Power Equipment Status Monitoring and Early Warning Method and System Based on Micro-Meteorological Sensing

Abstract

This application proposes a method and system for monitoring and warning the state of power equipment based on micro-meteorological perception. This method uses a binocular camera to form a depth image to identify the external morphology of power equipment, and combines micro-meteorological perception to analyze the fault evolution process of power equipment, so as to warn of situations such as power equipment discharge and external damage, providing technical support for improving the operation safety margin of power equipment in China under weather conditions such as strong wind, high temperature, extreme cold, snow and ice.

Description

Technical Field

[0001] This application belongs to the technical field of power operation and maintenance, and relates to a method and system for monitoring and warning the state of power equipment based on micro-meteorological perception. Background Art

[0002] The power grid has a vast coverage area. Under weather conditions such as strong winds, high temperatures, extreme cold, snow, and ice, various power equipment in transmission lines and substations will be affected by multiple weather factors, resulting in damage and discharge, which affects the stable transmission of electricity. Taking the icing flashover of transmission line insulators as an example, research shows that ice flash is mainly caused by the ice on the insulators. The ice-covered shape, thickness, and ice melting state of the insulators have a great influence on the ice flash of the insulators. Therefore, real-time monitoring of insulator icing is of great research significance and practical significance for warning and preventing ice flash accidents. Similarly, abnormal weather will also cause phenomena such as overheating and large-amplitude vibration of power equipment, and real-time monitoring is of great significance for preventing faults such as equipment discharge and damage caused by overheating, icing, and vibration.

[0003] From the existing equipment research, after icing, overheating, vibration, etc. occur, the current measures often still stay at observing through drones and edge terminal devices and then making manual judgments, or taking remedial measures after accidents occur. There is less research on the accident monitoring and warning of equipment under the influence of micro-meteorology. Taking the icing situation of high-voltage lines as an example, there are few warning means for situations such as icing flashover of insulators, ice shedding and jumping of lines, and line galloping under the influence of micro-meteorology, and there is also a lack of reliable judgment criteria for the icing degree of equipment. Traditional warning analysis methods for power equipment failures rely on manual judgment, and the massive monitoring data has caused low efficiency of manual warning. Real-time micro-meteorological analysis has high reference value for equipment status warning. There is an urgent need to propose a power equipment fault warning device under extreme weather conditions based on real-time micro-meteorological perception and empirical function prediction. Summary of the Invention

[0004] The present invention provides a method and system for monitoring and warning the state of power equipment based on micro-meteorological perception. By forming a depth image with a binocular camera to identify the external morphology of the power equipment, and combining micro-meteorological perception to analyze the fault evolution process of the power equipment, it warns of situations such as power equipment discharge and external damage, providing technical support for improving the operation safety margin of power equipment in China under weather conditions such as strong winds, high temperatures, extreme cold, snow, and ice.

[0005] An embodiment of one aspect of the present invention provides a method for monitoring and warning the state of power equipment based on micro-meteorological perception, including the following steps:

[0006] S1. Real-time obtain the environmental image of the power equipment, and use the trained target recognition algorithm model to extract the target power equipment in the image to obtain the three-dimensional depth image of the target power equipment;

[0007] S2. Calculate the coordinates in the three-dimensional depth image of the extracted target power equipment, integrate the coordinates of the target power equipment, calculate the integral difference between two adjacent moments, and obtain the ice accretion amount of the target power equipment;

[0008] S3. Obtain the micro-meteorological environment data of the target power equipment, and combine the obtained ice accretion amount to judge the current ice accretion type of the target power equipment;

[0009] S4. Obtain the historical fault data and current power data of the target power equipment. According to the fitting curve of the current power data and the historical fault data, predict the potential faults of the target power equipment under the current ice accretion type; send out early warning information according to the probability of the occurrence of the faults.

[0010] In the power equipment status monitoring and early warning method based on micro-meteorological perception provided by this application, the power equipment target in the two-dimensional image is extracted through image recognition, and the three-dimensional model of the power equipment is obtained through calculation of the depth image; through micro-meteorological perception combined with the dynamic deterioration process of the power equipment morphology and the historical fault data of the power equipment, the fault evolution process of the power equipment is deduced, and the time and degree of the occurrence of power equipment fault defects are warned. The method is simple and easy to implement, can effectively quantify and analyze the ice accretion amount, more accurately predict the probability and change trend of the occurrence of faults, take precautions, and effectively improve the intelligent operation and maintenance management level of transmission lines of power grid enterprises in China under extreme weather conditions such as ice accretion.

[0011] Preferably, in S2, calculating the coordinates in the three-dimensional depth image of the extracted target power equipment further includes the following steps: S201. Calibrate the internal parameter matrix and external parameter matrix of the binocular camera before depth image imaging to obtain the internal and external camera parameter matrices; S202. Perform stereo matching on the target power equipment captured by the binocular camera according to the obtained internal and external camera parameter matrices; S203. Obtain the coordinates of the target power equipment in the three-dimensional depth image according to the corresponding relationship between the two-dimensional image coordinates and the three-dimensional image coordinates.

