Partial discharge detection method and system based on acoustic signal and thermal imaging

Abstract

The embodiment of the invention relates to the technical field of partial discharge detection, and discloses a partial discharge detection method based on acoustic signals and thermal imaging, which is characterized by comprising the following steps: analyzing and processing sound information subjected to noise reduction and filtering to determine position information of a sound source in a current detection environment, and generating a corresponding sound source point location map according to the position information of the sound source; superposing the sound source point location map and the maintenance image to obtain a partial discharge display image; obtaining an infrared thermal image having the same visual angle as the visible light camera through the infrared camera, and carrying out thermal image analysis processing on the infrared thermal image to determine a corresponding abnormal temperature region; and updating and displaying the maintenance image or the partial discharge display image according to the actual pixel point position. According to the partial discharge detection method based on the acoustic signal and the thermal imaging in the embodiment of the invention, various information sources such as the acoustic signal, the visible light image and the infrared thermal image are combined, and automatic identification and positioning of the partial discharge point are realized through technical means such as algorithm processing and image superposition.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power maintenance, and in particular to a partial discharge detection method and system based on acoustic signals and thermal imaging. Background Art

[0002] At present, the all-round progress and development of today's society cannot be separated from the stable and reliable power support provided by the complex power network. As the core channel for regional power transmission, the inspection of high-voltage overhead transmission lines plays a vital role in ensuring the safe operation of local power transmission and distribution networks. However, during the operation of power transmission and transformation equipment, a variety of equipment abnormalities will occur, among which partial discharge is particularly common and extremely harmful. Partial discharge is not only a key factor leading to the eventual insulation damage of high-voltage transmission equipment, but also an important sign of the gradual decline in insulation performance. Therefore, designing a solution that can perform efficient line detection has become a technical problem that needs to be solved urgently by technicians in this field. Summary of the invention

[0003] In response to the above defects, an embodiment of the present invention discloses a partial discharge detection method based on acoustic signals and thermal imaging, which can improve detection efficiency and detection accuracy.

[0004] The first aspect of the embodiment of the present invention discloses a partial discharge detection method based on acoustic signals and thermal imaging, comprising:

[0005] Acquiring sound information in a current scene by means of a microphone array arranged in a first signal acquisition frequency band, and preprocessing the sound information to obtain sound information after noise reduction filtering; the microphone array is composed of a plurality of sound sensors, the positions of the plurality of sound sensors are different, and the microphone array is used to receive sound information from all directions;

[0006] Analyze and process the sound information after noise reduction filtering to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map based on the location information of the sound source;

[0007] Acquire the maintenance image of the current scene through the visible light camera, and superimpose the sound source point map and the maintenance image to obtain a partial discharge display image according to the mapping relationship between the image collected by the visible light camera and the sound point collected by the microphone;

[0008] If the number of local discharge points detected in the partial discharge display image is greater than or equal to two, the next step is executed; if the number of local discharge points detected in the partial discharge display image is one, the superimposed partial discharge display image is displayed;

[0009] Acquire an infrared thermal image having the same viewing angle as the visible light camera through an infrared camera, and perform thermal image analysis processing on the infrared thermal image to determine a corresponding abnormal temperature area;

[0010] If the abnormal temperature area matches the set discharge mode, a spatial position information set corresponding to the abnormal temperature area is obtained, and the coordinate transformation of the spatial position information set is performed to determine the actual pixel position of each abnormal temperature area in the maintenance image, and the maintenance image or partial discharge display image is updated and displayed according to the actual pixel position.

[0011] As an optional implementation, in the first aspect of the embodiment of the present invention, the microphone array includes 136 MIC spiral arrays to acquire sound signals; the sound information after noise reduction filtering is analyzed and processed to determine the position information of the sound source in the current detection environment, and a corresponding sound source point map is generated according to the position information of the sound source, including:

[0012] Analyze and process the sound information after noise reduction filtering to determine the time information when the sound source arrives at each sound sensor in the microphone array;

[0013] Calculate the time difference between the sound signal arriving at each sound sensor in the microphone array;

[0014] The location information of the sound source in the current detection environment is determined according to the calculated time difference and the preset sound source calculation formula; the sound source calculation formula is: Where θ is the direction angle of the sound source, δ is the distance between the two microphones, c is the speed of sound, and Δt is the time difference between the sound source signal reaching the two microphones;

[0015] Generate a corresponding sound source point map based on the location information of the sound source.

[0016] As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the detecting that the number of the local discharge point in the local discharge display image is 1, displaying the superimposed local discharge display image, further comprising:

[0017] Performing feature analysis on the sound information after noise reduction filtering to determine corresponding frequency feature information and amplitude feature information;

[0018] Performing state evaluation on the frequency characteristic information and amplitude characteristic information obtained by analysis to determine a first state parameter of a corresponding partial discharge point;

[0019] After the spatial position information set is subjected to coordinate transformation to determine the actual pixel position of each abnormal temperature area in the inspection image, the method further includes:

[0020] Preprocessing the infrared thermal image to obtain processed infrared image data, obtaining pixel point parameters of each data point in the infrared image data, and determining the grayscale difference and gradient difference between the corresponding data point and the adjacent data point based on the pixel point parameters of each data point;

[0021] Determine the grayscale difference and gradient difference between the corresponding data point and the adjacent data point according to the pixel point parameters of each data point to determine the corresponding mutation parameter, wherein the mutation parameter is determined by the grayscale difference and gradient difference;

[0022] Determine parameter difference information between each data point and other data points according to the mutation parameters of each data point in the obtained infrared image data, and determine regional association information between each data point and other data points according to the parameter difference information;

[0023] Clustering the infrared image data according to the regional association information of each data point and other data points to determine the corresponding regional information; and extracting the features of the regional information to obtain the regional feature information;

[0024] The regional characteristic information meeting the set requirements is output, and the second state parameter of the corresponding partial discharge point is determined according to the regional characteristic information.

[0025] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the partial discharge detection method further includes:

[0026] Receive a data analysis area selected by a user, perform statistics on parameters in the data analysis area to determine corresponding statistical parameter information, the statistical parameter information includes maximum temperature information and minimum temperature information, and the data analysis area is a rectangular analysis area;

[0027] The partial discharge detection method further includes:

[0028] The defect level of the corresponding partial discharge point is determined according to the first state parameter and / or the second state parameter, and the corresponding defect level is output.

