CN112445240A - Automatic line patrol method and automatic line patrol unmanned aerial vehicle - Google Patents
Automatic line patrol method and automatic line patrol unmanned aerial vehicle Download PDFInfo
- Publication number
- CN112445240A CN112445240A CN202011354508.3A CN202011354508A CN112445240A CN 112445240 A CN112445240 A CN 112445240A CN 202011354508 A CN202011354508 A CN 202011354508A CN 112445240 A CN112445240 A CN 112445240A
- Authority
- CN
- China
- Prior art keywords
- characteristic value
- inspection
- image
- equipment
- sample
- 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 61
- 238000007689 inspection Methods 0.000 claims abstract description 210
- 230000002159 abnormal effect Effects 0.000 claims abstract description 53
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 7
- 230000007547 defect Effects 0.000 abstract description 17
- 238000012216 screening Methods 0.000 abstract description 7
- 238000011835 investigation Methods 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 14
- 238000004364 calculation method Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 230000002950 deficient Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000013024 troubleshooting Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
- B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses an automatic line patrol method and an automatic line patrol unmanned aerial vehicle. The automatic line patrol method comprises the following steps: acquiring a preset sample characteristic value and a preset routing inspection route, wherein the routing inspection route carries routing inspection point information; cruising is carried out according to the patrol route so as to collect site images and site temperatures of equipment at the patrol point; pre-inspecting the inspection point equipment based on the field image, the field temperature and the sample characteristic value; and updating the inspection operation based on the pre-inspection result. Carry out the preliminary examination to equipment through unmanned aerial vehicle, can directly select the equipment that operates normally and have unusual equipment to decide subsequent operation of patrolling and examining according to the preliminary examination result, thereby can in time detect out the equipment situation, can avoid equipment to be in abnormal state for a long time from this, can reduce the risk that equipment trouble leads to the outage. Simultaneously, through carrying out the preliminary examination to equipment, defect equipment's image can be selected automatically to unmanned aerial vehicle, has alleviateed the work load of investigation stage manual screening like this.
Description
Technical Field
The embodiment of the invention relates to the technical field of power transmission application, in particular to an automatic line patrol method and an automatic line patrol unmanned aerial vehicle.
Background
In recent years, with the continuous development of unmanned aerial vehicle technology, the unmanned aerial vehicle is favored by various working fields with the advantages of convenient carrying, simple operation, rapid response, rich load, wide task application, low requirement on environment for taking off and landing, capability of flying autonomously and the like.
Wherein, use unmanned aerial vehicle to the electric power and patrol speed and the efficiency that the line aspect can improve electric power maintenance and overhaul greatly, make many work ability accomplish rapidly under the environment of complete electrification, ensured power consumption safety, reduce operation unmanned aerial vehicle work load, improve operation personnel's work efficiency.
The existing unmanned aerial vehicle line patrol scheme is to collect images of a patrol area at one time through the unmanned aerial vehicle, and to export all the images after the patrol is finished, and the images are analyzed by operators. The method has the following problems: a large amount of images are generated in the routing inspection process, a large amount of time is needed for screening the large amount of images, and errors are easy to occur; meanwhile, the inspection result has hysteresis, and live working equipment can cause line accident power failure and cause high power failure cost loss.
Disclosure of Invention
The embodiment of the invention provides an automatic line patrol method and an automatic line patrol unmanned aerial vehicle, so as to improve the field patrol efficiency.
In a first aspect, an embodiment of the present invention provides an automatic line patrol method, which is executed by an unmanned aerial vehicle, and includes:
acquiring a preset sample characteristic value and a preset routing inspection route, wherein the routing inspection route carries routing inspection point information;
cruising is carried out according to the patrol route so as to collect site images and site temperatures of equipment at the patrol point;
pre-inspecting the inspection point equipment based on the field image, the field temperature and the sample characteristic value;
and updating the inspection operation based on the pre-inspection result.
Optionally, the pre-inspecting the inspection point device based on the field image, the field temperature, and the sample characteristic value includes:
determining a current characteristic value of the inspection point equipment based on the field image and the field temperature;
and pre-inspecting the inspection point equipment based on the sample characteristic value and the current characteristic value.
Optionally, the determining the current characteristic value of the patrol point device based on the field image and the field temperature includes:
acquiring an appearance characteristic value of the inspection point equipment based on the field image and acquiring a temperature characteristic value of the inspection point equipment based on the field temperature;
and determining the current characteristic value of the patrol point equipment based on the appearance characteristic value and the field temperature characteristic value.
Optionally, the current characteristic value of the inspection point device is determined by using the following formula based on the appearance characteristic value and the field temperature characteristic value:
in the formula: CV ofRTFor the current feature value of the live image,
for appearance characteristic value, CV, of the live imaget RTIs the temperature characteristic value, alpha, of the field image1Is a weight coefficient, alpha, of the appearance characteristic value2Is the weight coefficient of the temperature characteristic value.
Optionally, the performing, on the basis of the sample characteristic value and the current characteristic value, a pre-inspection on the inspection point device includes:
comparing the current characteristic value with the sample characteristic value;
if the current characteristic value is larger than the sample characteristic value, determining the field image as an abnormal image;
and if the current characteristic value is less than or equal to the sample characteristic value, determining that the field image is a normal image, and storing the normal image in a preset common data area.
Optionally, the updating the inspection operation based on the pre-inspection result includes:
if the field image is a normal image, detecting the next inspection point equipment according to the inspection route; alternatively, the first and second electrodes may be,
if the field image is an abnormal image, outputting the abnormal image to a terminal platform to indicate the terminal platform to identify the abnormal image;
and updating the inspection operation in response to a control instruction output by the terminal platform, wherein the control instruction is generated by the terminal platform according to the identification result of the abnormal image.
