Method and system for performing unmanned aerial vehicle (UAV) ultraviolet detection on abnormal discharge of power equipment

Abstract

The invention discloses an unmanned aerial vehicle (UAV) ultraviolet detection method and system for abnormal discharge of power equipment, and relates to the technical field of operation and maintenance of the power equipment, and the method comprises the steps that a UAV platform collects an ultraviolet sensing signal, a terahertz point cloud, an infrared sensing signal and a visible light image of a power equipment area, and uploads the ultraviolet sensing signal, the terahertz point cloud, the infrared sensing signal and the visible light image to a cloud service platform; the cloud service platform comprehensively processes and analyzes the received ultraviolet sensing signal, the terahertz point cloud, the infrared sensing signal and the visible light image to obtain the local maximum field intensity, the defect expansion rate and the environmental deterioration factor, and adjusts the parameters of the discharge prediction model based on the accuracy of the previous N discharge prediction results. And processing the local maximum field intensity, the defect expansion rate and the environmental deterioration factor by using the adjusted discharge prediction model to generate a discharge prediction result. The method effectively improves the stability and accuracy of discharge prediction, remarkably reduces the misjudgment risk, and guarantees the safe operation of a power grid.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power equipment operation and maintenance, and particularly relates to a method and system for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment. BACKGROUND

[0002] With the accelerated construction of smart grids and the continuous expansion of the scale of new energy grid connection, the operating environment of power equipment is becoming increasingly complex, and insulation aging and equipment failure caused by partial discharge have become one of the main risks threatening the safety of power grids. The traditional manual inspection method is inefficient in complex terrains such as mountains and across rivers, and there is a risk of high-altitude operation, which cannot meet the demand of intelligent operation and maintenance of power grids.

[0003] At present, the unmanned aerial vehicle inspection technology has become an important means of power equipment state monitoring due to its efficiency, flexibility and non-contact detection advantages. However, the existing unmanned aerial vehicle inspection technology relies on a single ultraviolet or infrared sensor. For example, ultraviolet detection is easily affected by sunlight, and infrared imaging cannot penetrate insulating materials, resulting in a high rate of missed detection of hidden defects. Therefore, the existing unmanned aerial vehicle inspection technology cannot fully capture the multi-dimensional characteristics of discharge signals, and lacks a dynamic compensation mechanism for environmental interference, resulting in large fluctuations in discharge prediction accuracy. SUMMARY

[0004] In view of the problem in the prior art that the unmanned aerial vehicle inspection technology cannot fully capture the multi-dimensional characteristics of discharge signals, and lacks a dynamic compensation mechanism for environmental interference, resulting in large fluctuations in discharge prediction accuracy, the present application provides a method and system for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment, which can effectively improve the discharge prediction accuracy, significantly reduce the risk of misjudgment, and ensure the safe operation of power grids. The specific technical solutions are as follows: In a first aspect, the present application provides a method for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment, applied to a system for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment comprising a unmanned aerial vehicle platform and a cloud service platform, the unmanned aerial vehicle platform integrated with an edge computing module, an ultraviolet sensor, a terahertz radar, an infrared thermal imager and a bionic compound eye visual camera array; the method comprising: The unmanned aerial vehicle platform collects ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images of the power equipment area, and uploads them to the cloud service platform; The cloud service platform comprehensively processes and analyzes the received ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images to obtain the local maximum field strength, defect expansion rate and environmental deterioration factor; The cloud service platform adjusts discharge prediction model parameters based on the accuracy of previous N discharge prediction results, and uses the adjusted discharge prediction model to process the local maximum field strength, defect expansion rate, and environmental deterioration factor to generate a discharge prediction result; wherein N is a positive integer.

[0005] Preferably, the step of obtaining the defect expansion rate by the cloud service platform comprises: The cloud service platform determines the time characteristic information of the power equipment according to the ultraviolet sensing signal, the terahertz point cloud, and the infrared sensing signal, generates discharge time evolution trend information using the time characteristic information, historical discharge records of the power equipment, the ultraviolet sensing signal, the power equipment attributes, and the electrical topology relationship, and determines the defect expansion rate based on the discharge time evolution trend information.