[0029] As an optional implementation manner, in the first aspect of the embodiment of the present invention, before acquiring the sound information in the current scene by using the microphone array set in the first signal acquisition frequency band, it also includes:

[0030] Receiving voiceprint signals collected by a sound collection device of the unmanned aerial vehicle set in a second signal collection frequency band at each inspection point on the inspection route; the frequency band range of the second signal collection frequency band is greater than the frequency band range of the first signal collection frequency band;

[0031] Analyze and process the noise reduction filtered voiceprint signal to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map based on the location information of the sound source;

[0032] The inspection image of the current scene is acquired through a visible light camera, and the sound source point map and the inspection image are superimposed to obtain an inspection display image according to the mapping relationship between the image acquired by the visible light camera and the sound point acquired by the microphone;

[0033] Identify the inspection display image to determine whether there is a corresponding partial discharge maintenance point in the inspection display image, and if so, obtain the current flight position information of the unmanned aerial vehicle, and generate corresponding maintenance information according to the current flight position information and the inspection display image;

[0034] The maintenance information is sent to a background server, wherein the maintenance information includes maintenance location information and inspection display images.

[0035] As an optional implementation, in the first aspect of the embodiment of the present invention, the inspection display image is identified to determine whether there is a corresponding partial discharge maintenance point in the inspection display image, and if so, the current flight position information of the unmanned aerial vehicle is obtained, and the corresponding maintenance information is generated according to the current flight position information and the inspection display image, including:

[0036] Identify the inspection display image to determine whether there is a corresponding partial discharge maintenance point in the inspection display image;

[0037] Acquire partial discharge characteristic information associated with the partial discharge maintenance point, and match the partial discharge characteristic information with a preset partial discharge level, and if the partial discharge characteristic information matches a first partial discharge level, do not generate corresponding maintenance information;

[0038] If the partial discharge characteristic information matches the second partial discharge level, the current flight position information of the unmanned aerial vehicle is obtained, and corresponding maintenance information is generated according to the current flight position information and the inspection display image, wherein the maintenance information also includes a general maintenance level;

[0039] If the partial discharge characteristic information matches the third partial discharge level, the current flight position information of the unmanned aerial vehicle is obtained, and corresponding maintenance information is generated according to the current flight position information and the inspection display image, and the maintenance information also includes an emergency maintenance level.

[0040] As an optional implementation, in the first aspect of the embodiment of the present invention, the coordinate transformation of the spatial position information set to determine the actual pixel position of each abnormal temperature area in the inspection image includes:

[0041] Determine a first pixel resolution corresponding to the image acquired by the infrared camera and determine a second pixel resolution corresponding to the image acquired by the visible light camera;

[0042] The spatial position information set is subjected to coordinate transformation according to a coordinate transformation formula to determine the actual pixel position of each abnormal temperature area in the inspection image. The coordinate transformation formula is:

[0043] Y2=Y1*(H2 / H1), X2=X1*(W2 / W1);

[0044] Y2 is the Y-axis coordinate value in the visible light image coordinates, Y1 is the Y-axis coordinate value in the infrared thermal image coordinates, H1 is the vertical pixel value in the first pixel resolution, and H2 is the vertical pixel value in the second pixel resolution; X2 is the X-axis coordinate value in the visible light image coordinates, X1 is the X-axis coordinate value in the infrared thermal image coordinates, W1 is the horizontal pixel value in the first pixel resolution, and W2 is the horizontal pixel value in the second pixel resolution;

[0045] Or, the coordinate transformation of the spatial position information set to determine the actual pixel position of each abnormal temperature area in the inspection image includes:

[0046] The spatial position information set is subjected to coordinate transformation according to the infrared-visible light mapping relationship to determine the actual pixel position of each abnormal temperature area in the inspection image.

[0047] A second aspect of an embodiment of the present invention discloses a partial discharge detection system based on acoustic signals and thermal imaging, comprising:

[0048] A voiceprint acquisition module is used to acquire sound information in the current scene through a microphone array set in a first signal acquisition frequency band, and pre-process the sound information to obtain sound information after noise reduction filtering; the microphone array is composed of a plurality of sound sensors, and the positions of the plurality of sound sensors are different, and the microphone array is used to receive sound information from all directions;

[0049] Point determination module: used to analyze and process the sound information after noise reduction filtering to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map based on the location information of the sound source;

[0050] Image acquisition module: used to acquire the maintenance image of the current scene through the visible light camera, and to superimpose the sound source point map and the maintenance image to obtain a partial discharge display image according to the mapping relationship between the image acquired by the visible light camera and the sound point acquired by the microphone;

[0051] A judgment module: for executing the next step if the number of local discharge points detected in the partial discharge display image is greater than or equal to two, and for displaying the partial discharge display image obtained by superimposing if the number of local discharge points detected in the partial discharge display image is one;

[0052] Infrared image acquisition module: used to acquire an infrared thermal image having the same viewing angle as the visible light camera through an infrared camera, and perform thermal image analysis processing on the infrared thermal image to determine the corresponding abnormal temperature area;

[0053] Coordinate updating module: used to obtain a spatial position information set corresponding to the abnormal temperature area if the abnormal temperature area matches the set discharge mode, perform coordinate transformation on the spatial position information set to determine the actual pixel position of each abnormal temperature area in the maintenance image, and update the maintenance image or partial discharge display image according to the actual pixel position.

[0054] A third aspect of an embodiment of the present invention discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the partial discharge detection method based on acoustic signals and thermal imaging disclosed in the first aspect of the embodiment of the present invention.

[0055] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the partial discharge detection method based on acoustic signals and thermal imaging disclosed in the first aspect of an embodiment of the present invention.