Optionally, the updating the inspection operation in response to the control instruction output by the terminal platform includes:
responding to a continuous inspection instruction output by the terminal platform, and detecting next inspection point equipment according to the inspection route, wherein the continuous inspection instruction is output when the identification result of the terminal platform on the abnormal image is qualified; alternatively, the first and second electrodes may be,
responding an image updating instruction of the terminal platform, and updating and collecting a field image of the current inspection point equipment according to a preset angle, wherein the image updating instruction is output when the identification result of the terminal platform on the abnormal image is unqualified;
storing the updated and collected field image in a preset data area to be processed and outputting the field image to the terminal platform;
and detecting the next inspection point equipment according to the inspection route.
Optionally, before the obtaining of the preset sample characteristic value, the method further includes:
acquiring a preset sample image;
extracting appearance characteristic values of a sample device based on the sample image;
determining a sample characteristic value of the sample device based on the appearance characteristic value and a preset sample temperature.
In a second aspect, an embodiment of the present invention further provides an automatic inspection unmanned aerial vehicle, configured to execute the automatic line inspection method according to any embodiment of the present invention, where the automatic inspection unmanned aerial vehicle includes:
the aerial photographing platform is used for acquiring a field image of a patrol point;
the thermal infrared imager is used for acquiring the field temperature of each inspection point;
the flight control system is respectively connected with the aerial photographing platform and the thermal infrared imager and is used for:
acquiring a preset sample characteristic value and a preset routing inspection route, wherein the routing inspection route carries routing inspection point information;
cruising according to the routing inspection route;
pre-inspecting the inspection point equipment based on the field image, the field temperature and the sample characteristic value;
and updating the inspection operation based on the pre-inspection result.
Optionally, the sub-control system is further configured to:
acquiring an appearance characteristic value of the inspection point equipment based on the field image and acquiring a temperature characteristic value of the inspection point equipment based on the field temperature;
determining a current characteristic value of the inspection point equipment based on the appearance characteristic value and the field temperature characteristic value;
and pre-inspecting the inspection point equipment based on the sample characteristic value and the current characteristic value.
According to the automatic line patrol method provided by the embodiment of the invention, an unmanned aerial vehicle sequentially collects equipment information of each patrol point according to a preset patrol route and performs pre-detection on the equipment, specifically, the unmanned aerial vehicle collects image information and temperature information of each patrol point, and calculates the current characteristic value of the equipment based on the collected image information and temperature information through a built-in algorithm so as to reflect the current condition of the equipment through the current characteristic value; and then, the current characteristic value is compared with the sample characteristic value to pre-detect the equipment, and because the sample characteristic value represents the normal condition of the equipment, the equipment can be judged whether to have defects or not by comparing the sample characteristic value with the current characteristic value. This embodiment is carried out the preliminary examination by unmanned aerial vehicle to equipment, can directly select the equipment that operates normally and have unusual equipment to decide subsequent operation of patrolling and examining according to the preliminary examination result, compare in the current unmanned aerial vehicle and directly gather the method of patrolling and examining of on-the-spot image, the method of patrolling and examining of this embodiment can in time detect out the equipment situation, can avoid equipment to be in abnormal state for a long time from this, in time discover and handle, can reduce the risk that equipment trouble leads to the outage. Simultaneously, through carrying out the preliminary examination to equipment, unmanned aerial vehicle can select the image of defective devices automatically, and follow-up operation personnel no longer need follow a large amount of images of patrolling and examining and carry out manual screening when carrying out equipment analysis like this to alleviateed the work load of manual screening, improved operation personnel's work efficiency.
Drawings
Fig. 1 is a flowchart of an automatic line patrol method according to an embodiment of the present invention;
fig. 2 is a flowchart of another automatic line patrol method according to an embodiment of the present invention;
fig. 3 is a flowchart of another automatic line patrol method according to an embodiment of the present invention;
fig. 4 is a block diagram of a structure of an automatic inspection unmanned aerial vehicle according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Fig. 1 is a flowchart of an automatic line patrol method according to an embodiment of the present invention, which is applicable to a case of patrolling power equipment, so as to automatically perform equipment detection on each patrol point through an unmanned aerial vehicle. The method may be performed by a drone, and with reference to fig. 1, the method specifically includes the following steps:
and S110, acquiring a preset sample characteristic value and a preset routing inspection route.
The routing inspection route carries information of routing inspection points.
The preset sample characteristic value refers to a characteristic value of the equipment in a normal state. When the power equipment is damaged in the operation process, the appearance is damaged and the working temperature changes, so the embodiment mainly represents the characteristic value of the equipment through two factors of the appearance characteristic and the temperature characteristic of the equipment. Accordingly, the characteristic values may include an appearance characteristic value and an operating temperature characteristic value. The appearance characteristic value can be obtained by image characteristic extraction of a sample image of the device acquired in advance. Specific methods for determining the sample characteristic values of the device can be found in the description of the following embodiments. For example, the device in this embodiment may be a wire, a hardware fitting, an insulator, a lightning conductor, a tower, a bolt, or the like.
The preset routing inspection route is preset by an operator. Including a plurality of inspection points of making in advance in the route of patrolling and examining, unmanned aerial vehicle flies to each inspection point according to the route of patrolling and examining of making in advance, detects each equipment of inspecting point.
And S120, cruising according to the patrol route to acquire the field image and the field temperature of the patrol point.
Wherein, unmanned aerial vehicle can patrol and examine the route according to this and carry out automatic cruise after obtaining the predetermined route of patrolling and examining to cruising to the inspection point of prescribing a limit to, carry out image and temperature information collection to the equipment of inspection point, whether the equipment of inspection point exists unusually through image and the temperature information of gathering.
Dispose image acquisition equipment and temperature acquisition equipment among the unmanned aerial vehicle to through the on-the-spot image of image acquisition equipment collection inspection point and through temperature acquisition equipment collection inspection point site temperature.
In one embodiment, the image acquisition device is a zoom camera of the aerial platform, the temperature acquisition device is a thermal infrared imager, and accordingly the drone acquires a live image of the inspection point using the aerial platform and acquires a live temperature of the inspection point using the thermal infrared imager.
S130, pre-inspecting the inspection point equipment based on the field image, the field temperature and the sample characteristic value.
