Power grid inspection and fault early warning system and method based on unmanned aerial vehicle

Abstract

The invention relates to the technical field of electric power grid inspection, and discloses an electric power grid inspection and fault early warning system and method based on an unmanned aerial vehicle. The system can comprehensively and accurately collect the operation condition of the power grid equipment, the environmental condition and the flight state of the unmanned aerial vehicle, a high-quality data basis is formed, the data processing module organizes and fuses the data, the consistency and reliability of information are ensured, accurate support is provided for subsequent analysis and calculation, and the system is suitable for popularization and application. The first calculation module and the second calculation module help to judge whether the power grid equipment has potential faults or not through quantitative coefficient calculation, and the first analysis module and the second analysis module further optimize the decision-making process in a mode of comparing with a threshold value to ensure that the system can make a response in real time. Potential problems of power grid equipment can be timely handled, and accident expansion is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid inspection, and in particular to a power grid inspection and fault early warning system and method based on unmanned aerial vehicle (UAV). Background Art

[0002] With the continuous development of science and technology, drone technology has gradually been applied to many fields, especially in the power industry. Inspection and maintenance of power grids are crucial to ensure the stability and safety of power supply. Traditional power inspections usually rely on manual inspections or ground monitoring equipment, which are inefficient and high-risk. In recent years, drone-based power inspection technology has become an important innovation direction, especially the ability of drones to conduct real-time inspections at high altitudes and inaccessible areas, which improves the efficiency and safety of inspections. Furthermore, combined with advanced data acquisition and processing technologies, drones can obtain real-time operation data of power grids and use intelligent algorithms to warn of faults, providing power companies with more efficient and accurate operation and maintenance support. This technology has gradually developed into a key component of smart grid systems and is widely used in detection, fault analysis and early warning systems for power equipment.

[0003] Although drone-based power grid inspection technology has made some progress, there are still many problems with the existing system. Most of the current power inspection systems rely on a single data source or sensor, which cannot fully reflect the real-time operating status of power grid equipment, resulting in limited accuracy and timeliness of fault warnings. Especially in a complex power network environment, a single data input may not be able to effectively capture the potential failure risks of equipment. Therefore, the lack of diversified data integration and intelligent analysis makes fault detection dependent on human judgment, increasing the risk of misjudgment and missed judgment. In addition, traditional systems are relatively simple in data processing and alarm mechanisms, and lack adaptive adjustment and dynamic learning capabilities.

[0004] Therefore, we proposed a UAV-based power grid inspection and fault warning system to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a power grid inspection and fault warning system based on drones, so as to solve the problem that most of the power inspection systems proposed in the above background technology rely on a single data source or sensor, and cannot fully reflect the real-time operating status of power grid equipment, resulting in the accuracy and timeliness of fault warnings being limited. Especially in a complex power grid environment, a single data input may not be able to effectively capture the potential failure risks of equipment. Therefore, the lack of diversified data integration and intelligent analysis makes fault detection dependent on human judgment, increasing the risk of misjudgment and missed judgment.

[0006] To achieve the above-mentioned object, the present invention provides the following technical solutions: a power grid inspection and fault warning system based on a drone, comprising a first data acquisition module, a second data acquisition module, a data processing module, a first calculation module, a first analysis module, a second calculation module, a second analysis module and an alarm module;

[0007] The first data acquisition module and the second data acquisition module are used to respectively collect multi-source data of the UAV and the power grid, and form a first multi-source data group and a second multi-source data group;

[0008] The data processing module is used to sort the first multi-source data group and the second multi-source data group to generate a first data set, a second data set, a third data set, a fourth data set, a fifth data set and a sixth data set;

[0009] The first calculation module is used to integrate the first data set, the second data set and the third data set to calculate the auxiliary intervention judgment coefficient FJX;

[0010] The first analysis module is used to compare the auxiliary intervention determination coefficient FJX with a preset first threshold value YZ to generate a first comparison result, and determine whether to generate a multi-source auxiliary intervention coefficient according to the first comparison result;

[0011] The second calculation module is used to integrate and calculate the first data set, the second data set and the third data set into a first auxiliary intervention coefficient S1, a second auxiliary intervention coefficient S2 and a third auxiliary intervention coefficient S3 respectively, the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 constitute a multi-source auxiliary intervention coefficient, and according to the first comparison result, integrate and calculate the first auxiliary intervention coefficient, the second auxiliary intervention coefficient and the third auxiliary intervention coefficient with the fifth data set, the sixth data set and the seventh data set, so as to generate a first alarm coefficient AQX1 and a second alarm coefficient AQX2 respectively;

[0012] The second analysis module is used to compare the first alarm coefficient AQX1 with the preset second threshold value YR to generate a second comparison result, and compare the second alarm coefficient AQX2 with the preset third threshold value YS to generate a third comparison result, and judge whether the current power grid is abnormal according to the second and third comparison results;

[0013] The alarm module is used for generating an alarm according to the second comparison result and the third comparison result.

[0014] Preferably, the first data acquisition module includes an environment acquisition unit and a body acquisition unit;

[0015] The environment collection unit is arranged on the UAV and is used to collect the surrounding environment data of the UAV during flight, including the ambient temperature, ambient humidity, ambient wind speed and ambient visibility;

[0016] The body acquisition unit is arranged on the UAV and is used to collect the status data of the UAV during flight, including flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity and image transmission rate;

[0017] The ambient temperature, ambient humidity, ambient wind speed, ambient visibility, flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity and image transmission rate constitute a first multi-source data set;

[0018] The second data acquisition module includes an operation data acquisition unit, an electrical parameter acquisition unit and a characteristic data acquisition unit;

[0019] The operation data acquisition unit is arranged on the drone and is used to collect the equipment operation status data of the power grid, including the inclination angle of the tower, the slackness of the conductor and the corrosion area on the surface of the equipment;

[0020] The electrical parameter acquisition unit is arranged in the power grid terminal system and is used to collect electrical parameter data of the power grid, including operating current, operating voltage and load power;

[0021] The characteristic data acquisition unit is arranged in the power grid terminal system and is used to collect characteristic parameter data of the power grid, including operating temperature value, arc duration and insulation resistance value;

[0022] The second multi-source data set includes the tower inclination angle, conductor slack, equipment surface corrosion area, operating current, operating voltage, load power, operating temperature value, arc duration and insulation resistance value.