[0056] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0057] The partial discharge detection method based on acoustic signals and thermal imaging in the embodiment of the present invention combines multiple information sources such as acoustic signals, visible light images and infrared thermal images, and realizes automatic identification and positioning of partial discharge points through technical means such as algorithm processing and image superposition. This intelligent detection method not only improves the accuracy and efficiency of detection, but also reduces the dependence on manual intervention, and improves the intelligence level of the entire detection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1It is a flow chart of a partial discharge detection method based on acoustic signals and thermal imaging disclosed in an embodiment of the present invention;

[0060] Figure 2 It is a schematic diagram of a process for determining a sound source point map disclosed in an embodiment of the present invention;

[0061] Figure 3 It is a schematic diagram of a process for determining an abnormal infrared temperature according to an embodiment of the present invention;

[0062] Figure 4 It is a schematic diagram of a process of using an unmanned aerial vehicle for maintenance disclosed in an embodiment of the present invention;

[0063] Figure 5 It is a structural schematic diagram of a partial discharge detection system based on acoustic signals and thermal imaging provided by an embodiment of the present invention;

[0064] Figure 6 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] It should be noted that the terms "first", "second", "third", "fourth", etc. in the specification and claims of the present invention are used to distinguish different objects rather than to describe a specific order. The terms "including" and "having" in the embodiments of the present invention and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0067] During the operation of power transmission and transformation equipment, various equipment abnormalities may occur, among which partial discharge is particularly common and extremely harmful. Partial discharge is not only a key factor that leads to the final insulation damage of high-voltage power transmission equipment, but also an important sign of the gradual decline in insulation performance. Based on this, the embodiment of the present invention discloses a partial discharge detection method, system, electronic device and storage medium based on acoustic signals and thermal imaging, which combines multiple information sources such as acoustic signals, visible light images and infrared thermal images, and realizes automatic identification and positioning of partial discharge points through technical means such as algorithm processing and image superposition. This intelligent detection method not only improves the accuracy and efficiency of detection, but also reduces the dependence on manual intervention, and improves the intelligence level of the entire detection system.

[0068] Embodiment 1

[0069] See also Figure 1 , Figure 1 It is a flow chart of the partial discharge detection method based on acoustic signals and thermal imaging disclosed in the embodiment of the present invention. Among them, the execution subject of the method described in the embodiment of the present invention is an execution subject composed of software and / or hardware, and the execution subject can receive relevant information by wired or / and wireless means, and can send certain instructions. Of course, it can also have certain processing functions and storage functions. The execution subject can control multiple devices, such as a remote physical server or cloud server and related software, or it can be a local host or server and related software that performs related operations on a device placed somewhere. In some scenarios, multiple storage devices can also be controlled, and the storage devices can be placed in the same place or different places as the devices. For example Figure 1 As shown, the partial discharge detection method based on acoustic signals and thermal imaging includes the following steps:

[0070] S101: Acquire sound information in a current scene by means of a microphone array set in a first signal acquisition frequency band, and preprocess the sound information to obtain sound information after noise reduction filtering; the microphone array is composed of a plurality of sound sensors, the positions of the plurality of sound sensors are different, and the microphone array is used to receive sound information from all directions;

[0071] S102: Analyze and process the sound information after noise reduction filtering to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map according to the location information of the sound source;

[0072] S103: acquiring a maintenance image of the current scene through a visible light camera, and superimposing the sound source point map and the maintenance image to obtain a partial discharge display image according to a mapping relationship between the image collected by the visible light camera and the sound points collected by the microphone;

[0073] S104: if the number of the local discharge points detected in the partial discharge display image is greater than or equal to two, executing the next step, and if the number of the local discharge points detected in the partial discharge display image is one, displaying the partial discharge display image obtained by superposition;

[0074] S105: acquiring an infrared thermal image having the same viewing angle as the visible light camera through an infrared camera, and performing thermal image analysis processing on the infrared thermal image to determine a corresponding abnormal temperature area;

[0075] S106: If the abnormal temperature area matches the set discharge mode, a spatial position information set corresponding to the abnormal temperature area is obtained, and the coordinate transformation of the spatial position information set is performed to determine the actual pixel position of each abnormal temperature area in the maintenance image, and the maintenance image or the partial discharge display image is updated and displayed according to the actual pixel position.

[0076] The embodiment of the present invention acquires sound information by setting a microphone array in the first signal acquisition frequency band and performs noise reduction filtering, which can effectively reduce the interference of environmental noise and improve the quality of sound signals, thereby more accurately identifying sound signals related to partial discharge. The microphone array is composed of multiple sound sensors in different positions and can receive sound information from all directions, which helps to accurately locate the sound source, that is, the location of the partial discharge point.

[0077] The embodiment of the present invention converts the processed sound information into a sound source point map, and superimposes it with the maintenance image obtained by the visible light camera to obtain a partial discharge display image. This method converts abstract acoustic signals into intuitive image information, which makes it easier for workers to quickly identify and understand the location and number of partial discharge points.

[0078] When the number of local discharge points in the partial discharge display image is detected to be greater than or equal to two, the infrared thermal image is further acquired through the infrared camera, and the thermal image analysis and processing is performed. This step-by-step detection method can reduce unnecessary detection steps and improve detection efficiency while ensuring detection accuracy. Because in the specific implementation, if the number of local discharge points is greater than or equal to two, there will be a situation where the use of sound signal detection will cause a certain deviation in the specific detection point. If there is a deviation, it will cause certain troubles to the subsequent maintenance personnel, and it will not be possible to achieve efficient positioning.

[0079] The embodiment of the present invention can further confirm the existence and nature of the local discharge point by matching the abnormal temperature area in the infrared thermal image with the set discharge mode. At the same time, the spatial position information of the abnormal temperature area is obtained and converted into the actual pixel point position in the maintenance image, which helps the staff to locate the fault point more accurately and provide strong support for subsequent maintenance and replacement work.

[0080] More preferably, the microphone array includes 136 MIC spiral arrays to acquire sound signals; the spiral array of the embodiment of the present invention, due to its non-uniform distribution characteristics, can effectively avoid spatial repeated sampling, thereby reducing spatial ambiguity problems, significantly reducing the side lobe height, and improving the accuracy of sound source positioning. This is particularly important for partial discharge point detection, because partial discharge points usually have weak and complex acoustic characteristics, and high-precision positioning is required to accurately identify the location of the sound source. The main lobe width of the spiral array is wider, which can better focus on the target sound source while suppressing background noise and interference. This is very beneficial for partial discharge point detection, because partial discharge point signals are often masked by complex background noise, and the spiral array can improve the reliability of detection by enhancing the target signal and suppressing noise. The spiral array performs well in acoustic imaging and can provide higher spatial resolution and clearer imaging effects. This helps to accurately locate partial discharge points in power equipment, thereby timely discovering potential faults and hidden dangers. Compared with other array structures (such as rectangular arrays), the spiral array has fewer side lobes in the imaging image and smoother spectral peak imaging. This means that in the detection of partial discharge points, the spiral array can reduce misjudgment caused by side lobes and improve the accuracy of detection. The design of the spiral array enables it to adapt to complex spatial environments, capture sound signals in multiple dimensions, and achieve the focus and enhancement of sound in a specific direction through beamforming technology. This is especially important for the complex acoustic environment inside power equipment, and can ensure that partial discharge points can be accurately detected under various conditions.