After the unmanned aerial vehicle acquires the field image, the image features in the field image are extracted according to a preset algorithm so as to represent whether the equipment has defects or not and the number, severity and the like of the defects through the image features. The unmanned aerial vehicle further judges whether equipment works in a normal temperature range or not through the field temperature, and whether the equipment works in an overtemperature mode or not is judged. And then, a current characteristic value of the equipment is obtained by combining the image information and the temperature information through a built-in evaluation mechanism, and the current characteristic value is compared with the sample characteristic value to realize the pre-detection of the equipment.
The sample characteristic value represents the characteristic information of the equipment in a normal state, the current characteristic value represents the current characteristic information of the equipment, therefore, whether the equipment has defects or faults can be judged by comparing the current characteristic value with the sample characteristic value, and the unmanned aerial vehicle executes subsequent routing inspection operation according to the judgment result.
And S140, updating the inspection operation based on the pre-inspection result.
If the pre-inspection result is qualified, the inspection point equipment is normal, no defect exists, the unmanned aerial vehicle stores images according to a preset processing mechanism and continuously cruises to a subsequent inspection point for equipment inspection; if the pre-inspection result is unqualified, the inspection point equipment has defects and needs to be maintained, and the unmanned aerial vehicle carries out targeted processing on the current inspection point through a preset processing mechanism and then continuously cruises to a subsequent inspection point for equipment detection. The specific processing method of the drone in these two cases can be seen in the introduction of the following embodiments.
According to the automatic line patrol method provided by the embodiment of the invention, an unmanned aerial vehicle sequentially collects equipment information of each patrol point according to a preset patrol route and performs pre-detection on the equipment, specifically, the unmanned aerial vehicle collects image information and temperature information of each patrol point, and calculates the current characteristic value of the equipment based on the collected image information and temperature information through a built-in algorithm so as to reflect the current condition of the equipment through the current characteristic value; and then, the current characteristic value is compared with the sample characteristic value to pre-detect the equipment, and because the sample characteristic value represents the normal condition of the equipment, the equipment can be judged whether to have defects or not by comparing the sample characteristic value with the current characteristic value. This embodiment is carried out the preliminary examination by unmanned aerial vehicle to equipment, can directly select the equipment that operates normally and have unusual equipment to decide subsequent operation of patrolling and examining according to the preliminary examination result, compare in the current unmanned aerial vehicle and directly gather the method of patrolling and examining of on-the-spot image, the method of patrolling and examining of this embodiment can in time detect out the equipment situation, can avoid equipment to be in abnormal state for a long time from this, in time discover and in time handle, can reduce the risk that equipment trouble leads to the outage. Simultaneously, through carrying out the preliminary examination to equipment, unmanned aerial vehicle can select the image of defective devices automatically, and follow-up operation personnel no longer need follow a large amount of images of patrolling and examining and carry out manual screening when carrying out equipment analysis like this to alleviateed the work load of manual screening, improved operation personnel's work efficiency.
Optionally, fig. 2 is a flowchart of another automatic line patrol method provided in an embodiment of the present invention, which is optimized based on the above embodiment, and with reference to fig. 2, the method specifically includes the following steps:
s210, obtaining a sample characteristic value of the equipment and a preset routing inspection route, wherein the routing inspection route carries routing inspection point information.
S220, cruising is carried out according to the patrol route so as to collect the site image and the site temperature of the patrol point.
And S230, determining the current characteristic value of the inspection point equipment based on the field image and the field temperature.
According to the analysis of the embodiment, when the power equipment is damaged, the damaged power equipment is mainly shown as appearance damage and overhigh temperature, so that the unmanned aerial vehicle can obtain the characteristic information reflecting the appearance of the equipment through the field image according to a certain algorithm, and then the current characteristic value reflecting the whole operation condition of the equipment can be obtained by scoring and calculating the characteristic information reflecting the appearance of the equipment and the field temperature reflecting the working temperature of the equipment according to a certain evaluation mechanism.
In one embodiment, the step of determining the current characteristic value of the checkpoint device may be specifically optimized as follows:
acquiring an appearance characteristic value of the inspection point equipment based on the field image and acquiring a temperature characteristic value of the inspection point equipment based on the field temperature;
and determining the current characteristic value of the inspection point equipment based on the appearance characteristic value and the field temperature characteristic value.
The unmanned aerial vehicle can extract the characteristics of the live images according to a preset image processing algorithm to obtain the appearance characteristics of the equipment. For example, the drone may extract appearance features of the live image through a neural network model. The unmanned aerial vehicle further calculates appearance characteristic values based on the appearance characteristics according to a built-in evaluation mechanism so as to reflect the appearance condition of the whole equipment through the appearance characteristic values. For example, whether the device has a preset type of defect, such as a breakage, a white spot, etc. When the defects exist, the appearance characteristic value of the equipment is obtained by calculation according to the number, the type and the like of the defects. In the calculation, certain weights can be assigned to different defects, so that the obtained appearance characteristic value can reflect the appearance condition of the whole equipment.
Likewise, the drone may further calculate the temperature eigenvalues from the field temperature. For example, a plurality of temperature thresholds are pre-configured in the unmanned aerial vehicle, each temperature threshold corresponds to a score, and the flight control system compares the current field temperature with a preset temperature threshold to determine the score corresponding to the field temperature, namely the score is a temperature characteristic value reflecting the current operation condition of the equipment.
After the appearance characteristic value and the temperature characteristic value of the inspection point equipment are obtained through calculation, the unmanned aerial vehicle can perform weighted calculation on the temperature characteristic value and the appearance characteristic value of the equipment to obtain a current characteristic value reflecting the overall condition of the equipment.
For example, the flight control system of the drone may calculate the current characteristic value of the device according to the following method:
in the formula: CV ofRTFor the current feature value of the live image,
for appearance characteristic value, CV, of the live imaget RTFor the temperature characteristic value of the field image, alpha1Weight coefficient, alpha, of appearance characteristic value2Is the weight coefficient of the temperature characteristic value.
