be detected;
step D3: and the detection model respectively returns the coordinates and the category information of the rectangular frames at the positions of the air pressure critical area and the pointer area in a first format.
Wherein:
the horizontal coordinate of the lower right corner of the position rectangular frame is represented;
label indicates whether the region detected by the detection model is a pressure critical region or a pointer region.
Preferably, in the step F, an area intersection ratio of the air pressure critical region and the pointer region is obtained according to a formula one;
wherein:
rato represents an area intersection ratio;
Indicating the area of the pointer region, and the coordinate value of the pointer region can be expressed as;
Indicating the area of the intersection of the pointer region and the critical region of air pressure.
Preferably, the coordinate value of the intersection region is obtained according to the coordinate values of the air pressure critical region and the pointer region;
Wherein:
preferably, the surface of the air pressure critical region is obtained based on the coordinate value of the air pressure critical regionProduct of large quantities;
obtaining the area of the intersection region according to the coordinate value of the intersection region;
preferably, in the step F, judging whether the density meter is currently in the air pressure critical state according to the area intersection ratio includes:
if the area intersection ratio Rato is larger than the preset value, the density meter is judged to be in the air pressure critical state currently, and otherwise, the density meter is in the non-air pressure critical state currently.
Preferably, in the step G, when the density meter is in a non-air pressure critical state, the method respectively counts the number of corresponding pixels in the pointer region picture, and includes the following steps:
step G1: resetting the width and height of the pointer area picture to be pixels;
step G2: enhancing the contrast and saturation of the pointer region picture after the step G1 is executed;
step G3: extracting a first color channel picture and a second color channel picture of the pointer area picture;
step G4: carrying out binarization processing on the first color channel picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number of first color pixels in the pointer region picture;
and carrying out binarization processing on the second color channel picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number of second color pixels in the pointer region picture.
Preferably, in the step H, the following steps are performed:
when in useAnd isWhen the pressure is too low, the density meter is in a state of too low air pressure;
when in useAnd isWhen, ifThe density meter is in a state of low air pressure, ifIf so, the density meter is in a normal air pressure state;
wherein:
gn represents the number of first color pixels;
rn denotes the number of second color pixels.
The beneficial effect that this application's technical scheme produced:
according to the invention, the automatic judgment of three working states of normal air pressure, critical air pressure and low air pressure is automatically carried out according to the position relation between the critical air pressure region and the pointer region and the color of the pointer region by shooting the density meter picture by the robot, so that the method has the characteristics of simplicity in realization and high accuracy, can meet the performance requirement of the inspection machine, and perfectly solves the problems of large workload, low inspection efficiency and potential safety hazard in manual field inspection.
Drawings
FIG. 1 is a flow diagram of a method of determining an operating state of a density table according to one embodiment of the present invention;
FIG. 2 is a schematic illustration of a sulfur hexafluoride density meter target detection scheme in accordance with one embodiment of the present invention;
FIG. 3 is a schematic illustration of the area intersection ratio Rato according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
A large number of density meters are commonly arranged in a power distribution room, the appearance of the power distribution room is simple, and the power distribution room is composed of a colored pointer, a plurality of scale value numbers and two sections of arc scales with two different colors. For example, the sulfur hexafluoride density meter can visually display the density value of sulfur hexafluoride in a sulfur hexafluoride breaker through a pointer and scales, and is an instrument device which needs to be checked by power inspection personnel when the power inspection personnel go to the site for inspection each time. Because the number of power distribution rooms or switch stations of each power supply station is large, the current power distribution rooms are mainly inspected on site manually in daily life, and the problems of large workload, low inspection efficiency, potential safety hazards and the like exist. In order to solve the problems, more and more intelligent power distribution room inspection robots are widely applied to power distribution rooms to replace manual work for daily inspection work, and aiming at judging the working state of a density meter, the method for judging the working state of the density meter is provided by the application, and is suitable for judging the working state of the meter with the following structure, wherein the meter structure consists of a colored pointer, a plurality of scale value numbers and two sections of arc scales with two different colors, including but not limited to a sulfur hexafluoride density meter, and as shown in fig. 2, one total three states of the sulfur hexafluoride density meter need to be judged: the first state is a normal state of air pressure, and the pointer is positioned in the green arc scale at the moment; the second state is an air pressure critical state, the pointer is positioned at the junction of the red arc scale and the green arc scale, and the routing inspection personnel needs to prepare for replacing a sulfur hexafluoride density relay corresponding to the sulfur hexafluoride density meter; the third state is a state with too low air pressure, at the moment, the pointer is positioned in the red scale arc, the inspector needs to immediately replace the sulfur hexafluoride density relay corresponding to the sulfur hexafluoride density meter and perform inspection and report, and the technical scheme of the invention is explained by taking the sulfur hexafluoride density meter as a specific embodiment.
