CN116953444A - Unmanned aerial vehicle-based double/multiple porcelain insulator string live detection device and method - Google Patents
Unmanned aerial vehicle-based double/multiple porcelain insulator string live detection device and method Download PDFInfo
- Publication number
- CN116953444A CN116953444A CN202310869862.7A CN202310869862A CN116953444A CN 116953444 A CN116953444 A CN 116953444A CN 202310869862 A CN202310869862 A CN 202310869862A CN 116953444 A CN116953444 A CN 116953444A
- Authority
- CN
- China
- Prior art keywords
- electric field
- telescopic rod
- aerial vehicle
- unmanned aerial
- strings
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 109
- 238000001514 detection method Methods 0.000 title claims abstract description 52
- 229910052573 porcelain Inorganic materials 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000005684 electric field Effects 0.000 claims abstract description 137
- 239000000523 sample Substances 0.000 claims abstract description 18
- 230000033001 locomotion Effects 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000002360 preparation method Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 239000013307 optical fiber Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 238000009413 insulation Methods 0.000 description 4
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 230000009194 climbing Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 239000003822 epoxy resin Substances 0.000 description 2
- 238000001125 extrusion Methods 0.000 description 2
- 239000011810 insulating material Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000088 plastic resin Substances 0.000 description 2
- 229920000647 polyepoxide Polymers 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 239000005341 toughened glass Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052797 bismuth Inorganic materials 0.000 description 1
- JCXGWMGPZLAOME-UHFFFAOYSA-N bismuth atom Chemical compound [Bi] JCXGWMGPZLAOME-UHFFFAOYSA-N 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 231100000817 safety factor Toxicity 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000012211 strain insulator Substances 0.000 description 1
- 238000000825 ultraviolet detection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1245—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of line insulators or spacers, e.g. ceramic overhead line cap insulators; of insulators in HV bushings
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U20/00—Constructional aspects of UAVs
- B64U20/80—Arrangement of on-board electronics, e.g. avionics systems or wiring
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
- G01R29/12—Measuring electrostatic fields or voltage-potential
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/14—Circuits therefor, e.g. for generating test voltages, sensing circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Abstract
The invention discloses a double/multiple porcelain insulator chain electrified detection device and method based on an unmanned aerial vehicle, wherein the device comprises the unmanned aerial vehicle and an electric field probe, the unmanned aerial vehicle is connected with a telescopic rod through a nacelle, the front end of the telescopic rod is provided with the electric field probe, the electric field probe is at least provided with three electric field sensors aiming at the double/multiple porcelain insulator chain, the three electric field sensors are horizontally arranged at intervals, the middle electric field sensor in the three electric field sensors is arranged at the top end of the telescopic rod, the installation planes of the electric field sensors at the two ends and the installation plane of the middle electric field sensor are arranged at an included angle of 60-90 degrees, and a distance measuring sensor and an image collector are respectively arranged along with the three electric field sensors.
Description
Technical Field
The invention relates to a double/multiple porcelain insulator string live detection device and method based on an unmanned aerial vehicle.
Background
The insulator is a key device of a high-voltage transmission line, and under the action of factors such as long-term power on, heat, force and the like, the insulator can be subjected to insulation degradation to form a low-value or even zero-value insulator, so that serious faults such as broken strings, insulation failure and the like are caused, and the safe operation of a power grid is threatened. The insulators can be divided into porcelain insulators, composite insulators and toughened glass insulators according to materials, wherein the toughened glass insulators have zero-value self-explosion characteristics, the zero-value insulators are easy to identify after being formed, and zero-value problems do not exist in the composite insulators. The porcelain zero-value insulator has larger detection difficulty, and how to quickly and accurately identify the porcelain zero-value insulator is an important problem facing the operation and maintenance of the transmission line.
At present, an insulation resistance method is often adopted for detecting the zero-value insulator of the power transmission line, a tower climbing worker uses a megameter to measure the resistance value of the insulator, the detection result is accurate, but the tower climbing work engineering quantity and the potential safety hazard are large, and meanwhile, the stable operation of a power grid is seriously affected by power failure. In recent years, scholars at home and abroad have developed various charged detection methods such as electric field detection method, infrared detection method, ultraviolet detection method, ultrasonic detection method, etc. The electric field detection method utilizes the electric field sensor to measure the distribution of the electric field in the space around the insulator, and judges the insulation state of the insulator by identifying the distortion of the electric field, so that the electric field detection method has small influence on environment and high accuracy. Particularly, the method is combined with an unmanned aerial vehicle, is simple and quick to operate, remarkably improves the detection efficiency of the charged insulator string, and is a non-contact detection method which is developed faster in recent years.