[0023] Preferably, the data processing module preprocesses and dimensionlessly converts the first multi-source data group and the second multi-source data group, and sorts the processed first multi-source data group and the second multi-source data group to generate a first data set, a second data set, a third data set, a fourth data set, a fifth data set, a sixth data set, and a seventh data set;

[0024] The first data set includes flight altitude, flight speed, flight tilt angle, and image resolution;

[0025] The flight altitude is divided into GD1, GD2, GD3, ..., GDn according to the timestamp;

[0026] The flight speed is divided into SD1, SD2, SD3, ..., SDn according to the timestamp;

[0027] The flight tilt angles are divided into JD1, JD2, JD3, ..., JDn according to the timestamp;

[0028] Image resolution is divided into FB1, FB2, FB3, ..., FBn according to timestamp;

[0029] The second data set includes surface temperature, arc current intensity, signal intensity, and image transmission rate;

[0030] The surface temperature is divided into BW1, BW2, BW3, ..., BWn according to the timestamp;

[0031] The arc current intensity is divided into DH1, DH2, DH3, ..., DHn according to the timestamp;

[0032] The signal strength is divided into XH1, XH2, XH3, ..., XHn according to the timestamp;

[0033] The image transmission rate is divided into TX1, TX2, TX3, ..., TXn according to the timestamp;

[0034] The third data set includes ambient temperature, ambient humidity, ambient wind speed, and ambient visibility;

[0035] The ambient temperature is divided into HW1, HW2, HW3, ..., HWn according to the timestamp;

[0036] Ambient humidity is divided into HS1, HS2, HS3, ..., HSn according to the timestamp;

[0037] The ambient wind speed is divided into HF1, HF2, HF3, ..., HFn according to the timestamp;

[0038] Environmental visibility is divided into HN1, HN2, HN3, ..., HNn according to the timestamp;

[0039] The fourth data set includes the tower tilt angle, conductor slack, and equipment surface corrosion area;

[0040] The tower inclination angles are divided into QX1, QX2, QX3, ..., QXn according to the timestamp;

[0041] The wire slack is divided into SC1, SC2, SC3, ..., SCn according to the timestamp;

[0042] The equipment surface corrosion area is divided into FS1, FS2, FS3, ..., FSn according to the timestamp;

[0043] The fifth data set includes operating current, operating voltage, and load power;

[0044] The working current is divided into GL1, GL2, GL3, ..., GLn according to the timestamp;

[0045] The working voltage is divided into GY1, GY2, GY3, ..., GYn according to the timestamp;

[0046] The load power is divided into FZ1, FZ2, FZ3, ..., FZn according to the timestamp;

[0047] The sixth data set includes operating temperature values, arc duration, and insulation resistance values;

[0048] The operating temperature values ​​are divided into YW1, YW2, YW3, ..., YWn according to the timestamp;

[0049] The arc duration is divided into HC1, HC2, HC3, ..., HCn according to the timestamp;

[0050] The insulation resistance values ​​are divided into DZ1, DZ2, DZ3, ..., DZn according to the time stamp.

[0051] Preferably, the data processing module calculates and obtains FJX by the following formula:

[0052] FJX=a1×FXZ+a2×TXZ+a3×HJZ;

[0053] Where: FXZ is the flight state reference coefficient, TXZ is the communication state reference coefficient, and HJZ is the environment state reference coefficient, which are calculated and obtained through the first data set, the second data set, and the third data set respectively;

[0054] a1, a2 and a3 are weight values, and the values ​​of a1, a2 and a3 are adjusted and set by the user.

[0055] Preferably, the data processing module calculates and obtains the flight state reference coefficient FXZ, the communication state reference coefficient TXZ and the environment state reference coefficient HJZ respectively through the following formulas:

[0056]

[0057]

[0058] Wherein: GDn, SDn, JDn, FBn, BWn, DHn, XHn, TXn, HWn, HSn, HFn and QXn are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the nth timestamp;

[0059] GD1, SD1, JD1, FB1, BW1, DH1, XH1, TX1, HW1, HS1, HF1 and QX1 are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the first timestamp;

[0060] PGD, PSD, PJD, PFB, PBW, PDH, PXH, PTX, PHW, PHS, PHF and PQX are the average flight altitude, average flight speed, average flight inclination angle, average image resolution, average surface temperature, average arc current intensity, average signal strength, average image transmission rate, average ambient temperature, average ambient humidity, average ambient wind speed and average ambient visibility respectively.

[0061] Preferably, the data processing module calculates and obtains the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 respectively through the following formulas:

[0062]

[0063] Wherein: GDn, SDn, JDn, FBn, BWn, DHn, XHn, TXn, HWn, HSn, HFn and QXn are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the nth timestamp;

[0064] GDn-1, SDn-1, JDn-1, FBn-1, BWn-1, DHn-1, XHn-1, TXn-1, HWn-1, HSn-1, HFn-1 and QXn-1 are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the n-1th timestamp;

[0065] b1, b2, b3 and b4 are weight values, and the values ​​of b1, b2, b3 and b4 are adjusted and set by the user.

[0066] Preferably, the first comparison result is as follows:

[0067] When FJX≤YZ, it means that there is no need to generate a multi-source auxiliary intervention coefficient. When FJX>YZ, it means that a multi-source auxiliary intervention coefficient needs to be generated.

[0068] Preferably, the first calculation module calculates and obtains the first alarm coefficient AQX1 and the second alarm coefficient AQX2 by the following formulas respectively:

[0069]

[0070] Where: S1 is the first auxiliary intervention coefficient, S2 is the second auxiliary intervention coefficient, and S3 is the third auxiliary intervention coefficient;

[0071] QXn, SCn, FSn, GLn, GYn, FZn, YWn, HCn and DZn are the tower inclination angle, conductor slack, equipment surface corrosion area, working current, working voltage, load power, operating temperature, arc duration and insulation resistance value at the nth timestamp respectively.

[0072] Preferably, the second comparison result is as follows:

[0073] When AQX1≤YR, it means that the current power grid is safe, and when AQX1>YR, it means that the current power grid is unsafe;

[0074] When AQX2≤YS, it means that the current power grid is safe, and when AQX2>YS, it means that the current power grid is unsafe.

[0075] This application also includes a power grid inspection and fault warning method based on drones, and the specific steps are as follows:

[0076] S1. First, multi-source data of the UAV and the power grid are collected by a first data collection module and a second data collection module to form a first multi-source data group and a second multi-source data group;

[0077] S2, sorting and preprocessing the first multi-source data group and the second multi-source data group by a data processing module to generate multiple data sets after processing;

[0078] S3, integrating the first data set, the second data set and the third data set into an auxiliary intervention judgment coefficient FJX through a first calculation module, comparing the auxiliary intervention judgment coefficient with a preset first threshold YZ through a first analysis module, thereby generating a first comparison result, and judging whether to generate a multi-source auxiliary intervention coefficient according to the first comparison result;

[0079] S4, integrating and calculating the first data set, the second data set and the third data set into a first auxiliary intervention coefficient S1, a second auxiliary intervention coefficient S2 and a third auxiliary intervention coefficient S3 respectively through a second calculation module, wherein the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 constitute a multi-source auxiliary intervention coefficient, and integrating and calculating the first auxiliary intervention coefficient, the second auxiliary intervention coefficient and the third auxiliary intervention coefficient with the fifth data set, the sixth data set and the seventh data set according to the first comparison result, so as to generate a first alarm coefficient and a second alarm coefficient respectively;

[0080] S5. Compare the first alarm coefficient with the preset second threshold value YR through the second analysis module to generate a second comparison result, and compare the second alarm coefficient with the preset third threshold value YS to generate a third comparison result. According to the second and third comparison results, determine whether the current power grid is abnormal, and issue an alarm according to the second comparison result and the third comparison result through the alarm module.

