CN117291872A - Unmanned aerial vehicle line inspection defect content identification system and method - Google Patents
Unmanned aerial vehicle line inspection defect content identification system and method Download PDFInfo
- Publication number
- CN117291872A CN117291872A CN202311112833.2A CN202311112833A CN117291872A CN 117291872 A CN117291872 A CN 117291872A CN 202311112833 A CN202311112833 A CN 202311112833A CN 117291872 A CN117291872 A CN 117291872A
- Authority
- CN
- China
- Prior art keywords
- equipment
- defect
- power transmission
- data
- defects
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 259
- 238000007689 inspection Methods 0.000 title claims abstract description 74
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000005540 biological transmission Effects 0.000 claims abstract description 132
- 238000012216 screening Methods 0.000 claims abstract description 9
- 230000007613 environmental effect Effects 0.000 claims description 18
- 238000012502 risk assessment Methods 0.000 claims description 14
- 238000004088 simulation Methods 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000013210 evaluation model Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 229910000976 Electrical steel Inorganic materials 0.000 description 1
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02G—INSTALLATION OF ELECTRIC CABLES OR LINES, OR OF COMBINED OPTICAL AND ELECTRIC CABLES OR LINES
- H02G1/00—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines
- H02G1/02—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines for overhead lines or cables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- 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
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a system and a method for identifying inspection defect content of an unmanned aerial vehicle line, relates to the technical field of inspection of power transmission lines, and solves the technical problems that the completeness of image data is difficult to ensure in the prior art, and the defect identification accuracy and inspection efficiency of the power transmission lines are affected; according to the method, equipment defect matching is conducted on a plurality of power transmission equipment on the power transmission line to be inspected, equipment defects are evaluated, and an acquisition characteristic sequence is set; screening a plurality of target defects from defect catalogues of all power transmission equipment according to specific conditions, and integrating to obtain a target characteristic sequence; and planning a unmanned aerial vehicle routing inspection route on the basis of the target characteristic sequence, and completing image data acquisition. According to the invention, the target characteristic sequence is reasonably constructed by evaluating the equipment defects, and the inspection work is completed based on the target characteristic sequence, so that the inspection coverage rate of the equipment defects can be ensured, the inspection efficiency can be improved, and unnecessary inspection work can be reduced.
Description
Technical Field
The invention belongs to the field of inspection of transmission lines, relates to unmanned aerial vehicles and image processing technology, and particularly relates to a system and a method for identifying inspection defect content of a transmission line of an unmanned aerial vehicle.
Background
With the continuous expansion of large power grid interconnection and power grid scale, the problem of safety and stability of power grid operation is attracting a great deal of attention. In order to ensure safe and stable operation of the power grid, the power enterprises need to periodically patrol equipment such as a power transmission line, a transformer substation and the like. Unmanned aerial vehicle inspection has advantages such as fly height is low, mobility is strong, easy operation, inspection scope are wide, can overcome topography, traffic, sleet ice and seismic factor effectively and patrol the inconvenience that the circuit brought to the manual work. Meanwhile, the unmanned aerial vehicle can carry corresponding detection equipment, such as a thermal infrared imager, a high-definition camera and the like, and can comprehensively, effectively, real-time, safely and stably monitor the power transmission equipment.
The prior art (the invention patent application with publication number of CN 111311570A) discloses a transmission line key device defect identification method based on unmanned aerial vehicle inspection, which collects a sample data set of key devices in a transmission line and builds a defect detection model based on the sample data set; and carrying out defect detection on real-time videos acquired by the unmanned aerial vehicle frame by frame through a defect detection model, so that the state detection of key devices in the power transmission line is realized, and the safe operation of the power transmission line is ensured. The prior art mainly classifies the image data collected by the classification idea, so as to achieve the aim of identifying the defects; however, it cannot be guaranteed that the image data can cover the power transmission line in a full-scale mode, which can cause difficulty in identifying defects on the power transmission line in an inaccurate mode, and meanwhile inspection efficiency is affected.