Currently, single electric field sensors are used for measuring single-link insulator strings, however, little research is done on double/multiple-link insulator string detection. The main difference between the double/multiple insulator strings and the single insulator string is that the electric field generated by the adjacent insulator strings affects the detection result. Taking a single-wire 70kN duplex strain insulator string as an example, the distance between the centers of the two insulator strings is 40cm, and the radius of the umbrella skirt is 15cm. If the electric field sensor is positioned at 10cm outside the insulator string, the electric field generated by the adjacent insulator string accounts for 15% -30% of the synthesized electric field. And as the detection distance increases, the electric field duty ratio of the adjacent insulator strings is continuously increased. The current electric field detection scheme needs to measure each insulator string along the outer side, cannot effectively remove the influence of the electric field of adjacent insulator strings, is easy to produce the problems of misjudgment, missed judgment and the like, and influences the detection accuracy. In addition, using current electric field detection schemes requires measuring each insulator string individually, especially for multiple insulator strings, which is difficult to operate and labor intensive.
Disclosure of Invention
The invention aims to provide a double/multiple porcelain insulator string live detection device and method based on an unmanned aerial vehicle, which aim at the problems, a plurality of electric field sensors are utilized to simultaneously obtain multi-point electric field intensity signals near the double/multiple porcelain insulator string, and the degradation degree of the insulator string and the position of a zero-value insulator are judged by different insulator string surface potential and field intensity distribution curves through a neural network model (PINN) based on physical information.
In order to achieve the above object, the technical scheme of the present invention is as follows:
the utility model provides a pair/allies oneself with porcelain insulator chain electrified detection device more based on unmanned aerial vehicle, includes unmanned aerial vehicle and electric field probe, and unmanned aerial vehicle passes through nacelle and connects a telescopic link, and the front end of telescopic link sets up electric field probe, wherein: the electric field probe is at least three electric field sensors aiming at the double/multiple porcelain insulator strings, the three electric field sensors are horizontally arranged at intervals, the middle electric field sensor among the three electric field sensors is arranged at the top end of the telescopic rod, the electric field sensors at the two ends of the three electric field sensors are supported and fixed by two connecting rods connected with the telescopic rod, the installation planes of the electric field sensors at the two ends and the installation plane of the middle electric field sensor are arranged at an included angle of 60-90 degrees, a distance measuring sensor and an image acquisition device are simultaneously and respectively arranged along with the three electric field sensors, a data acquisition control module is arranged in the nacelle, the electric field sensors, the distance measuring sensor and the image acquisition device are connected with a data acquisition control module through optical fibers, and the data acquisition control module is wirelessly connected with a ground analysis control computer.
The scheme is further as follows: when the tested insulator string is two strings: the electric field sensors at two ends face two strings of insulator strings respectively, and when the insulator strings to be tested are three strings: the three electric field sensors face the three strings of insulator strings, respectively.
The scheme is further as follows: the connecting rod is right angle connecting rod, and electric field sensor in both ends is fixed the top of right angle connecting rod respectively.
The scheme is further as follows: the three electric field sensors are respectively connected and fixed with the telescopic rod and the connecting rod through universal joints, and the included angles of the electric field sensors in the middle of the electric field sensors at the two ends are adjusted through the universal joints.
The scheme is further as follows: the distance measuring sensor and the image collector are arranged in the same plane with the electric field sensor.
The scheme is further as follows: the tail end of the telescopic rod is provided with a balance weight, the telescopic rod is provided with a balance adjusting device between the balance weight and the electric field probe, the balance adjusting device is connected with the nacelle as a balance lifting point of the telescopic rod, a telescopic rod moving controller is arranged in the balance adjusting device, when the telescopic rod is required to be adjusted to balance in the air, the telescopic rod is moved through the telescopic rod moving controller, and the telescopic rod balance adjusting device is always positioned at the balance lifting point of the telescopic rod.