[0081] Compared with the prior art, the present invention has the following beneficial effects:

[0082] 1. Through the multi-source fusion of flight status, power grid equipment and its environmental data in the first data acquisition module and the second data acquisition module, the system can comprehensively and accurately collect the operation status of power grid equipment, environmental conditions and flight status of drones, forming a high-quality data foundation. The data processing module 3 organizes and integrates these data to ensure the consistency and reliability of information and provide accurate support for subsequent analysis and calculation. The first calculation module and the second calculation module help to determine whether there is a potential fault in the power grid equipment through quantitative coefficient calculation, while the first analysis module and the second analysis module further optimize the decision-making process by comparing with the threshold to ensure that the system can respond in real time. The alarm module ensures that potential problems of power grid equipment can be handled in time through instant feedback and alarm to avoid the expansion of accidents. Overall, this system not only improves the inspection efficiency of the power grid, but also greatly improves the accuracy of fault warning, providing a strong guarantee for the safe and stable operation of the power system.

[0083] 2. By setting the first threshold value YZ and comparing the threshold value with the comprehensive judgment coefficient FJX, the system can decide whether it is necessary to generate a multi-source auxiliary intervention coefficient. The introduction of this comparison mechanism realizes the intelligent decision-making of the inspection task. The system determines whether further intervention is needed based on the current situation. The threshold comparison mechanism avoids manual intervention and excessive intervention by setting a clear critical value for FJX. When the FJX value is less than or equal to YZ, it indicates that the status during the inspection process is still within the normal range. The system can keep the current inspection task unchanged without additional intervention operations. When the FJX value is greater than YZ, the system will respond promptly according to the real-time data changes, generate a multi-source auxiliary intervention coefficient to further optimize the inspection task and reduce potential risks. This mechanism can improve the automation and intelligence level of the system, reduce human intervention, and improve inspection efficiency.

[0084] 3. By introducing two alarm coefficients, the system can calculate multiple alarm indicators based on different influencing factors, and judge the safety status of the power grid based on the comparison results of these indicators. The calculation formulas of AQX1 and AQX2 combine different reference coefficients and use multi-dimensional data input. This design of multiple alarm coefficients increases the comprehensive perception of potential problems by the power grid inspection and fault warning system. Compared with the traditional monitoring method of a single alarm coefficient, this multi-dimensional alarm coefficient design improves the accuracy and sensitivity of monitoring. When various power grid parameters change greatly, the system can sensitively capture abnormal fluctuations in the power grid state and issue an alarm in advance. This enables the system to detect potential problems at an earlier stage, avoid the spread of equipment failures, and improve the reliability and stability of the power grid. By considering multiple factors, the system can more accurately reflect the overall status of the power grid. For example, the tilt of the tower and the relaxation of the conductor may cause abnormal changes in electrical parameters, which are directly related to the surface corrosion of the equipment and the electrical load. Traditional early warning systems often ignore the combined impact of these factors, and this system can timely discover potential safety risks of equipment by calculating a variety of factors, thereby effectively preventing the occurrence of failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 It is a system flow chart of the present invention.

[0086] Figure 2 It is a diagram of the method steps of the present invention.

[0087] In the figure: 1. First data acquisition module; 11. Environment acquisition unit; 12. Body acquisition unit; 2. Second data acquisition module; 21. Operation data acquisition unit; 22. Electrical parameter acquisition unit; 23. Feature data acquisition unit; 3. Data processing module; 4. First calculation module; 5. First analysis module; 6. Second calculation module; 7. Second analysis module; 8. Alarm module. DETAILED DESCRIPTION

[0088] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0089] Example 1: Please refer to Figure 1 , a power grid inspection and fault warning system based on drone, comprising a first data acquisition module 1, a second data acquisition module 2, a data processing module 3, a first calculation module 4, a first analysis module 5, a second calculation module 6, a second analysis module 7 and an alarm module 8;

[0090] The first data acquisition module 1 and the second data acquisition module 2 are used to collect multi-source data of the UAV and the power grid respectively, and form a first multi-source data group and a second multi-source data group;

[0091] The data processing module 3 is used to sort the first multi-source data group and the second multi-source data group to generate a first data set, a second data set, a third data set, a fourth data set, a fifth data set and a sixth data set;

[0092] The first calculation module 4 is used to integrate the first data set, the second data set and the third data set to calculate the auxiliary intervention judgment coefficient FJX;

[0093] The first analysis module 5 is used to compare the auxiliary intervention determination coefficient FJX with a preset first threshold value YZ, thereby generating a first comparison result, and judging whether to generate a multi-source auxiliary intervention coefficient according to the first comparison result;

[0094] The second calculation module 6 is used for integrating and calculating the first data set, the second data set and the third data set into a first auxiliary intervention coefficient S1, a second auxiliary intervention coefficient S2 and a third auxiliary intervention coefficient S3 respectively, wherein the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 constitute a multi-source auxiliary intervention coefficient, and integrating and calculating the first auxiliary intervention coefficient, the second auxiliary intervention coefficient and the third auxiliary intervention coefficient with the fifth data set, the sixth data set and the seventh data set according to the first comparison result, so as to generate a first alarm coefficient AQX1 and a second alarm coefficient AQX2 respectively;

[0095] The second analysis module 7 is used to compare the first alarm coefficient AQX1 with the preset second threshold value YR to generate a second comparison result, and compare the second alarm coefficient AQX2 with the preset third threshold value YS to generate a third comparison result, and judge whether the current power grid is abnormal according to the second and third comparison results;

[0096] The alarm module 8 is used for generating an alarm according to the second comparison result and the third comparison result.

[0097] In this embodiment: the first data acquisition module 1 is responsible for acquiring multi-source data of power grid inspection from the drone. Through the various sensors carried on the drone, the module can collect the appearance, environment and operating status data of the power grid equipment in real time. Specifically, it includes information such as the inclination angle of the tower, the slackness of the wire, and the corrosion condition of the equipment surface. These data provide a basis for subsequent data processing and calculation, help to timely capture the potential hidden dangers or failures of the power grid equipment, and lay a data foundation for the intelligent inspection system.

[0098] The second data acquisition module 2 is responsible for acquiring relevant operating data from various devices and sensors in the power grid. These data include electrical parameters such as voltage, current, frequency, and information such as the operating status, load, and temperature of the equipment. These data are crucial for determining whether there are potential faults or unstable factors in the power grid. By comprehensively collecting multi-dimensional data of the power grid, the second data acquisition module 2 provides more comprehensive and accurate data support for subsequent fault diagnosis and early warning.

[0099] The function of the data processing module 3 is to sort, fuse and optimize the multi-source data from the first data acquisition module 1 and the second data acquisition module 2. Through efficient data cleaning, denoising, standardization and normalization, the module can convert data from different sources and formats into a unified standard data set that is easy to process later. Through data integration, multiple data sets including the first data set, the second data set, the third data set, the fourth data set, the fifth data set and the sixth data set are generated, providing accurate and comprehensive data support for subsequent calculation and analysis modules, ensuring the accuracy and reliability of the system.