The invention provides a system and a method for identifying line inspection defect content of an unmanned aerial vehicle, which are used for solving the technical problems.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art; therefore, the invention provides an unmanned aerial vehicle line inspection defect content recognition system and method, which are used for solving the technical problems that the completeness of image data is difficult to ensure in the prior art, and the defect recognition accuracy and inspection efficiency of a power transmission line are affected.
In order to achieve the above object, a first aspect of the present invention provides an unmanned aerial vehicle line inspection defect content recognition system, which includes a central control module, and a data acquisition module and a defect early warning module connected with the central control module; the defect early warning module carries out early warning on the identified equipment defects through the intelligent terminal; a central control module: identifying a plurality of power transmission devices on the power transmission line to be inspected, and matching the device defects corresponding to the plurality of power transmission devices; evaluating and sequencing equipment defects based on historical data, and obtaining defect catalogues of a plurality of power transmission equipment; sequentially extracting equipment defects in the defect catalogue, and setting an acquisition characteristic sequence for the equipment defects; screening a plurality of target defects corresponding to each power transmission device from the defect catalogue, and integrating the plurality of target defects and the corresponding acquired characteristic sequences into a target characteristic sequence; and controlling the data acquisition module to acquire image data based on the target characteristic sequence, and judging whether the power transmission equipment has equipment defects or not through the image data.
In the prior art, a pre-trained defect detection model is used for analyzing the acquired real-time video frame by frame, and whether defects exist in each frame of image or not is identified; this requires that the defect detection model needs to be sufficiently sophisticated and accurate to ensure accuracy of defect identification, which certainly requires a large amount of training data. The prior art also does not have a detailed scheme for acquiring and designing the real-time video, and cannot ensure that the real-time video can cover all possible defects of the power transmission equipment, so that certain defects cannot be identified, and the accuracy of defect identification is affected.
According to the method, equipment defect matching is conducted on a plurality of power transmission equipment on the power transmission line to be inspected, equipment defects are evaluated, and an acquisition characteristic sequence is set; screening a plurality of target defects from defect catalogues of all power transmission equipment according to specific conditions, and integrating to obtain a target characteristic sequence; and planning a unmanned aerial vehicle routing inspection route on the basis of the target characteristic sequence, and completing image data acquisition. According to the invention, the target characteristic sequence is reasonably constructed by evaluating the equipment defects, and the inspection work is completed based on the target characteristic sequence, so that the inspection coverage rate of the equipment defects can be ensured, the inspection efficiency can be improved, and unnecessary inspection work can be reduced.
The central control module is respectively communicated and/or electrically connected with the data acquisition module and the defect early warning module; the defect early warning module is in communication and/or electrical connection with the intelligent terminal; the intelligent terminal comprises a mobile phone or a computer; the data acquisition module is in communication and/or electrical connection with a plurality of unmanned aerial vehicles and controls the unmanned aerial vehicles to carry out inspection work; the unmanned aerial vehicle is provided with a high-definition camera and a thermal infrared imaging camera.
Some of the defects of the power transmission equipment are caused by equipment aging, and some of the defects are caused by external factors. These equipment defects are mainly characterized in two aspects, one is appearance change such as tower inclination caused by typhoons, and the other is abnormal temperature of power transmission equipment when the power transmission equipment works, such as surface temperature overhigh caused by aging. Therefore, aiming at the two aspects, the unmanned aerial vehicle is provided with the high-definition camera and the infrared imaging camera so as to ensure that all equipment defects of the power transmission equipment can be accurately identified.
The historical data in the invention comprises historical inspection data and historical environment data, wherein the historical inspection data mainly refers to data recorded when the power transmission equipment is inspected, and the historical environment data refers to the environment of the power transmission equipment in the past. The acquisition characteristic sequence comprises a defect position, an acquisition position and an image type, wherein the acquisition position refers to the optimal angle of an unmanned aerial vehicle for acquiring an image of the defect position, and the image type comprises a high-definition image and an infrared thermal imaging image.
Preferably, the evaluating and aligning the device defect based on the history data includes: matching a plurality of corresponding equipment defects for a plurality of power transmission equipment based on historical experience data; calculating risk assessment coefficients of a plurality of equipment defects in the power transmission equipment based on the historical data; and ordering a plurality of equipment defects of the power transmission equipment based on the risk assessment coefficient, and obtaining a defect catalog.