The scheme is further as follows: the telescopic rod is divided into a front-end telescopic section and a rear-end balancing section, a balancing weight and a balancing adjusting device are arranged on the balancing section, a linear movement control motor is arranged at the front end of the balancing section and connected with the telescopic section, the linear movement control motor is controlled by a data acquisition control module, and the linear movement control motor controls the telescopic rod to stretch out and draw back.
The scheme is further as follows: the telescopic rod movement controller comprises a driving gear and a driven gear, wherein the driven gear is provided with a threaded hole, the surface of a balance section of the telescopic rod is provided with external threads, the balance section is connected with the driven gear through the threaded hole of the external threads, the driving gear and the driven gear are meshed with each other, a driving motor is connected with the driving gear, the driving motor is controlled by a data acquisition control module, and the rotation of the driving gear drives the telescopic rod to move back and forth through the driven gear.
The double/multiple porcelain insulator string live detection method based on unmanned aerial vehicle comprises ground preparation, air adjustment and detection, and is characterized in that,
the ground preparation includes: adjusting the included angle between the electric field sensors at two ends and the middle electric field sensor between 60 degrees and 90 degrees; connecting the unmanned aerial vehicle nacelle with a balance adjusting device; the length of the telescopic rod is adjusted to enable the balance adjusting device serving as a balance lifting point to be located at a safe distance from the electric field sensor; controlling the unmanned aerial vehicle to lift to enable the telescopic rod to hover at a height of 1m to 1.5m away from the ground, and adjusting the counterweight or adjusting the telescopic rod movement controller to enable the lifting point to be at the balance point;
the air adjustment includes: the unmanned aerial vehicle lifts the telescopic rod to a measurement height to hover, and then horizontally moves to position the test distance between the electric field sensor and the insulator string through the ranging sensor and the image collector;
the detection comprises the following steps: the unmanned aerial vehicle controls the electric field sensor to move from bottom to top or from top to bottom along the insulator string, and simultaneously acquires electric field intensity data of different positions of the insulator string; analyzing data by adopting a PINN method to obtain surface potential and field intensity distribution curves of each insulator string from top to bottom; the null insulators are identified by the potential and field strength profile and the position is recorded.
The scheme is further as follows: the process of analyzing data by adopting the PINN method comprises the following steps:
step 1: establishing three-dimensional coordinates of surrounding insulator strings, and uniformly selecting a plurality of points as calculation points;
step 2: establishing a functional relation between the potential of the calculated point and the three-dimensional coordinate of the calculated point through a neural network model;
step 3: substituting the function obtained in the step 2 into an electric field equation, a potential continuous and boundary condition constraint function formula 2, a constraint function formula 3 and a constraint function formula 4, substituting the results obtained by the formulas 2, 3 and 4 into the formula 1, continuously iterating to reduce the residual error, and ending calculation when the residual error is smaller than 0.1; forming a surface potential and field intensity distribution curve of each insulator string from top to bottom, wherein the formula 1, the formula 2, the formula 3 and the formula 4 are respectively as follows:
wherein:
l (θ) is the total residual
L f (θ；T f )、L i (θ；T i )、L b (θ；T b ) Residual errors of an electric field equation, electric potential continuity and boundary conditions are respectively;
α 1 、α 2 、α 3 respectively weighing, and setting the weight to 1;
is the measured potential value;
u (t, x, y, z) is the potential fitted by the neural network;
is the measured field strength value;
T f 、T i 、T b the number of points is calculated for the electric field equation, the electric potential continuity and the boundary condition, respectively.