[0012] In this embodiment, a binocular camera is used to obtain the image information of the power equipment. Compared with an ordinary camera that can only obtain a single-angle planar image, the image of the power equipment obtained by the binocular camera is a multi-angle image, which is convenient for synthesizing the three-dimensional depth image, and then the power equipment target in the two-dimensional image is extracted through the image recognition algorithm. The spatial three-dimensional depth data and the three-dimensional depth data of the power equipment are obtained through image stereo matching and data fusion algorithms to support the calculation of the power equipment morphology.

[0013] Preferably, in any of the above embodiments, in S2, the following formula is used to obtain the integral difference of the coordinates in the three-dimensional depth image of the target power equipment at two adjacent moments:

[0014]

[0015] Among them, V1 = f(x1, y1, z1) represents the coordinates of the three-dimensional depth map of the target power equipment at the previous moment; V2 = f(x2, y2, z2) represents the coordinates of the three-dimensional depth map of the target power equipment at the current moment.

[0016] In this embodiment, by obtaining the coordinates of the three-dimensional image and further using the integral difference algorithm to determine the change in the external morphology of the target power equipment, the change process of the external morphology of the target power equipment can be grasped according to the size of the integral difference. Compared with other forms of measurement methods, it can quantitatively analyze the ice coverage more accurately, and there is no need to rely on other measurement tools. The structure is simple and it is widely applicable to various ice coverage types.

[0017] Preferably, in any of the above embodiments, in S3, the micro-meteorological environment data includes temperature value, humidity value, wind speed value, wind direction, tensile value and geographical location.

[0018] Preferably, in S3, the method for judging the ice coverage type of the target power equipment includes the following:

[0019] Obtain the temperature value, humidity value, wind speed value and the calculated ice coverage from the micro-meteorological environment data; judge in turn according to the preset priority whether any of the preset threshold ranges of the ice coverage types is satisfied, and the threshold ranges include temperature range, humidity range, wind speed range and ice coverage range;

[0020] If the temperature value, humidity value, wind speed value and ice coverage all satisfy the threshold range of the same ice coverage type, then it belongs to that type of ice coverage.

[0021] Preferably, in any of the above embodiments, the ice coverage types include any one of the following: glaze, rime, mixed glaze, frost, snow cover.

[0022] In this embodiment, by using the integral difference to quantify the ice coverage and combining the micro-meteorological information collected by a variety of meteorological sensors, it is possible to accurately judge the final ice coverage type formed by the ice coverage of the power equipment and the change trend of the ice coverage type. According to the grasped change trend, the occurrence of faults can be prevented in time.

[0023] Preferably, in any of the above embodiments, in S4, predicting potential faults of the target power equipment under the current icing type includes the following method: extracting the discharge voltage and discharge time during the fault from the historical fault data, and drawing the historical experience curves of the discharge voltage time for different icing types; performing curve fitting based on the power data of the current target power equipment, combining the icing type to which the current target power equipment belongs and the current meteorological environment data, and judging the fitting degree between the fitting curve of the current target power equipment and the historical experience curve under the same icing type; judging whether the fitting degree meets the preset threshold, and if it meets the preset threshold, predicting the potential fault of the current target power equipment according to the fault of the historical experience curve.

[0024] Further, in S4, calculate the likelihood of a fault occurring according to the following method: obtain the icing flashover discharge time of the target power equipment according to the historical experience curves of the discharge voltage time for different icing types, and judge the severity of the discharge according to the magnitude of the discharge voltage corresponding to the discharge time. The severity of the discharge is linearly corresponding to the likelihood of a fault occurring, and the likelihood of a fault occurring is obtained.

[0025] In this embodiment, micro-meteorological information is collected by a variety of meteorological sensors, combined with the dynamic deterioration process of the power equipment morphology, and the fault evolution process of the power equipment is deduced based on the historical fault data of the power equipment, warning the time and degree of the occurrence of power equipment fault defects, enabling early detection or prevention of equipment faults, taking precautions before they occur, and avoiding major power accidents.

[0026] The present invention also provides a power equipment status monitoring and warning system based on micro-meteorological perception, including an equipment image calculation module, a micro-meteorological monitoring module, and an abnormal fault warning module; the equipment image calculation module includes a binocular camera unit and an image calculation unit, and the binocular camera unit is used to obtain the power equipment environment image in real time by using binocular cameras;

[0027] The image calculation unit is used to automatically extract the target power equipment in the image by using the built-in target recognition algorithm model to obtain the three-dimensional depth image of the target power equipment; and extract the coordinates of the target power equipment in the three-dimensional depth image, integrate the coordinates of the target power equipment, calculate the integral difference between two adjacent moments, and obtain the ice accretion amount of the target power equipment;

[0028] The micro-meteorological monitoring module is used to obtain the micro-meteorological environment data of the location where the target power equipment is located;

[0029] The abnormal fault warning module includes an abnormal analysis unit and a fault warning unit; the abnormal analysis unit is used to judge the current icing type of the target power equipment according to the micro-meteorological environment data of the target power equipment and the obtained ice accretion amount;

[0030] The fault warning unit is used to obtain the historical fault data and current power data of the target power equipment, predict the potential faults of the target power equipment under the current icing type according to the fitting curve of the current power data and the historical fault data, and send out warning information according to the probability of the occurrence of the faults.