As shown in fig. 1, the method specifically comprises the following steps:
step A: collecting density meter pictures under different illumination and different angles;
in this embodiment, the power distribution room inspection robot automatically inspects and collects 3000 sulfur hexafluoride density meter pictures containing various illumination and angles.
And B: marking the density table pictures, storing the marking information of each density table picture into a corresponding marking information file, and establishing a training data set containing the density table pictures and the marking information file;
preferably, in the step B, the following steps are performed:
step B1: respectively marking the position and the type name of an air pressure critical area and a pointer area in each density table picture;
step B2: correspondingly establishing a marking information file for each density table picture, and storing the marking information of each density table picture into the corresponding marking information file;
step B3: and establishing a training data set, wherein the training data set comprises all density table pictures and marking information files.
In this embodiment, the positions and type names of the air pressure critical region and the pointer region in each sulfur hexafluoride density table picture are marked by third-party marking software Labelimage, marking information is stored in an xml file corresponding to each picture, and finally a training data set including 3000 indicator light pictures and 3000 xml files is established.
And C: training a target detection network based on the training data set to obtain a detection model, wherein the detection model is used for detecting an air pressure critical area and a pointer area of a density meter picture;
in this embodiment, the YOLOv4 target detection network is trained by using the established training data set, so as to obtain a detection model Object _ detector capable of accurately detecting the air pressure critical area and the pointer area.
Step D: inputting the picture of the density meter to be detected into the detection model to obtain the coordinates and the category information of the rectangular frames of the positions of the air pressure critical area and the pointer area in the picture of the density meter to be detected;
preferably, in the step D, the following steps are performed:
step D1: inputting the to-be-detected density chart picture into a detection model;
step D2: the detection model respectively detects an air pressure critical area and a pointer area in the picture of the density meter to be detected;
step D3: and the detection model respectively returns the coordinates and the category information of the rectangular frames at the positions of the air pressure critical area and the pointer area in a first format.
Wherein:
the horizontal coordinate of the lower right corner of the position rectangular frame is represented;
label indicates whether the region detected by the detection model is a pressure critical region or a pointer region.
Step E: respectively cutting an air pressure critical area picture and a pointer area picture from the to-be-detected density meter picture according to the position rectangular frame coordinates;
step F: acquiring an area intersection ratio of the atmospheric pressure critical region and the pointer region based on the atmospheric pressure critical region picture and the pointer region picture, judging whether a density meter is in an atmospheric pressure critical state currently according to the area intersection ratio, and executing the step G if the density meter is in a non-atmospheric pressure critical state;
in this embodiment, as shown in fig. 3, it is determined whether the sulfur hexafluoride density meter is in the air pressure critical state or the non-air pressure critical state by determining an area intersection ratio Rato of the air pressure critical region and the pointer region, and if the area intersection ratio Rato is greater than a preset value, it is determined that the density meter is currently in the air pressure critical state, otherwise, the density meter is currently in the non-air pressure critical state. The preset value in this embodiment is 0.7, and the size of the preset value is set according to actual operation and is not a fixed value.