The beneficial effects of the invention are as follows: the invention utilizes a plurality of electric field sensors to simultaneously obtain multi-point electric field intensity signals near the double/multiple porcelain insulator strings, and can meet the detection requirement only by cruising once. Compared with the existing electric field detection method, the method has the advantages of being few in cruising times, free of influence of detection positions, simple to operate, high in accuracy, safe and reliable and the like. Meanwhile, the potential and space field intensity distribution of different positions of the insulator string is obtained by utilizing a neural network model (PINN) based on physical information, the influence of electric fields of adjacent insulator strings is removed, the judgment and positioning accuracy of zero-value insulators is further improved, and the problems that the electric field distribution of the double/multiple porcelain insulator strings is complex and the judgment difficulty is high are solved. In addition, the detection distance has great influence on the measured field intensity distribution curve, but is limited by safety factors such as electromagnetic interference, operation and the like, and the unmanned aerial vehicle cannot be too close to the insulator, so that the field intensity signal resolution is lower, and the problem of bottleneck of unmanned aerial vehicle electric field detection is solved. The PINN method is adopted to fit the spatial potential and the field intensity distribution through a plurality of real measurement points, so that the surface potential of the insulator and the adjacent spatial electric field can be simulated, the detection precision is improved to a certain extent, the detection distance can be properly increased, and the unmanned aerial vehicle safety operation is facilitated.
The present invention will be described in detail with reference to the accompanying drawings and examples.
Drawings
FIG. 1 is a schematic diagram of a charged detection device according to the present invention;
FIG. 2 is a schematic diagram of an array type electric field probe facing duplex porcelain insulator string;
FIG. 3 is a schematic diagram of an array type electric field probe facing a triple porcelain insulator string;
FIG. 4 is a schematic diagram of a balance adjustment device;
FIG. 5 is a block diagram of a detection control circuit;
FIG. 6 is a PINN method computation flow diagram;
FIG. 7 is a schematic diagram of the relationship between the potential real point and the solving point of the porcelain insulator string.
Detailed Description
Example 1:
the utility model provides a pair/allies oneself with porcelain insulator chain electrified detection device based on unmanned aerial vehicle, as shown in fig. 1, fig. 2, fig. 3, fig. 4 and fig. 5, electrified detection device includes unmanned aerial vehicle 1 and electric field probe 2, and unmanned aerial vehicle passes through nacelle 3 and connects a telescopic link 4, and the front end of telescopic link 4 sets up electric field probe 2, wherein: the electric field probes are arranged for the double/multiple porcelain insulator strings 5, and the double/multiple porcelain insulator strings 5 are supported between the tower cross arm 6 and the high-voltage transmission line 7; as shown in fig. 2 and 3, the array type electric field probe comprises at least three electric field sensors 201, the three electric field sensors 201 are horizontally arranged at intervals, a middle electric field sensor in the three electric field sensors 201 is arranged at the top end of a telescopic rod 4, two electric field sensors in the three electric field sensors are supported and fixed by two connecting rods 8 connected with the telescopic rod 4, the installation planes 201-1 of the two electric field sensors and the installation plane 201-2 of the middle electric field sensor are arranged at an included angle of 60 degrees to 90 degrees, a laser ranging sensor 9 and an image acquisition device 10 are respectively arranged along with the three electric field sensors at the same time, a data acquisition control module 11 is arranged in a nacelle 3, the three electric field sensors 201, the 3 laser ranging sensors 9 and the 3 image acquisition devices 10 are connected with the data acquisition control module 11 through optical fibers, and the data acquisition control module 11 is in wireless connection with a ground analysis control computer 12; the laser ranging sensor 9 and the image collector 10 are arranged in the same installation plane as the electric field sensor 201.
Wherein: when the tested insulator string is two strings: as shown in fig. 2, the electric field sensors at two ends face two insulator strings respectively, and when the insulator strings to be tested are three strings: as shown in fig. 3, three electric field sensors face three strings of insulators, respectively.
The connecting rod 8 is a 90-degree right-angle connecting rod, and the electric field sensors 201 at two ends are respectively fixed at the top ends of the right-angle connecting rod 8. The three electric field sensors are respectively connected and fixed with the telescopic rod and the connecting rod through universal joints, and the included angles of the electric field sensors in the middle of the electric field sensors at the two ends are adjusted through the universal joints.
In order to maintain the balance of the telescopic rod and to adjust the lifting point: the tail end of the telescopic rod 4 is provided with a balance weight 13, the telescopic rod is provided with a balance adjusting device 14 between the balance weight 13 and the electric field probe 2, the balance adjusting device 14 is connected with the nacelle 3 as a balance lifting point of the telescopic rod 4, a telescopic rod moving controller is arranged in the balance adjusting device 14, when the telescopic rod is required to be adjusted to be balanced in the air, the telescopic rod is moved through the telescopic rod moving controller, and the telescopic rod balance adjusting device is always positioned at the balance lifting point of the telescopic rod.