[0031] In the power equipment status monitoring and warning system based on micro-meteorological perception provided by the present application, the device image calculation module extracts the power equipment target in the two-dimensional image through image recognition, and obtains the three-dimensional model of the power equipment through depth image calculation; through the micro-meteorological monitoring module, the micro-meteorological perception is combined with the dynamic deterioration process of the power equipment morphology and the historical fault data of the power equipment to deduce the fault evolution process of the power equipment, and the abnormal fault warning module warns the time and degree of the occurrence of the power equipment fault defects. The structure is simple and the implementation is convenient, which can effectively quantify the ice accretion amount, more accurately grasp the change trend of the faults, and effectively improve the intelligent operation and maintenance management level of the transmission lines of the power grid enterprises in China under extreme weather conditions such as icing.

[0032] Preferably, it further includes a background warning operation module, which is used to receive the warning information and issue an audible and visual warning according to the received warning information.

[0033] Preferably, in any of the above embodiments, the micro-meteorological monitoring module includes a temperature sensor for obtaining the temperature value, a humidity sensor for obtaining the humidity value, a wind speed sensor for obtaining the wind speed value, a wind direction sensor for obtaining the wind direction, a tension sensor for obtaining the tension value; and it further includes a locator for obtaining the geographical location.

[0034] In this embodiment, the ice accretion amount is quantified by using the integral difference, and combined with the micro-meteorological information collected by a variety of meteorological sensors, it can accurately judge the final ice accretion type formed by the ice accretion amount of the power equipment and the change trend of the ice accretion type. According to the mastered change trend, the occurrence of faults can be prevented in time. Brief Description of the Drawings

[0035] The specification drawings forming a part of the present application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0036] Figure 1 It is a flowchart of a method for monitoring and warning the status of power equipment based on micro-meteorological perception provided by an embodiment of the present application;

[0037] Figure 2 It is a structural block diagram of a power equipment status monitoring and warning system based on micro-meteorological perception provided by an embodiment of the present application;

[0038] Figure 3 Schematic diagram of a power equipment status monitoring and early warning system based on micro-meteorological perception provided by another embodiment of the present application.

[0039] Figure 4 Schematic diagram of the icing type judgment process of a power equipment status monitoring and early warning method based on micro-meteorological perception provided by another embodiment of the present application.

[0040] Figure 5 Schematic diagram of the curve of the discharge voltage time of different icing types of a power equipment status monitoring and early warning method based on micro-meteorological perception provided by another embodiment of the present application. Detailed implementation manners

[0041] The present invention will be described in detail below with reference to the drawings and in conjunction with embodiments. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0042] The following detailed descriptions are all exemplary descriptions, aiming to provide further detailed descriptions of the present invention. Unless otherwise specified, all technical terms adopted by the present invention have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs. The terms used in the present invention are only for describing specific implementation manners and are not intended to limit the exemplary embodiments according to the present invention.

[0043] As Figure 1 shown, an embodiment of one aspect of the present invention provides a power equipment status monitoring and early warning method based on micro-meteorological perception, including the following steps:

[0044] S1. Obtain the power equipment environment image in real time, and use the trained target recognition algorithm model to extract the target power equipment in the image to obtain the three-dimensional depth image of the target power equipment;

[0045] S2. Calculate the coordinates in the three-dimensional depth image of the extracted target power equipment, integrate the coordinates of the target power equipment, calculate the integral difference between two adjacent moments, and obtain the ice accretion amount of the target power equipment;

[0046] S3. Obtain the micro-meteorological environment data of the target power equipment, and combine the obtained ice accretion amount to judge the current icing type of the target power equipment;

[0047] S4. Obtain the historical fault data and current power data of the target power equipment, predict the potential faults of the target power equipment under the current icing type according to the fitting curve of the current power data and the historical fault data; issue a warning message according to the probability of the occurrence of the fault.

[0048] In the power equipment status monitoring and early warning method based on micro-meteorological perception provided by this application, the power equipment target in the two-dimensional image is extracted through image recognition, and the three-dimensional model of the power equipment is obtained through the calculation of the depth image; by combining micro-meteorological perception with the dynamic deterioration process of the power equipment morphology and the historical fault data of the power equipment, the fault evolution process of the power equipment is deduced, and the time and fault degree of the occurrence of power equipment fault defects are warned. The method is simple and easy to implement, can effectively quantify the ice accretion amount, more accurately predict the possibility and change trend of the occurrence of faults, prevent problems before they happen, and effectively improve the intelligent operation and maintenance management level of transmission lines of power grid enterprises in China under extreme weather conditions such as icing.