[0100] The first calculation module 4 is responsible for integrating and calculating the processed data set to obtain the auxiliary intervention judgment coefficient FJX. This coefficient is the result of a comprehensive evaluation of the power grid inspection data, combining multiple factors such as flight status and equipment operation status. The calculated auxiliary intervention judgment coefficient can provide a basis for subsequent intervention decisions, ensuring that the drone can detect potential faults or safety hazards in a timely manner, thereby optimizing the inspection process and improving the operational safety of power grid equipment.

[0101] The first analysis module 5 is responsible for comparing the calculated auxiliary intervention judgment coefficient FJX with the preset first threshold value YZ to generate a first comparison result. If FJX exceeds the set threshold value YZ, it indicates that some factors in the inspection process may be abnormal, and the system needs to trigger further fault diagnosis and auxiliary intervention. Through comparative analysis, the first analysis module 5 can effectively identify potential problems of power grid equipment and provide a basis for subsequent intervention, avoiding omissions and delays in manual inspections and improving the timeliness and accuracy of fault warnings.

[0102] The second calculation module 6 further refines the analysis of the inspection data, integrates and calculates the first data set, the second data set and the third data set, and obtains the first, second and third auxiliary intervention coefficients S1, S2, S3, which constitute the multi-source auxiliary intervention coefficients. Combined with the first comparison result, the second calculation module 6 will also perform a comprehensive calculation of these auxiliary intervention coefficients with the fifth, sixth and seventh data sets according to the set standards to obtain the first alarm coefficient and the second alarm coefficient. These alarm coefficients provide an important basis for whether the system triggers an alarm and intervention, and help determine whether manual intervention is required to prevent the accident from expanding.

[0103] The main task of the second analysis module 7 is to compare the calculated first alarm coefficient with the preset second threshold value YR to generate a second comparison result, and to compare the second alarm coefficient with the third threshold value YS to generate a third comparison result. If any alarm coefficient exceeds the set threshold, the system will consider that there is an abnormality in the power grid, which may trigger the alarm system for processing. This analysis process can effectively determine whether there are abnormalities in the operation of the power grid, thereby discovering possible faults in the power grid in advance, and taking corresponding preventive and intervention measures to reduce the risk of faults.

[0104] The alarm module 8 is the last line of defense of the system, and is responsible for determining whether an alarm needs to be triggered based on the second and third comparison results. If both the second and third comparison results show that there is an abnormality in the power grid, the alarm module 8 will alert relevant personnel and may trigger an emergency processing mechanism. This module can respond to abnormal power grid conditions in real time, minimize the occurrence and expansion of power grid accidents, and ensure the stability and security of power supply.

[0105] Through the multi-source fusion of flight status, power grid equipment and its environmental data in the first data acquisition module 1 and the second data acquisition module 2, the system can comprehensively and accurately collect the operation status of power grid equipment, environmental conditions and flight status of drones, forming a high-quality data foundation. The data processing module 3 organizes and integrates these data to ensure the consistency and reliability of information and provide accurate support for subsequent analysis and calculation. The first calculation module 4 and the second calculation module 6 help to determine whether there is a potential fault in the power grid equipment through quantitative coefficient calculation, while the first analysis module 5 and the second analysis module 7 further optimize the decision-making process by comparing with the threshold value to ensure that the system can respond in real time. The alarm module 8 ensures that the potential problems of the power grid equipment can be handled in time through instant feedback and alarm to avoid the expansion of accidents. Overall, the system not only improves the inspection efficiency of the power grid, but also greatly improves the accuracy of fault warning, providing a strong guarantee for the safe and stable operation of the power system.

[0106] Example 2: Please refer to Figure 1 , the first data acquisition module 1 includes an environment acquisition unit 11 and a body acquisition unit 12;

[0107] The environment collection unit 11 is arranged on the UAV and is used to collect the surrounding environment data of the UAV during flight, including the ambient temperature, ambient humidity, ambient wind speed and ambient visibility;

[0108] The body acquisition unit 12 is arranged on the UAV and is used to collect the status data of the UAV during flight, including flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity and image transmission rate;

[0109] Ambient temperature, ambient humidity, ambient wind speed, ambient visibility, flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, and image transmission rate constitute a first multi-source data set;

[0110] The second data acquisition module 2 includes an operation data acquisition unit 21, an electrical parameter acquisition unit 22 and a characteristic data acquisition unit 23;

[0111] The operation data acquisition unit 21 is arranged on the drone and is used to collect the equipment operation status data of the power grid, including the inclination angle of the tower, the slackness of the conductor and the corrosion area of ​​the equipment surface;

[0112] The electrical parameter acquisition unit 22 is arranged in the power grid terminal system and is used to collect electrical parameter data of the power grid, including operating current, operating voltage and load power;

[0113] The characteristic data acquisition unit 23 is arranged in the power grid terminal system and is used to collect characteristic parameter data of the power grid, including operating temperature value, arc duration and insulation resistance value;

[0114] The second multi-source data set includes the tower inclination angle, conductor slack, equipment surface corrosion area, working current, working voltage, load power, operating temperature value, arc duration and insulation resistance value.

[0115] In this embodiment: the first data acquisition module 1 integrates the environmental data and body state data of the UAV during flight through the environmental acquisition unit 11 and the body acquisition unit 12. The environmental data includes temperature, humidity, wind speed and visibility, while the body state data includes flight altitude, speed, tilt angle, image resolution, surface temperature, arc current intensity, signal strength and image transmission rate. This design can realize multi-dimensional real-time monitoring of the UAV during flight, providing more comprehensive and accurate data support for inspection tasks, and multi-source data fusion can effectively improve the inspection accuracy. For example, during flight, factors such as ambient temperature, humidity, wind speed and visibility will have an important impact on the flight stability and image acquisition quality of the UAV. By collecting these data in real time, the flight strategy can be adjusted in time to avoid inspection deviations caused by environmental factors. At the same time, the body state data can ensure the stability of the UAV during flight, thereby improving the safety and reliability of the inspection task.

[0116] The second data acquisition module 2 collects key operating status data, electrical parameter data and equipment characteristic data of the power grid equipment through the operation data acquisition unit 21, the electrical parameter acquisition unit 22 and the characteristic data acquisition unit 23. Specifically, it includes the inclination angle of the tower, the slack of the conductor, the corrosion area of ​​the equipment surface, the working current, the working voltage, the load power, the operating temperature, the arc duration and the insulation resistance, etc. These data help to realize the comprehensive monitoring of the status of the power grid equipment. Through the real-time health monitoring of the power grid equipment, the system can issue early warnings in time when abnormalities occur. For example, the inclination angle of the tower and the slack of the conductor are important indicators that lead to damage or failure of the power grid equipment. Timely monitoring can avoid potential safety hazards. At the same time, electrical parameters such as working current, voltage and load power can help identify power grid overload or other electrical fault problems, and ensure the safety and stability of the operation of power grid equipment.