Wherein: the telescopic rod 4 is divided into a front-end telescopic section 401 and a rear-end balancing section 402, a balancing weight 13 and a balancing adjusting device 14 are arranged on the balancing section, a linear movement control motor 15 is arranged at the front end of the balancing section, the linear movement control motor 15 is connected with the front-end telescopic section 401, the linear movement control motor 15 is controlled by the data acquisition control module 11, and the linear movement control motor 15 controls the telescopic rod 401 to stretch out and draw back.
The telescopic link motion controller can have multiple control structures, for example running roller extrusion structure, through the back-and-forth movement of squeeze roll extrusion telescopic link: in this embodiment, a gear transmission mechanism is adopted, as shown in fig. 4, the telescopic rod movement controller includes a driving gear 1402 and a driven gear 1403 which are disposed in a housing 1401 of the balance adjusting device 14, the driven gear 1403 is provided with a threaded hole 1403-1, a surface of a balancing section 402 of the telescopic rod 4 is provided with external threads, the balancing section 402 is connected with the driven gear 1403 through the threaded hole 1403-1, the driving gear 1402 and the driven gear 140 are meshed with each other, a driving motor 16 is connected with the driving gear 1402, a power battery 17 is disposed in the housing 1401, the power battery 17 supplies power to the driving motor through a remote control switch 18, the driving motor is controlled by a data acquisition control module 12 through the remote control switch 18, and the rotation of the driving gear 1402 drives the telescopic rod to move back and forth through the driven gear 140.
In the examples: the electric field sensor uses a shielding electrode type photoelectric sensor, the material is bismuth germanate crystal, and the size is 50 x 10 x 5mm. The connecting rod 8 is made of insulating materials such as plastic or epoxy resin, and the length can be adjusted within 40-80 cm. The telescopic rod 4 is made of insulating materials such as plastic or epoxy resin, and the length adjustment range is 50-150 cm.
Example 2:
the double/multiple porcelain insulator string live detection method based on the unmanned aerial vehicle is based on the detection method of the double/multiple porcelain insulator string live detection device described in the embodiment 1; thus, the contents of embodiment 1 are applicable to the present embodiment, and the detection method includes ground preparation, air adjustment, and detection, wherein:
the ground preparation includes: adjusting the included angle between the electric field sensors at two ends and the middle electric field sensor between 60 degrees and 90 degrees; connecting the unmanned aerial vehicle nacelle with a balance adjusting device; the length of the telescopic rod is adjusted to enable the balance adjusting device serving as a balance lifting point to be located at a safe distance from the electric field sensor; controlling the unmanned aerial vehicle to lift to enable the telescopic rod to hover at a height of 1m to 1.5m away from the ground, and adjusting the counterweight or adjusting the telescopic rod movement controller to enable the lifting point to be at the balance point;
the air adjustment includes: the unmanned aerial vehicle lifts the telescopic rod to a measurement height to hover, and then horizontally moves to position the test distance between the electric field sensor and the insulator string through the ranging sensor and the image collector;
the detection comprises the following steps: the unmanned aerial vehicle controls the electric field sensor to move along the insulator string from bottom to top or from top to bottom at a speed of 0.1m/s, and simultaneously acquires electric field intensity data of different positions of the insulator string; analyzing data by adopting a PINN method to obtain surface potential and field intensity distribution curves of each insulator string from top to bottom; the null insulators are identified by the potential and field strength profile and the position is recorded.