The historical experience data in the invention comprises experimental simulation data and historical inspection data of the same type of power transmission equipment, and the experimental simulation data and the historical inspection data are not equivalent to the historical data of the power transmission equipment. The experimental simulation data are mainly used for simulating equipment defects of the power transmission equipment when the power transmission equipment works in various environments, and the historical inspection data refer to equipment defects of the same type of power transmission equipment in the previous inspection process. And merging and de-duplicating the equipment defects in the experimental simulation data and the historical inspection data to obtain all the equipment defects possibly existing in the power transmission equipment.
Then, calculating risk assessment coefficients of corresponding equipment defects by combining historical inspection data and historical environment data of the power transmission equipment in the power transmission line to be inspected; the risk assessment coefficient is used to assess the probability of occurrence of the device defect. And sequencing the risk assessment coefficients from large to small to obtain a defect catalogue. According to the method, the possible equipment defects of the power transmission equipment are listed, and the equipment defects are evaluated and sequenced based on the historical data to obtain the defect catalogue, so that omission of equipment defect identification can be effectively avoided.
Preferably, the calculating the risk assessment coefficient of the plurality of equipment defects in the power transmission equipment based on the historical data includes: extracting occurrence probability of each equipment defect through historical inspection data, and acquiring influence coefficients of historical environment data of power transmission equipment on each equipment defect; marking the occurrence probability and the influence coefficient as FG and YX respectively; the risk assessment coefficient FPX is calculated by the formula fpx=fg+α×exp (YX).
In the present invention, α is a scaling factor greater than 0, exp () is an exponential function based on a natural number e. The occurrence frequency of each equipment defect can be extracted through the historical inspection data corresponding to the power transmission equipment, and the ratio of the occurrence frequency to the inspection frequency is used as the occurrence probability. It should be noted that, once the equipment defect is identified in the history inspection process, the equipment defect is processed before the next inspection.
After the occurrence probability of the equipment defect is determined, the influence coefficient of the historical environment data of the power transmission equipment in the working process is obtained. And combining the occurrence probability and the influence coefficient to obtain a risk assessment coefficient. According to the invention, the historical inspection data and the historical environment data are combined, so that the defects of each power transmission device are reasonably evaluated, a data foundation is laid for the subsequent construction of the target characteristic sequence, and the identification accuracy and the identification efficiency of the defects of the device are improved.
Preferably, the obtaining the influence coefficient of the historical environmental data of the power transmission equipment on the defects of each equipment includes: obtaining standard training data by simulating the influence of various environmental data on equipment defects, and training an artificial intelligent model based on the standard training data to obtain an influence evaluation model; and acquiring historical environment data of the power transmission equipment, and acquiring an influence coefficient corresponding to the historical environment data based on the influence evaluation model.
The simulation of the influence of the environmental data of each type on the equipment defect can be understood as the influence degree of the environmental data of each type on the equipment defect, namely, the larger the influence coefficient is, the larger the influence of the environmental data on the equipment defect is. The historical environmental data in the invention is consistent with the content attribute of the environmental simulation data, and the historical environmental data comprises environmental factors such as temperature, humidity, wind power and the like which can influence equipment defects.
According to the method, the relationship between the environmental data and the influence coefficient of the environmental data on the equipment defects is subjected to nonlinear fitting through the artificial intelligent model, so that the influence evaluation model is obtained. In the subsequent data processing, taking the equipment defect as a reference, acquiring historical environment data corresponding to the equipment defect, and integrating the historical environment data into input data of an influence evaluation model to obtain a corresponding influence coefficient.
Preferably, the setting an acquisition characteristic sequence for the equipment defect includes: determining a defect position of the equipment defect based on the historical inspection data, and acquiring the optimal position of the unmanned aerial vehicle on the defect position and the image type of the equipment defect which is most easily identified; integrating the defect position, the acquisition position and the image type of the equipment defect to generate an acquisition characteristic sequence; and associating the acquired characteristic sequence with the corresponding defect type.