[0006] Preferably, the step of obtaining the environmental deterioration factor by the cloud service platform comprises: A first salt concentration is determined according to the terahertz point cloud, a second salt concentration is obtained by predicting the image of the power equipment region in the visible light image, and a target salt concentration is determined based on the first salt concentration and the second salt concentration. A contaminated area is segmented using a visible light image, a first contamination level is determined based on the contaminated area, a second contamination level is obtained by processing the ultraviolet sensing signal based on the spatial correlation characteristics of the discharge hot spot and the contamination, a third contamination level is determined using a local temperature rise model caused by contamination and the infrared sensing signal, a fourth contamination level is determined using historical contamination records, and a target contamination level is determined based on the first contamination level, the second contamination level, the third contamination level, and the fourth contamination level. A humidity level is determined based on the humidity information of the power equipment, and the weight of the target salt concentration is adjusted based on the humidity information of the power equipment and the type of the power equipment; and / or, the weight of the humidity level is adjusted based on the type of the power equipment. The environmental deterioration factor is obtained according to the target salt concentration and the weight, the target contamination level, the humidity level, and the weight.

[0007] Preferably, the step of obtaining the local maximum field strength by the cloud service platform comprises: The cloud service platform determines the local maximum field strength based on the terahertz point cloud.

[0008] Preferably, the unmanned aerial vehicle platform further integrates an edge computing module. The edge computing module performs denoising and spatio-temporal alignment preprocessing on the ultraviolet sensing signal, the terahertz point cloud, the infrared sensing signal, and the visible light image, and uploads the cloud service platform.

[0009] Preferably, the method of detecting abnormal discharge of power equipment by unmanned aerial vehicle ultraviolet detection further comprises: The edge computing module analyzes the terahertz point cloud and adjusts the signal collection angle of the ultraviolet sensor, terahertz radar, infrared thermal imager and bionic compound eye visual camera array based on the analysis result.

[0010] Preferably, the edge computing module analyzes the terahertz point cloud and adjusts the signal collection angle of the ultraviolet sensor, terahertz radar, infrared thermal imager and bionic compound eye visual camera array based on the analysis result comprises: The edge computing module extracts the conductor point cloud in the terahertz point cloud, determines the dancing frequency and dancing amplitude of the conductor based on the extracted conductor point cloud, uses the ranging result of the UWB of the conductor to obtain the phase compensation amount of the conductor based on the time difference of arrival, determines the conductor displacement amount according to the phase compensation amount, dancing frequency and dancing amplitude, generates a pulse firing frequency according to the conductor displacement amount, generates a pulse sequence, generates a PWM signal with adjustable duty cycle based on multiple pulse sequences, generates a rudder angle based on the PWM signal with adjustable duty cycle, and adjusts the signal collection angle of the ultraviolet sensor, terahertz radar, infrared thermal imager and bionic compound eye visual camera array based on the rudder angle.

[0011] Preferably, the discharge prediction model is as follows: Wherein, is the local maximum field strength; is the defect expansion rate output by the spatiotemporal graph neural network; is the environmental deterioration factor; σ represents the algorithm corresponding to the discharge prediction model.

[0012] Preferably, the calculation formula of the environmental deterioration factor is as follows: Wherein, α, β and γ are weight coefficients corresponding to the humidity level, target salt concentration and target contamination level, respectively; is the normalized humidity level; is the normalized target salt concentration; is the normalized target contamination level.

[0013] In a second aspect, the present application also provides a system for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment, comprising: An unmanned aerial vehicle platform integrated with an edge computing module, an ultraviolet sensor, a terahertz radar, an infrared thermal imager and a bionic compound eye visual camera array, for collecting ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images of a power equipment area and uploading a cloud service platform; The cloud service platform is used for comprehensive processing and analysis of received ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images, to obtain a local maximum field strength, a defect expansion rate and an environmental deterioration factor, adjust discharge prediction model parameters based on the accuracy of previous N discharge prediction results, and process the local maximum field strength, the defect expansion rate and the environmental deterioration factor using the adjusted discharge prediction model to generate a discharge prediction result; wherein N is a positive integer.