Wherein: the process of analyzing data by adopting the PINN method comprises the following steps:
step 1: establishing a three-dimensional coordinate system surrounding the insulator string; uniformly selecting a plurality of points as calculation points, as shown in fig. 7, aiming at three actual measurement points a1, a2 and a3 of two or three insulator strings, and the rest is an array of solution points b which are calculated around the actual measurement point band, wherein the closer the interval between the array solution points b and b is, the more accurate the calculation result is, but the larger the calculation amount is; the sparse the array, the faster the calculation speed, but the worse the precision and the convergence, the actual interval can be 0.1-1 cm;
step 2: acquiring electric field intensity data and three-dimensional coordinates of different positions of the insulator string, and establishing a function relation between electric field potential of a calculation point and the three-dimensional coordinates; generating calculated point potentials u (x, y, z) through a neural network model, wherein the initial values can be all set to 0V;
step 3: substituting the functions obtained in the step 2, namely substituting the calculated point potentials u (x, y, z) into an electric field physical equation, a potential continuous and boundary condition constraint function formula 2, a potential continuous and boundary condition constraint function formula 3 and a boundary condition constraint function formula 4 respectively, substituting the results obtained in the formulas 2, 3 and 4 into a total residual calculation formula 1 to obtain a total residual, performing continuous iterative calculation through substituting the functions of the electric field potential and the three-dimensional coordinates to continuously reduce the residual, and finishing calculation when the residual is smaller than 0.1; forming a top-to-bottom surface potential and spatial field intensity distribution of each insulator string; equation 1, equation 2, equation 3 and equation 4 are as follows:
wherein:
x, y, z are three-dimensional space coordinates;
θ is a neural network model parameter;
l (θ) is the total residual
L f (θ；T f )、L i (θ；T i )、L b (θ；T b ) Residual errors of an electric field equation, electric potential continuity and boundary conditions are respectively calculated, and the residual errors refer to average errors between fitting values and measured values of the neural network of each calculation point;
α 1 、α 2 、α 3 respectively weighing, and setting the weight to 1; that is, the weights are the regulation electric field equation, the electric potential continuity and the boundary condition ratio, and are generally set to be 1:1:1;
is the measured potential value;
u (t, x, y, z) is the potential fitted by the neural network;
is the measured field strength value;
T f 、T i 、T b the number of points is calculated for the electric field equation, the electric potential continuity and the boundary condition, respectively.
The above calculations are implemented by Python programming. And the COMSOL software is used for simulating the space electric field of the extra-high voltage line insulator string, so that characteristic curves with different detection distances can be obtained. Through the difference of comparison experiments and simulation results, if the electric field of a certain insulator is reduced, the electric field of the adjacent insulator is enhanced, and the amplitude exceeds 5%. The sheet insulator is considered to have a deterioration phenomenon.
The above-mentioned method PINN solving process is a continuous optimization iterative process, and when the initial potential u (all set to 0V) is brought into the electric field equation (laplace equation), the continuity equation (first and last sheet potentials) and the boundary condition (measured field strength), it definitely has a difference from the measured value, and this difference is the residual error. The PINN method essentially consists in constantly proposing new potentials u through the neural network until their residuals are small to an acceptable extent; if one solving point is very close to the steel cap, the potential of the solving point is considered as the potential of the steel cap, the influence of the adjacent insulator string on the solving point is negligible, and the influence of the electric field of the adjacent insulator string is removed by adopting a PINN model mode.
Claims (10)
1. The utility model provides a pair/many porcelain insulator chain electrified detection device based on unmanned aerial vehicle, includes unmanned aerial vehicle and electric field probe, and unmanned aerial vehicle passes through the nacelle and connects a telescopic link, and the front end of telescopic link sets up electric field probe, its characterized in that, electric field probe has three electric field sensor at least to pair/many porcelain insulator chain, and three electric field sensor is the horizontal interval setting, and middle electric field sensor among the three electric field sensor sets up on the top of telescopic link, and the both ends electric field sensor among the three electric field sensor is supported fixedly by two connecting rods that are connected with the telescopic link, and the mounting plane of both ends electric field sensor is 60 degrees to 90 degrees contained angles setting with middle electric field sensor, has arranged range finding sensor and image acquisition respectively simultaneously along with three electric field sensor, is provided with data acquisition control module in the nacelle, and electric field sensor and range finding sensor pass through optical fiber connection data acquisition control module, and data acquisition control module wireless connection ground analysis control computer.
2. The apparatus for detecting electrification of a double/multiple porcelain insulator string according to claim 1, wherein when the insulator string to be detected is two strings: the electric field sensors at two ends face two strings of insulator strings respectively, and when the insulator strings to be tested are three strings: the three electric field sensors face the three strings of insulator strings, respectively.
3. The live detection device for double/multiple porcelain insulator strings according to claim 1, wherein the connecting rods are right-angle connecting rods, and the electric field sensors at two ends are respectively fixed at the top ends of the right-angle connecting rods.