The weighting coefficient of the appearance characteristic value and the weighting coefficient of the temperature characteristic value can be adjusted by combining environmental factors such as the temperature and the weather of the operating area of the power equipment, so that the current characteristic value obtained by calculation can truly reflect the overall condition of the equipment.
S240, pre-inspecting the inspection point equipment based on the sample characteristic value and the current characteristic value.
The current characteristic value represents the overall situation of the equipment under the current situation, and the sample characteristic value represents the overall situation of the equipment under the normal situation, so that whether the current situation of the equipment is normal can be judged by comparing the current characteristic value with the sample characteristic value.
This embodiment unmanned aerial vehicle carries out the preliminary examination to equipment through built-in algorithm, can select to have obvious defect's equipment, can carry out classified storage to equipment image according to the preliminary examination result from this. In one embodiment, the process of pre-inspecting the inspection point device can be subdivided into:
comparing the current characteristic value with the sample characteristic value;
if the current characteristic value is larger than the sample characteristic value, determining the field image as an abnormal image;
and if the current characteristic value is less than or equal to the sample characteristic value, determining that the field image is a normal image, and storing the normal image in a preset common data area.
The current characteristic value is larger than the sample characteristic value, which indicates that the equipment has more defects and needs to be maintained. And the unmanned aerial vehicle determines the device image at the moment as an abnormal image.
In this step, the unmanned aerial vehicle only stores the normal image in the general data area, and the abnormal image needs to wait for further confirmation result and then carries out corresponding storage. In this embodiment, the unmanned aerial vehicle is preconfigured with a normal data area and a to-be-processed data area, and an abnormal image is stored in the to-be-processed data area when the abnormal image is determined to be abnormal after being identified by the terminal platform in the subsequent step, or else, the images are stored in the normal data area. The normal images and the abnormal images are respectively stored by dividing the common data area and the data area to be processed for the unmanned aerial vehicle, so that the screening and classification of the equipment images are completed in the line patrol process, operators can directly obtain the equipment images with problems in the subsequent inspection stage, the operators are not required to manually screen, the working efficiency of the inspection stage of the operators is improved, and the damaged condition of abnormal parts can be more conveniently and systematically known.
In some embodiments, the drone performs pre-inspection on inspection point devices based on the following formula:
|CVRT-CVN|≤ε (2)
in the formula, CVRTFor the current feature value, CV, of the live imageNAnd epsilon is a preset error coefficient for the sample characteristic value of the sample image.
If the comparison result of the field characteristic value of the inspection point equipment and the sample characteristic value accords with the formula (2), the unmanned aerial vehicle confirms that the inspection point equipment is qualified in pre-inspection and the corresponding field image is a normal image; otherwise, if the comparison result does not satisfy the formula (2), the pre-inspection of the inspection point is determined to be unqualified, and the corresponding field image is an abnormal image.
In other embodiments, when the unmanned aerial vehicle performs the preliminary examination to the inspection point equipment, the unmanned aerial vehicle also performs the individual detection to the appearance and the temperature of the inspection point equipment respectively, and specifically, the unmanned aerial vehicle confirms whether the appearance and the temperature of the inspection point equipment meet the requirements respectively according to the following formula:
|CVt RT-CVt N|≤ε2 (4)
in the formula (I), the compound is shown in the specification,
in order to inspect the appearance characteristic value of the point device,
for appearance characteristic value, CV, of sample imaget RTFor temperature characteristic value, CV, of equipment at inspection pointt NIs the temperature characteristic value of the sample image, epsilon1For a predetermined appearance error factor, epsilon2Is a preset temperature error coefficient.
The unmanned aerial vehicle detects the inspection point equipment through the formulas (2), (3) and (4), and only when the formulas (2), (3) and (4) are all met, the unmanned aerial vehicle confirms that the pre-inspection is qualified, namely, the field image is a normal image; otherwise, when any one of the images is not satisfied, the pre-inspection is determined to be unqualified, namely the field image is an abnormal image.
And S250, if the field image is a normal image, detecting the next inspection point equipment according to the inspection route.
When the unmanned aerial vehicle confirms that the field images are normal, the unmanned aerial vehicle automatically stores the normal images in a preset common data area, so that the operators can bypass the normal images in the subsequent troubleshooting stage, the working strength of the operators is greatly reduced, and the troubleshooting efficiency of the operators is improved.
When the unmanned aerial vehicle confirms that the field image is normal, the unmanned aerial vehicle flies to the next inspection point according to the preset inspection route to continuously perform inspection operation on the equipment. The unmanned aerial vehicle executes the above operation on each inspection point until the whole line inspection is completed.
S260, if the field image is an abnormal image, outputting the abnormal image to a terminal platform to indicate the terminal platform to identify the abnormal image; and updating the inspection operation in response to the control instruction output by the terminal platform.
And the control instruction is generated by the terminal platform according to the identification result of the abnormal image.
When the unmanned aerial vehicle confirms that the field image is an abnormal image, the unmanned aerial vehicle outputs the abnormal image to the terminal platform, and the terminal platform performs further identification and detection. The terminal platform can, for example, be used by a worker to screen the images to determine whether there are abnormalities in the images. Correspondingly, the terminal platform outputs different control instructions according to the recognition result of the image, and the unmanned aerial vehicle correspondingly acts according to the acquired control instructions. The process can be further optimized as follows:
responding to a continuous inspection instruction output by the terminal platform, and detecting next inspection point equipment according to an inspection route, wherein the continuous inspection instruction is output when the identification result of the terminal platform on the abnormal image is qualified; alternatively, the first and second electrodes may be,
responding an image updating instruction of the terminal platform, and updating and collecting a field image of the current inspection point equipment according to a preset angle, wherein the image updating instruction is output when the identification result of the terminal platform on the abnormal image is unqualified;
storing the updated and collected field image in a preset data area to be processed and outputting the field image to a terminal platform;
and detecting the next inspection point equipment according to the inspection route.