Preferably, in the step F, an area intersection ratio of the air pressure critical region and the pointer region is obtained according to a formula one;
wherein:
rato represents an area intersection ratio;
Indicating the area of the pointer region, and the coordinate value of the pointer region can be expressed as;
Indicating the area of the intersection of the pointer region and the critical region of air pressure.
In this embodiment, the rectangle A is the critical area of air pressure and the coordinate value is(ii) a Rectangle B is the pointer area and the coordinate value isThe rectangular area C is the intersection area of the air pressure critical area and the pointer area.
Preferably, the coordinate value of the intersection region is obtained according to the coordinate values of the air pressure critical region and the pointer region;
Wherein:
preferably, the area of the air pressure critical region is obtained according to the coordinate value of the air pressure critical region;
obtaining the area of the intersection region according to the coordinate value of the intersection region;
step G: respectively counting the number of corresponding pixels in the pointer region picture;
preferably, in the step G, when the density meter is in a non-air pressure critical state, the method respectively counts the number of corresponding pixels in the pointer region picture, and includes the following steps:
step G1: resetting the width and height of the pointer area picture to be pixels;
step G2: enhancing the contrast and saturation of the pointer region picture after the step G1 is executed;
step G3: extracting a first color channel picture and a second color channel picture of the pointer area picture;
step G4: carrying out binarization processing on the first color channel picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number of first color pixels in the pointer region picture;
and carrying out binarization processing on the second color channel picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number of second color pixels in the pointer region picture.
If the sulfur hexafluoride density table is in the non-atmospheric pressure critical state in step F, the number Gn of the green pixels and the number Rn of the red pixels in the picture of the pointer region are respectively counted, in this embodiment, three states of the sulfur hexafluoride density table are needed to be determined: the first state is a normal state of air pressure, and the pointer is positioned in the green arc scale at the moment; the second state is an air pressure critical state, the pointer is positioned at the junction of the red arc scale and the green arc scale, and the routing inspection personnel needs to prepare for replacing a sulfur hexafluoride density relay corresponding to the sulfur hexafluoride density meter; and the third state is a state that the air pressure is too low, the pointer is positioned in the red scale arc, and the inspector needs to replace the sulfur hexafluoride density relay corresponding to the sulfur hexafluoride density meter immediately and perform inspection and report.
Therefore, by judging the number Gn of green pixels and the number Rn of red pixels in the pointer region picture, it can be definitely known in which arc scale the current pointer is located.
The specific statistical method for the number of corresponding pixels of the pointer region picture comprises the following steps:
step G1: the width and height of the re-fix pointer region picture are both 30 pixels.
Step G2: and enhancing the contrast and the saturation of the pointer area picture with the fixed size, and increasing the color difference of the pixels.
Step G3: the green channel picture (G _ img) and the red channel picture (R _ img) of the pointer area map are extracted.
Step G4: and carrying out binarization processing on the G _ img picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number Gn of green pixels in the pointer region picture.
Step G5: and similarly, carrying out binarization processing on the R _ img picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number Rn of the red pixels in the pointer region picture.
Step H: and judging the working state of the density table in a non-air pressure critical state according to the number of the corresponding pixels in the pointer region picture.
Preferably, in the step H, the following steps are performed:
when in useAnd isWhen the pressure is too low, the density meter is in a state of too low air pressure;
when in useAnd isWhen, ifThe density meter is in a state of low air pressure, ifIf so, the density meter is in a normal air pressure state;
wherein:
gn represents the number of first color pixels;
rn denotes the number of second color pixels.
In this embodiment, taking a sulfur hexafluoride density table as an example, the first color pixel represents a green pixel, and the second color pixel represents a red pixel.