4. The live detection device for the double/multiple porcelain insulator strings according to claim 1, wherein the three electric field sensors are respectively connected and fixed with the telescopic rod and the connecting rod through universal joints, and the included angles of electric field sensors in the middle of the electric field sensors at two ends are adjusted through the universal joints.
5. The apparatus of claim 1, wherein the ranging sensor and the image collector are disposed in the same plane as the electric field sensor.
6. The live detection device for the double/multiple porcelain insulator strings according to claim 1, wherein the tail end of the telescopic rod is provided with a balance weight, the telescopic rod is provided with a balance adjusting device between the balance weight and the electric field probe, the balance adjusting device is connected with the nacelle as a balance lifting point of the telescopic rod, a telescopic rod moving controller is arranged in the balance adjusting device, and when the telescopic rod is required to be adjusted for balancing in the air, the telescopic rod is moved through the telescopic rod moving controller, so that the telescopic rod balance adjusting device is always positioned at the balance lifting point of the telescopic rod.
7. The device for detecting the electrification of the double/multiple porcelain insulator strings according to claim 6, wherein the telescopic rod is divided into a front-end telescopic section and a rear-end balancing section, the balancing weight and the balancing adjusting device are arranged on the balancing section, a linear movement control motor is arranged at the front end of the balancing section and connected with the telescopic section, the linear movement control motor is controlled by the data acquisition control module, and the linear movement control motor controls the telescopic rod to stretch.
8. The device for detecting the electrification of the double/multiple porcelain insulator strings according to claim 7, wherein the telescopic rod movement controller comprises a driving gear and a driven gear, the driven gear is provided with a threaded hole, the surface of a balancing section of the telescopic rod is provided with external threads, the balancing section is connected with the driven gear through the external threads screwed into the threaded hole, the driving gear and the driven gear are meshed with each other, a driving motor is connected with the driving gear, the driving motor is controlled by the data acquisition control module, and the rotation of the driving gear drives the telescopic rod to move back and forth through the driven gear.
9. The unmanned aerial vehicle-based double/multiple porcelain insulator string live detection method is based on the detection method of the double/multiple porcelain insulator string live detection device according to claim 6, and comprises ground preparation, air adjustment and detection, and is characterized in that,
the ground preparation includes: adjusting the included angle between the electric field sensors at two ends and the middle electric field sensor between 60 degrees and 90 degrees; connecting the unmanned aerial vehicle nacelle with a balance adjusting device; the length of the telescopic rod is adjusted to enable the balance adjusting device serving as a balance lifting point to be located at a safe distance from the electric field sensor; controlling the unmanned aerial vehicle to lift to enable the telescopic rod to hover at a height of 1m to 1.5m away from the ground, and adjusting the counterweight or adjusting the telescopic rod movement controller to enable the lifting point to be at the balance point;
the air adjustment includes: the unmanned aerial vehicle lifts the telescopic rod to a measurement height to hover, and then horizontally moves to position the test distance between the electric field sensor and the insulator string through the ranging sensor and the image collector;
the detection comprises the following steps: the unmanned aerial vehicle controls the electric field sensor to move from bottom to top or from top to bottom along the insulator string, and simultaneously acquires electric field intensity data of different positions of the insulator string; analyzing the data by adopting a PINN method to obtain the surface potential and field intensity distribution of each insulator string from top to bottom; the null insulators are identified by the potential and field strength profile and the position is recorded.