The invention determines the positions of a plurality of equipment defects through historical inspection data and from which angle excellent image data can be acquired. And synthesizing the defect position, the acquisition position and the image type of each equipment defect into an acquisition characteristic sequence, wherein the acquisition characteristic sequence is also the basis for acquiring the image data of the equipment defect by the follow-up unmanned aerial vehicle. The acquisition position of the invention comprises an acquisition angle and an acquisition distance, and the image type comprises a high-definition image and a thermal infrared image.
Preferably, the integrating the plurality of target defects and the corresponding acquired feature sequences into the target feature sequence includes: acquiring the service life and the set life of power transmission equipment, wherein the service life and the set life are respectively marked as SN and DN; the integration ratio ZL is obtained through calculation of a formula ZL=beta multiplied by SN/DN; acquiring the total number of equipment defects in a defect catalog corresponding to the power transmission equipment; determining target defects based on the total number of the equipment defects and the integration ratio ZL; and integrating the acquired characteristic sequence of the target defect into a target characteristic sequence.
The set period in the invention is the maximum service life of the power transmission equipment, and beta is a proportionality coefficient larger than 1. And indirectly determining which equipment defects of the power transmission equipment are required to be acquired according to the integration proportion, and integrating the acquisition characteristic sequences of the equipment defects into a target characteristic sequence. That is, the target feature sequence includes main content in the next inspection, the unmanned aerial vehicle flight route can be planned according to the defect position, the acquisition angle and the acquisition distance of the unmanned aerial vehicle at the power transmission equipment can be planned according to the acquisition position, and the camera is switched according to the image type to complete the image acquisition work.
Preferably, the determining, according to the image data, whether the power transmission device has a device defect includes: planning a routing inspection route of the unmanned aerial vehicle based on the target feature sequence, controlling the unmanned aerial vehicle to fly according to the routing inspection route, and acquiring image data according to a plurality of acquisition feature sequences in the target feature sequence; identifying whether equipment defects exist in the image data through an image identification technology; if yes, generating an early warning signal; if not, judging whether equipment defects exist or not by combining the image history data with the corresponding acquisition positions of the image data; wherein the image history data is image data of the acquisition position acquired in the previous inspection process.
The invention identifies the collected image data through an image identification technology, such as the abnormal appearance of the power transmission equipment according to the high-definition image, the abnormal working temperature of the power transmission equipment according to the infrared thermal imaging image, and the like. It should be noted that in some cases, it is difficult to identify a defect of the apparatus from a single image data, for example, when the tower is inclined (the inclination is not large) and it is desired to identify the defect from one image data, it is necessary to ensure that a reference object exists in the image data; in order to improve the recognition efficiency, the invention combines a plurality of pieces of image data to recognize, the acquisition angle and the acquisition distance of each piece of image data are fixed, and the type of equipment defect can be recognized efficiently.
The second aspect of the invention provides a method for identifying line inspection defect content of an unmanned aerial vehicle, which comprises the following steps: identifying a plurality of power transmission devices on the power transmission line to be inspected, and matching the device defects corresponding to the plurality of power transmission devices; evaluating and sequencing equipment defects based on historical data, and obtaining defect catalogues of a plurality of power transmission equipment; sequentially extracting equipment defects in the defect catalogue, and setting an acquisition characteristic sequence for the equipment defects; the historical data comprises historical inspection data and historical environment data; screening a plurality of target defects corresponding to each power transmission device from the defect catalogue, and integrating the plurality of target defects and the corresponding acquired characteristic sequences into a target characteristic sequence; acquiring image data based on a target feature sequence, and judging whether equipment defects exist in power transmission equipment or not through the image data; wherein the acquisition characteristic sequence comprises a defect position, an acquisition position and an image type.
