CN-121978475-A - Unmanned aerial vehicle-based direct-current insulator state diagnosis method and system

CN121978475ACN 121978475 ACN121978475 ACN 121978475ACN-121978475-A

Abstract

The invention relates to the technical field of electric power system detection, and discloses a direct current insulator state diagnosis method and system based on an unmanned aerial vehicle, wherein voltage signals, temperature and image data of a target direct current insulator are acquired in real time through the unmanned aerial vehicle, the voltage signals are subjected to temperature compensation correction by using the temperature and the image data, and a time space correlation map of the insulator is constructed according to correction results, the temperature and the image data and historical inspection multidimensional data of the target direct current insulator; the method has the advantages that the identification prediction model obtained through training based on the space-time characteristic dynamic learning rate adjustment mechanism is adopted to analyze the insulator space-time correlation map, the correction result, the temperature and the image data, the real-time state diagnosis result and the degradation trend prediction result of the target direct-current insulator are obtained, the traditional single-point static detection mode is broken through, and the accuracy, the environmental adaptability and the foresight of the state diagnosis of the direct-current insulator are remarkably improved through temperature compensation, space-time correlation modeling and fusion deep learning.

Inventors

DING JIAN
GAO YUFENG
SU LIANGZHI
WU WEIHUA
JIANG YUNTU
FANG XIANG
HUANG ZHONGHUA
BIAN XUEJING
Lu Rentao

Assignees

国网浙江省电力有限公司杭州供电公司

Dates

Publication Date: 20260505
Application Date: 20260120

Claims (10)