[0014] Compared with the prior art, the present application has the following advantages: The method for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment of the present application cooperates the unmanned aerial vehicle platform with the cloud service platform, realizes multi-dimensional signal synchronous acquisition of discharge ultraviolet photons, local temperature rise, defect structure and visible light scene by integrating four types of sensors of ultraviolet, terahertz, infrared and visible light, the cloud service platform extracts three core indexes of local maximum field strength, defect expansion rate and environmental deterioration factor from the multi-dimensional signals using a fusion algorithm, establishes a quantitative relationship between discharge development and environmental disturbance, and at the same time, uses historical prediction accuracy as feedback to adaptively adjust the model weight and threshold value online, dynamically compensates the time-varying interference of environmental variables such as temperature, humidity, wind speed and air pressure, eliminates the error drift caused by the fixed parameters of the traditional model, and continuously improves the prediction accuracy and stabilizes it at a high level. The present application not only improves the discharge prediction accuracy from large fluctuations to a stable high level, significantly reduces the risk of misjudgment, and ensures the safe operation of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the specific embodiments or the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual proportion.

[0016] Figure 1 The method flowchart of the present application.

[0017] Figure 2 The system principle diagram of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] It should be understood that the terms "comprise" and "comprising" when used in this specification, indicate the presence of the described features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0020] It should also be understood that the terms used in the present specification are only for the purpose of describing particular embodiments and are not intended to limit the present application. As used in the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0021] It should be further understood that the term "and / or" used in the present specification means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0022] The following examples are described with reference to Figure 1 and Figure 2 .

[0023] As Figure 1 shown, it is a flow chart of the method for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment of the present embodiment, the execution subject of the present embodiment is a system with data processing capability, which includes an unmanned aerial vehicle platform and a cloud service platform, the unmanned aerial vehicle platform is integrated with an edge computing module, an ultraviolet sensor, a terahertz radar, an infrared thermal imager, and a bionic compound eye visual camera array.

[0024] Specifically, the method of the present embodiment can include the following steps: S1, the unmanned aerial vehicle platform collects ultraviolet sensing signals, terahertz point clouds, infrared sensing signals, and visible light images of the power equipment area, and uploads them to the cloud service platform; The ultraviolet sensor, terahertz radar, infrared thermal imager, and bionic compound eye visual camera array are used to collect information of the power equipment area respectively, and obtain ultraviolet sensing signals, terahertz point clouds, infrared sensing signals, and visible light images respectively.

[0025] The above-mentioned ultraviolet sensor can select a perovskite quantum dot ultraviolet sensor. The perovskite quantum dot ultraviolet sensor (CsPbBr) is adopted, with a sensitivity of 1 photon / second, which is 5 times higher than traditional ICCD, realizing quantum-enhanced ultraviolet detection.

[0026] The above-mentioned bionic compound eye visual camera array is integrated with a quantum dot filter. Based on the sub-decimeter level positioning of compound eye vision and UWB / terahertz radar, the compound eye vision can use an eight-camera array.

[0027] In some embodiments, the edge computing module is used to preprocess the ultraviolet sensing signal, terahertz point cloud, infrared sensing signal and visible light image by denoising and spatio-temporal alignment, and the preprocessed ultraviolet sensing signal, terahertz point cloud, infrared sensing signal and visible light image are transmitted to the cloud service platform.

[0028] The preprocessing includes denoising and spatio-temporal alignment. Taking denoising steps can effectively reduce the interference of noise on effective signals and improve the accuracy of detection. Adopting spatio-temporal alignment can improve the accuracy of abnormal discharge detection.

[0029] The edge computing module transmits the preprocessed ultraviolet sensing signal, terahertz point cloud, infrared sensing signal and visible light image to the cloud service platform by using the 6G communication mode. Here, the 6G backhaul data can effectively improve the speed and security of data transmission.

[0030] S2, the cloud service platform comprehensively processes and analyzes the received ultraviolet sensing signal, terahertz point cloud, infrared sensing signal and visible light image to obtain the local maximum field strength, defect expansion rate and environmental deterioration factor; S3, the cloud service platform adjusts the discharge prediction model parameters based on the accuracy of the previous N discharge prediction results, and processes the local maximum field strength, defect expansion rate and environmental deterioration factor by using the adjusted discharge prediction model to generate a discharge prediction result; wherein N is a positive integer.

[0031] The above discharge prediction model is a digital twin model, as follows: wherein, is the local maximum field strength; is the defect expansion rate output by the spatio-temporal graph neural network; is the environmental deterioration factor; and σ represents the algorithm corresponding to the discharge prediction model.