[0049] Preferably, in S2, calculating the coordinates in the three-dimensional depth image of the extracted target power equipment further includes the following steps: S201, calibrating the internal parameter matrix and external parameter matrix of the binocular camera before depth image imaging to obtain the internal and external camera parameter matrices; S202, performing stereo matching on the target power equipment photographed by the binocular camera according to the obtained internal and external camera parameter matrices; S203, obtaining the coordinates of the target power equipment in the three-dimensional depth image according to the correspondence between the two-dimensional image coordinates and the three-dimensional image coordinates.

[0050] In this embodiment, a binocular camera is used to obtain the image information of the power equipment. Compared with an ordinary camera that can only obtain a single-angle planar image, the image of the power equipment obtained by the binocular camera is a multi-angle image, which is convenient for synthesizing the three-dimensional depth image, and then the power equipment target in the two-dimensional image is extracted through an image recognition algorithm. Through image stereo matching and data fusion algorithms, spatial three-dimensional depth data and power equipment three-dimensional depth data are obtained to support the calculation of the power equipment morphology.

[0051] Preferably, in any of the above embodiments, in S2, the following formula is used to obtain the integral difference between the coordinates in the three-dimensional depth images of the target power equipment at the current moment and the previous moment:

[0052]

[0053] Among them, V1 = f(x1, y1, z1) represents the coordinates of the three-dimensional depth map of the target power equipment at the previous moment; V2 = f(x2, y2, z2) represents the coordinates of the three-dimensional depth map of the target power equipment at the current moment.

[0054] In this embodiment, by obtaining the coordinates of the three-dimensional image and further using the integral difference algorithm to determine the change magnitude of the external morphology of the target power equipment, and grasping the change process of the external morphology of the target power equipment according to the magnitude of the integral difference. Compared with other forms of measurement methods, it can more accurately quantitatively analyze the ice accretion amount, and does not require other measurement tools, has a simple structure, and is generally applicable to various ice accretion types.

[0055] In S3, the micro-meteorological environment data includes temperature value, humidity value, wind speed value, wind direction, tensile force value and geographical location. The icing types include any one of the following: glaze, rime, mixed glaze, frost, snow accumulation.

[0056] As Figure 4 shown, further, the method for judging the icing type of the target power equipment includes the following:

[0057] Obtain the icing amount calculated by combining the temperature value, humidity value, and wind speed value from the micro-meteorological environment data; sequentially judge whether it meets the preset threshold range of any icing type according to the preset priority, and the threshold range includes temperature range, humidity range, wind speed range and icing amount range;

[0058] If the temperature value, humidity value, wind speed value and icing amount all meet the threshold range of the same icing type, it belongs to this type of icing.

[0059] First, according to existing research, set the ranges of temperature, humidity, and wind speed in the micro-meteorological conditions corresponding to glaze, rime, mixed glaze, and frost. Use t, h, and s to represent the values of temperature, humidity, and wind speed respectively. The numerical ranges of the micro-meteorological conditions corresponding to different icing types are shown in Table 1 below:

[0060] Ice accretion type Temperature Humidity Wind speed Rime <![CDATA[t1<t<t2]]> <![CDATA[h1 < h < h2]]> <![CDATA[s1<s<s2]]> Mixed rime <![CDATA[t3 < t < t4]]> <![CDATA[h3<h<h4]]> <![CDATA[s3 < s < s4]]> Glaze <![CDATA[t5 < t < t6]]> <![CDATA[h5 < h < h6]]> <![CDATA[s5 < s < s6 <!-- 5 -->]]> Frost <![CDATA[t7 < t < t8]]> <![CDATA[h7 < h < h8]]> <![CDATA[s7 < s < s8]]>

[0061] Table 1. Icing Type Judgment Table

[0062] When the actually measured micro-meteorological condition values t0, h0, s0 all match a certain icing type, it is easy to obtain the icing type. When t0, h0, s0 respectively match the index ranges corresponding to different icing types, the icing type is judged according to the priority level of humidity > temperature > wind speed. The process of judging the icing type is as Figure 4 shown.

[0063] In this embodiment, by using the integral difference to quantify the icing amount and combining the micro-meteorological information collected by multiple meteorological sensors, it is possible to accurately judge the icing amount, the final formed icing type and the change trend of the icing type of the power equipment. According to the mastered change trend, the occurrence of faults can be prevented in time.

[0064] As Figure 5 shown, preferably in any of the above embodiments, in S4, predicting the potential faults of the target power equipment under the current icing type includes the following method:

[0065] S401. Extract the discharge voltage and discharge time during the fault from the historical fault data, and draw the historical experience curve of the discharge voltage time of different icing types;

[0066] S402. Perform curve fitting based on the power data of the current target power equipment, and combine the icing type to which the current target power equipment belongs and the current meteorological environment data to determine the fitting degree between the fitting curve of the current target power equipment and the historical experience curve under the same icing type;

[0067] S403. Determine whether the fitting degree meets a preset threshold. If it meets the preset threshold, predict the potential faults of the current target power equipment based on the faults of the historical experience curve.