[0081] like Figure 2 As shown, the sound information after noise reduction filtering is analyzed and processed to determine the location information of the sound source in the current detection environment, and a corresponding sound source point map is generated according to the location information of the sound source, including:

[0082] S1021: Analyze and process the sound information after the noise reduction filter to determine the time information when the sound source arrives at each sound sensor in the microphone array;

[0083] S1022: Calculate the time difference between the sound signal reaching each sound sensor in the microphone array;

[0084] S1023: Determine the location information of the sound source in the current detection environment according to the calculated time difference and a preset sound source calculation formula; the sound source calculation formula is: Where θ is the direction angle of the sound source, δ is the distance between the two microphones, c is the speed of sound, and Δt is the time difference between the sound source signal reaching the two microphones;

[0085] S1024: Generate a corresponding sound source point map according to the location information of the sound source.

[0086] In the process of partial discharge detection, the embodiment of the present invention performs noise reduction filtering on the sound information, which can effectively remove environmental noise and other interference factors, making the sound signal received by the microphone array purer. By analyzing and processing the sound information after noise reduction filtering, the time information of the sound source reaching each sound sensor in the microphone array can be more accurately determined, thereby calculating the time difference of the sound signal reaching each sensor. Using the pre-set sound source calculation formula, combined with the time difference, the location information of the sound source can be accurately determined, thereby improving the accuracy of partial discharge detection.

[0087] The technology of the embodiment of the present invention can process sound information in real time and calculate the location information of the sound source in a short time, thereby realizing the real-time positioning of the partial discharge source. By generating a sound source point map, the location distribution of the partial discharge source can be intuitively displayed, providing a clear visual reference for monitoring personnel. This helps monitoring personnel to promptly discover and deal with potential partial discharge problems and avoid equipment failures and safety accidents.

[0088] More preferably, if the number of the local discharge point in the local discharge display image is detected to be 1, after displaying the superimposed local discharge display image, the method further includes:

[0089] Performing feature analysis on the sound information after noise reduction filtering to determine corresponding frequency feature information and amplitude feature information;

[0090] Performing state evaluation on the frequency characteristic information and amplitude characteristic information obtained by analysis to determine a first state parameter of a corresponding partial discharge point;

[0091] like Figure 3 As shown, after the spatial position information set is subjected to coordinate transformation to determine the actual pixel position of each abnormal temperature area in the inspection image, it also includes:

[0092] S1061: preprocessing the infrared thermal image to obtain processed infrared image data, obtaining pixel point parameters of each data point in the infrared image data, and determining a grayscale difference and a gradient difference between a corresponding data point and an adjacent data point based on the pixel point parameters of each data point;

[0093] S1062: Determine a grayscale difference and a gradient difference between a corresponding data point and an adjacent data point according to the pixel point parameters of each data point to determine a corresponding mutation parameter, wherein the mutation parameter is determined by the grayscale difference and the gradient difference;

[0094] S1063: determining parameter difference information between each data point and other data points according to the mutation parameters of each data point in the obtained infrared image data, and determining regional association information between each data point and other data points according to the parameter difference information;

[0095] S1064: performing a clustering operation on the infrared image data according to regional association information of each data point with other data points to determine corresponding regional information; and performing feature extraction on the regional information to obtain regional feature information;

[0096] S1065: Outputting the regional characteristic information that meets the set requirements, and determining the second state parameter of the corresponding partial discharge point according to the regional characteristic information.

[0097] The embodiment of the present invention performs feature analysis on the sound information after noise reduction filtering, extracts frequency feature information and amplitude feature information, and can more deeply understand the physical characteristics of the partial discharge point, such as discharge intensity, discharge frequency, etc. The first state parameter of the partial discharge point is determined through state evaluation, which provides a more accurate basis for subsequent fault diagnosis and maintenance.

[0098] The embodiment of the present invention preprocesses the infrared thermal image, obtains the pixel point parameters of each data point, and calculates the grayscale difference and gradient difference, which helps to capture the temperature change information in the infrared image more finely. By determining the mutation parameters, abnormal hot spots or temperature mutation areas in the infrared image can be identified, and these areas are often closely related to the local discharge points. Clustering operations are performed according to the mutation parameters of the data points, and similar areas in the infrared image can be automatically grouped, thereby improving the efficiency and accuracy of image processing. Feature extraction is performed on the clustered areas to obtain regional feature information, which helps to further analyze the thermal characteristics of the local discharge points, such as temperature distribution, thermal diffusion rate, etc. Combined with the feature analysis results of the sound signal and the regional feature information of the infrared image, the state of the local discharge point can be evaluated more comprehensively and accurately. By determining the first state parameter and the second state parameter, more reliable data support is provided for the fault warning, positioning, diagnosis and maintenance of the local discharge point.

[0099] Different partial discharge situations will result in different changes in temperature images. Based on the temperature change results of different partial discharges, we can identify which type of partial discharge it is, and each partial discharge image will definitely correspond to a special partial discharge temperature distribution diagram. The particularity of the change is determined by the center of the circle of the partial discharge center point, and the partial discharge type can be further determined in combination with environmental factors such as temperature and humidity. After determining the type, we can further judge the degree of partial discharge.

[0100] When determining the regional feature information, it can be determined in the following way: starting from the center point of the region, draw extension lines from the center point to the eight neighborhood directions, and stop when the extension lines intersect the edge of the region, and obtain eight neighborhood straight lines. The variance of the grayscale values ​​of all data points passing through each neighborhood straight line is used as the grayscale variance of the neighborhood straight line. Each two neighborhood straight lines that are symmetrical with the center are grouped together to obtain four groups of neighborhood straight lines.

[0101] According to the difference in grayscale variance between two neighboring lines in each group of neighboring lines, the difference mean of the grayscale variance corresponding to the four groups of neighboring lines is determined. The sum of the difference mean and the grayscale variance mean of the eight neighboring lines is used as the regional feature information of the corresponding area, and the average temperature data of the area is statistically used as the regional feature information. The temperature distribution state is characterized by the regional feature information, and the feature is used to assist in judging the type of partial discharge, which includes corona discharge, suspended discharge, and surface discharge.