[0032] The method for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment of the application cooperates an unmanned aerial vehicle platform with a cloud service platform, realizes multi-dimensional signal synchronous collection of discharge ultraviolet photons, local temperature rise, defect structure and visible light scene through integration of four types of sensors of ultraviolet, terahertz, infrared and visible light, the cloud service platform extracts three core indexes of local maximum field strength, defect expansion rate and environmental deterioration factor from the multi-dimensional signals by using a fusion algorithm, establishes a quantitative relationship between discharge development and environmental disturbance, simultaneously, takes historical prediction accuracy as feedback, adjusts model weight and threshold value online and adaptively, dynamically compensates time-varying interference of environmental variables such as temperature, humidity, wind speed and air pressure, eliminates error drift caused by fixed parameters of a traditional model, and continuously improves and stabilizes the prediction accuracy at a high level, so that the prediction accuracy is improved from fluctuation to stability, the misjudgment risk is significantly reduced, and the safe operation of the power grid is ensured.

[0033] In some embodiments, the local maximum field strength can be determined based on the terahertz point cloud, and specifically, the finite element method can be used to solve the local maximum field strength.

[0034] In some embodiments, the defect expansion rate can be determined by the following steps: determining time characteristic information of the power equipment by using the ultraviolet sensing signal, the terahertz point cloud and the infrared sensing signal, generating discharge time evolution trend information by using the time characteristic information, historical discharge records of the power equipment, the ultraviolet sensing signal, properties of the power equipment and electrical topological relationship, and determining the defect expansion rate based on the discharge time evolution trend information.

[0035] The time characteristic information can represent the discharge dynamic evolution process of the power equipment. The historical discharge records can reflect the historical health status of the power equipment. The ultraviolet sensing signal includes an ultraviolet photon stream and can reflect the current discharge intensity. The properties of the power equipment include device types and the like, and can represent the static properties of the equipment. The electrical topological relationship can reflect the electrical coupling effect between devices.

[0036] In specific implementation, the spatio-temporal graph neural network can be pre-trained, the trained spatio-temporal graph neural network can be used to process the ultraviolet sensing signal, the terahertz point cloud and the infrared sensing signal, and the defect expansion rate can be output.

[0037] The spatio-temporal graph neural network can not only output the defect expansion rate, but also output the risk level and risk probability of the power equipment, and can also perform preliminary alarm.

[0038] In some embodiments, the environmental deterioration factor is determined by the following steps: determining a first salt concentration using the terahertz point cloud, determining a second salt concentration using an image of the power equipment region in the visible light image; determining a target salt concentration based on the first salt concentration and the second salt concentration; segmenting the visible light image to obtain a pollution region, determining a first pollution level based on the pollution region, processing the ultraviolet sensing signal based on the spatial correlation feature of the discharge hot spot and the pollution to obtain a second pollution level; determining a third pollution level using a local temperature rise model caused by pollution and the infrared sensing signal, determining a fourth pollution level using historical pollution records; determining a target pollution level based on the first pollution level, the second pollution level, the third pollution level and the fourth pollution level; determining a humidity level based on the humidity information of the power equipment; adjusting the weight of the target salt concentration based on the humidity information of the power equipment and the type of the power equipment; and / or adjusting the weight of the humidity level based on the type of the power equipment; determining the environmental deterioration factor using the target salt concentration and the weight, the target pollution level, the humidity level and the weight.

[0039] The humidity information can be obtained from an integrated capacitive humidity sensor, which collects the humidity around the power equipment in real time.

[0040] The salt concentration can be determined by the characteristics of the 0.3 THZ band absorption peak in the terahertz reflectance spectrum. In addition, it can also be predicted by processing the visible light image through the trained RstNet model.

[0041] Generally, the target pollution level can be determined by weighted summation based on the first pollution level, the second pollution level, the third pollution level and the fourth pollution level, for example, the weight of the first pollution level is set to 0.4, the weight of the second pollution level is set to 0.3, the weight of the third pollution level is set to 0.2, and the weight of the fourth pollution level is set to 0.1.

[0042] The environmental deterioration factor can be determined by the following formula: Wherein, a, β and γ are the weight coefficients corresponding to the humidity level, the target salt concentration and the target pollution level, respectively. is the normalized humidity level; is the normalized target salt concentration; is the normalized target pollution level.

