Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle-based power inspection system and method, which aim to overcome the defect of single inspection service in the prior art.
In a first aspect: the embodiment of the invention provides an electric power inspection system based on an unmanned aerial vehicle, which comprises the unmanned aerial vehicle, a control unit and an analysis unit;
the unmanned aerial vehicle is used for performing power inspection and acquiring inspection data according to set route data, wherein the source of the route data comprises external data interaction equipment and the control unit, and the power inspection comprises inspection of a joint of power equipment on an inspection line, hardware inspection, temperature inspection and peripheral environment inspection;
the analysis unit is used for analyzing the routing inspection data to obtain analysis data;
the control unit is used for generating result data according to the analysis data and transmitting the result data to the unmanned aerial vehicle, so that the unmanned aerial vehicle conducts power inspection according to the result data, wherein the result data comprise control data used for controlling the unmanned aerial vehicle and updated route data.
As a preferred technical solution of the present invention, the analysis unit is configured to analyze the inspection data to obtain analysis data, and specifically includes:
performing data cleaning on the routing inspection data;
classifying the cleaned routing inspection data to obtain classified data;
respectively processing the classified data according to a preset classification model and a standard library so as to obtain defect hidden danger information corresponding to various data, wherein the standard library comprises a power grid standard defect library and a power grid standard hidden danger library;
and automatically coding the obtained information of the hidden troubles of the defects to obtain the analysis data.
As a preferred technical solution of the present invention, the unmanned aerial vehicle is further used for acquiring meteorological data; the analysis unit is also used for carrying out data correction on the analysis data according to the meteorological data.
As a preferred technical solution of the present invention, the control unit is configured to generate result data according to the analysis data, and specifically includes:
obtaining the defect grade according to the automatically coded data;
and if the defect grade exceeds a set threshold value, replanning the air route data and the corresponding control data of the unmanned aerial vehicle.
As a preferred technical solution of the present invention, the control unit is further configured to determine whether to adjust the flight path data set by the online unmanned aerial vehicle according to data of nodes of other unmanned aerial vehicles.
In a second aspect: a power inspection method based on an unmanned aerial vehicle is applied to the power inspection system based on the unmanned aerial vehicle in the first aspect, and comprises the unmanned aerial vehicle, a control unit and an analysis unit; the method comprises the following steps:
the method comprises the following steps of utilizing an unmanned aerial vehicle to carry out power inspection according to set route data and collect inspection data, wherein the source of the route data comprises external data interaction equipment and a control unit, and the power inspection comprises inspection of a joint of power equipment on an inspection line, hardware inspection, temperature inspection and peripheral environment inspection;
analyzing the routing inspection data through an analysis unit to obtain analysis data;
and generating result data by the control unit according to the analysis data, and transmitting the result data to the unmanned aerial vehicle, so that the unmanned aerial vehicle performs power inspection according to the result data, wherein the result data comprises control data for controlling the unmanned aerial vehicle and updated route data.
As a preferred technical solution of the present invention, the analyzing unit analyzes the inspection data to obtain analysis data, and specifically includes the following steps:
performing data cleaning on the routing inspection data;
classifying the cleaned routing inspection data to obtain classified data;
respectively processing the classified data according to a preset classification model and a standard library so as to obtain defect hidden danger information corresponding to various data, wherein the standard library comprises a power grid standard defect library and a power grid standard hidden danger library;
and automatically coding the obtained information of the hidden troubles of the defects to obtain the analysis data.
As a preferred embodiment of the present invention, the method further comprises:
acquiring meteorological data by the unmanned aerial vehicle;
and performing data correction on the analysis data according to the meteorological data by the analysis unit.
As a preferred technical solution of the present invention, the control unit generates result data according to the analysis data, and specifically includes the following steps:
obtaining the defect grade according to the automatically coded data;
and if the defect grade exceeds a set threshold value, replanning the air route data and the corresponding control data of the unmanned aerial vehicle.
As a preferred embodiment of the present invention, the method further comprises:
and judging whether the air route data set by the online unmanned aerial vehicle needs to be adjusted or not by utilizing the control unit according to the data of other unmanned aerial vehicle nodes.