10. The method of claim 9, wherein the process of analyzing the data using the PINN method is:
step 1: establishing three-dimensional coordinates of surrounding insulator strings, and uniformly selecting a plurality of points as calculation points;
step 2: establishing a functional relation between the potential of the calculated point and the three-dimensional coordinate of the calculated point through a neural network model;
step 3: substituting the function obtained in the step 2 into an electric field equation, a potential continuous and boundary condition constraint function formula 2, a constraint function formula 3 and a constraint function formula 4, substituting the results obtained by the formulas 2, 3 and 4 into the formula 1, continuously iterating to reduce the residual error, and ending calculation when the residual error is smaller than 0.1; forming a surface potential and field intensity distribution curve of each insulator string from top to bottom, wherein the formula 1, the formula 2, the formula 3 and the formula 4 are respectively as follows:
L(θ)＝α 1 L f (θ；T f )+α 2 L i (θ；T i )+α 3 L b (θ；T b ) Equation 1
Wherein:
l (θ) is the total residual
L f (θ；T f )、L i (θ；T i )、L b (θ；T b ) Residual errors of an electric field equation, electric potential continuity and boundary conditions are respectively;
α 1 、α 2 、α 3 respectively weighing, and setting the weight to 1;
is the measured potential value;
u (t, x, y, z) is the potential fitted by the neural network;
is the measured field strength value;
T f 、T i 、T b the number of points is calculated for the electric field equation, the electric potential continuity and the boundary condition, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310869862.7A CN116953444A (en) | 2023-07-17 | 2023-07-17 | Unmanned aerial vehicle-based double/multiple porcelain insulator string live detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310869862.7A CN116953444A (en) | 2023-07-17 | 2023-07-17 | Unmanned aerial vehicle-based double/multiple porcelain insulator string live detection device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116953444A true CN116953444A (en) | 2023-10-27 |
Family
ID=88443875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310869862.7A Pending CN116953444A (en) | 2023-07-17 | 2023-07-17 | Unmanned aerial vehicle-based double/multiple porcelain insulator string live detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116953444A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117330883A (en) * | 2023-12-01 | 2024-01-02 | 国网山西省电力公司电力科学研究院 | Overhead line insulator running state monitoring system and method |
-
2023
- 2023-07-17 CN CN202310869862.7A patent/CN116953444A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117330883A (en) * | 2023-12-01 | 2024-01-02 | 国网山西省电力公司电力科学研究院 | Overhead line insulator running state monitoring system and method |
| CN117330883B (en) * | 2023-12-01 | 2024-02-27 | 国网山西省电力公司电力科学研究院 | Overhead line insulator running state monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116953444A (en) | Unmanned aerial vehicle-based double/multiple porcelain insulator string live detection device and method | |
| CN106841957A (en) | Transmission line of electricity zero resistance insulator measuring device with electricity and method based on unmanned plane | |
| CN108827158B (en) | Laser monitoring device and method for main tower deviation of long-span bridge | |
| CN111121645B (en) | High-precision overhead transmission conductor sag detection method | |
| CN103323167B (en) | A kind of power line conductive uniaxial stress and sag monitoring method | |
| CN108344379B (en) | System and method for measuring cross-section profile shape and creepage distance of insulator | |
| CN104122560B (en) | Electric transmission line wide area ice condition monitoring method | |
| CN105403162B (en) | The automatic testing method of semitrailer outer profile size | |
| CN109443689A (en) | The wind tunnel test measuring device and its measurement method of dynamic aerodynamics when a kind of radar antenna rotary work | |
| CN106526292A (en) | Non-wire and non-contact electricity testing system and method thereof for common-tower and multi-circuit ultra-high-voltage AC and DC lines | |
| CN110031828A (en) | A kind of unmanned plane range-measurement system and method based on transmission line of electricity magnetic distribution | |
| CN204203381U (en) | Motion guide rail formula electric transmission line isolator automatic detection device | |
| CN204881602U (en) | A device for measuring building engineering deformation of member | |
| CN206638774U (en) | Transmission line of electricity zero resistance insulator measuring device with electricity based on unmanned plane | |
| CN110440721A (en) | A kind of three-dimensional mobile platform movement angle error rapid measurement device and method | |
| CN110220666B (en) | Wind field detection device based on microstrain and online wind field detection and evaluation method | |
| CN105974187A (en) | Portable voltage on-line measurement device | |
| CN111580531B (en) | Unmanned aerial vehicle electricity inspection method and device for power transmission line | |
| CN104727234A (en) | Rotating platform mechanism used for detecting cable | |
| CN203298739U (en) | Monitoring system for measuring tunnel convergence in real time | |
| CN105115439A (en) | Embedded fiber Bragg grating strain sensor for measuring strain of encapsulation of dry-type air-core reactor and method for using same | |
| CN203164435U (en) | Four rod type length adjustable submarine cable detection antenna array | |
| CN102589783B (en) | Universal testing system for intelligent airplane loading mechanism | |
| CN218646262U (en) | Steel beam deformation detection device | |
| CN207894579U (en) | Rail traffic bridge degree of disturbing detection device |
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 |