[0043] In some embodiments, the values of a, b, and g can be 0.4, 0.3, and 0.3, respectively. The values of a, b, and g can be adjusted according to the current actual situation, for example, under high humidity (H>80%), wet salt contamination is more likely to cause flashover, so the salt density (SDD) weight is automatically increased to 0.4 (originally 0.3); for example, according to the type of equipment, the weight is adjusted: for GIS equipment, the sealing property is reduced, so the salt density is reduced, and therefore the humidity is focused on, and a is set to 0.5; for insulator strings, due to exposure to atmospheric pollution, the salt density is focused on, and therefore b is set to 0.5.

[0044] In some embodiments, the edge computing module is further configured to extract a conductor point cloud from the terahertz point cloud, and determine a conductor dancing frequency and a conductor dancing amplitude based on the extracted conductor point cloud; determine a phase compensation amount of the conductor based on a time difference of arrival (TDOA) calculation using a ranging result of a UWB of the conductor; determine a conductor displacement amount based on the phase compensation amount, the conductor dancing frequency, and the conductor dancing amplitude; generate a pulse firing frequency based on the conductor displacement amount, and generate a pulse sequence; generate a pulse width modulation (PWM) signal with adjustable duty cycle based on the pulse sequence; generate a rudder angle based on the PWM signal with adjustable duty cycle; and adjust a signal acquisition angle of the ultraviolet sensor, the terahertz radar, the infrared thermal imager, and the bionic compound eye vision camera array based on the rudder angle.

[0045] Specifically, the conductor center line is extracted by DBSCAN clustering using the terahertz point cloud, and the conductor dancing frequency and the conductor dancing amplitude are determined based on the conductor center line. The phase compensation amount is calculated based on TDOA using a ranging result of a UWB.

[0046] The above-mentioned generation of a PWM signal with adjustable duty cycle based on a plurality of pulse sequences can be to calculate an average firing rate of several pulse sequences, and to generate a PWM signal with adjustable duty cycle based on the average firing rate.

[0047] In addition, during the detection process, if no pulse is detected for several consecutive frames, an emergency hovering mode is triggered.

[0048] The above-mentioned edge computing module executes the above-mentioned step of adjusting the signal acquisition angle when the conductor dancing frequency and the conductor dancing amplitude change, so that only sensor events, such as a displacement mutation detected by the terahertz radar, trigger the operation, and the power consumption is reduced.

[0049] The above-mentioned technical solutions of the present disclosure combine multi-dimensional data fusion of ultraviolet signals (used for detecting photon flow of discharge), terahertz signals (used for detecting internal defects), infrared signals (used for detecting temperature rise), and the like, to realize accurate positioning of discharge points, improve the detection rate of abnormal discharge of power equipment, reduce the false alarm rate, and support stable detection in extreme scenarios such as conductor dancing and strong electromagnetic interference.

[0050] Based on the same inventive concept, the disclosure provides a system for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment, the steps performed by the components of the device are the same or similar to the above method, and therefore similar places will not be described again. As shown in Figure 2 The system for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment of the embodiment comprises: The unmanned aerial vehicle platform in the method of the above embodiment; wherein the unmanned aerial vehicle platform is integrated with an edge computing module, an ultraviolet sensor, a terahertz radar, an infrared thermal imager, and an array of bionic compound eye vision cameras; and the cloud service platform in the method of the above embodiment.

[0051] The ultraviolet sensor, the terahertz radar, the infrared thermal imager, and the array of bionic compound eye vision cameras respectively collect information of the power equipment region, and respectively obtain an ultraviolet sensing signal, a terahertz point cloud, an infrared sensing signal, and a visible light image.

[0052] The edge computing module pre-processes the ultraviolet sensing signal, the terahertz point cloud, the infrared sensing signal, and the visible light image.

[0053] The edge computing module transmits the pre-processed ultraviolet sensing signal, terahertz point cloud, infrared sensing signal, and visible light image to the cloud service platform.

[0054] The cloud service platform determines a local maximum field strength, a defect expansion rate, and an environmental deterioration factor by using the received ultraviolet sensing signal, terahertz point cloud, infrared sensing signal, and visible light image; adjusts discharge prediction model parameters based on the accuracy of the previous N discharge prediction results, and processes the local maximum field strength, defect expansion rate, and environmental deterioration factor by using the adjusted discharge prediction model to generate a discharge prediction result; wherein N is a positive integer.