By adopting the technical scheme, the method has the following advantages: according to the power inspection system and method based on the unmanned aerial vehicle, the labor intensity of manual inspection is reduced, the inspection efficiency and the equipment coverage rate are improved, the inspection content is more refined, the shooting service of a single channel and a tower body is avoided, the inspection data processing level is improved by processing and intelligently analyzing the inspection data instead of manual judgment, the high-precision rapid analysis of the defects of power transmission equipment is realized, and the depth and the width of inspection application are increased.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific examples, which are used for illustrating the present invention and are not intended to limit the scope of the present invention.
It should be noted that the terms "first", "second", "third" and "fourth" etc. in the description and claims of the present invention are used for distinguishing different objects, and are not used for describing a specific order. The terms "comprises," "comprising," and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, an embodiment of the present invention provides an electric power inspection system based on an unmanned aerial vehicle, including an unmanned aerial vehicle, a control unit, and an analysis unit.
Specifically, the number of the unmanned aerial vehicles is at least one, and the unmanned aerial vehicles are provided with various detection devices and sensors, which are mature applications and are not described herein again; in other embodiments, the unmanned aerial vehicle is further provided with an execution device, the execution device comprises a corresponding contraction nozzle, a control valve and a material storage device, and the material storage device comprises one or more of a cooling material, a fire extinguishing material and an anticorrosive material, such as liquid nitrogen, dry powder, anticorrosive paint and other substances; the control unit and the analysis unit can be arranged separately or integrally, and are not described herein again; it should be noted that the functions of flight learning, task management, map application, data storage, flight recording and system setting are not described repeatedly.
The unmanned aerial vehicle is used for carrying out power inspection according to set course data and carrying out data acquisition, wherein the source of the course data comprises external data interaction equipment and the control unit, and the power inspection comprises inspection of the joint of power equipment on an inspection line, hardware inspection, temperature inspection and peripheral environment inspection.
Specifically, one unmanned aerial vehicle can receive a plurality of route data, and one of the route data is selected as current route data; each route data comprises a route for routing inspection flight according to the sequence of the serial numbers of the power equipment; the method comprises the steps that a plurality of pieces of electrical equipment contained in each route data are sorted in advance, and corresponding detection sensors and the like are further arranged on the electrical equipment; the patrol data includes various temperature data, geographical data, image data, and the like.
The analysis unit is used for analyzing the routing inspection data to obtain analysis data.
Specifically, data cleaning is carried out on the routing inspection data, including data consistency checking, invalid value processing, missing value processing and the like;
classifying the cleaned routing inspection data to obtain classified data, wherein the classified data comprises temperature data, geographic data, image data and the like, and the geographic data comprises three-dimensional point cloud data;
respectively processing the classified data according to a preset classification model and a standard library so as to obtain defect hidden danger information corresponding to various data, wherein the standard library comprises a power grid standard defect library and a power grid standard hidden danger library;
when the method is applied, different classification data correspond to different classification models;
when the temperature data is obtained, predicting the temperature corresponding to the random forest model; in this way, it is possible to predict whether there is a possibility that the temperature of the relevant power equipment is too high, for example, the oil temperature of the transformer;
in the case of geographic data, the displacement prediction model corresponds to, for example, a regression prediction model, which performs prediction based on the correlation between independent variables and dependent variables, the number of the independent variables may be one or more, where multivariate regression prediction is adopted, and a non-linear regression method is preferable based on the correlation between the independent variables and the dependent variables; by the mode, landslide risk, tree interference and barrier dumping can be well predicted in advance, so that the risk of major accidents is reduced;
when image data is processed, the image processing model sequentially processes the following steps:
firstly, RGB-L ab color space conversion is carried out, a b-component image is extracted, then median filtering and image expansion operation are carried out on the extracted b-component image to generate a preprocessed image, otsu threshold segmentation is carried out on the preprocessed image to generate an image segmentation image, and finally Canny edge detection and accumulative Hough transformation are carried out to search and identify the boundary of the power equipment.
And automatically coding the obtained information of the hidden troubles of the defects to obtain the analysis data.