[0068] It also includes that in S405, calculate the probability of the occurrence of a fault according to the following method: obtain the icing flashover discharge time of the target power equipment based on the historical experience curve of the discharge voltage time of different icing types, and judge the severity of the discharge according to the magnitude of the discharge voltage corresponding to the discharge time. The severity of the discharge is linearly corresponding to the probability of the occurrence of a fault, and the probability of the occurrence of a fault is obtained.

[0069] In this embodiment, micro-meteorological information is collected through a variety of meteorological sensors, combined with the dynamic deterioration process of the power equipment morphology, and the fault evolution process of the power equipment is deduced based on the historical fault data of the power equipment, so as to warn the time and degree of the occurrence of power equipment fault defects, be able to detect or prevent equipment faults early, take precautions before they happen, and avoid causing large power accidents.

[0070] It should be noted that the meteorological state monitoring sensors include one or several of the following sensors: temperature sensor, humidity sensor, and wind speed sensor. The abnormal operating conditions include any one of the following icing types: glaze, rime, mixed glaze, frost, and snow accumulation.

[0071] As Figure 3 shown, the following will be described with specific embodiments. In the figure, 1 is the insulator to be monitored, 2 is the binocular and micro-meteorological perception and warning device, and 3 is the background power grid warning center.

[0072] Taking the icing monitoring and warning of 220 kV line insulators as an example, the technical solution of the present invention realizes the above object through the following steps:

[0073] First, use a binocular camera to aim at the position of the insulator in the transmission line, as Figure 3 shown, record the image data of the insulator, and store the image data in the storage medium;

[0074] Then, use the trained target recognition algorithm model to extract the image of the insulator from the image data, and then obtain the coordinates (x, y, z) in the three-dimensional depth image of the insulator.

[0075] It should be noted that the insulators captured by the binocular camera need to be pre-annotated in advance to train the target recognition algorithm model to achieve the automatic extraction of insulator targets in the captured images. The algorithm is deployed in the monitoring device, and the target recognition model is calculated through the processor and the graphics computing card.

[0076] Before the depth image is formed, the internal parameter matrix and external parameter matrix of the binocular camera are first calibrated. After obtaining the internal and external camera parameter matrices, stereo matching is performed on the insulator images captured by the binocular camera to form the corresponding relationship between the two-dimensional image coordinates and the three-dimensional image coordinates. Furthermore, the coordinates (x, y, z) in the three-dimensional depth image of the insulator are obtained. The coordinate representations of the three-dimensional depth maps of the insulator before and after icing are as follows:

[0077] V1 = f(x1, y1, z1) (Formula 1)

[0078] V2 = f(x2, y2, z2) (Formula 2)

[0079] The difference in the three-dimensional integral of the outer surface of the insulator before and after icing obtained by the above formula is the ice accretion amount.

[0080]

[0081] Then, the data of the temperature, humidity, and wind speed micro-meteorological sensors are dynamically recorded to analyze the types of ice accretion on the insulators (such as glaze ice, rime ice, mixed glaze ice, frost, etc.). Based on the dynamic data of the micro-meteorological sensors and the light information recorded by the camera, combined with the melting laws of different types of ice accretion, the dynamic melting process of the ice accretion on the insulators is judged.

[0082] Regarding the judgment of glaze ice according to the ice accretion formation process, if the precipitation type is rain and the temperature is between 0 and -6 degrees, the wind speed is 0 - 20 m / s, and the ice accretion amount ratio is 0.8 - 0.92, then it is considered that the formed ice accretion type is glaze ice. Since glaze ice is formed by freezing rain or sleet weather, with a smooth freezing layer, cold wind accelerating freezing, and strong adhesion force, when there is no wind or irregular wind, a uniform ice accretion around the insulator disc is formed, usually forming hanging icicles.

[0083] Regarding rime ice, if the precipitation type is fog, it can be further classified into soft rime ice and hard rime ice according to the thinness of the fog; if it is light fog and the temperature is between -5 and -25 degrees, the wind speed is 0 - 5 m / s, and the ice accretion amount ratio is 0.1 - 0.6, then it is considered that the formed ice accretion type is soft rime ice. If it is thick fog and the temperature is between -3 and -8 degrees, the wind speed is 5 - 10 m / s, and the ice accretion amount ratio is 0.5 - 0.8.

[0084] Since rime ice is a precipitate formed by supercooled clouds and extremely small water particles, soft rime ice is fluffy, white crystalline particles, often occurring in the western winter and will fill and wrap the entire insulator string. Hard rime ice is formed by the freezing and accumulation of small water particles and has a relatively large adhesion force.

[0085] Secondly, according to the predicted dynamic melting process of ice-covered insulators and combined with the empirical data of ice-covered insulator flashover, predict the flashover discharge time and discharge severity of ice-covered insulators, and issue a warning according to the prediction results.