[0055] The defect expansion rate is determined by the following steps: determining time characteristic information of the power equipment by using the ultraviolet sensing signal, the terahertz point cloud, and the infrared sensing signal; generating discharge time evolution trend information by using the time characteristic information, historical discharge records of the power equipment, the ultraviolet sensing signal, properties of the power equipment, and electrical topology relationships; and determining the defect expansion rate based on the discharge time evolution trend information. The environmental deterioration factor is determined by the following steps: determining a first salt concentration by using the terahertz point cloud, determining a second salt concentration by using an image of a power equipment region in a visible light image, determining a target salt concentration based on the first salt concentration and the second salt concentration, segmenting a dirt region from the visible light image, determining a first dirt level based on the dirt region, processing an ultraviolet sensing signal based on a spatial correlation feature between a discharge hot spot and dirt to obtain a second dirt level, determining a third dirt level by using a local temperature rise model caused by dirt and an infrared sensing signal, determining a fourth dirt level by using historical dirt records, determining a target dirt level based on the first dirt level, the second dirt level, the third dirt level, and the fourth dirt level, determining a humidity level based on humidity information of the power equipment, adjusting a weight of the target salt concentration based on the humidity information of the power equipment and a type of the power equipment, and / or adjusting a weight of the humidity level based on the type of the power equipment, and determining the environmental deterioration factor by using the target salt concentration and the weight, the target dirt level, the humidity level, and the weight. A local maximum field strength is determined based on the terahertz point cloud.

[0056] The edge computing module is further configured to extract a conductor point cloud from the terahertz point cloud, determine a dancing frequency and a dancing amplitude of the conductor based on the extracted conductor point cloud, determine a phase compensation amount of the conductor based on a time difference of arrival by using a ranging result of UWB of the conductor, determine a conductor displacement amount based on the phase compensation amount, the dancing frequency, and the dancing amplitude, generate a pulse firing frequency based on the conductor displacement amount, generate a pulse sequence, generate a pulse width modulation (PWM) signal with adjustable duty cycle based on the pulse sequence, generate a steering engine angle based on the PWM signal with adjustable duty cycle, and adjust a signal collection angle of the ultraviolet sensor, the terahertz radar, the infrared thermal imager, and the bionic compound eye vision camera array based on the steering engine angle. The edge computing module is configured to perform the above steps of adjusting the signal collection angle when the dancing frequency and the dancing amplitude change.

[0057] Those skilled in the art can appreciate that the units of the examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components of the examples have been described in general terms in the above description. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0058] In the embodiments provided by the present application, it should be understood that the division of the units is merely a logical functional division, and in actual implementation, another division manner can be used, for example, a plurality of units can be combined into one unit, one unit can be split into a plurality of units, or some features can be ignored, etc.

[0059] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0060] When the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that makes a contribution to the prior art, or all or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various program code storage media.

[0061] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should be covered in the scope of the specification of the present application.

Claims

1. A method for unmanned aerial vehicle ultraviolet detection of abnormal discharge of electrical equipment, characterized in that, The application is applied to a system for unmanned aerial vehicle ultraviolet detection of abnormal discharge of power equipment including an unmanned aerial vehicle platform and a cloud service platform, wherein the unmanned aerial vehicle platform is integrated with an edge computing module, an ultraviolet sensor, a terahertz radar, an infrared thermal imager and a bionic compound eye visual camera array; the method comprises the following steps: The unmanned aerial vehicle platform collects ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images of a power equipment area and uploads the cloud service platform; The cloud service platform comprehensively processes and analyzes the received ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images to obtain a local maximum field strength, a defect expansion rate and an environmental deterioration factor; The cloud service platform adjusts discharge prediction model parameters based on the accuracy of the previous N discharge prediction results and processes the local maximum field strength, the defect expansion rate and the environmental deterioration factor by using the discharge prediction model after the adjustment to generate a discharge prediction result; wherein N is a positive integer.