The defect hidden danger description of the power supply and transmission equipment is described according to a standard defect library specified by a national grid company, and a new adding and importing function of new defect type description is supported.
The control unit is used for generating result data according to the analysis data and transmitting the result data to the unmanned aerial vehicle, so that the unmanned aerial vehicle conducts power inspection according to the result data, wherein the result data comprise control data used for controlling the unmanned aerial vehicle and updated route data.
Specifically, the defect grade is obtained according to the automatically coded data;
and if the defect grade exceeds a set threshold value, replanning the air route data and the corresponding control data of the unmanned aerial vehicle.
When the unmanned aerial vehicle is applied, during routine inspection, the route of the unmanned aerial vehicle is fixed, and when the defect level exceeds a set threshold value, in order to better find problems and facilitate the follow-up personnel to handle, aiming at the special situation, the unmanned aerial vehicle is controlled to fly around the defect part and fly in a height-variable manner to acquire data in multiple directions; here, only the case of a certain device is taken as an example, the surrounding flight and the high-altitude flight enable the course data of the unmanned aerial vehicle to be re-planned, and the relative flight attitude is changed, so that the control data is also changed.
During implementation, the inspection content comprises the types of common ground objects in 14 line channels such as towers, wires, ground wires, trees, roads, railways, rivers and the like, and during analysis, the requirement of safe running distance of the power transmission line of each voltage class relative to various different ground objects is met; the method includes the steps of constructing pixel three-dimensional point clouds by three-dimensional point cloud data acquired by tree barrier inspection, conducting wire modeling and three-dimensional point cloud classification, utilizing a space measurement technology to conduct automatic measurement of clearance of crossing spanning objects such as passage tree barriers and the like, automatically classifying, analyzing defects and hidden dangers and automatically generating reports, wherein the tree barrier inspection is taken as an example for illustration, and other wires, roads, railways, rivers and the like are not repeated herein.
Through above-mentioned scheme, reduced artifical tour intensity of labour, promoted tour efficiency and equipment coverage for it is more meticulous to patrol and examine the content, no longer is the shooting business of single passageway, shaft tower body, and through to patrolling and examining data processing, intelligent analysis, replace artifical the judgement, also promotes and patrols and examines data processing level, realizes the high accuracy quick analysis of transmission equipment defect, has increased and has patrolled and examined degree of depth, the width of using.
Further, the unmanned aerial vehicle is also used for acquiring meteorological data; the analysis unit is also used for carrying out data correction on the analysis data according to the meteorological data.
Specifically, meteorological data is introduced to realize refined early warning of power grid equipment, professional data such as thunder, ice, wind, fire and the like are fused to realize layered early warning, and production management information collection, process management and control, early warning study and judgment and command coordination are realized;
in implementation, the reanalysis process is performed on the basis of the temperature data, the geographic data and the image data, and specifically, the reanalysis process is performed as follows:
during temperature data, on the basis, a plurality of iron towers are positioned in a deep mountain, trees surround the iron towers, and the risk of forest fire is caused, so that thunder and fire in seasonal data and environmental data and real-time acquired temperature data are comprehensively processed to improve the accuracy of prediction;
during geographic data, on the basis of the above, the wind speed is also considered in the regression prediction model, so that the prediction is more comprehensive and accurate;
during image data, ice and rain are also considered in the image processing model on the basis, so that the edge detection and the boundary search of the image are more accurate, for example, horizontal distance measurement, vertical distance measurement, clearance distance measurement, any profile analysis and the like;
by the scheme, the data correction of the analysis data is realized, so that the routing inspection is more scientific and refined.
Further, unmanned aerial vehicle or analysis unit still judge the security of self process of patrolling and examining according to meteorological data, for example, the security of patrolling and examining is guaranteed like this to bearable wind-force level, rainfall size, visibility.
Further, the control unit is also used for judging whether the air route data set by the online unmanned aerial vehicle needs to be adjusted according to the data of other unmanned aerial vehicle nodes.