[0117] Example 3: Please refer to Figure 1 , the data processing module 3 preprocesses and dimensionlessly converts the first multi-source data group and the second multi-source data group, and sorts the processed first multi-source data group and the second multi-source data group to generate a first data set, a second data set, a third data set, a fourth data set, a fifth data set, a sixth data set, and a seventh data set;

[0118] The first data set includes flight altitude, flight speed, flight tilt angle, and image resolution;

[0119] The flight altitude is divided into GD1, GD2, GD3, ..., GDn according to the timestamp;

[0120] The flight speed is divided into SD1, SD2, SD3, ..., SDn according to the timestamp;

[0121] The flight tilt angles are divided into JD1, JD2, JD3, ..., JDn according to the timestamp;

[0122] Image resolution is divided into FB1, FB2, FB3, ..., FBn according to timestamp;

[0123] The second data set includes surface temperature, arc current intensity, signal intensity, and image transmission rate;

[0124] The surface temperature is divided into BW1, BW2, BW3, ..., BWn according to the timestamp;

[0125] The arc current intensity is divided into DH1, DH2, DH3, ..., DHn according to the timestamp;

[0126] The signal strength is divided into XH1, XH2, XH3, ..., XHn according to the timestamp;

[0127] The image transmission rate is divided into TX1, TX2, TX3, ..., TXn according to the timestamp;

[0128] The third data set includes ambient temperature, ambient humidity, ambient wind speed, and ambient visibility;

[0129] The ambient temperature is divided into HW1, HW2, HW3, ..., HWn according to the timestamp;

[0130] Ambient humidity is divided into HS1, HS2, HS3, ..., HSn according to the timestamp;

[0131] The ambient wind speed is divided into HF1, HF2, HF3, ..., HFn according to the timestamp;

[0132] Environmental visibility is divided into HN1, HN2, HN3, ..., HNn according to the timestamp;

[0133] The fourth data set includes the tower tilt angle, conductor slack, and equipment surface corrosion area;

[0134] The tower inclination angles are divided into QX1, QX2, QX3, ..., QXn according to the timestamp;

[0135] The wire slack is divided into SC1, SC2, SC3, ..., SCn according to the timestamp;

[0136] The equipment surface corrosion area is divided into FS1, FS2, FS3, ..., FSn according to the timestamp;

[0137] The fifth data set includes operating current, operating voltage, and load power;

[0138] The working current is divided into GL1, GL2, GL3, ..., GLn according to the timestamp;

[0139] The working voltage is divided into GY1, GY2, GY3, ..., GYn according to the timestamp;

[0140] The load power is divided into FZ1, FZ2, FZ3, ..., FZn according to the timestamp;

[0141] The sixth data set includes operating temperature values, arc duration, and insulation resistance values;

[0142] The operating temperature values ​​are divided into YW1, YW2, YW3, ..., YWn according to the timestamp;

[0143] The arc duration is divided into HC1, HC2, HC3, ..., HCn according to the timestamp;

[0144] The insulation resistance values ​​are divided into DZ1, DZ2, DZ3, ..., DZn according to the time stamp.

[0145] In this embodiment: the data processing module 3 preprocesses and dimensionless the first multi-source data set and the second multi-source data set to eliminate the dimension differences between the various data sources and unify the data format. This step enables data from different sources to be analyzed and compared more effectively. The dimensionless processing can convert data of different units and dimensions into a comparable standard form, reducing calculation errors caused by inconsistent units or dimension differences. At the same time, the preprocessing of the data improves the quality and consistency of the data, providing an accurate basis for subsequent analysis and decision-making.

[0146] The data processing module 3 generates multiple data sets, including a first data set, a second data set, a third data set, etc., by arranging the first multi-source data set and the second multi-source data set. Each data set contains data items marked with timestamps. This arrangement method processes complex raw data separately according to different dimensions, improves the operability and visualization of the data, and the arrangement of data sets makes each data set more structured, and provides convenient input for subsequent analysis, model training and fault prediction. The division of each data set is based on timestamps, which helps to accurately track data changes at each moment, and then conduct real-time monitoring and dynamic adjustment. For example, flight data, environmental data, electrical parameter data, etc. organized by timestamps can help accurately capture potential abnormal changes and equipment failure trends.

[0147] By assigning numbers to each data item according to the timestamp, the data processing module 3 provides a clear structure for the management and analysis of time series data. This design can effectively distinguish data at different time points, which is convenient for analyzing and modeling time series. The data marked with timestamps can help track the real-time status changes of drones and power grid equipment, especially in the monitoring process. It can identify anomalies in time. Through time series analysis, the system can detect potential trends or periodic faults, and make early warnings based on the laws of historical data, thereby improving the intelligent level of power grid inspection. This functional distinction provides higher flexibility and operability for subsequent data analysis, model building and prediction. By analyzing each type of data independently, the system can optimize different task areas in a targeted manner, further improving the inspection efficiency and the accuracy of fault warning. For example, if the arc current intensity changes abnormally, it can be directly detected through the relevant data in the second data set; if the image transmission rate is low, the problem in the flight environment and flight equipment can be immediately located.

[0148] By arranging various types of data such as flight data, environmental data, and electrical parameters into multiple data sets according to timestamps, the data processing module 3 provides support for the multi-dimensional monitoring of the system. Each data set not only reflects the changes in a certain type of data, but can also be jointly analyzed with other data sets in practical applications to obtain more comprehensive power grid inspection and fault warning results. The construction of multi-dimensional data sets provides the system with powerful comprehensive analysis capabilities, which can simultaneously consider multiple factors such as flight environment, equipment status, and electrical parameters, and help detect faults that may be caused by environmental changes or equipment abnormalities. For example, changes in flight speed and flight altitude may affect image quality, and thus affect the accuracy of equipment monitoring; the current and voltage fluctuations of the power grid are also related to the corrosion degree or tilt angle of the equipment, which can provide early warning of equipment failures.

[0149] Example 4: Please refer to Figure 1 , the data processing module 3 calculates and obtains FJX through the following formula:

[0150] FJX=a1×FXZ+a2×TXZ+a3×HJZ;

[0151] Where: FXZ is the flight state reference coefficient, TXZ is the communication state reference coefficient, and HJZ is the environment state reference coefficient, which are calculated and obtained through the first data set, the second data set, and the third data set respectively;

[0152] a1, a2 and a3 are weight values, and the values ​​of a1, a2 and a3 are adjusted and set by the user.

[0153] The data processing module 3 calculates and obtains the flight state reference coefficient FXZ, the communication state reference coefficient TXZ and the environment state reference coefficient HJZ respectively through the following formulas:

[0154]

[0155]

[0156] Wherein: GDn, SDn, JDn, FBn, BWn, DHn, XHn, TXn, HWn, HSn, HFn and QXn are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the nth timestamp;

[0157] GD1, SD1, JD1, FB1, BW1, DH1, XH1, TX1, HW1, HS1, HF1 and QX1 are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the first timestamp;

[0158] PGD, PSD, PJD, PFB, PBW, PDH, PXH, PTX, PHW, PHS, PHF and PQX are the average flight altitude, average flight speed, average flight inclination angle, average image resolution, average surface temperature, average arc current intensity, average signal strength, average image transmission rate, average ambient temperature, average ambient humidity, average ambient wind speed and average ambient visibility respectively.

[0159] In this embodiment: the data processing module 3 calculates the flight status reference coefficient FXZ, the communication status reference coefficient TXZ and the environmental status reference coefficient HJZ through a formula, and weights and integrates the three types of reference coefficients through a weighted coefficient, and finally obtains the auxiliary intervention judgment coefficient FJX. This calculation method comprehensively considers data inputs in multiple dimensions, thereby more comprehensively evaluating the inspection status of the power grid.