The method for judging the working state of the sulfur hexafluoride density meter according to the number of the pixels comprises the following steps:
(1) and isAnd then, the situation that no red pixel exists in the pointer area picture and only a green pixel exists is shown, and the sulfur hexafluoride density meter is judged to be in the normal state of the air pressure.
(2)And isAnd then, it is shown that no green pixel exists in the pointer area picture, only a red pixel exists, and the sulfur hexafluoride density meter is judged to be in a state of too low air pressure.
(3) When in useAnd isWhen, it is illustrated that there are both green and red pixels in the pointer region picture. When Rn is>And Gn, judging that the sulfur hexafluoride density meter is in a state of excessively low air pressure, and otherwise, judging that the sulfur hexafluoride density meter is in a state of normal air pressure.
The technical principle of the present invention is described above in connection with specific embodiments. The description is made for the purpose of illustrating the principles of the invention and should not be construed in any way as limiting the scope of the invention. Based on the explanations herein, those skilled in the art will be able to conceive of other embodiments of the present invention without inventive effort, which would fall within the scope of the present invention.
Claims (10)
1. A method of determining an operating state of a density meter, comprising: the method comprises the following steps:
step A: collecting density meter pictures under different illumination and different angles;
and B: marking the density table pictures, storing the marking information of each density table picture into a corresponding marking information file, and establishing a training data set containing the density table pictures and the marking information file;
and C: training a target detection network based on the training data set to obtain a detection model, wherein the detection model is used for detecting an air pressure critical area and a pointer area of a density meter picture;
step D: inputting the picture of the density meter to be detected into the detection model to obtain the coordinates and the category information of the rectangular frames of the positions of the air pressure critical area and the pointer area in the picture of the density meter to be detected;
step E: respectively cutting an air pressure critical area picture and a pointer area picture from the to-be-detected density meter picture according to the position rectangular frame coordinates;
step F: acquiring an area intersection ratio of the atmospheric pressure critical region and the pointer region based on the atmospheric pressure critical region picture and the pointer region picture, judging whether a density meter is in an atmospheric pressure critical state currently according to the area intersection ratio, and executing the step G if the density meter is in a non-atmospheric pressure critical state;
step G: respectively counting the number of corresponding pixels in the pointer region picture;
step H: and judging the working state of the density table in a non-air pressure critical state according to the number of the corresponding pixels in the pointer region picture.
2. The method of claim 1, wherein the step of determining the operating state of the density meter comprises:
in the step B, the following steps are performed:
step B1: respectively marking the position and the type name of an air pressure critical area and a pointer area in each density table picture;
step B2: correspondingly establishing a marking information file for each density table picture, and storing the marking information of each density table picture into the corresponding marking information file;
step B3: and establishing a training data set, wherein the training data set comprises all density table pictures and marking information files.
3. The method of claim 1, wherein the step of determining the operating state of the density meter comprises:
in the step D, the following steps are performed:
step D1: inputting the to-be-detected density chart picture into a detection model;
step D2: the detection model respectively detects an air pressure critical area and a pointer area in the picture of the density meter to be detected;
step D3: and the detection model respectively returns the coordinates and the category information of the rectangular frames at the positions of the air pressure critical area and the pointer area in a first format.
4. A method of determining the operating state of a density meter according to claim 3, characterized in that:
Wherein:
the horizontal coordinate of the lower right corner of the position rectangular frame is represented;
label indicates whether the region detected by the detection model is a pressure critical region or a pointer region.