Specifically, when the unmanned aerial vehicle is used for power inspection, the unmanned aerial vehicle is respectively in communication connection with the control unit and the analysis unit, and correspondingly, when a plurality of unmanned aerial vehicles are connected with the control unit and the analysis unit;
the control unit is also used for scheduling other online unmanned aerial vehicles to change route data for support and processing according to data of other unmanned aerial vehicle nodes, wherein the data comprises defect levels, fault data of the unmanned aerial vehicles and the like, namely when the defect levels reach a certain level and the conditions of real-time monitoring change or return flight, forced landing and the like of the unmanned aerial vehicles are needed; therefore, data of a plurality of unmanned aerial vehicles are linked, the situation of information isolated islands is avoided, and the application of the unmanned aerial vehicles is deepened.
Referring to fig. 2, based on the above inventive concept, the present invention further provides an electric power inspection method based on an unmanned aerial vehicle, which is applied to the electric power inspection system based on an unmanned aerial vehicle described above, wherein the system includes an unmanned aerial vehicle, a control unit and an analysis unit; the method comprises the following steps:
s101, the unmanned aerial vehicle is used for carrying out power inspection according to set route data and collecting inspection data, wherein the source of the route data comprises external data interaction equipment and the control unit, and the power inspection comprises inspection of a joint of power equipment on an inspection line, hardware inspection, temperature inspection and peripheral environment inspection.
Specifically, one unmanned aerial vehicle can receive a plurality of route data, and one of the route data is selected as current route data; each route data comprises a route for routing inspection flight according to the sequence of the serial numbers of the power equipment; the method comprises the steps that a plurality of pieces of electrical equipment contained in each route data are sorted in advance, and corresponding detection sensors and the like are further arranged on the electrical equipment; the patrol data includes various temperature data, geographical data, image data, and the like.
S102, analyzing the routing inspection data through an analyzing unit to obtain analysis data.
Specifically, data cleaning is carried out on the routing inspection data, including data consistency checking, invalid value processing, missing value processing and the like;
classifying the cleaned routing inspection data to obtain classified data, wherein the classified data comprises temperature data, geographic data, image data and the like, and the geographic data comprises three-dimensional point cloud data.
Respectively processing the classified data according to a preset classification model and a standard library so as to obtain defect hidden danger information corresponding to various data, wherein the standard library comprises a power grid standard defect library and a power grid standard hidden danger library;
when the method is applied, different classification data correspond to different classification models;
when the temperature data is obtained, predicting the temperature corresponding to the random forest model; in this way, it is possible to predict whether there is a possibility that the temperature of the relevant power equipment is too high, for example, the oil temperature of the transformer;
in the case of geographic data, the displacement prediction model corresponds to, for example, a regression prediction model, which performs prediction based on the correlation between independent variables and dependent variables, the number of the independent variables may be one or more, where multivariate regression prediction is adopted, and a non-linear regression method is preferable based on the correlation between the independent variables and the dependent variables; by the mode, landslide risk, tree interference and barrier dumping can be well predicted in advance, so that the risk of major accidents is reduced;
when image data is processed, the image processing model sequentially processes the following steps:
firstly, RGB-L ab color space conversion is carried out, a b-component image is extracted, then median filtering and image expansion operation are carried out on the extracted b-component image to generate a preprocessed image, otsu threshold segmentation is carried out on the preprocessed image to generate an image segmentation image, and finally Canny edge detection and accumulative Hough transformation are carried out to search and identify the boundary of the power equipment.
And automatically coding the obtained information of the hidden troubles of the defects to obtain the analysis data.
The defect hidden danger description of the power supply and transmission equipment is described according to a standard defect library specified by a national grid company, and a new adding and importing function of new defect type description is supported.
And S103, generating result data by the control unit according to the analysis data, and transmitting the result data to the unmanned aerial vehicle, so that the unmanned aerial vehicle performs power inspection according to the result data, wherein the result data comprises control data used for controlling the unmanned aerial vehicle and updated route data.
Specifically, the defect grade is obtained according to the automatically coded data;
and if the defect grade exceeds a set threshold value, replanning the air route data and the corresponding control data of the unmanned aerial vehicle.