[0160] By integrating different data sources in a weighted manner, the system can provide a comprehensive evaluation result, thereby considering the comprehensive impact of multiple variables on the inspection effect in real time during the power grid inspection process. This weighted calculation mechanism can dynamically adjust the weight of each dimension according to actual needs and situations, improve the adaptability and accuracy of the system, and ensure that accurate judgment results can be provided in different environments.

[0161] When calculating each reference coefficient, the system realizes multi-period dynamic analysis of time series data by performing difference and standardization on the values ​​of each data item at different timestamps, further enhancing the ability to capture flight status, communication status and environmental changes. Based on the dynamic analysis of time series data, the system can identify the trend of data changes over time and promptly detect abnormal fluctuations or deviations from the normal range. For example, changes in parameters such as flight altitude, speed, and tilt angle may be associated with inspection results or abnormal conditions of power grid equipment. In this way, the system can effectively warn of potential equipment failures, flight safety hazards or communication problems, significantly improving the accuracy of real-time monitoring.

[0162] By comparing the data of the first timestamp and the nth timestamp of each data item during the inspection, calculating their difference, and standardizing them relative to the mean, the comparability of the data and the ability to detect abnormal fluctuations are improved. This method not only compares the current data with the initial data, but also reflects the changing trend of the data throughout the inspection process. Using the mean as a benchmark for data comparison helps capture small changes that deviate from the normal range, especially in long-term monitoring. This method can not only detect obvious anomalies, but also discover progressive or potential risks, such as the gradual degradation of power equipment at different inspection stages or fluctuations in communication quality, thereby providing more accurate fault prediction and early warning.

[0163] The weighting coefficients a1, a2 and a3 are set by the user, giving the user the ability to customize the weights of each reference coefficient according to actual needs. This flexibility enables the system to flexibly adjust the importance of flight status, communication status and environmental status according to different working environments, inspection tasks and priority requirements.

[0164] Example 5: Please refer to Figure 1The data processing module 3 calculates and obtains the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 respectively through the following formulas:

[0165]

[0166] Wherein: GDn, SDn, JDn, FBn, BWn, DHn, XHn, TXn, HWn, HSn, HFn and QXn are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the nth timestamp;

[0167] GDn-1, SDn-1, JDn-1, FBn-1, BWn-1, DHn-1, XHn-1, TXn-1, HWn-1, HSn-1, HFn-1 and QXn-1 are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the n-1th timestamp;

[0168] b1, b2, b3 and b4 are weight values, and the values ​​of b1, b2, b3 and b4 are adjusted and set by the user.

[0169] In this embodiment: the data processing module 3 can accurately reflect the changes in flight status, communication status and environmental status, and dynamically generate the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 according to these changes. This mechanism not only enhances the system's ability to perceive small changes, but also improves the system's flexibility and adaptability in complex power grid inspection environments. Compared with traditional power grid inspection methods, this system can achieve more accurate and efficient inspections through comprehensive multi-dimensional data analysis and intelligent decision support, and timely warn of potential equipment failures and flight safety issues, thereby greatly improving the safety, reliability and efficiency of power grid inspections.

[0170] Example 6: Please refer to Figure 1 , the first comparison results are as follows:

[0171] When FJX≤YZ, it means that there is no need to generate a multi-source auxiliary intervention coefficient. When FJX>YZ, it means that a multi-source auxiliary intervention coefficient needs to be generated.

[0172] The first calculation module 4 calculates and obtains the first alarm coefficient AQX1 and the second alarm coefficient AQX2 by the following formulas:

[0173]

[0174] Where: S1 is the first auxiliary intervention coefficient, S2 is the second auxiliary intervention coefficient, and S3 is the third auxiliary intervention coefficient;

[0175] QXn, SCn, FSn, GLn, GYn, FZn, YWn, HCn and DZn are the tower inclination angle, conductor slack, equipment surface corrosion area, working current, working voltage, load power, operating temperature, arc duration and insulation resistance value at the nth timestamp respectively.

[0176] In this embodiment: by setting a first threshold value YZ, and based on the comparison between the threshold value and the comprehensive judgment coefficient FJX, the system can decide whether it is necessary to generate a multi-source auxiliary intervention coefficient. The introduction of this comparison mechanism realizes the intelligent decision-making of the inspection task. The system determines whether further intervention is needed based on the current situation. The threshold comparison mechanism avoids manual intervention and excessive intervention by setting a clear critical value for FJX. When the FJX value is less than or equal to YZ, it indicates that the status during the inspection process is still within the normal range. The system can keep the current inspection task unchanged without additional intervention operations. When the FJX value is greater than YZ, the system will respond promptly according to the real-time data changes, generate a multi-source auxiliary intervention coefficient to further optimize the inspection task and reduce potential risks. This mechanism can improve the automation and intelligence level of the system, reduce human intervention, and improve inspection efficiency.

[0177] The comparison result automatically triggers the decision of whether to generate a multi-source auxiliary intervention coefficient based on the relationship between FJX and YZ. If FJX exceeds the set first threshold YZ, the system will automatically generate a multi-source auxiliary intervention coefficient to adjust the drone inspection strategy. This process does not rely on manual intervention and can respond promptly to changes in data. Through the intelligent decision-making mechanism, the system can evaluate whether the status is abnormal in real time during the inspection process and automatically adjust it according to the degree of abnormality. This automatic adjustment capability significantly improves the efficiency and accuracy of inspections, especially in complex environments, avoiding inspection errors caused by delayed or incorrect manual judgment. For example, if environmental changes cause the FJX value to exceed the preset threshold, the system will automatically trigger early warning and adjustment measures to ensure that the inspection personnel can grasp the equipment operation status in time and avoid power grid failures caused by ignoring details. By setting the comparison rules of FJX and YZ, the system can avoid generating multi-source auxiliary intervention coefficients when it is not necessary, thereby reducing ineffective intervention and waste of resources. Only when the FJX value exceeds YZ will the multi-source auxiliary intervention coefficient be generated for further adjustment.

[0178] Example 7: Please refer to Figure 1 , the second comparison results are as follows:

[0179] When AQX1≤YR, it means that the current power grid is safe, and when AQX1>YR, it means that the current power grid is unsafe;

[0180] When AQX2≤YS, it means that the current power grid is safe, and when AQX2>YS, it means that the current power grid is unsafe.

[0181] In this embodiment: by introducing two alarm coefficients, the system can calculate multiple alarm indicators based on different influencing factors, and judge the safety status of the power grid according to the comparison results of these indicators. The calculation formulas of AQX1 and AQX2 combine different reference coefficients and use multi-dimensional data input. This design of multiple alarm coefficients increases the comprehensive perception of potential problems by the power grid inspection and fault warning system. Compared with the traditional monitoring method of a single alarm coefficient, this multi-dimensional alarm coefficient design improves the accuracy and sensitivity of monitoring. When the various power grid parameters change greatly, the system can sensitively capture the abnormal fluctuations in the power grid state and issue an alarm in advance. This enables the system to detect potential problems at an earlier stage, avoid the spread of equipment failures, and improve the reliability and stability of the power grid. By considering multiple factors, the system can more accurately reflect the overall state of the power grid. For example, the tilt of the tower and the looseness of the conductor may cause abnormal changes in electrical parameters, which are directly related to the surface corrosion of the equipment and the electrical load. Traditional early warning systems often ignore the combined impact of these factors, and this system can timely discover the potential safety risks of the equipment by calculating a variety of factors, thereby effectively preventing the occurrence of failures.