[0102] In addition to the above methods, when partial discharge is performed, the surrounding temperature is not stable, because partial discharge will make the surrounding temperature not fixed. In this way, the corresponding positioning can be determined by detecting the temperature areas of the same location at different times and comparing the temperature images at different times, and a variety of algorithms can be combined to determine the location of the partial discharge.

[0103] More preferably, the partial discharge detection method further comprises:

[0104] Receive a data analysis area selected by a user, perform statistics on parameters in the data analysis area to determine corresponding statistical parameter information, the statistical parameter information includes maximum temperature information and minimum temperature information, and the data analysis area is a rectangular analysis area;

[0105] The embodiment of the present invention receives the data analysis area selected by the user, and the method allows the user to select a specific analysis range according to actual needs, rather than indiscriminately analyzing the entire image or data set. This improves the flexibility of data analysis and enables the user to focus on the area of ​​interest more accurately.

[0106] Statistics of parameters in the data analysis area and determination of statistical parameter information such as the highest and lowest temperatures help users to more intuitively understand the temperature distribution in the area, and then judge the severity of the partial discharge point and the possible impact range. Allowing users to select the data analysis area and receive statistical parameter information, as well as output defect levels, all enhance the interactivity between users and the partial discharge detection system. Users can customize the analysis process according to their own judgment and needs, and obtain analysis results instantly, thereby improving the ease of use of the system and user satisfaction.

[0107] During specific implementation, various forms of area selection methods may be combined, such as line point selection, to perform corresponding area status analysis.

[0108] The partial discharge detection method further includes:

[0109] The defect level of the corresponding partial discharge point is determined according to the first state parameter and / or the second state parameter, and the corresponding defect level is output.

[0110] The embodiment of the present invention determines the defect level of the partial discharge point according to the first state parameter (based on the characteristic analysis of the sound signal) and / or the second state parameter (based on the regional characteristic information of the infrared image). This approach combines information from multiple data sources to improve the accuracy and reliability of defect level assessment.

[0111] Outputting the corresponding defect level not only provides users with intuitive evaluation results, but also helps users take corresponding maintenance measures according to the defect level, thereby ensuring the safe operation of the equipment. Through automated and intelligent data processing and analysis, this method reduces the links of manual intervention and judgment, and improves the overall efficiency of partial discharge detection. Users only need to select the data analysis area and wait for the results to be output to quickly understand the operating status and potential problems of the equipment. The output defect level information provides users with a basis for decision-making. Users can judge whether immediate action is needed based on the defect level, such as shutting down for maintenance, replacing parts, etc., to avoid potential failures and safety accidents. In addition, this method also supports preventive maintenance. Through regular inspection and analysis, users can promptly discover and deal with potential partial discharge problems and extend the service life of the equipment.

[0112] like Figure 4 As shown, more preferably, before acquiring the sound information in the current scene by using the microphone array set in the first signal acquisition frequency band, it also includes:

[0113] S100a: receiving voiceprint signals collected by a sound collection device of the unmanned aerial vehicle set in a second signal collection frequency band at each inspection point on the inspection route; the frequency band range of the second signal collection frequency band is greater than the frequency band range of the first signal collection frequency band;

[0114] S100b: Analyze and process the voiceprint signal after noise reduction filtering to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map according to the location information of the sound source;

[0115] S100c: Acquire a maintenance image in the current scene through a visible light camera, and superimpose the sound source point map and the maintenance image to obtain an inspection display image according to a mapping relationship between the image acquired by the visible light camera and the sound points acquired by the microphone;

[0116] S100d: Identify the inspection display image to determine whether there is a corresponding partial discharge maintenance point in the inspection display image, and if so, obtain the current flight position information of the unmanned aerial vehicle, and generate corresponding maintenance information according to the current flight position information and the inspection display image;

[0117] S100e: Send the maintenance information to a background server, wherein the maintenance information includes maintenance location information and inspection display images.

[0118] The embodiment of the present invention can collect voiceprint signals within a wider frequency band through the sound collection device set in the second signal collection frequency band on the unmanned aerial vehicle. This means that the system can capture more types of sound information, including partial discharge sound signals that may be outside the first signal collection frequency band but are still meaningful. When performing specific implementation, the second signal collection frequency band here can be set at 30kHz-45kHz, which can not only clearly reflect the location of partial discharge, but also effectively shield the noise and interference on the scene.

[0119] When designing the frequency band, the narrower the frequency band range, the higher the sensitivity. Therefore, when implementing it, you can first use the 30kHz-40kHz frequency band in conjunction with an unmanned aerial vehicle to conduct preliminary partial discharge inspections. After finding suspicious points, narrow the frequency band to 37.5kHz-40kHz for subsequent precise detection of ultrasonic intensity.

[0120] Before the formal partial discharge detection (i.e. before using the microphone array set in the first signal acquisition frequency band), the system can identify potential partial discharge points in the current detection environment in advance through the collection and analysis of voiceprint signals. This helps to provide more accurate target areas for subsequent detection work and improve detection efficiency. And the use of drones for pre-inspection can greatly improve the corresponding maintenance efficiency.

[0121] By using the mapping relationship between the inspection image acquired by the visible light camera and the sound points collected by the microphone, the sound source point map can be accurately superimposed on the inspection image to obtain the inspection display image. This association method not only provides a visual display of sound information, but also allows users to intuitively see the location of the sound source in the physical space.

[0122] The system can automatically identify whether there are partial discharge inspection points in the inspection display image, and generate corresponding inspection information based on the current flight position information of the unmanned aerial vehicle. This information includes the inspection location information and the inspection display image, which can provide detailed guidance and reference for subsequent maintenance work. Inspections by unmanned aerial vehicles not only reduce the labor intensity of manual inspections, but also improve the efficiency and safety of inspections. At the same time, the system can generate and send inspection information to the background server in real time, so that managers can understand the operating status of the equipment in a timely manner and make corresponding decisions.

[0123] After the maintenance information is sent to the backend server, managers can remotely access the information to monitor and analyze the operating status of the equipment in real time. This helps to promptly identify and deal with potential problems, reduce the risk of equipment failure, and ensure the stable operation of the power system.