When the unmanned aerial vehicle is applied, during routine inspection, the route of the unmanned aerial vehicle is fixed, and when the defect level exceeds a set threshold value, in order to better find problems and facilitate the follow-up personnel to handle, aiming at the special situation, the unmanned aerial vehicle is controlled to fly around the defect part and fly in a height-variable manner to acquire data in multiple directions; here, only the case of a certain device is taken as an example, the surrounding flight and the high-altitude flight enable the course data of the unmanned aerial vehicle to be re-planned, and the relative flight attitude is changed, so that the control data is also changed.
During implementation, the inspection content comprises the types of common ground objects in 14 line channels such as towers, wires, ground wires, trees, roads, railways, rivers and the like, and during analysis, the requirement of safe running distance of the power transmission line of each voltage class relative to various different ground objects is met; the method includes the steps of constructing pixel three-dimensional point clouds by three-dimensional point cloud data acquired by tree barrier inspection, conducting wire modeling and three-dimensional point cloud classification, utilizing a space measurement technology to conduct automatic measurement of clearance of crossing spanning objects such as passage tree barriers and the like, automatically classifying, analyzing defects and hidden dangers and automatically generating reports, wherein the tree barrier inspection is taken as an example for illustration, and other wires, roads, railways, rivers and the like are not repeated herein.
Further, the method further comprises:
acquiring meteorological data by the unmanned aerial vehicle;
and performing data correction on the analysis data according to the meteorological data by the analysis unit.
Specifically, meteorological data is introduced to realize refined early warning of power grid equipment, professional data such as thunder, ice, wind, fire and the like are fused to realize layered early warning, and production management information collection, process management and control, early warning study and judgment and command coordination are realized;
in implementation, the reanalysis process is performed on the basis of the temperature data, the geographic data and the image data, and specifically, the reanalysis process is performed as follows:
during temperature data, on the basis, a plurality of iron towers are positioned in a deep mountain, trees surround the iron towers, and the risk of forest fire is caused, so that thunder and fire in seasonal data and environmental data and real-time acquired temperature data are comprehensively processed to improve the accuracy of prediction;
during geographic data, on the basis of the above, the wind speed is also considered in the regression prediction model, so that the prediction is more comprehensive and accurate;
during image data, ice and rain are also considered in the image processing model on the basis, so that the edge detection and the boundary search of the image are more accurate, for example, horizontal distance measurement, vertical distance measurement, clearance distance measurement, any profile analysis and the like;
therefore, data correction is carried out on the analysis data, and the routing inspection is more scientific, accurate and refined.
Further, unmanned aerial vehicle or analysis unit still judge the security of self process of patrolling and examining according to meteorological data, for example, the security of patrolling and examining is guaranteed like this to bearable wind-force level, rainfall size, visibility.
Further, the method further comprises: and judging whether the air route data set by the online unmanned aerial vehicle needs to be adjusted or not by utilizing the control unit according to the data of other unmanned aerial vehicle nodes.
Specifically, when the unmanned aerial vehicle is used for power inspection, the unmanned aerial vehicle is respectively in communication connection with the control unit and the analysis unit, and correspondingly, when a plurality of unmanned aerial vehicles are connected with the control unit and the analysis unit;
the control unit is also used for scheduling other online unmanned aerial vehicles to change route data for support and processing according to data of other unmanned aerial vehicle nodes, wherein the data comprises defect levels, fault data of the unmanned aerial vehicles and the like, namely when the defect levels reach a certain level and the conditions of real-time monitoring change or return flight, forced landing and the like of the unmanned aerial vehicles are needed; therefore, data of a plurality of unmanned aerial vehicles are linked, the situation of information isolated islands is avoided, and the application of the unmanned aerial vehicles is deepened.
By the method, the inspection result data of the unmanned aerial vehicle are uniformly stored, uniformly managed and uniformly analyzed, high-precision analysis of the inspection data is realized, the inspection data processing level is improved, the inspection quality, efficiency and benefit of the unmanned aerial vehicle are improved, the inspection service of the power transmission line is supported to be developed, the sensing capability of the current equipment state is comprehensively improved, the active prediction early warning capability is improved, the auxiliary diagnosis decision making capability is improved, and the intensive operation inspection management and control capability is improved.
Finally, it should be noted that the above description is only a preferred embodiment of the present application and is illustrative of the technical principles applied. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the present application. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.