1. A DC insulator state diagnosis system based on an unmanned aerial vehicle is characterized by comprising the unmanned aerial vehicle, an intelligent sensing module, a voltage correction module, a map construction module and a data processing module which are carried on the unmanned aerial vehicle, The intelligent sensing module is used for collecting voltage signals, temperature and image data of the target direct current insulator in real time in the inspection process of the unmanned aerial vehicle; the voltage correction module is used for carrying out temperature compensation correction on the voltage signal based on the temperature and the image data to obtain a corrected voltage signal; the map construction module is used for constructing an insulator time-space correlation map according to the temperature and image data, the correction voltage signal and the historical inspection multidimensional data of the target direct current insulator; The data processing module is used for analyzing the insulator space-time correlation map, the correction voltage signal, the temperature and image data by adopting an identification prediction model to obtain a real-time state diagnosis result and a degradation trend prediction result of the target direct current insulator, wherein the identification prediction model is obtained by training a dynamic learning rate adjustment mechanism based on space-time characteristics.
2. The unmanned aerial vehicle-based direct current insulator state diagnosis system according to claim 1, wherein the intelligent sensing module comprises: the ultrasonic ranging unit is used for collecting inspection track data of the unmanned aerial vehicle and distance data between the unmanned aerial vehicle and the target direct current insulator when the unmanned aerial vehicle flies to a detection point of the target direct current insulator, and controlling the distance between the unmanned aerial vehicle and the target direct current insulator to be in a preset range based on the distance data; The optical voltage sensor is used for collecting the voltage signal of the target direct current insulator in real time in the inspection process of the unmanned aerial vehicle; The temperature sensor is used for collecting the ambient temperature of the target direct current insulator in real time; And the camera system is used for acquiring the temperature distribution thermal image and the insulator surface image of the target direct current insulator in real time in the inspection process of the unmanned aerial vehicle to serve as the temperature and image data.
3. The unmanned aerial vehicle-based direct current insulator condition diagnosis system according to claim 2, wherein the optical voltage sensor comprises: The electric field sensing probe is used for sensing first potential information around the target direct current insulator and converting the first potential information into a first electric signal; A light source for emitting an optical signal; The Pockels effect crystal is used for modulating the optical signal according to the first electric signal so as to change the polarization state or the phase of the optical signal; an optical analysis sub-component for detecting a polarization or phase change of the optical signal and converting the polarization or phase change into a light intensity change; the photoelectric detection component is used for extracting second potential information from the light intensity change and obtaining a second electric signal according to the second potential information; And the signal processing sub-component is used for amplifying and filtering the second electric signal and obtaining the voltage signal of the target direct current insulator by adopting a differential measurement method.
4. The unmanned aerial vehicle-based direct current insulator condition diagnosis system of claim 2, wherein the voltage correction module comprises: A measurement error calculation unit for determining a measurement error caused by the ambient temperature according to the ambient temperature and a temperature coefficient of the temperature sensor; and the temperature compensation correction unit is used for correcting the voltage signal based on the measurement error to obtain the corrected voltage signal.
5. The unmanned aerial vehicle-based direct current insulator condition diagnosis system according to claim 2, wherein the map construction module comprises: The node attribute setting unit is used for taking the target direct current insulator as a target node and setting an attribute vector of the target node; The data association unit is used for constructing a space-time anchor point according to the routing inspection track data and associating the historical routing inspection multidimensional data based on the space-time anchor point to construct a historical node, wherein the historical routing inspection multidimensional data comprises historical distance data, historical voltage signals, historical environment temperature, historical temperature, image data and historical state diagnosis results; The time edge construction unit is used for establishing a time edge between the target node and the historical node and constructing edge weights of the time edge based on similarity and routing inspection time difference between attribute vectors in the target node and the historical node; The space edge construction unit is used for taking a target node corresponding to a target direct current insulator belonging to the same inspection and the same insulator string as a space node, and establishing a space edge between the space nodes; And the map generation unit is used for integrating the temperature and image data, the correction voltage signal and the historical inspection multidimensional data based on the time edge and the edge weight thereof, the space edge and the edge weight thereof and the target node and the attribute vector thereof to obtain an insulator time space correlation map.
6. The unmanned aerial vehicle-based direct current insulator state diagnosis system of claim 1, wherein the recognition prediction model adopts a fusion structure of a one-dimensional convolutional neural network, a gating circulation unit and a graph convolution network, wherein, The data processing module is specifically configured to: extracting local features in the correction voltage signals through the one-dimensional convolutional neural network; Capturing timing characteristics in the corrected voltage signal and the temperature and image data with the gating loop unit; adopting the graph convolution network to mine space correlation characteristics in the space correlation map of the insulator; and processing the local characteristics, the time sequence characteristics and the space correlation characteristics through a full connection layer and a Softmax function, and outputting a real-time state diagnosis result and a degradation trend prediction result of the target direct current insulator.
7. The unmanned aerial vehicle-based direct current insulator status diagnosis system according to claim 1, wherein the dynamic learning rate adjustment mechanism based on space-time features comprises: determining a characteristic vector of the target direct current insulator based on the insulator space-time correlation map, and determining characteristic change intensity according to the characteristic vector; initializing a learning rate, dynamically adjusting the initialized learning rate to a first preset multiple of a current value when the characteristic change intensity is larger than a first preset change threshold value, and dynamically adjusting the initialized learning rate to a second preset multiple of the current value when the characteristic change intensity is smaller than a second preset change threshold value.
8. A DC insulator state diagnosis method based on unmanned aerial vehicle is characterized by comprising the following steps: Acquiring voltage signals and temperature and image data of a target direct current insulator in real time in the inspection process of the unmanned aerial vehicle; performing temperature compensation correction on the voltage signal based on the temperature and the image data to obtain a corrected voltage signal; constructing an insulator time-space correlation map according to the temperature and image data, the correction voltage signal and the historical inspection multidimensional data of the target direct current insulator; And analyzing the insulator time-space correlation map, the correction voltage signal, the temperature and the image data by adopting an identification prediction model to obtain a real-time state diagnosis result and a degradation trend prediction result of the target direct current insulator, wherein the identification prediction model is obtained by training a dynamic learning rate adjustment mechanism based on time-space characteristics.
9. An electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the unmanned aerial vehicle-based dc insulator status diagnostic method of claim 8 when the computer program is executed.
10. A computer readable storage medium, wherein the computer readable storage medium comprises a stored computer program, and the direct current insulator state diagnosis method based on the unmanned aerial vehicle according to claim 8 is realized when the computer program is executed by a device where the computer readable storage medium is located.