[0124] More preferably, the inspection display image is identified to determine whether there is a corresponding partial discharge maintenance point in the inspection display image, and if so, the current flight position information of the unmanned aerial vehicle is obtained, and corresponding maintenance information is generated according to the current flight position information and the inspection display image, including:

[0125] Identify the inspection display image to determine whether there is a corresponding partial discharge maintenance point in the inspection display image;

[0126] Acquire partial discharge characteristic information associated with the partial discharge maintenance point, and match the partial discharge characteristic information with a preset partial discharge level, and if the partial discharge characteristic information matches a first partial discharge level, do not generate corresponding maintenance information;

[0127] If the partial discharge characteristic information matches the second partial discharge level, the current flight position information of the unmanned aerial vehicle is obtained, and corresponding maintenance information is generated according to the current flight position information and the inspection display image, wherein the maintenance information also includes a general maintenance level;

[0128] If the partial discharge characteristic information matches the third partial discharge level, the current flight position information of the unmanned aerial vehicle is obtained, and corresponding maintenance information is generated according to the current flight position information and the inspection display image, and the maintenance information also includes an emergency maintenance level.

[0129] The system of the embodiment of the present invention first identifies whether there are partial discharge inspection points in the inspection display image, which is the basis for ensuring the targetedness of subsequent processing. Through accurate identification, unnecessary analysis of irrelevant areas can be avoided, thereby improving detection efficiency. Next, the system obtains partial discharge feature information associated with the partial discharge inspection point and matches it with the pre-set partial discharge level. This hierarchical processing method helps the system to make different responses according to the severity of the partial discharge and realize the rational allocation of resources.

[0130] When the partial discharge characteristic information matches the first partial discharge level, the system does not generate maintenance information. This can avoid excessive responses caused by minor partial discharges, reduce unnecessary maintenance work, and thus save manpower and material resources. For partial discharge maintenance points that match the second partial discharge level, the system generates maintenance information containing general maintenance levels. This helps maintenance personnel understand the severity of partial discharges and take appropriate maintenance measures to ensure the safe operation of equipment. For partial discharge maintenance points that match the third partial discharge level, the system generates maintenance information containing emergency maintenance levels. This can quickly attract the attention of maintenance personnel and ensure that timely measures can be taken in emergency situations to prevent the expansion of faults. By matching partial discharge characteristic information with partial discharge levels and generating corresponding maintenance information based on the matching results, the system can provide maintenance personnel with more accurate and specific guidance. This helps improve maintenance efficiency and reduce the risk of equipment failure caused by misjudgment or missed judgment.

[0131] The maintenance information generated by the system includes key information such as maintenance location information, inspection display images, and maintenance level, which can provide comprehensive decision-making support for managers. Managers can reasonably dispatch maintenance resources according to the severity and urgency of the maintenance information to ensure the smooth progress of maintenance work.

[0132] More preferably, the coordinate transformation of the spatial position information set to determine the actual pixel position of each abnormal temperature area in the inspection image includes:

[0133] Determine a first pixel resolution corresponding to the image acquired by the infrared camera and determine a second pixel resolution corresponding to the image acquired by the visible light camera;

[0134] The spatial position information set is subjected to coordinate transformation according to a coordinate transformation formula to determine the actual pixel position of each abnormal temperature area in the inspection image. The coordinate transformation formula is:

[0135] Y2=Y1*(H2 / H1), X2=X1*(W2 / W1);

[0136] Y2 is the Y-axis coordinate value in the visible light image coordinates, Y1 is the Y-axis coordinate value in the infrared thermal image coordinates, H1 is the vertical pixel value in the first pixel resolution, and H2 is the vertical pixel value in the second pixel resolution; X2 is the X-axis coordinate value in the visible light image coordinates, X1 is the X-axis coordinate value in the infrared thermal image coordinates, W1 is the horizontal pixel value in the first pixel resolution, and W2 is the horizontal pixel value in the second pixel resolution;

[0137] Or, the coordinate transformation of the spatial position information set to determine the actual pixel position of each abnormal temperature area in the inspection image includes:

[0138] The spatial position information set is subjected to coordinate transformation according to the infrared-visible light mapping relationship to determine the actual pixel position of each abnormal temperature area in the inspection image.

[0139] The embodiment of the present invention can accurately map the abnormal temperature area in the infrared thermal image to the actual pixel position in the visible light image by determining the pixel resolution corresponding to the images acquired by the infrared camera and the visible light camera respectively, and converting them using the coordinate conversion formula. This pixel-level precise positioning helps maintenance personnel to accurately find the abnormal area and improve maintenance efficiency and accuracy.

[0140] The coordinate conversion formula takes into account the fact that the infrared camera and the visible light camera may have different pixel resolutions. This compatibility allows the system to be flexibly applied to camera combinations with different resolutions without the need for additional calibration or adjustment of the cameras. The application of the coordinate conversion formula simplifies the complexity of coordinate conversion. Through simple mathematical operations, the coordinate conversion between infrared thermal images and visible light images can be achieved, reducing the difficulty and cost of technical implementation.

[0141] In addition to the coordinate conversion formula based on pixel resolution, the embodiment of the present invention also provides a coordinate conversion method based on infrared-visible light mapping relationship. This method may involve more complex algorithms or models, but can more accurately reflect the correspondence between infrared thermal images and visible light images, especially in complex scenes or nonlinear mapping relationships.

[0142] By providing two coordinate conversion methods, the system can select the most appropriate conversion method according to actual needs. This enhances the flexibility and adaptability of the system and can cope with application requirements under different scenarios and conditions. Through the automated coordinate conversion process, the system can quickly generate maintenance images containing the actual pixel locations of abnormal temperature areas. This helps maintenance personnel quickly locate problem areas and improve the intelligence level and efficiency of maintenance work.

[0143] The partial discharge detection method based on acoustic signals and thermal imaging in the embodiment of the present invention combines multiple information sources such as acoustic signals, visible light images and infrared thermal images, and realizes automatic identification and positioning of partial discharge points through technical means such as algorithm processing and image superposition. This intelligent detection method not only improves the accuracy and efficiency of detection, but also reduces the dependence on manual intervention, and improves the intelligence level of the entire detection system.