[0086] Finally, according to the flashover discharge warning situation, form text record data and send it to the warning center of the power grid company through the communication unit of the monitoring device. During the ice melting process of different ice-covered types, the flashover discharge voltage will change over time, and its empirical data is shown in the discharge curve in the following figure. The horizontal axis is time and the vertical axis is the discharge voltage. The discharge voltage-time curves corresponding to different ice-covered types are different. At the same time, the steepness of the discharge voltage curve in the following figure changes with factors such as ice-covered amount, ambient temperature, and wind speed. According to the environmental conditions recorded by the micro-meteorology, as well as the ice-covered type and ice-covered amount, by referring to the corresponding discharge voltage-time empirical curve, the flashover discharge time of the ice-covered insulator can be inferred, and the discharge severity can be judged based on the magnitude of the discharge voltage, realizing fault prediction and warning.

[0087] As Figure 2 shown, the present invention also provides a power equipment status monitoring and warning system based on micro-meteorology perception for implementing the above method, including an equipment image calculation module, a micro-meteorology monitoring module, an abnormal fault warning module, and a background warning operation module; it should be noted that in this application, the equipment image calculation module, the micro-meteorology monitoring module, and the abnormal fault warning module are integrated at one end of the target power equipment. The background warning operation module is set in the background control center; the abnormal fault warning module and the background warning operation module communicate with each other in a wired or wireless form to send alarm information.

[0088] Including an equipment image calculation module, a micro-meteorology monitoring module, and an abnormal fault warning module; the equipment image calculation module includes a binocular camera unit and an image calculation unit, and the binocular camera unit is used to obtain the environmental image of the power equipment in real time by using a binocular camera;

[0089] The image calculation unit is used to automatically extract the target power equipment in the image by using the built-in target recognition algorithm model to obtain the three-dimensional depth image of the target power equipment; and extract the coordinates of the target power equipment in the three-dimensional depth image, integrate the coordinates of the target power equipment, calculate the integral difference between two adjacent moments, and obtain the ice-covered amount of the target power equipment;

[0090] The micro-meteorology monitoring module is used to obtain the micro-meteorology environment data where the target power equipment is located;

[0091] The abnormal fault warning module includes an abnormal analysis unit and a fault warning unit; the abnormal analysis unit is used to judge the current icing type of the target power equipment according to the micro-meteorological environment data of the target power equipment and the obtained icing amount.

[0092] The fault warning unit is used to obtain the historical fault data and current power data of the target power equipment, predict the potential faults of the target power equipment under the current icing type according to the fitting curve of the current power data and the historical fault data, and send out a warning message according to the probability of the occurrence of the fault.

[0093] In the power equipment status monitoring and warning system based on micro-meteorological perception provided by the present application, the equipment image calculation module extracts the power equipment target in the two-dimensional image through image recognition, and obtains the three-dimensional model of the power equipment through depth image calculation; through the micro-meteorological monitoring module, the micro-meteorological perception is combined with the dynamic deterioration process of the power equipment morphology and the historical fault data of the power equipment to deduce the fault evolution process of the power equipment, and the abnormal fault warning module warns the time and degree of the occurrence of the power equipment fault defect. The structure is simple and the implementation is convenient, which can effectively quantify and analyze the icing amount, more accurately grasp the change trend of the fault, and effectively improve the intelligent operation and maintenance management level of the transmission lines of power grid enterprises in China under extreme weather conditions such as icing.

[0094] It further includes a background warning operation module, which is used to receive the warning information and issue an audible and visual warning according to the received warning information.

[0095] Preferably, in any of the above embodiments, the micro-meteorological monitoring module includes a temperature sensor for obtaining the temperature value, a humidity sensor for obtaining the humidity value, a wind speed sensor for obtaining the wind speed value, a wind direction sensor for obtaining the wind direction, a tension sensor for obtaining the tension value; and further includes a locator for obtaining the geographical location.

[0096] In the power equipment status monitoring and warning system based on micro-meteorological perception provided by the present application, the equipment image calculation module extracts the power equipment target in the two-dimensional image through image recognition, and obtains the three-dimensional model of the power equipment through depth image calculation; through the micro-meteorological monitoring module, the micro-meteorological perception is combined with the dynamic deterioration process of the power equipment morphology and the historical fault data of the power equipment to deduce the fault evolution process of the power equipment, and the abnormal fault warning module warns the time and degree of the occurrence of the power equipment fault defect. The structure is simple and the implementation is convenient, which can effectively quantify and analyze the icing amount, more accurately grasp the change trend of the fault, and effectively improve the intelligent operation and maintenance management level of the transmission lines of power grid enterprises in China under extreme weather conditions such as icing.

[0097] Preferably, when calculating the integral difference of the coordinates in the three-dimensional depth images of the target power equipment at the current moment and the previous moment, the image calculation unit adopts the following formula:

[0098]

[0099] wherein, V1 = f(x1, y1, z1) represents the coordinates of the three-dimensional depth map of the target power equipment at the previous moment; V2 = f(x2, y2, z2) represents the coordinates of the three-dimensional depth map of the target power equipment at the current moment.