5. The method of claim 1, wherein the step of determining the operating state of the density meter comprises:
in the step F, acquiring an area intersection ratio of the air pressure critical area and the pointer area according to a formula I;
wherein:
rato represents an area intersection ratio;
Indicating the area of the pointer region, and the coordinate value of the pointer region can be expressed as;
6. The method of claim 5, wherein the step of determining the operating state of the density meter comprises:
obtaining the coordinate value of the intersection region according to the coordinate values of the air pressure critical region and the pointer region;
Wherein:
7. the method of claim 6, wherein the step of determining the operating state of the density meter comprises:
obtaining the area of the air pressure critical area according to the coordinate value of the air pressure critical area;
obtaining the area of the intersection region according to the coordinate value of the intersection region;
8. the method of claim 5, wherein the step of determining the operating state of the density meter comprises:
in the step F, judging whether the density table is currently in the air pressure critical state according to the area intersection ratio includes:
if the area intersection ratio Rato is larger than the preset value, the density meter is judged to be in the air pressure critical state currently, and otherwise, the density meter is in the non-air pressure critical state currently.
9. The method of claim 1, wherein the step of determining the operating state of the density meter comprises:
in the step G, when the density table is in the non-air pressure critical state, respectively counting the number of corresponding pixels in the pointer region picture, including the following steps:
step G1: resetting the width and height of the pointer area picture to be pixels;
step G2: enhancing the contrast and saturation of the pointer region picture after the step G1 is executed;
step G3: extracting a first color channel picture and a second color channel picture of the pointer area picture;
step G4: carrying out binarization processing on the first color channel picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number of first color pixels in the pointer region picture;
and carrying out binarization processing on the second color channel picture to obtain a binarized picture, and counting the number of pixels with the pixel values equal to 255 in the binarized picture, wherein the number is the number of second color pixels in the pointer region picture.
10. The method of claim 9, wherein the step of determining the operating state of the density meter comprises:
in the step H, the following steps are performed:
when in useAnd isWhen the pressure is too low, the density meter is in a state of too low air pressure;
when in useAnd isWhen, ifThe density meter is in a state of low air pressure, ifIf so, the density meter is in a normal air pressure state;
wherein:
gn represents the number of first color pixels;
rn denotes the number of second color pixels.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111558015.6A CN113947720B (en) | 2021-12-20 | 2021-12-20 | Method for judging working state of density meter |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111558015.6A CN113947720B (en) | 2021-12-20 | 2021-12-20 | Method for judging working state of density meter |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113947720A true CN113947720A (en) | 2022-01-18 |
CN113947720B CN113947720B (en) | 2022-05-20 |
Family
ID=79339180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111558015.6A Active CN113947720B (en) | 2021-12-20 | 2021-12-20 | Method for judging working state of density meter |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113947720B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955907A (en) * | 2014-04-17 | 2014-07-30 | 国家电网公司 | Method for telemetering pointer type SF6 gas density meter |
CN107038444A (en) * | 2016-02-03 | 2017-08-11 | 上海慕荣电气有限公司 | A kind of image-recognizing method of pointer dial plate |
CN109447062A (en) * | 2018-09-29 | 2019-03-08 | 南京理工大学 | Pointer-type gauges recognition methods based on crusing robot |
CN111950330A (en) * | 2019-05-16 | 2020-11-17 | 杭州测质成科技有限公司 | Pointer instrument indicating number detection method based on target detection |
CN112115898A (en) * | 2020-09-24 | 2020-12-22 | 深圳市赛为智能股份有限公司 | Multi-pointer instrument detection method and device, computer equipment and storage medium |
US20210142099A1 (en) * | 2019-11-07 | 2021-05-13 | Sap Se | Pointer recognition for analog instrument image analysis |