Compared with the prior art, the invention has the beneficial effects that: according to the method, equipment defect matching is conducted on a plurality of power transmission equipment on the power transmission line to be inspected, equipment defects are evaluated, and an acquisition characteristic sequence is set; screening a plurality of target defects from defect catalogues of all power transmission equipment according to specific conditions, and integrating to obtain a target characteristic sequence; and planning a unmanned aerial vehicle routing inspection route on the basis of the target characteristic sequence, and completing image data acquisition. According to the invention, the target characteristic sequence is reasonably constructed by evaluating the equipment defects, and the inspection work is completed based on the target characteristic sequence, so that the inspection coverage rate of the equipment defects can be ensured, the inspection efficiency can be improved, and unnecessary inspection work can be reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the system principle of the present invention;
FIG. 2 is a schematic diagram of the method steps of the present invention;
FIG. 3 is a schematic diagram of defect list construction according to the present invention;
FIG. 4 is a schematic diagram of the construction of a target feature sequence of the present invention;
FIG. 5 is a schematic diagram of a device defect identification process according to the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, an embodiment of a first aspect of the present invention provides an unmanned aerial vehicle line inspection defect content recognition system, which includes a central control module, and a data acquisition module and a defect early warning module connected with the central control module; the defect early warning module carries out early warning on the identified equipment defects through the intelligent terminal; a central control module: identifying a plurality of power transmission devices on the power transmission line to be inspected, and matching the device defects corresponding to the plurality of power transmission devices; evaluating and sequencing equipment defects based on historical data, and obtaining defect catalogues of a plurality of power transmission equipment; sequentially extracting equipment defects in the defect catalogue, and setting an acquisition characteristic sequence for the equipment defects; screening a plurality of target defects corresponding to each power transmission device from the defect catalogue, and integrating the plurality of target defects and the corresponding acquired characteristic sequences into a target characteristic sequence; and controlling the data acquisition module to acquire image data based on the target characteristic sequence, and judging whether the power transmission equipment has equipment defects or not through the image data.
Referring to fig. 3, the first step in this embodiment is to identify a plurality of power transmission devices on a power transmission line to be inspected, and match device defects corresponding to the plurality of power transmission devices; evaluating and sequencing equipment defects based on historical data, and obtaining defect catalogues of a plurality of power transmission equipment; and sequentially extracting the equipment defects in the defect list, and setting an acquisition characteristic sequence for the equipment defects.
Firstly, determining a power transmission line to be inspected, and identifying a plurality of power transmission devices on the power transmission line. The power transmission equipment mainly comprises a power transmission wire, a transformer, a switch device, a high-voltage insulator, a pole tower and the like. Extracting equipment defects existing in a plurality of power transmission equipment from historical experience data, such as possible anomalies of a transformer, comprises: poor contact of the tapping switch, turn-to-turn short circuit of windings, short circuit loop among iron core silicon steel sheets, local overheating caused by poor contact of other parts, and the like. Thus each transmission line comprises several transmission devices, each comprising several device defects.
And then sorting a plurality of equipment defects through the historical inspection data and the historical environment data of the power transmission equipment, mainly determining the occurrence probability of the plurality of equipment defects according to the historical inspection data of the power transmission equipment, determining the influence coefficient of the historical environment data on the plurality of equipment defects, and further calculating the risk assessment coefficient of each equipment defect. And sequencing the risk assessment coefficients from large to small to obtain a defect catalogue of the power transmission equipment. It should be noted that each power transmission device corresponds to a defect list. According to the embodiment, the influence coefficient of the historical environmental data on each equipment defect is determined mainly through the influence evaluation model, equipment defect identification, equipment defect service life, environmental performance corresponding to the service life and the like are integrated into model input data, and the input refers to the influence evaluation model to obtain the corresponding influence coefficient; the device defect identification is a corresponding positive integer number.
It should be noted that the integration of environmental performance and the like corresponding to the service life into model input data can be referred to as the following steps: acquiring a monthly temperature mean value of the service life, acquiring a temperature change curve through fitting of a plurality of temperature mean values, and incorporating the characteristics of the temperature change curve into the input data of the model, wherein the acquisition principles of the pressure change curve, the humidity change curve and the like are the same. If the equipment defect mark is 1, the service life is 3, the temperature change curve is y1=alpha 1 x 3+beta 1 x 2+gamma 1 x 1, the humidity change curve is y2=α2×xρ5+β2×xρ4+γ2×x+ψ2, and the humidity change curve is y3=α3×xρ4+β3×xρ3+γ3×xρ2+ψ3; the model input data may be integrated into {1,3, [ (3, α1), (2, β1), (1, γ1), ψ1], [ (5, α2), (4, β2), (1, γ2), ψ2], [ (4, α3), (3, β3), (2, γ3), ψ3] }; of course, the input data of the artificial intelligent model is consistent with the content attribute of the input data of the model in the training process, namely the format and the contained content are consistent, and only the content values are different.