If the terminal platform is identified, it is determined that the inspection point equipment has no defects and does not need maintenance, the terminal platform outputs a continuous inspection instruction, the unmanned aerial vehicle responds to the continuous inspection instruction and flies to the next inspection point, and the next inspection point equipment is detected according to the same method. It should be noted that, in this embodiment, after the confirmation by the terminal platform, if there is no defect after the abnormal image in the pre-inspection process is identified by the terminal platform, the unmanned aerial vehicle stores the corresponding image in the general data area.
If the terminal platform is identified and the equipment is confirmed to be defective, the terminal platform outputs an image updating instruction, and the unmanned aerial vehicle updates and collects the image of the equipment at the inspection point according to a preset angle after acquiring the image updating instruction. Exemplarily, the unmanned aerial vehicle can carry out 360 all-round shootings to the point equipment of patrolling and examining to acquire the full angle image of this equipment, supply the operation personnel from carrying out detailed analysis to this point equipment of patrolling and examining. It should be noted that, in this embodiment, after the identification by the terminal platform, if the abnormal image in the pre-inspection process is actually defective, the unmanned aerial vehicle stores all the abnormal image and the re-acquired image in the area to be processed.
After the field image of the inspection point equipment is collected again, the unmanned aerial vehicle can continuously fly to the next inspection point according to the inspection route, and the next inspection point equipment is detected according to the same method.
The unmanned aerial vehicle executes the detection process through each inspection point device until the inspection is finished.
According to the automatic line patrol method provided by the embodiment of the invention, an unmanned aerial vehicle extracts appearance characteristic information of patrol point equipment according to a collected field image according to a preset algorithm, calculates a corresponding appearance characteristic value according to the appearance characteristic information, calculates a temperature characteristic value of the equipment through the collected field temperature, calculates a current characteristic value of the equipment based on the appearance characteristic value and the temperature characteristic value by the unmanned aerial vehicle, compares the current characteristic value with a sample characteristic value of the equipment in a normal state, and pre-detects the equipment, so that whether the patrol point equipment is abnormal or not is preliminarily detected in the process of patrolling the equipment, and the image of the patrol point equipment is classified and stored according to a detection result. When the unmanned aerial vehicle detects the equipment anomaly, the unmanned aerial vehicle further outputs the acquired abnormal image to the terminal platform, more accurate identification is carried out by the terminal platform, when the terminal platform confirms that the equipment of the inspection point really has the anomaly, the unmanned aerial vehicle responds to an image updating instruction of the terminal platform, the equipment is shot in all directions again, so that the field image of the whole angle can be obtained, the images are output to the terminal platform, the terminal platform is used for carrying out comprehensive analysis, the equipment with the anomaly can be detected in the inspection process, defects can be found in time, information can be provided in time, line accident power failure is avoided, and high power failure cost loss is recovered. Meanwhile, the unmanned aerial vehicle can realize the pre-detection of the equipment, so that the site images can be automatically classified according to the pre-detection result, the site images can be output in a targeted manner, the operating personnel can directly acquire the site images with the abnormal conditions, the workload of the operating personnel is reduced, the working efficiency of the operating personnel is improved, and the corresponding conditions of fault points are accurately found.
Optionally, on the basis of the above technical solution, before obtaining the sample characteristic value of the device, the automatic line patrol method further includes:
acquiring a preset sample image;
extracting appearance characteristic values of the sample device based on the sample image;
a sample characteristic value of the sample device is determined based on the appearance characteristic value and a preset sample temperature.
The unmanned aerial vehicle acquires appearance characteristics of the sample image by acquiring the sample image and performing characteristic extraction on the sample image, and then calculates appearance characteristic values of the sample image based on the appearance characteristics according to a preset algorithm. The method for calculating the appearance characteristic value by the unmanned aerial vehicle is similar to the method for calculating the appearance characteristic value of the live image, and is not repeated in this embodiment.
Similarly, the unmanned aerial vehicle calculates the temperature characteristic value of the sample image based on preset environment temperature information, and obtains the sample characteristic value by performing weighted calculation on the appearance characteristic value and the temperature characteristic value of the sample image.
In one embodiment, the drone calculates the sample eigenvalues based on the following formula:
in the formula: CV ofNIn order to be the characteristic value of the sample,
for the value of the appearance characteristic of the sample, CVt NIs a characteristic value of the temperature of the sample, alpha1Weight coefficient, alpha, of appearance characteristic value2Is the weight coefficient of the temperature characteristic value.
Optionally, fig. 3 is a flowchart of another automatic line patrol method provided in an embodiment of the present invention, which is optimized based on the above embodiment, and referring to fig. 3, the method specifically includes the following steps:
and S310, importing the sample image and the cruising route.
Wherein, unmanned aerial vehicle is before patrolling the line, by leading-in unmanned aerial vehicle of the sample image that the operation personnel prepared in advance to lead-in cruise route. And a flight control system in the unmanned aerial vehicle processes the sample image through a built-in algorithm to obtain a sample characteristic value reflecting the normal state of the equipment to be detected. The sample image refers to an image of a normal state of the apparatus, and thus the image features extracted based on the sample image reflect appearance features of the apparatus in the normal state.
The cruise route carries information of each inspection point, and when the unmanned aerial vehicle cruises to the corresponding inspection point, the unmanned aerial vehicle acquires an equipment image corresponding to the inspection point through the built-in zoom camera and acquires an equipment temperature corresponding to the inspection point through the built-in thermal infrared imager.
And S320, carrying out automatic line patrol shooting.
The unmanned aerial vehicle flies to each inspection point according to the cruising route and shoots each inspection point device in sequence.
And S330, judging whether the acquired image meets the requirements.
This step is that this inspection point equipment of image pair through gathering is examined in advance to through unmanned aerial vehicle at the preliminary detection of cruising phenomenon. The pre-detection process of the unmanned aerial vehicle can refer to the description of the above embodiments, and the description of this embodiment is not repeated.
If the collected image does not meet the requirement, the step S340 is executed; otherwise, if the acquired image meets the requirement, the process proceeds to step S370.