[0182] Two different thresholds are introduced, and the safety status of the power grid is judged by comparing the values ​​of the alarm coefficients AQX1 and AQX2 with these thresholds. This setting not only provides a more accurate judgment standard, but also enables the system to make reasonable judgments based on actual data fluctuations when evaluating whether the power grid is safe. By setting different thresholds, the system can flexibly adjust the alarm standards according to the actual power grid status. In different operating scenarios, users can adjust these thresholds as needed, and make dynamic adjustments, making the system's early warning mechanism more adaptable in different environments. For power grid operators, this flexible setting makes the system more accurate in early warning response, avoiding false alarms or missed alarms caused by improper threshold settings.

[0183] This application also includes a method for power grid inspection and fault warning based on drones, please refer to Figure 2 , the specific steps are as follows:

[0184] S1, firstly, the multi-source data of the UAV and the power grid are collected by the first data collection module 1 and the second data collection module 2 respectively to form a first multi-source data group and a second multi-source data group;

[0185] S2, sorting and preprocessing the first multi-source data set and the second multi-source data set by the data processing module 3 to generate multiple data sets after processing;

[0186] S3, integrating the first data set, the second data set and the third data set into an auxiliary intervention judgment coefficient FJX through the first calculation module 4, comparing the auxiliary intervention judgment coefficient with a preset first threshold value YZ through the first analysis module 5, thereby generating a first comparison result, and judging whether to generate a multi-source auxiliary intervention coefficient according to the first comparison result;

[0187] S4, integrating and calculating the first data set, the second data set and the third data set into a first auxiliary intervention coefficient S1, a second auxiliary intervention coefficient S2 and a third auxiliary intervention coefficient S3 respectively through the second calculation module 6, the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 constitute a multi-source auxiliary intervention coefficient, and integrating and calculating the first auxiliary intervention coefficient, the second auxiliary intervention coefficient and the third auxiliary intervention coefficient with the fifth data set, the sixth data set and the seventh data set according to the first comparison result, so as to generate a first alarm coefficient and a second alarm coefficient respectively;

[0188] S5. The first alarm coefficient is compared with the preset second threshold value YR through the second analysis module 7 to generate a second comparison result, and the second alarm coefficient is compared with the preset third threshold value YS to generate a third comparison result. According to the second and third comparison results, it is determined whether the current power grid is abnormal, and an alarm is issued according to the second comparison result and the third comparison result through the alarm module 8.

[0189] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

[0190] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A power grid inspection and fault warning system based on drones, characterized by: It comprises a first data acquisition module (1), a second data acquisition module (2), a data processing module (3), a first calculation module (4), a first analysis module (5), a second calculation module (6), a second analysis module (7) and an alarm module (8); The first data acquisition module (1) and the second data acquisition module (2) are used to respectively collect multi-source data of the drone and the power grid, and form a first multi-source data group and a second multi-source data group; The data processing module (3) is used to sort the first multi-source data set and the second multi-source data set to generate a first data set, a second data set, a third data set, a fourth data set, a fifth data set and a sixth data set; The first calculation module (4) is used to integrate the first data set, the second data set and the third data set to calculate the auxiliary intervention judgment coefficient FJX; The first analysis module (5) is used to compare the auxiliary intervention determination coefficient FJX with a preset first threshold value YZ, thereby generating a first comparison result, and judging whether to generate a multi-source auxiliary intervention coefficient according to the first comparison result; The second calculation module (6) is used to integrate and calculate the first data set, the second data set and the third data set into a first auxiliary intervention coefficient S1, a second auxiliary intervention coefficient S2 and a third auxiliary intervention coefficient S3 respectively, the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 constitute a multi-source auxiliary intervention coefficient, and according to the first comparison result, integrate and calculate the first auxiliary intervention coefficient, the second auxiliary intervention coefficient and the third auxiliary intervention coefficient with the fifth data set, the sixth data set and the seventh data set, so as to generate a first alarm coefficient AQX1 and a second alarm coefficient AQX2 respectively; The second analysis module (7) is used to compare the first alarm coefficient AQX1 with a preset second threshold value YR, thereby generating a second comparison result, and to compare the second alarm coefficient AQX2 with a preset third threshold value YS, thereby generating a third comparison result, and to determine whether an abnormality occurs in the current power grid according to the second and third comparison results; The alarm module (8) is used to issue an alarm according to the second comparison result and the third comparison result.

2. The power grid inspection and fault warning system based on drone according to claim 1 is characterized by: The first data acquisition module (1) comprises an environment acquisition unit (11) and a body acquisition unit (12); The environment collection unit (11) is arranged on the UAV and is used to collect the surrounding environment data of the UAV during flight, including the ambient temperature, ambient humidity, ambient wind speed and ambient visibility; The body acquisition unit (12) is arranged on the UAV and is used to collect state data of the UAV during flight, including flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity and image transmission rate; The ambient temperature, ambient humidity, ambient wind speed, ambient visibility, flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity and image transmission rate constitute a first multi-source data set; The second data acquisition module (2) comprises an operation data acquisition unit (21), an electrical parameter acquisition unit (22) and a characteristic data acquisition unit (23); The operation data collection unit (21) is arranged on the drone and is used to collect the equipment operation status data of the power grid, including the inclination angle of the tower, the slackness of the conductor and the corrosion area of ​​the equipment surface; The electrical parameter acquisition unit (22) is arranged in the power grid terminal system and is used to collect electrical parameter data of the power grid, including operating current, operating voltage and load power; The characteristic data acquisition unit (23) is arranged in the power grid terminal system and is used to collect characteristic parameter data of the power grid, including operating temperature value, arc duration and insulation resistance value; The second multi-source data set includes the tower inclination angle, conductor slack, equipment surface corrosion area, operating current, operating voltage, load power, operating temperature value, arc duration and insulation resistance value.