After the defect catalogue corresponding to the power transmission equipment is determined, the defect position, the acquisition position and the type of the image to be acquired of the defects of each equipment are determined according to experience (field investigation, simulation investigation or inspection experience). The acquisition characteristic sequence is set for each equipment defect, so that the unmanned aerial vehicle can acquire high-quality image data conveniently.
Referring to fig. 4, in the second step of this embodiment, a plurality of target defects corresponding to each power transmission device are screened from the defect catalog, and the plurality of target defects and the corresponding acquired feature sequences are integrated into a target feature sequence; and controlling the data acquisition module to acquire image data based on the target characteristic sequence, and judging whether the power transmission equipment has equipment defects or not through the image data.
Calculating according to the service life of each power transmission device and the set service life to obtain an integration ratio ZL, if the service life of a certain power transmission device is 2 years, the set service life is 5 years, and beta is 1.2, the integration ratio is 0.72; the equipment defect of the first 72% of the corresponding defect list of the power transmission equipment is taken as the target defect.
And extracting the acquired feature sequence of the determined target defect, and integrating the acquired feature sequence into a target feature sequence. And (3) roughly planning a flight route of the unmanned aerial vehicle according to the defect position in the target feature sequence, and optimizing the flight speed and the flight attitude of the unmanned aerial vehicle in each power transmission device in the flight route by acquiring the position to obtain a final flight video. And then controlling the unmanned aerial vehicle to fly according to the flight route through the data acquisition module, completing image data acquisition of the corresponding image type at the acquisition position, and returning the image data to the central control module.
Referring to fig. 5, the third step of the present embodiment is that the central control module determines whether the power transmission device has a device defect according to the returned image data; when equipment defects exist, the defect early warning module is used for early warning.
For the returned image data, firstly identifying whether equipment defects exist in the image data through an image identification technology; if yes, generating an early warning signal and marking the power transmission equipment; otherwise, determining the acquisition position of the image data, acquiring a historical image corresponding to the acquisition position, and combining the image data with the historical image to judge whether equipment defects exist in the image data. The historical image may be a standard image of each acquisition position of the power transmission device, and the standard image refers to image data corresponding to the power transmission device when the power transmission device is normal.
The partial data in the formula is obtained by removing dimension and taking the numerical value for calculation, and the formula is obtained by simulating a large amount of acquired data through software and is closest to the real situation; the preset parameters and the preset threshold values in the formula are set by those skilled in the art according to actual conditions or are obtained through mass data simulation.
The working principle of the invention is as follows: identifying a plurality of power transmission devices on the power transmission line to be inspected, and matching the device defects corresponding to the plurality of power transmission devices; evaluating and sequencing equipment defects based on historical data, and obtaining defect catalogues of a plurality of power transmission equipment; and sequentially extracting the equipment defects in the defect list, and setting an acquisition characteristic sequence for the equipment defects. Screening a plurality of target defects corresponding to each power transmission device from the defect catalogue, and integrating the plurality of target defects and the corresponding acquired characteristic sequences into a target characteristic sequence; and acquiring image data based on the target feature sequence, and judging whether the power transmission equipment has equipment defects or not through the image data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. The unmanned aerial vehicle line inspection defect content recognition system comprises a central control module, and a data acquisition module and a defect early warning module which are connected with the central control module; the defect early warning module carries out early warning on the identified equipment defects through the intelligent terminal; the method is characterized in that:
a central control module: identifying a plurality of power transmission devices on the power transmission line to be inspected, and matching the device defects corresponding to the plurality of power transmission devices; evaluating and sequencing equipment defects based on historical data, and obtaining defect catalogues of a plurality of power transmission equipment; sequentially extracting equipment defects in the defect catalogue, and setting an acquisition characteristic sequence for the equipment defects; the historical data comprises historical inspection data and historical environment data; the method comprises the steps of,
screening a plurality of target defects corresponding to each power transmission device from the defect catalogue, and integrating the plurality of target defects and the corresponding acquired characteristic sequences into a target characteristic sequence; the data acquisition module is controlled to acquire image data based on the target feature sequence, and whether equipment defects exist in the power transmission equipment is judged through the image data; wherein the acquisition characteristic sequence comprises a defect position, an acquisition position and an image type.