CN112949564A (en) * | 2021-02-02 | 2021-06-11 | 电子科技大学 | Pointer type instrument automatic reading method based on deep learning |
CN113469178A (en) * | 2021-07-05 | 2021-10-01 | 安徽南瑞继远电网技术有限公司 | Electric power meter identification method based on deep learning |
-
2021
- 2021-12-20 CN CN202111558015.6A patent/CN113947720B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103955907A (en) * | 2014-04-17 | 2014-07-30 | 国家电网公司 | Method for telemetering pointer type SF6 gas density meter |
CN107038444A (en) * | 2016-02-03 | 2017-08-11 | 上海慕荣电气有限公司 | A kind of image-recognizing method of pointer dial plate |
CN109447062A (en) * | 2018-09-29 | 2019-03-08 | 南京理工大学 | Pointer-type gauges recognition methods based on crusing robot |
CN111950330A (en) * | 2019-05-16 | 2020-11-17 | 杭州测质成科技有限公司 | Pointer instrument indicating number detection method based on target detection |
US20210142099A1 (en) * | 2019-11-07 | 2021-05-13 | Sap Se | Pointer recognition for analog instrument image analysis |
CN112115898A (en) * | 2020-09-24 | 2020-12-22 | 深圳市赛为智能股份有限公司 | Multi-pointer instrument detection method and device, computer equipment and storage medium |
CN112949564A (en) * | 2021-02-02 | 2021-06-11 | 电子科技大学 | Pointer type instrument automatic reading method based on deep learning |
CN113469178A (en) * | 2021-07-05 | 2021-10-01 | 安徽南瑞继远电网技术有限公司 | Electric power meter identification method based on deep learning |
Non-Patent Citations (1)
Title |
---|
黄为民 等: "基于LoRa与机器视觉的SF6密度表读数采集***", 《计算机***应用》 * |
Also Published As
Publication number | Publication date |
---|---|
CN113947720B (en) | 2022-05-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107392116A (en) | A kind of indicator lamp recognition methods and system | |
CN109520706B (en) | Screw hole coordinate extraction method of automobile fuse box | |
CN109358064A (en) | Pole piece film-making winding defect global function detection method, equipment, medium and system | |
CN112713652A (en) | Intelligent power distribution room comprehensive monitoring management system based on cloud computing platform | |
CN113325001A (en) | Automatic distinguishing and detecting equipment and method for surface appearance flaws of copper foil | |
CN106971390A (en) | A kind of detection method for labelling quality | |
CN111912850A (en) | Slice cigarette debris detecting system based on artificial intelligence | |
CN113947720B (en) | Method for judging working state of density meter | |
CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
CN115908432A (en) | Material output quality detection system and prediction method | |
CN111312023A (en) | Device and method for automatically drawing middle school physics circuit experiment circuit diagram | |
CN114298557A (en) | Community environment quality analysis method and device | |
CN113018725A (en) | Intelligent fire fighting analysis and management integrated platform based on remote image analysis and processing technology | |
CN111649865A (en) | Wind power and wind direction detection method based on image processing technology | |
CN114943915A (en) | Whole fire control safety intelligent system of building | |
CN112418231A (en) | System algorithm for collecting operation and maintenance and AI model | |
CN107607492A (en) | The detection method and equipment of motor-vehicle tail-gas standard | |
CN107144244A (en) | A kind of leaf area measurement method | |
CN204203109U (en) | Coding automatic detection device | |
CN115165087A (en) | Automatic test system for emergency evacuation indicating lamp | |
CN109632055A (en) | A kind of mechanical water meter dynamic vision measurement method based on intelligent terminal | |
CN103234975B (en) | A kind of detection and location method of cotton foreign fiber | |
CN115060323A (en) | Smart city environment influence assessment device and method | |
CN114820461A (en) | Surface flaw quality inspection platform and method based on image recognition algorithm | |
CN204204690U (en) | Arc Distinguishing Device for Circuit Breakers and be provided with the circuit breaker of this Arc Distinguishing Device for Circuit Breakers |
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 | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Method for Judging the Working State of Density Tables Effective date of registration: 20231107 Granted publication date: 20220520 Pledgee: Shunde Guangdong rural commercial bank Limited by Share Ltd. Daliang branch Pledgor: GUANGDONG KEYSTAR INTELLIGENCE ROBOT Co.,Ltd. Registration number: Y2023980064495 |
|
PE01 | Entry into force of the registration of the contract for pledge of patent right |