And S340, sending the abnormal image to a terminal platform.
And outputting the abnormal image to a terminal platform, and further confirming whether the current inspection point equipment is abnormal or not by the terminal platform.
And S350, the terminal platform confirms.
For a specific method for the terminal platform to perform the confirmation, reference may be made to the description of the foregoing embodiment, and details are not described in this embodiment. If the terminal platform confirms that the abnormal image is qualified, the step S370 is carried out; otherwise, the process proceeds to step S360.
And S360, carrying out all-dimensional shooting on the line patrol point, storing the image in a work area to be processed, and carrying out the next line patrol point.
The unmanned aerial vehicle responds to an image reacquisition instruction of the terminal platform, and shoots a current inspection point for 360 degrees to obtain a full-angle image of the current inspection point. After the unmanned aerial vehicle collects the images of the inspection points again, the images are stored in a data area to be processed and used as a reference basis for follow-up operation personnel to perform troubleshooting. Simultaneously, unmanned aerial vehicle saves these images of gathering again to pending data area, and the operation personnel can directly obtain the equipment image of unusual inspection point when deriving the image of patrolling and examining like this, and the operation personnel need not to carry out manual sorting, has improved operation personnel's work efficiency.
And S370, carrying out the next line patrol point, and storing the acquired image in a common working area.
In the step, the normal images are stored in the common working area, so that the collected equipment images are classified and stored according to the pre-detection result, the workload of the operating personnel in the inspection stage is reduced, and the working efficiency of the operating personnel is improved.
And S380, completing automatic line patrol.
Optionally, fig. 4 is a block diagram of a structure of an automatic inspection unmanned aerial vehicle according to an embodiment of the present invention, where the automatic inspection unmanned aerial vehicle may automatically execute an automatic line inspection method according to any embodiment of the present invention, and referring to fig. 3, the automatic inspection unmanned aerial vehicle 40 includes:
the aerial photography platform 410 is used for collecting a field image of a patrol point;
the thermal infrared imager 420 is used for collecting the field temperature of each inspection point;
and the flight control system 430 is respectively connected with the aerial photographing platform 410 and the thermal infrared imager 420, and the flight control system 430 is used for:
acquiring a preset sample characteristic value and a preset routing inspection route, wherein the routing inspection route carries routing inspection point information;
cruising according to the patrol route;
pre-inspecting the inspection point equipment based on the field image, the field temperature and the sample characteristic value;
and updating the inspection operation based on the pre-inspection result.
Optionally, on the basis of the above embodiment, the flight control system 430 is further specifically configured to:
determining a current characteristic value of the inspection point equipment based on the field image and the field temperature;
and pre-inspecting the inspection point equipment based on the sample characteristic value and the current characteristic value.
Optionally, on the basis of the above embodiment, the flight control system 430 is further specifically configured to:
acquiring an appearance characteristic value of the inspection point equipment based on the field image and acquiring a temperature characteristic value of the inspection point equipment based on the field temperature;
and determining the current characteristic value of the inspection point equipment based on the appearance characteristic value and the field temperature characteristic value.
Optionally, on the basis of the above embodiment, the flight control system 430 is further specifically configured to:
and determining the current characteristic value of the inspection point equipment by adopting the following formula based on the appearance characteristic value and the field temperature characteristic value:
in the formula: CV ofRTFor the current feature value of the live image,
for appearance characteristic value, CV, of the live imaget RTFor the temperature characteristic value of the field image, alpha1Weight coefficient, alpha, of appearance characteristic value2Is the weight coefficient of the temperature characteristic value.
Optionally, on the basis of the above embodiment, the flight control system 430 is further specifically configured to:
comparing the current characteristic value with the sample characteristic value;
if the current characteristic value is larger than the sample characteristic value, determining that the field image is an abnormal image, and storing the abnormal image in a preset data area to be processed;
and if the current characteristic value is less than or equal to the sample characteristic value, determining that the field image is a normal image, and storing the normal image in a preset common data area.
Optionally, on the basis of the above embodiment, the flight control system 430 is further specifically configured to:
if the field image is a normal image, detecting the next inspection point equipment according to the inspection route; alternatively, the first and second electrodes may be,
if the field image is an abnormal image, outputting the abnormal image to the terminal platform to indicate the terminal platform to identify the abnormal image;
and updating the inspection operation in response to a control instruction output by the terminal platform, wherein the control instruction is generated by the terminal platform according to the identification result of the abnormal image.
Optionally, on the basis of the above embodiment, the flight control system 430 is further specifically configured to:
responding to a continuous inspection instruction output by the terminal platform, and detecting next inspection point equipment according to an inspection route, wherein the continuous inspection instruction is output when the identification result of the terminal platform on the abnormal image is qualified; alternatively, the first and second electrodes may be,
responding an image updating instruction of the terminal platform, and updating and collecting a field image of the current inspection point equipment according to a preset angle, wherein the image updating instruction is output when the identification result of the terminal platform on the abnormal image is unqualified;
storing the updated and collected field image in a preset data area to be processed and outputting the field image to a terminal platform;
and detecting the next inspection point equipment according to the inspection route.
Optionally, on the basis of the above embodiment, the flight control system 430 is further specifically configured to:
acquiring a preset sample image;
extracting appearance characteristic values of the sample device based on the sample image;
a sample characteristic value of the sample device is determined based on the appearance characteristic value and a preset sample temperature.
Optionally, on the basis of the above embodiment, the automatic inspection unmanned aerial vehicle 40 further includes four motors, a battery, an STM32F107 development board, an OpenMV module, a 2.4GRC receiver, and an RC remote controller.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An automatic line patrol method, performed by an unmanned aerial vehicle, the method comprising:
acquiring a preset sample characteristic value and a preset routing inspection route, wherein the routing inspection route carries routing inspection point information;
cruising is carried out according to the patrol route so as to collect site images and site temperatures of equipment at the patrol point;
pre-inspecting the inspection point equipment based on the field image, the field temperature and the sample characteristic value;
and updating the inspection operation based on the pre-inspection result.