2. The unmanned aerial vehicle line inspection defect content recognition system of claim 1, wherein the evaluating and aligning equipment defects based on historical data comprises:
matching a plurality of corresponding equipment defects for a plurality of power transmission equipment based on historical experience data; the historical experience data comprise experimental simulation data and historical inspection data of the same type of power transmission equipment;
calculating risk assessment coefficients of a plurality of equipment defects in the power transmission equipment based on the historical data; and ordering a plurality of equipment defects of the power transmission equipment based on the risk assessment coefficient, and obtaining a defect catalog.
3. The unmanned aerial vehicle line inspection defect content recognition system of claim 2, wherein the calculating risk assessment coefficients of a plurality of equipment defects in the power transmission equipment based on the historical data comprises:
extracting occurrence probability of each equipment defect through historical inspection data, and acquiring influence coefficients of historical environment data of power transmission equipment on each equipment defect; marking the occurrence probability and the influence coefficient as FG and YX respectively;
calculating a risk assessment coefficient FPX by the formula fpx=fg+α×exp (YX); where α is a scaling factor greater than 0, exp () is an exponential function based on a natural number e.
4. The unmanned aerial vehicle line inspection defect content recognition system according to claim 3, wherein the obtaining the influence coefficient of the historical environment data of the power transmission equipment on the defects of each equipment comprises:
obtaining standard training data by simulating the influence of various environmental data on equipment defects, and training an artificial intelligent model based on the standard training data to obtain an influence evaluation model; the standard training data comprise environment simulation data and influence coefficients of the environment simulation data on equipment defects;
acquiring historical environment data of the power transmission equipment, and acquiring an influence coefficient corresponding to the historical environment data based on an influence evaluation model; wherein the historical environmental data is consistent with the content attributes of the environmental simulation data, and the historical environmental data includes temperature, humidity and wind power.
5. The unmanned aerial vehicle line inspection defect content recognition system of claim 1, wherein the setting of the collection feature sequence for the equipment defect comprises:
determining a defect position of the equipment defect based on the historical inspection data, and acquiring the optimal position of the unmanned aerial vehicle on the defect position and the image type of the equipment defect which is most easily identified; the acquisition position comprises an acquisition angle and an acquisition distance;
integrating the defect position, the acquisition position and the image type of the equipment defect to generate an acquisition characteristic sequence; associating the acquired feature sequence with a corresponding defect type; wherein the image types include high definition images and thermal infrared images.
6. The unmanned aerial vehicle line inspection defect content recognition system of claim 1, wherein the integrating the plurality of target defects with the corresponding acquisition feature sequences into the target feature sequences comprises:
acquiring the service life and the set life of power transmission equipment, wherein the service life and the set life are respectively marked as SN and DN; the integration ratio ZL is obtained through calculation of a formula ZL=beta multiplied by SN/DN; setting the service life as the maximum service life of the power transmission equipment, and setting beta as a proportionality coefficient larger than 1;
acquiring the total number of equipment defects in a defect catalog corresponding to the power transmission equipment; determining target defects based on the total number of the equipment defects and the integration ratio ZL; and integrating the acquired characteristic sequence of the target defect into a target characteristic sequence.