[0100] It should be noted that before the depth image is formed, the internal parameter matrix and the external parameter matrix of the binocular camera are calibrated to obtain the internal and external camera parameter matrices; according to the obtained internal and external camera parameter matrices, stereo matching is performed on the target power equipment photographed by the binocular camera; according to the corresponding relationship between the two-dimensional image coordinates and the three-dimensional image coordinates, the coordinates of the target power equipment in the three-dimensional depth image are obtained.

[0101] Based on the obtained historical fault data of the power equipment and the predicted dynamic melting process of the ice covering on the target power equipment, the icing flashover empirical data of the target power equipment under different icing types are analyzed and obtained; according to the abnormal operation data of the current target power equipment, combined with the icing flashover empirical data, the icing flashover discharge time and the severity of the discharge of the insulator are predicted, and the possibility of a fault occurring is predicted according to the prediction result.

[0102] In this embodiment, by using the integral difference to quantify the ice covering amount and combining the micro-meteorological information collected by a variety of meteorological sensors, it is possible to accurately judge the final formed icing type of the ice covering amount of the power equipment and the change trend of the icing type. According to the mastered change trend, the occurrence of a fault can be prevented in a timely manner.

[0103] The temperature sensing unit, the humidity sensing unit and the wind speed sensing unit are used to record the micro-meteorological conditions where the power equipment is located, and the abnormal operation conditions of the power equipment under specific meteorological conditions are recorded in real time, such as the vibration, heat expansion, ice covering, etc. of the power equipment under strong wind, high temperature, wind and snow. Combining the historical fault data of the power equipment, the potential faults of the power equipment under abnormal micro-meteorological conditions are analyzed, and the possibility of the development and evolution of the equipment fault is deduced. And early warnings are given for the faults with a relatively high occurrence possibility in combination with the micro-meteorological conditions. After receiving the information from the fault warning unit, the background warning unit gives an audible and visual warning in the background control center. The equipment operation unit sends an operation signal to the corresponding power equipment to control the work of devices such as relay protection and defect elimination devices; by introducing artificial intelligence technologies such as three-dimensional imaging and image recognition of binocular cameras, combined with micro-meteorological perception and historical fault data analysis, an intelligent, highly sensitive and real-time power equipment status monitoring and early warning device under harsh meteorological conditions based on depth images and micro-meteorological perception is proposed to support the research on the safety control technology of power equipment.

[0104] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0105] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0106] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that realize the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, thereby providing steps for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks by the instructions executed on the computer or other programmable devices.

[0108] As is known by common technical knowledge, the present invention can be implemented by other embodiments that do not depart from its spiritual essence or necessary features. Therefore, the above-disclosed embodiments are illustrative in all aspects and not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are encompassed by the present invention.

Claims

1. A method for monitoring and warning the state of power equipment based on micro-meteorological perception, characterized in that It includes the following steps: S1. Obtain the environmental image of the power equipment in real time, and use the trained target recognition algorithm model to extract the target power equipment in the image to obtain the three-dimensional depth image of the target power equipment; S2. Calculate the coordinates in the three-dimensional depth image of the extracted target power equipment, integrate the coordinates of the target power equipment, calculate the integral difference between two adjacent moments, and obtain the ice accretion amount of the target power equipment; S3. Obtain the micro-meteorological environment data of the target power equipment, and combine the obtained ice accretion amount to judge the current ice accretion type of the target power equipment; S4. Obtain the historical fault data and current power data of the target power equipment, and predict the potential faults of the target power equipment under the current ice accretion type according to the fitting curve of the current power data and the historical fault data; issue a warning message according to the likelihood of the occurrence of the fault; In S2, the following steps are used to calculate the coordinates in the three-dimensional depth image of the extracted target power equipment: S201. Calibrate the internal parameter matrix and external parameter matrix of the binocular camera before depth image imaging to obtain the internal and external camera parameter matrices; S202. Perform stereo matching on the target power equipment photographed by the binocular camera according to the obtained internal and external camera parameter matrices; S203. Obtain the coordinates of the target power equipment in the three-dimensional depth image according to the correspondence between the two-dimensional image coordinates and the three-dimensional image coordinates; The micro-meteorological environment data includes temperature value, humidity value, wind speed value, wind direction, tensile value and geographical location; In S3, to judge the ice accretion type of the target power equipment, the following method is included: Obtain the temperature value, humidity value, wind speed value and the calculated ice accretion amount from the micro-meteorological environment data; sequentially judge whether any of them meets the preset threshold range of any ice accretion type according to the preset priority, and the threshold range includes temperature range, humidity range, wind speed range and ice accretion amount range; If the temperature value, humidity value, wind speed value and ice accretion amount all meet the threshold range of the same ice accretion type, it belongs to this type of ice accretion; In S2, the following formula is used to obtain the integral difference of the coordinates in the three-dimensional depth image of the target power equipment at two adjacent moments: wherein, V1 = f(x1, y1, z1) represents the coordinates of the three-dimensional depth map of the target power equipment at the previous moment; V2 = f(x2, y2, z2) represents the coordinates of the three-dimensional depth map of the target power equipment at the current moment; In S4, to predict the potential faults of the target power equipment under the current ice accretion type, the following method is included: Extract the discharge voltage and discharge time during the fault from the historical fault data, and draw the historical experience curves of the discharge voltage time of different ice accretion types; Perform curve fitting according to the power data of the current target power equipment, and combine the ice accretion type to which the current target power equipment belongs and the current meteorological environment data to judge the fitting degree of the fitting curve of the current target power equipment and the historical experience curve under the same ice accretion type; Judge whether the fitting degree meets the preset threshold. If it meets the preset threshold, predict the potential faults of the current target power equipment according to the faults of the historical experience curve; In S4, the likelihood of the occurrence of the fault is calculated according to the following method: Based on the historical experience curve of the discharge voltage time for different ice-covering types, obtain the ice-covered flashover discharge time of the target power equipment, and determine the severity of the discharge according to the magnitude of the discharge voltage corresponding to this discharge time. The severity of the discharge is linearly corresponding to the possibility of a fault occurring, and thus obtain the magnitude of the possibility of a fault occurring.