[0144] Embodiment 2

[0145] See also Figure 5 , Figure 5 Schematic diagram of the structure of the partial discharge detection system based on acoustic signals and thermal imaging disclosed in the embodiment of the present invention. Figure 5 As shown, the partial discharge detection system based on acoustic signals and thermal imaging may include:

[0146] The voiceprint acquisition module 21 is used to acquire the sound information in the current scene by means of a microphone array set in the first signal acquisition frequency band, and pre-process the sound information to obtain the sound information after noise reduction filtering; the microphone array is composed of a plurality of sound sensors, and the positions of the plurality of sound sensors are different, and the microphone array is used to receive sound information from all directions;

[0147] The point determination module 22 is used to analyze and process the sound information after noise reduction filtering to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map according to the location information of the sound source;

[0148] Image acquisition module 23: used to acquire the maintenance image of the current scene through the visible light camera, and to superimpose the sound source point map and the maintenance image to obtain a partial discharge display image according to the mapping relationship between the image acquired by the visible light camera and the sound point acquired by the microphone;

[0149] The judgment module 24 is used for executing the next step if the number of the local discharge points detected in the local discharge display image is greater than or equal to two, and for displaying the superimposed local discharge display image if the number of the local discharge points detected in the local discharge display image is one;

[0150] Infrared image acquisition module 25: used to acquire an infrared thermal image having the same viewing angle as the visible light camera through an infrared camera, and perform thermal image analysis processing on the infrared thermal image to determine a corresponding abnormal temperature area;

[0151] Coordinate updating module 26: used to obtain a spatial position information set corresponding to the abnormal temperature area if the abnormal temperature area matches the set discharge mode, perform coordinate transformation on the spatial position information set to determine the actual pixel position of each abnormal temperature area in the maintenance image, and update and display the maintenance image or partial discharge display image according to the actual pixel position.

[0152] The partial discharge detection method based on acoustic signals and thermal imaging in the embodiment of the present invention combines multiple information sources such as acoustic signals, visible light images and infrared thermal images, and realizes automatic identification and positioning of partial discharge points through technical means such as algorithm processing and image superposition. This intelligent detection method not only improves the accuracy and efficiency of detection, but also reduces the dependence on manual intervention, and improves the intelligence level of the entire detection system.

[0153] Embodiment 3

[0154] See also Figure 6 , Figure 6 Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. The electronic device may be a computer, a server, etc. Of course, in certain circumstances, it may also be a smart device such as a mobile phone, a tablet computer, a monitoring terminal, and an image acquisition device with processing functions. Figure 6 As shown, the electronic device may include:

[0155] A memory 510 storing executable program codes;

[0156] a processor 520 coupled to the memory 510;

[0157] The processor 520 calls the executable program code stored in the memory 510 to execute part or all of the steps in the partial discharge detection method based on acoustic signals and thermal imaging in the first embodiment.

[0158] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute part or all of the steps in the partial discharge detection method based on acoustic signals and thermal imaging in Embodiment 1.

[0159] The embodiment of the present invention further discloses a computer program product, wherein when the computer program product is run on a computer, the computer executes part or all of the steps in the partial discharge detection method based on acoustic signals and thermal imaging in embodiment one.

[0160] An embodiment of the present invention further discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes part or all of the steps in the partial discharge detection method based on acoustic signals and thermal imaging in embodiment one.

[0161] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0162] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0163] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0164] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the method described in each embodiment of the present invention.

[0165] In the embodiments provided by the present invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0166] A person of ordinary skill in the art can understand that some or all of the steps in the various methods of the embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0167] The above is a detailed introduction to the partial discharge detection method, system, electronic device and storage medium based on acoustic signals and thermal imaging disclosed in the embodiments of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A partial discharge detection method based on acoustic signals and thermal imaging, characterized in that: include: Acquiring sound information in a current scene by using a microphone array set in a first signal acquisition frequency band, and preprocessing the sound information to obtain sound information that has been subjected to noise reduction filtering; The microphone array is composed of a plurality of sound sensors, the positions of the plurality of sound sensors are different, and the microphone array is used to receive sound information from all directions; Analyze and process the sound information after noise reduction filtering to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map based on the location information of the sound source; Acquire the maintenance image of the current scene through the visible light camera, and superimpose the sound source point map and the maintenance image to obtain a partial discharge display image according to the mapping relationship between the image collected by the visible light camera and the sound point collected by the microphone; If the number of local discharge points detected in the partial discharge display image is greater than or equal to two, the next step is executed; if the number of local discharge points detected in the partial discharge display image is one, the superimposed partial discharge display image is displayed; Acquire an infrared thermal image having the same viewing angle as the visible light camera through an infrared camera, and perform thermal image analysis processing on the infrared thermal image to determine a corresponding abnormal temperature area; If the abnormal temperature area matches the set discharge mode, a spatial position information set corresponding to the abnormal temperature area is obtained, and the coordinate transformation of the spatial position information set is performed to determine the actual pixel position of each abnormal temperature area in the maintenance image, and the maintenance image or partial discharge display image is updated and displayed according to the actual pixel position.

2. The partial discharge detection method based on acoustic signals and thermal imaging according to claim 1, characterized in that: The microphone array includes 136 MIC spiral arrays to acquire sound signals; the sound information after noise reduction filtering is analyzed and processed to determine the location information of the sound source in the current detection environment, and a corresponding sound source point map is generated according to the location information of the sound source, including: Analyze and process the sound information after noise reduction filtering to determine the time information when the sound source arrives at each sound sensor in the microphone array; Calculate the time difference between the sound signal arriving at each sound sensor in the microphone array; The location information of the sound source in the current detection environment is determined according to the calculated time difference and the preset sound source calculation formula; the sound source calculation formula is: Where θ is the direction angle of the sound source, δ is the distance between the two microphones, c is the speed of sound, and Δt is the time difference between the sound source signal reaching the two microphones; Generate a corresponding sound source point map based on the location information of the sound source.

3. The partial discharge detection method based on acoustic signals and thermal imaging according to claim 1, characterized in that: After the partial discharge display image obtained by superimposing is displayed if the number of the partial discharge point detected in the partial discharge display image is one, the method further includes: Performing feature analysis on the sound information after noise reduction filtering to determine corresponding frequency feature information and amplitude feature information; Performing state evaluation on the frequency characteristic information and amplitude characteristic information obtained by analysis to determine a first state parameter of a corresponding partial discharge point; After the spatial position information set is subjected to coordinate transformation to determine the actual pixel position of each abnormal temperature area in the inspection image, the method further includes: Preprocessing the infrared thermal image to obtain processed infrared image data, obtaining pixel point parameters of each data point in the infrared image data, and determining the grayscale difference and gradient difference between the corresponding data point and the adjacent data point based on the pixel point parameters of each data point; Determine the grayscale difference and gradient difference between the corresponding data point and the adjacent data point according to the pixel point parameters of each data point to determine the corresponding mutation parameter, wherein the mutation parameter is determined by the grayscale difference and gradient difference; Determine parameter difference information between each data point and other data points according to the mutation parameters of each data point in the obtained infrared image data, and determine regional association information between each data point and other data points according to the parameter difference information; Clustering the infrared image data according to the regional association information of each data point and other data points to determine the corresponding regional information; and extracting the features of the regional information to obtain the regional feature information; The regional characteristic information meeting the set requirements is output, and the second state parameter of the corresponding partial discharge point is determined according to the regional characteristic information.