7. The unmanned aerial vehicle line inspection defect content recognition system according to claim 1, wherein the determining whether the power transmission equipment has the equipment defect by the image data comprises:
planning a routing inspection route of the unmanned aerial vehicle based on the target feature sequence, controlling the unmanned aerial vehicle to fly according to the routing inspection route, and acquiring image data according to a plurality of acquisition feature sequences in the target feature sequence;
identifying whether equipment defects exist in the image data through an image identification technology; if yes, generating an early warning signal; if not, judging whether equipment defects exist or not by combining the image history data with the corresponding acquisition positions of the image data; wherein the image history data is image data of the acquisition position acquired in the previous inspection process.
8. A method for identifying unmanned aerial vehicle line inspection defect content, which is applied to the unmanned aerial vehicle line inspection defect content identification system as claimed in any one of claims 1 to 7, and is characterized by comprising the following steps:
identifying a plurality of power transmission devices on the power transmission line to be inspected, and matching the device defects corresponding to the plurality of power transmission devices; evaluating and sequencing equipment defects based on historical data, and obtaining defect catalogues of a plurality of power transmission equipment; sequentially extracting equipment defects in the defect catalogue, and setting an acquisition characteristic sequence for the equipment defects; the historical data comprises historical inspection data and historical environment data;
screening a plurality of target defects corresponding to each power transmission device from the defect catalogue, and integrating the plurality of target defects and the corresponding acquired characteristic sequences into a target characteristic sequence; acquiring image data based on a target feature sequence, and judging whether equipment defects exist in power transmission equipment or not through the image data; wherein the acquisition characteristic sequence comprises a defect position, an acquisition position and an image type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112833.2A CN117291872A (en) | 2023-08-29 | 2023-08-29 | Unmanned aerial vehicle line inspection defect content identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112833.2A CN117291872A (en) | 2023-08-29 | 2023-08-29 | Unmanned aerial vehicle line inspection defect content identification system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117291872A true CN117291872A (en) | 2023-12-26 |
Family
ID=89239992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311112833.2A Pending CN117291872A (en) | 2023-08-29 | 2023-08-29 | Unmanned aerial vehicle line inspection defect content identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117291872A (en) |
-
2023
- 2023-08-29 CN CN202311112833.2A patent/CN117291872A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110018389B (en) | Online fault monitoring method and system for power transmission line | |
| CN106771856B (en) | Electric power transmission line lightning stroke point determination method based on unmanned aerial vehicle technology | |
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| CN111311597A (en) | Unmanned aerial vehicle inspection method and system for defective insulator | |
| CN112013907A (en) | Routing planning method for electric unmanned aerial vehicle inspection | |
| CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
| CN110827435A (en) | External damage monitoring method and system based on intelligent warning post and readable storage medium | |
| CN116523506A (en) | Circuit fault prediction analysis system based on digital twin transformer station technology | |
| CN112614130A (en) | Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3 | |
| CN112697798A (en) | Infrared image-oriented diagnosis method and device for current-induced thermal defects of power transformation equipment | |
| CN115290696A (en) | Infrared thermal imaging defect detection method and device for transformer substation insulator | |
| CN112432667A (en) | Intelligent on-line monitoring system for conducting wire state of power transmission line | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| CN111917178B (en) | Inspection method of operation and maintenance integrated transformer substation | |
| CN117375226A (en) | Power grid operation monitoring device | |
| CN112683916A (en) | Method and device for identifying missing or mounting error of small hardware fittings of current collecting line tower | |
| CN117291872A (en) | Unmanned aerial vehicle line inspection defect content identification system and method | |
| CN111678558A (en) | Infrared thermal imaging oil level and temperature monitoring system and method applied to oil filling equipment | |
| CN108470141B (en) | Statistical feature and machine learning-based insulator identification method in distribution line | |
| CN115297302B (en) | Unmanned system of railway substation | |
| CN111127690A (en) | Unmanned aerial vehicle inspection system and method for distribution network overhead transmission line | |
| CN113284103B (en) | Substation equipment defect online detection method based on space transformation fast R-CNN model | |
| CN115147591A (en) | Transformer equipment infrared image voltage heating type defect diagnosis method and system | |
| CN104714068A (en) | Robot for outdoor electric energy meter to read meter | |
| CN115224795A (en) | Intelligent substation equipment operation monitoring and early warning system and method |
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 |