2. The automatic line patrol method according to claim 1, wherein the pre-inspecting the patrol point device based on the field image, the field temperature, and the sample characteristic value comprises:
determining a current characteristic value of the inspection point equipment based on the field image and the field temperature;
and pre-inspecting the inspection point equipment based on the sample characteristic value and the current characteristic value.
3. The automatic line patrol method according to claim 2, wherein the determining a current feature value of the patrol point device based on the live image and the live temperature comprises:
acquiring an appearance characteristic value of the inspection point equipment based on the field image and acquiring a temperature characteristic value of the inspection point equipment based on the field temperature;
and determining the current characteristic value of the patrol point equipment based on the appearance characteristic value and the field temperature characteristic value.
4. The automatic line patrol method according to claim 3, wherein the current characteristic value of the patrol point device is determined based on the appearance characteristic value and the field temperature characteristic value by using the following formula:
in the formula: CV ofRTFor the current feature value of the live image,
for appearance characteristic value, CV, of the live imaget RTIs the temperature characteristic value, alpha, of the field image1Is a weight coefficient, alpha, of the appearance characteristic value2Is the weight coefficient of the temperature characteristic value.
5. The automatic line patrol method according to claim 2, wherein the pre-inspecting the patrol point device based on the sample feature value and the current feature value comprises:
comparing the current characteristic value with the sample characteristic value;
if the current characteristic value is larger than the sample characteristic value, determining the field image as an abnormal image;
and if the current characteristic value is less than or equal to the sample characteristic value, determining that the field image is a normal image, and storing the normal image in a preset common data area.
6. The automatic line patrol method according to claim 1, wherein the updating of patrol operations based on the pre-inspection results comprises:
if the field image is a normal image, detecting the next inspection point equipment according to the inspection route; alternatively, the first and second electrodes may be,
if the field image is an abnormal image, outputting the abnormal image to a terminal platform to indicate the terminal platform to identify the abnormal image;
and updating the inspection operation in response to a control instruction output by the terminal platform, wherein the control instruction is generated by the terminal platform according to the identification result of the abnormal image.
7. The automatic line patrol method according to claim 6, wherein the updating of patrol operations in response to the control instructions output by the terminal platform comprises:
responding to a continuous inspection instruction output by the terminal platform, and detecting next inspection point equipment according to the inspection route, wherein the continuous inspection instruction is output when the identification result of the terminal platform on the abnormal image is qualified; alternatively, the first and second electrodes may be,
responding an image updating instruction of the terminal platform, and updating and collecting a field image of the current inspection point equipment according to a preset angle, wherein the image updating instruction is output when the identification result of the terminal platform on the abnormal image is unqualified;
storing the updated and collected field image in a preset data area to be processed and outputting the field image to the terminal platform;
and detecting the next inspection point equipment according to the inspection route.
8. The automatic line patrol method according to claim 1, wherein, before the obtaining of the preset sample characteristic value, the method further comprises:
acquiring a preset sample image;
extracting appearance characteristic values of a sample device based on the sample image;
determining a sample characteristic value of the sample device based on the appearance characteristic value and a preset sample temperature.
9. An automatic inspection drone for performing the automatic line patrol method according to any one of claims 1 to 8, the automatic inspection drone comprising:
the aerial photographing platform is used for acquiring a field image of a patrol point;
the thermal infrared imager is used for acquiring the field temperature of each inspection point;
the flight control system is respectively connected with the aerial photographing platform and the thermal infrared imager and is used for:
acquiring a preset sample characteristic value and a preset routing inspection route, wherein the routing inspection route carries routing inspection point information;
cruising according to the routing inspection route;
pre-inspecting the inspection point equipment based on the field image, the field temperature and the sample characteristic value;
and updating the inspection operation based on the pre-inspection result.
10. The automated inspection drone of claim 9, wherein the sub-control system is further configured to:
acquiring an appearance characteristic value of the inspection point equipment based on the field image and acquiring a temperature characteristic value of the inspection point equipment based on the field temperature;
determining a current characteristic value of the inspection point equipment based on the appearance characteristic value and the field temperature characteristic value;
and pre-inspecting the inspection point equipment based on the sample characteristic value and the current characteristic value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011354508.3A CN112445240A (en) | 2020-11-26 | 2020-11-26 | Automatic line patrol method and automatic line patrol unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011354508.3A CN112445240A (en) | 2020-11-26 | 2020-11-26 | Automatic line patrol method and automatic line patrol unmanned aerial vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112445240A true CN112445240A (en) | 2021-03-05 |
Family
ID=74737972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011354508.3A Pending CN112445240A (en) | 2020-11-26 | 2020-11-26 | Automatic line patrol method and automatic line patrol unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112445240A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102941920A (en) * | 2012-12-05 | 2013-02-27 | 南京理工大学 | High-tension transmission line inspection robot based on multi-rotor aircraft and method using robot |