2. The method for detecting abnormal discharge of power equipment by using UAV ultraviolet detection according to claim 1, characterized in that, The step of obtaining the defect expansion rate by the cloud service platform comprises the following steps: The cloud service platform determines time characteristic information of the power equipment according to the ultraviolet sensing signals, the terahertz point clouds and the infrared sensing signals, generates discharge time evolution trend information by using the time characteristic information, historical discharge records of the power equipment, the ultraviolet sensing signals, power equipment attributes and electrical topology relationships and determines the defect expansion rate based on the discharge time evolution trend information. 3.The method of claim 1, wherein The step of obtaining the environmental deterioration factor by the cloud service platform comprises the following steps: A first salt concentration is determined according to the terahertz point clouds, a second salt concentration is obtained by predicting an image of the power equipment area in the visible light image, a target salt concentration is determined based on the first salt concentration and the second salt concentration; A pollution area is obtained by using visible light image segmentation, a first pollution level is determined based on the pollution area, a second pollution level is obtained by processing the ultraviolet sensing signals based on the spatial correlation characteristics of the discharge hot spot and the pollution, a third pollution level is determined by using a local temperature rise model caused by pollution and the infrared sensing signals, a fourth pollution level is determined by using historical pollution records, a target pollution level is determined based on the first pollution level, the second pollution level, the third pollution level and the fourth pollution level; A humidity level is determined based on humidity information of the power equipment, the weight of the target salt concentration is adjusted based on the humidity information of the power equipment and the type of the power equipment; and / or, the weight of the humidity level is adjusted based on the type of the power equipment; The environmental deterioration factor is obtained according to the target salt concentration and the weight, the target pollution level, the humidity level and the weight.

4. The method of claim 1, wherein the method further comprises: The step of obtaining the local maximum field strength by the cloud service platform comprises the following steps: The cloud service platform determines the local maximum field strength based on the terahertz point clouds.

5. The method of claim 4, wherein the method further comprises: The unmanned aerial vehicle platform is further integrated with an edge computing module; The edge computing module performs denoising and spatio-temporal alignment preprocessing on the ultraviolet sensing signals, the terahertz point clouds, the infrared sensing signals and the visible light images and uploads the cloud service platform.

6. The method for detecting abnormal discharge of power equipment by UAV ultraviolet according to claim 5, characterized in that, Further comprising: The edge computing module analyzes the terahertz point cloud and adjusts the signal collection angle of the ultraviolet sensor, terahertz radar, infrared thermal imager and bionic compound eye visual camera array based on the analysis result.

7. The method of claim 6, wherein the method further comprises: The edge computing module analyzes the terahertz point cloud and adjusts the signal collection angle of the ultraviolet sensor, terahertz radar, infrared thermal imager and bionic compound eye visual camera array based on the analysis result. The edge computing module extracts the wire point cloud in the terahertz point cloud, determines the dancing frequency and dancing amplitude of the wire based on the extracted wire point cloud, uses the ranging result of the UWB of the wire to obtain the phase compensation amount of the wire based on the time difference of arrival, determines the wire displacement amount according to the phase compensation amount, dancing frequency and dancing amplitude, generates the pulse firing frequency according to the wire displacement amount, generates the pulse sequence, generates the PWM signal with adjustable duty cycle based on the multiple pulse sequences, generates the steering engine angle based on the PWM signal with adjustable duty cycle, and adjusts the signal collection angle of the ultraviolet sensor, terahertz radar, infrared thermal imager and bionic compound eye visual camera array based on the steering engine angle.

8. A method for detecting abnormal discharge of power equipment using ultraviolet light from a UAV according to claim 2, characterized in that, The discharge prediction model is as follows: wherein, is the local maximum field strength; is the defect expansion rate output by the spatio-temporal graph neural network; is the environmental deterioration factor; and σ represents an algorithm corresponding to the discharge prediction model.

9. A method for detecting abnormal discharge of power equipment using ultraviolet light from a UAV according to claim 3, characterized in that, The calculation formula of the environmental deterioration factor is: Wherein, α, β and γ are weight coefficients corresponding to humidity level, target salt concentration and target contamination level respectively; is the normalized humidity level; is the normalized target salt concentration; is the normalized target contamination level.

10. A system for unmanned aerial vehicle ultraviolet detection of abnormal electrical discharge of electrical equipment, characterized in that, including: The unmanned aerial vehicle platform is integrated with an edge computing module, an ultraviolet sensor, a terahertz radar, an infrared thermal imager and a bionic compound eye visual camera array, and is used to collect ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images of the power equipment area and upload a cloud service platform. The cloud service platform is used to comprehensively process and analyze the received ultraviolet sensing signals, terahertz point clouds, infrared sensing signals and visible light images to obtain a local maximum field strength, a defect expansion rate and an environmental deterioration factor, adjust the discharge prediction model parameters based on the accuracy of the previous N discharge prediction results, and process the local maximum field strength, the defect expansion rate and the environmental deterioration factor using the adjusted discharge prediction model to generate a discharge prediction result; wherein N is a positive integer.

Images