4. The partial discharge detection method based on acoustic signals and thermal imaging according to claim 3, characterized in that: The partial discharge detection method further includes: Receive a data analysis area selected by a user, perform statistics on parameters in the data analysis area to determine corresponding statistical parameter information, the statistical parameter information includes maximum temperature information and minimum temperature information, and the data analysis area is a rectangular analysis area; The partial discharge detection method further includes: The defect level of the corresponding partial discharge point is determined according to the first state parameter and / or the second state parameter, and the corresponding defect level is output.

5. The partial discharge detection method based on acoustic signals and thermal imaging according to claim 1, characterized in that: Before acquiring the sound information in the current scene by using the microphone array set in the first signal acquisition frequency band, the method further includes: Receiving voiceprint signals collected by a sound collection device of the unmanned aerial vehicle set in a second signal collection frequency band at each inspection point on the inspection route; the frequency band range of the second signal collection frequency band is greater than the frequency band range of the first signal collection frequency band; Analyze and process the noise reduction filtered voiceprint signal to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map based on the location information of the sound source; The inspection image of the current scene is acquired through a visible light camera, and the sound source point map and the inspection image are superimposed to obtain an inspection display image according to the mapping relationship between the image acquired by the visible light camera and the sound point acquired by the microphone; Identify the inspection display image to determine whether there is a corresponding partial discharge maintenance point in the inspection display image, and if so, obtain the current flight position information of the unmanned aerial vehicle, and generate corresponding maintenance information according to the current flight position information and the inspection display image; The maintenance information is sent to a background server, wherein the maintenance information includes maintenance location information and inspection display images.

6. The partial discharge detection method based on acoustic signals and thermal imaging according to claim 5, characterized in that: The step of identifying the inspection display image to determine whether there is a corresponding partial discharge maintenance point in the inspection display image, and if so, obtaining the current flight position information of the unmanned aerial vehicle, and generating corresponding maintenance information according to the current flight position information and the inspection display image, includes: Identify the inspection display image to determine whether there is a corresponding partial discharge maintenance point in the inspection display image; Acquire partial discharge characteristic information associated with the partial discharge maintenance point, and match the partial discharge characteristic information with a preset partial discharge level, and if the partial discharge characteristic information matches a first partial discharge level, do not generate corresponding maintenance information; If the partial discharge characteristic information matches the second partial discharge level, the current flight position information of the unmanned aerial vehicle is obtained, and corresponding maintenance information is generated according to the current flight position information and the inspection display image, wherein the maintenance information also includes a general maintenance level; If the partial discharge characteristic information matches the third partial discharge level, the current flight position information of the unmanned aerial vehicle is obtained, and corresponding maintenance information is generated according to the current flight position information and the inspection display image, and the maintenance information also includes an emergency maintenance level.

7. The partial discharge detection method based on acoustic signals and thermal imaging according to claim 1, characterized in that: The coordinate transformation of the spatial position information set to determine the actual pixel position of each abnormal temperature area in the inspection image includes: Determine a first pixel resolution corresponding to the image acquired by the infrared camera and determine a second pixel resolution corresponding to the image acquired by the visible light camera; The spatial position information set is subjected to coordinate transformation according to a coordinate transformation formula to determine the actual pixel position of each abnormal temperature area in the inspection image. The coordinate transformation formula is: Y2=Y1*(H2 / H1), X2=X1*(W2 / W1); Y2 is the Y-axis coordinate value in the visible light image coordinates, Y1 is the Y-axis coordinate value in the infrared thermal image coordinates, H1 is the vertical pixel value in the first pixel resolution, and H2 is the vertical pixel value in the second pixel resolution; X2 is the X-axis coordinate value in the visible light image coordinates, X1 is the X-axis coordinate value in the infrared thermal image coordinates, W1 is the horizontal pixel value in the first pixel resolution, and W2 is the horizontal pixel value in the second pixel resolution; Or, the coordinate transformation of the spatial position information set to determine the actual pixel position of each abnormal temperature area in the inspection image includes: The spatial position information set is subjected to coordinate transformation according to the infrared-visible light mapping relationship to determine the actual pixel position of each abnormal temperature area in the inspection image.

8. A partial discharge detection system based on acoustic signals and thermal imaging, characterized in that: include: A voiceprint acquisition module: used to acquire the sound information in the current scene through a microphone array set in the first signal acquisition frequency band, and pre-process the sound information to obtain the sound information after noise reduction filtering; The microphone array is composed of a plurality of sound sensors, the positions of the plurality of sound sensors are different, and the microphone array is used to receive sound information from all directions; Point determination module: used to analyze and process the sound information after noise reduction filtering to determine the location information of the sound source in the current detection environment, and generate a corresponding sound source point map based on the location information of the sound source; Image acquisition module: used to acquire the maintenance image of the current scene through the visible light camera, and to superimpose the sound source point map and the maintenance image to obtain a partial discharge display image according to the mapping relationship between the image acquired by the visible light camera and the sound point acquired by the microphone; A judgment module: for executing the next step if the number of local discharge points detected in the partial discharge display image is greater than or equal to two, and for displaying the partial discharge display image obtained by superimposing if the number of local discharge points detected in the partial discharge display image is one; Infrared image acquisition module: used to acquire an infrared thermal image having the same viewing angle as the visible light camera through an infrared camera, and perform thermal image analysis processing on the infrared thermal image to determine the corresponding abnormal temperature area; Coordinate updating module: used to obtain a spatial position information set corresponding to the abnormal temperature area if the abnormal temperature area matches the set discharge mode, perform coordinate transformation on the spatial position information set to determine the actual pixel position of each abnormal temperature area in the maintenance image, and update the maintenance image or partial discharge display image according to the actual pixel position.

9. An electronic device, characterized in that: include: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the partial discharge detection method based on acoustic signals and thermal imaging as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute the partial discharge detection method based on acoustic signals and thermal imaging according to any one of claims 1 to 7.

Images