| CN103235830A (en) * | 2013-05-13 | 2013-08-07 | 北京臻迪科技有限公司 | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV |
| CN103776654A (en) * | 2014-02-21 | 2014-05-07 | 黑龙江省科学院自动化研究所 | Method for diagnosing faults of multi-sensor information fusion |
| CN103823150A (en) * | 2013-12-11 | 2014-05-28 | 贵州电力试验研究院 | Turbo generator rotor interturn short circuit fault diagnosis method based on multi sensor joint |
| CN106162089A (en) * | 2016-07-26 | 2016-11-23 | 广东容祺智能科技有限公司 | A kind of power-line patrolling image automatic identification analyzes system and the method for analysis thereof |
| CN106504363A (en) * | 2016-10-19 | 2017-03-15 | 广东容祺智能科技有限公司 | A kind of airborne pair of light cruising inspection system stabilized platform automatic tracking method of intelligence |
| CN107316353A (en) * | 2017-07-03 | 2017-11-03 | 国网冀北电力有限公司承德供电公司 | A kind of unmanned plane inspection approaches to IM, system and server |
| CN108037770A (en) * | 2017-11-22 | 2018-05-15 | 国网山东省电力公司济宁供电公司 | Unmanned plane power transmission line polling system and method based on artificial intelligence |
| CN108280449A (en) * | 2018-02-06 | 2018-07-13 | 国网山西省电力公司电力科学研究院 | Power equipment image collecting method based on multispectral sensor group |
| WO2018214054A1 (en) * | 2017-05-24 | 2018-11-29 | 深圳配天智能技术研究院有限公司 | Visual inspection method, device and system, and apparatus with storage function |
| CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
| CN110598736A (en) * | 2019-08-06 | 2019-12-20 | 西安理工大学 | Power equipment infrared image fault positioning, identifying and predicting method |
| CN110824293A (en) * | 2019-10-15 | 2020-02-21 | 淮阴工学院 | Power grid fault diagnosis method based on multi-feature fusion parameters of wolf pack algorithm |
| CN110989685A (en) * | 2019-12-31 | 2020-04-10 | 深圳市贝贝特科技实业有限公司 | Unmanned aerial vehicle cruise detection system and cruise detection method thereof |
-
2020
- 2020-11-26 CN CN202011354508.3A patent/CN112445240A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102941920A (en) * | 2012-12-05 | 2013-02-27 | 南京理工大学 | High-tension transmission line inspection robot based on multi-rotor aircraft and method using robot |
| CN103235830A (en) * | 2013-05-13 | 2013-08-07 | 北京臻迪科技有限公司 | Unmanned aerial vehicle (UAV)-based electric power line patrol method and device and UAV |
| CN103823150A (en) * | 2013-12-11 | 2014-05-28 | 贵州电力试验研究院 | Turbo generator rotor interturn short circuit fault diagnosis method based on multi sensor joint |
| CN103776654A (en) * | 2014-02-21 | 2014-05-07 | 黑龙江省科学院自动化研究所 | Method for diagnosing faults of multi-sensor information fusion |
| CN106162089A (en) * | 2016-07-26 | 2016-11-23 | 广东容祺智能科技有限公司 | A kind of power-line patrolling image automatic identification analyzes system and the method for analysis thereof |
| CN106504363A (en) * | 2016-10-19 | 2017-03-15 | 广东容祺智能科技有限公司 | A kind of airborne pair of light cruising inspection system stabilized platform automatic tracking method of intelligence |
| WO2018214054A1 (en) * | 2017-05-24 | 2018-11-29 | 深圳配天智能技术研究院有限公司 | Visual inspection method, device and system, and apparatus with storage function |
| CN107316353A (en) * | 2017-07-03 | 2017-11-03 | 国网冀北电力有限公司承德供电公司 | A kind of unmanned plane inspection approaches to IM, system and server |
| CN108037770A (en) * | 2017-11-22 | 2018-05-15 | 国网山东省电力公司济宁供电公司 | Unmanned plane power transmission line polling system and method based on artificial intelligence |
| CN108280449A (en) * | 2018-02-06 | 2018-07-13 | 国网山西省电力公司电力科学研究院 | Power equipment image collecting method based on multispectral sensor group |
| CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
| CN110598736A (en) * | 2019-08-06 | 2019-12-20 | 西安理工大学 | Power equipment infrared image fault positioning, identifying and predicting method |
| CN110824293A (en) * | 2019-10-15 | 2020-02-21 | 淮阴工学院 | Power grid fault diagnosis method based on multi-feature fusion parameters of wolf pack algorithm |
| CN110989685A (en) * | 2019-12-31 | 2020-04-10 | 深圳市贝贝特科技实业有限公司 | Unmanned aerial vehicle cruise detection system and cruise detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111311597B (en) | Unmanned aerial vehicle inspection method and system for defective insulator | |
| CN109785289B (en) | Transmission line defect detection method and system and electronic equipment | |
| EP2776815B1 (en) | System and method for improving automated defect detection user interface | |
| WO2018028005A1 (en) | Fault detection algorithm for battery panel in large-scale photovoltaic power station | |
| CN110472510A (en) | Based on infrared and visual picture electrical equipment fault detection method and assessment equipment | |
| CN114898232B (en) | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic group string data analysis | |
| CN112906620B (en) | Unmanned aerial vehicle-assisted insulator fault detection method and device and electronic equipment | |
| CN111157530B (en) | Unmanned aerial vehicle-based safety detection method for power transmission line | |
| CN111337789A (en) | Method and system for detecting fault electrical element in high-voltage transmission line | |
| CN115933746A (en) | Automatic inspection method and device for power distribution network | |
| CN114721430A (en) | Power line safety inspection and intelligent diagnosis system based on unmanned aerial vehicle | |
| CN115169602A (en) | Maintenance method and device for power equipment, storage medium and computer equipment | |
| CN112697798A (en) | Infrared image-oriented diagnosis method and device for current-induced thermal defects of power transformation equipment | |
| CN115393347A (en) | Intelligent power grid inspection method and system based on urban brain | |
| CN112595936A (en) | Power transmission line composite insulator intelligent detection system based on unmanned aerial vehicle patrols and examines | |
| CN113065540A (en) | Power transmission line element failure identification method and system based on machine patrol image | |
| CN112445240A (en) | Automatic line patrol method and automatic line patrol unmanned aerial vehicle | |
| CN116977907A (en) | Image recognition-based power inspection fault diagnosis method and system | |
| CN116106656A (en) | Auxiliary identification method for defects of power equipment based on mobile application terminal | |
| CN113449767B (en) | Multi-image fusion transformer substation equipment abnormity identification and positioning method | |
| CN113406107B (en) | Fan blade defect detection system | |
| CN113033556A (en) | Insulator rapid distinguishing and positioning method and system based on machine vision | |
| CN114648510A (en) | State detection method and device of photovoltaic module, storage medium and electronic equipment | |
| CN113808081A (en) | Transmission line small-size gold utensil defect detecting system | |
| CN117498225B (en) | Unmanned aerial vehicle intelligent power line inspection system |
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 |