2. A power equipment status monitoring and early warning system based on micro-meteorological perception, characterized in that, Including an equipment image calculation module, a micro-meteorological monitoring module, and an abnormal fault warning module; The equipment image calculation module includes a binocular camera unit and an image calculation unit. The binocular camera unit is used to obtain the environmental image of the power equipment in real time using a binocular camera; The image calculation unit is used to automatically extract the target power equipment in the image using the built-in target recognition algorithm model to obtain the three-dimensional depth image of the target power equipment; And extract the coordinates of the target power equipment in the three-dimensional depth image, integrate the coordinates of the target power equipment, calculate the integral difference between two adjacent moments, and obtain the ice-covering amount of the target power equipment; The following formula is used to calculate the integral difference of the coordinates in the three-dimensional depth image of the target power equipment at two adjacent moments: Wherein, V1 = f(x1, y1, z1) represents the coordinates of the three-dimensional depth map of the target power equipment at the previous moment; V2 = f(x2, y2, z2) represents the coordinates of the three-dimensional depth map of the target power equipment at the current moment; Used to calculate the coordinates in the three-dimensional depth image of the extracted target power equipment by the following steps: S201. Calibrate the internal parameter matrix and the external parameter matrix of the binocular camera before the depth image is formed to obtain the internal and external camera parameter matrices; S202. Perform stereo matching on the target power equipment photographed by the binocular camera according to the obtained internal and external camera parameter matrices; S203. Obtain the coordinates of the target power equipment in the three-dimensional depth image according to the corresponding relationship between the two-dimensional image coordinates and the three-dimensional image coordinates; The micro-meteorological monitoring module is used to obtain the micro-meteorological environment data where the target power equipment is located; The abnormal fault warning module includes an abnormal analysis unit and a fault warning unit; The abnormal analysis unit is used to judge the current ice-covering type of the target power equipment according to the micro-meteorological environment data of the target power equipment and the obtained ice-covering amount; The following method is used to judge the ice-covering type of the target power equipment: Obtain the temperature value, humidity value, wind speed value from the micro-meteorological environment data combined with the calculated ice-covering amount; Judging in turn according to the preset priority whether it meets the preset threshold range of any ice-covering type, and the threshold range includes a temperature range, a humidity range, a wind speed range, and an ice-covering amount range; If the temperature value, humidity value, wind speed value, and ice-covering amount all meet the threshold range of the same ice-covering type, it belongs to this type of ice-covering; The fault warning unit is used to obtain the historical fault data and the current power data of the target power equipment, and predict the potential fault of the target power equipment under the current ice-covering type according to the fitting curve of the current power data and the historical fault data; Send a warning message according to the magnitude of the possibility of a fault occurring; Among them, predicting the potential fault of the target power equipment under the current ice-covering type includes the following methods: Extract the discharge voltage and discharge time during the fault from the historical fault data, and draw the historical experience curve of the discharge voltage time for different icing types; Perform curve fitting based on the power data of the current target power equipment, and combine the icing type to which the current target power equipment belongs and the current meteorological environment data to judge the fitting degree of the fitting curve of the current target power equipment and the historical experience curve under the same icing type; Judge whether the fitting degree meets the preset threshold. If it meets the preset threshold, predict the potential fault of the current target power equipment according to the fault of the historical experience curve; Calculate the probability of the occurrence of the fault according to the following method: According to the historical experience curve of the discharge voltage time of different icing types, obtain the icing flashover discharge time of the target power equipment, and judge the severity of the discharge according to the magnitude of the discharge voltage corresponding to the discharge time. The severity of the discharge is linearly corresponding to the probability of the occurrence of the fault, and the probability of the occurrence of the fault is obtained; The micro-meteorological monitoring module includes any one or more of the following sensors: A temperature sensor for obtaining temperature values, a humidity sensor for obtaining humidity values, a wind speed sensor for obtaining wind speed values, a wind direction sensor for obtaining wind direction, a tensile force sensor for obtaining tensile force values; it also includes a locator for obtaining geographical locations; It also includes a background warning operation module, which is used to receive warning information and issue an audible and visual warning according to the received warning information.

Images