Description

Unmanned aerial vehicle-based direct-current insulator state diagnosis method and system Technical Field The invention relates to the technical field of power system detection, in particular to a direct current insulator state diagnosis method and system based on an unmanned aerial vehicle. Background In the power transmission process, the performance of the direct current insulator is important to guaranteeing the stable operation of the power transmission line. With the continuous expansion of the power grid scale and the increasing demand for the reliability of the power, the voltage measurement and the state monitoring of the direct current insulator become key links of the power maintenance work. At present, an unmanned plane and an optical voltage sensor are utilized for carrying out target identification, so that an insulator is positioned and the voltage of the insulator is measured, but the method does not consider the influence of the ambient temperature on the measurement precision of the optical voltage sensor, so that errors exist in measurement results under different working conditions, and the method only carries out static detection at a single time point, lacks associated analysis on historical state data of the insulator, and cannot capture the time-space rule of state evolution of the insulator. Therefore, how to solve the problems that the existing direct current insulator detection technology has poor environmental adaptability and can only perform static detection is a technical problem to be solved urgently by those skilled in the art. Disclosure of Invention The invention provides a direct current insulator state diagnosis method and system based on an unmanned aerial vehicle, which solve the problems that the existing direct current insulator detection technology is poor in environmental adaptability and can only carry out static detection. In order to solve the technical problems, the first aspect of the invention provides a direct current insulator state diagnosis system based on an unmanned aerial vehicle, which comprises the unmanned aerial vehicle, and an intelligent sensing module, a voltage correction module, a map construction module and a data processing module which are carried on the unmanned aerial vehicle, The intelligent sensing module is used for collecting voltage signals, temperature and image data of the target direct current insulator in real time in the inspection process of the unmanned aerial vehicle; the voltage correction module is used for carrying out temperature compensation correction on the voltage signal based on the temperature and the image data to obtain a corrected voltage signal; the map construction module is used for constructing an insulator time-space correlation map according to the temperature and image data, the correction voltage signal and the historical inspection multidimensional data of the target direct current insulator; The data processing module is used for analyzing the insulator space-time correlation map, the correction voltage signal, the temperature and image data by adopting an identification prediction model to obtain a real-time state diagnosis result and a degradation trend prediction result of the target direct current insulator, wherein the identification prediction model is obtained by training a dynamic learning rate adjustment mechanism based on space-time characteristics. As one preferable solution, the intelligent sensing module includes: the ultrasonic ranging unit is used for collecting inspection track data of the unmanned aerial vehicle and distance data between the unmanned aerial vehicle and the target direct current insulator when the unmanned aerial vehicle flies to a detection point of the target direct current insulator, and controlling the distance between the unmanned aerial vehicle and the target direct current insulator to be in a preset range based on the distance data; The optical voltage sensor is used for collecting the voltage signal of the target direct current insulator in real time in the inspection process of the unmanned aerial vehicle; The temperature sensor is used for collecting the ambient temperature of the target direct current insulator in real time; And the camera system is used for acquiring the temperature distribution thermal image and the insulator surface image of the target direct current insulator in real time in the inspection process of the unmanned aerial vehicle to serve as the temperature and image data. As one preferable aspect, the optical voltage sensor includes: The electric field sensing probe is used for sensing first potential information around the target direct current insulator and converting the first potential information into a first electric signal; A light source for emitting an optical signal; The Pockels effect crystal is used for modulating the optical signal according to the first electric signal so as to change the polarization state or the phase of the