3. The power grid inspection and fault warning system based on drone according to claim 2 is characterized by: The data processing module (3) pre-processes and dimensionlessly converts the first multi-source data group and the second multi-source data group, and sorts the processed first multi-source data group and the second multi-source data group to generate a first data set, a second data set, a third data set, a fourth data set, a fifth data set, a sixth data set, and a seventh data set; The first data set includes flight altitude, flight speed, flight tilt angle, and image resolution; The flight altitude is divided into GD1, GD2, GD3, ..., GDn according to the timestamp; The flight speed is divided into SD1, SD2, SD3, ..., SDn according to the timestamp; The flight tilt angles are divided into JD1, JD2, JD3, ..., JDn according to the timestamp; Image resolution is divided into FB1, FB2, FB3, ..., FBn according to timestamp; The second data set includes surface temperature, arc current intensity, signal intensity, and image transmission rate; The surface temperature is divided into BW1, BW2, BW3, ..., BWn according to the timestamp; The arc current intensity is divided into DH1, DH2, DH3, ..., DHn according to the timestamp; The signal strength is divided into XH1, XH2, XH3, ..., XHn according to the timestamp; The image transmission rate is divided into TX1, TX2, TX3, ..., TXn according to the timestamp; The third data set includes ambient temperature, ambient humidity, ambient wind speed, and ambient visibility; The ambient temperature is divided into HW1, HW2, HW3, ..., HWn according to the timestamp; Ambient humidity is divided into HS1, HS2, HS3, ..., HSn according to the timestamp; The ambient wind speed is divided into HF1, HF2, HF3, ..., HFn according to the timestamp; Environmental visibility is divided into HN1, HN2, HN3, ..., HNn according to the timestamp; The fourth data set includes the tower tilt angle, conductor slack, and equipment surface corrosion area; The tower inclination angles are divided into QX1, QX2, QX3, ..., QXn according to the timestamp; The wire slack is divided into SC1, SC2, SC3, ..., SCn according to the timestamp; The equipment surface corrosion area is divided into FS1, FS2, FS3, ..., FSn according to the timestamp; The fifth data set includes operating current, operating voltage, and load power; The working current is divided into GL1, GL2, GL3, ..., GLn according to the timestamp; The working voltage is divided into GY1, GY2, GY3, ..., GYn according to the timestamp; The load power is divided into FZ1, FZ2, FZ3, ..., FZn according to the timestamp; The sixth data set includes operating temperature values, arc duration, and insulation resistance values; The operating temperature values ​​are divided into YW1, YW2, YW3, ..., YWn according to the timestamp; The arc duration is divided into HC1, HC2, HC3, ..., HCn according to the timestamp; The insulation resistance values ​​are divided into DZ1, DZ2, DZ3, ..., DZn according to the time stamp.

4. The power grid inspection and fault warning system based on drone according to claim 3 is characterized by: The data processing module (3) calculates FJX using the following formula: FJX=a1×FXZ+a2×TXZ+a3×HJZ; Where: FXZ is the flight state reference coefficient, TXZ is the communication state reference coefficient, and HJZ is the environment state reference coefficient, which are calculated and obtained through the first data set, the second data set, and the third data set respectively; a1, a2 and a3 are weight values, and the values ​​of a1, a2 and a3 are adjusted and set by the user.

5. The power grid inspection and fault warning system based on drone according to claim 4 is characterized by: The data processing module (3) calculates and obtains the flight state reference coefficient FXZ, the communication state reference coefficient TXZ and the environment state reference coefficient HJZ respectively through the following formulas: Wherein: GDn, SDn, JDn, FBn, BWn, DHn, XHn, TXn, HWn, HSn, HFn and QXn are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the nth timestamp; GD1, SD1, JD1, FB1, BW1, DH1, XH1, TX1, HW1, HS1, HF1 and QX1 are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the first timestamp; PGD, PSD, PJD, PFB, PBW, PDH, PXH, PTX, PHW, PHS, PHF and PQX are the average flight altitude, average flight speed, average flight inclination angle, average image resolution, average surface temperature, average arc current intensity, average signal strength, average image transmission rate, average ambient temperature, average ambient humidity, average ambient wind speed and average ambient visibility respectively.

6. The power grid inspection and fault warning system based on drone according to claim 5 is characterized by: The data processing module (3) calculates and obtains the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 respectively through the following formulas: Wherein: GDn, SDn, JDn, FBn, BWn, DHn, XHn, TXn, HWn, HSn, HFn and QXn are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the nth timestamp; GDn-1, SDn-1, JDn-1, FBn-1, BWn-1, DHn-1, XHn-1, TXn-1, HWn-1, HSn-1, HFn-1 and QXn-1 are respectively the flight altitude, flight speed, flight tilt angle, image resolution, surface temperature, arc current intensity, signal intensity, image transmission rate, ambient temperature, ambient humidity, ambient wind speed and ambient visibility at the n-1th timestamp; b1, b2, b3 and b4 are weight values, and the values ​​of b1, b2, b3 and b4 are adjusted and set by the user.

7. The power grid inspection and fault warning system based on drone according to claim 6 is characterized by: The first comparison result is as follows: When FJX≤YZ, it means that there is no need to generate a multi-source auxiliary intervention coefficient. When FJX>YZ, it means that a multi-source auxiliary intervention coefficient needs to be generated.

8. The power grid inspection and fault warning system based on drone according to claim 7 is characterized by: The first calculation module (4) calculates and obtains the first alarm coefficient AQX1 and the second alarm coefficient AQX2 respectively through the following formulas: Where: S1 is the first auxiliary intervention coefficient, S2 is the second auxiliary intervention coefficient, and S3 is the third auxiliary intervention coefficient; QXn, SCn, FSn, GLn, GYn, FZn, YWn, HCn and DZn are the tower inclination angle, conductor slack, equipment surface corrosion area, working current, working voltage, load power, operating temperature, arc duration and insulation resistance value at the nth timestamp respectively.

9. The power grid inspection and fault warning system based on drone according to claim 8 is characterized by: The second comparison result is as follows: When AQX1≤YR, it means that the current power grid is safe, and when AQX1>YR, it means that the current power grid is unsafe; When AQX2≤YS, it means that the current power grid is safe, and when AQX2>YS, it means that the current power grid is unsafe.

10. A method for power grid inspection and fault warning based on drones, characterized in that: The specific steps are as follows: S1. First, multi-source data of the UAV and the power grid are collected by a first data collection module (1) and a second data collection module (2) respectively to form a first multi-source data group and a second multi-source data group; S2, sorting and preprocessing the first multi-source data set and the second multi-source data set by a data processing module (3), and generating a plurality of data sets after processing; S3, integrating the first data set, the second data set and the third data set into an auxiliary intervention determination coefficient FJX through a first calculation module (4), comparing the auxiliary intervention determination coefficient with a preset first threshold value YZ through a first analysis module (5), thereby generating a first comparison result, and judging whether to generate a multi-source auxiliary intervention coefficient according to the first comparison result; S4, integrating and calculating the first data set, the second data set and the third data set into a first auxiliary intervention coefficient S1, a second auxiliary intervention coefficient S2 and a third auxiliary intervention coefficient S3 respectively through a second calculation module (6), wherein the first auxiliary intervention coefficient S1, the second auxiliary intervention coefficient S2 and the third auxiliary intervention coefficient S3 constitute a multi-source auxiliary intervention coefficient, and integrating and calculating the first auxiliary intervention coefficient, the second auxiliary intervention coefficient and the third auxiliary intervention coefficient with the fifth data set, the sixth data set and the seventh data set according to the first comparison result, thereby generating a first alarm coefficient and a second alarm coefficient respectively; S5. The first alarm coefficient is compared with a preset second threshold value YR through the second analysis module (7) to generate a second comparison result, and the second alarm coefficient is compared with a preset third threshold value YS to generate a third comparison result. Based on the second and third comparison results, it is determined whether the current power grid is abnormal, and an alarm is issued through the alarm module (8) based on the second and third comparison results.

Images