Method and apparatus for locating partial discharge in transformers

Abstract

This invention discloses a method and apparatus for locating partial discharge in transformers. The method includes: acquiring pulse current signals from multiple first preset locations on the target transformer, constructing polarity feature vectors to determine whether partial discharge exists inside the target transformer; after confirming internal partial discharge, acquiring the arrival times of acoustic signals from multiple second preset locations on the target transformer, determining the first coordinates of the partial discharge source inside the target transformer in a first preset coordinate system; based on preset original point cloud data of the target transformer, converting the first coordinates into second coordinates in a second preset coordinate system, and displaying the position of the second coordinates in the second preset coordinate system. This application achieves integrated detection with instant scanning, automatic alignment, and perspective visualization, significantly improving fault location accuracy and maintenance efficiency.

Description

Technical Field

[0001] This invention relates to the field of partial discharge detection in transformers, and more specifically, to a method and apparatus for locating partial discharge in transformers. Background Technology

[0002] Power transformers are core equipment in power grid systems, and their insulation condition directly affects the safe and stable operation of the power system. Partial discharge, as an early sign of transformer insulation deterioration, is a major cause of insulation breakdown and sudden faults. Therefore, conducting live partial discharge detection on operating transformers and achieving precise spatial location of the discharge source is a key technical means to prevent major equipment accidents and ensure the reliable operation of the power grid.

[0003] Currently, the mainstream partial discharge detection technologies in the power industry mainly include the High-Frequency Current Transformer (HFCT), Ultra-High Frequency (UHF), and Acoustic Emission (AE). Among them, the acoustic-electric joint localization technology based on UHF and AE signals has been widely used in the three-dimensional localization of partial discharge sources inside transformers due to its strong anti-electromagnetic interference capability and relatively high spatial positioning accuracy.

[0004] However, in practical engineering applications, existing partial discharge location systems generally suffer from abstract location results and a lack of intuitive physical references. Maintenance personnel can usually only obtain a set of abstract three-dimensional mathematical coordinates based on the sensor array, making it difficult to quickly and accurately map these coordinates to the specific physical structure of the transformer body (e.g., is it located on the surface of the high-voltage winding, near the tap changer lead, or in the core clamping area?), which severely restricts the efficiency and accuracy of fault diagnosis.

[0005] There is currently no effective solution to the above problems. Summary of the Invention

[0006] This invention provides a method and apparatus for locating partial discharge in transformers, which at least solves the technical problems of traditional methods relying on drawings, large errors in manual calibration, and invisible positioning results, resulting in low positioning accuracy and poor maintenance efficiency.

[0007] According to one aspect of the present invention, a method for locating partial discharge in a transformer is provided, comprising: acquiring pulse current signals of a target transformer at multiple first preset locations; determining a polarity feature vector based on the pulse current signals at the multiple first preset locations, wherein the polarity feature vector characterizes the polarity state of the pulse current at the multiple preset locations; determining whether partial discharge exists inside the target transformer based on the polarity feature vector; if partial discharge exists inside the target transformer, acquiring the arrival time of acoustic signals at multiple second preset locations of the target transformer; determining a first coordinate of a partial discharge source inside the target transformer in a first preset coordinate system based on the arrival time of the acoustic signals at the multiple second preset locations of the target transformer; converting the first coordinate into a second coordinate in a second preset coordinate system based on preset original point cloud data of the target transformer, and displaying the position of the second coordinate in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

[0008] Optionally, the multiple first preset locations include: the end screen grounding wire of the three-phase bushing on the high-voltage side of the target transformer, the neutral point grounding wire of the target transformer, the core grounding wire of the target transformer, the clamp grounding wire of the target transformer, the auxiliary grounding point of the target transformer housing, and the low-voltage side grounding wire of the target transformer housing.

[0009] Optionally, based on the pulse current signals at multiple first preset locations, a polarity feature vector is determined, including: within a preset time window, determining the first pulse waveform corresponding to the pulse current signals at each of the multiple first preset locations; extracting the polarity of the first pulse waveform to form a polarity feature vector, wherein the polarity includes positive polarity, negative polarity, or no polarity, positive polarity indicates that the pulse current flows from the target transformer to the ground, negative polarity indicates that the pulse current flows from the ground to the target transformer, and no polarity indicates that there is no significant signal.

[0010] Optionally, based on the polarity feature vector, determining whether there is partial discharge inside the target transformer includes: determining that there is no partial discharge inside the target transformer when all elements in the polarity feature vector are positive; or determining that there is partial discharge inside the target transformer when the elements in the polarity feature vector include both positive and negative polarities.

[0011] Optionally, based on the arrival times of the acoustic signals at multiple second preset locations of the target transformer, the first coordinate of the partial discharge source inside the target transformer in the first preset coordinate system is determined, including: constructing and solving a set of nonlinear positioning equations to obtain the first coordinate, wherein the mathematical expression of the set of nonlinear positioning equations is as follows:

[0012] ,

[0013] As the first coordinate, The coordinates of the ultrasonic sensor used to acquire sound wave signals are given, and the ultrasonic sensor is positioned at a second preset position. The speed of sound wave signal propagation. The arrival time of the sound wave signal. This is the first arrival time of the pulse current signal. This is the preset delay time.

[0014] Optionally, based on the preset original point cloud data of the target transformer, the first coordinates are converted into second coordinates in a second preset coordinate system, and the position of the second coordinates is displayed in the second preset coordinate system. This includes: locating the positions of multiple ultrasonic sensors used to acquire acoustic signals in the original point cloud data based on preset feature identifiers, obtaining the centroid coordinates of multiple point cloud clusters; matching the centroid coordinates of the multiple point cloud clusters with the coordinates of the multiple ultrasonic sensors in the first preset coordinate system, obtaining multiple point pairs; calculating the rotation matrix and translation vector for coordinate transformation based on the multiple point pairs; and converting the first coordinates into the second coordinates based on the rotation matrix and translation vector.

[0015] According to another aspect of the present invention, a partial discharge locating device for a transformer is also provided, comprising: a first acquisition module, configured to acquire pulse current signals of a target transformer at a plurality of first preset locations; a first determination module, configured to determine a polarity feature vector based on the pulse current signals at the plurality of first preset locations, wherein the polarity feature vector characterizes the polarity state of the pulse current at the plurality of preset locations; a judgment module, configured to determine whether a partial discharge exists inside the target transformer based on the polarity feature vector; a second acquisition module, configured to acquire the arrival time of acoustic signals at a plurality of second preset locations of the target transformer when a partial discharge exists inside the target transformer; a second determination module, configured to determine a first coordinate of a partial discharge source inside the target transformer in a first preset coordinate system based on the arrival time of the acoustic signals at the plurality of second preset locations of the target transformer; and a conversion module, configured to convert the first coordinates into second coordinates in a second preset coordinate system based on preset original point cloud data of the target transformer, and display the position of the second coordinates in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

[0016] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-described partial discharge location methods for transformers.

[0017] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor, the processor being configured to run a program, wherein the program, when running, executes any of the above-described methods for locating partial discharge of a transformer.

[0018] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the above-described methods for locating partial discharge in a transformer.

[0019] In this embodiment of the invention, a partial discharge location method for transformers is adopted. By acquiring the pulse current signals of the target transformer at multiple first preset locations, a polarity feature vector is constructed to determine whether there is a partial discharge inside the target transformer. After confirming the internal partial discharge, the arrival time of the acoustic signals of the target transformer at multiple second preset locations is acquired to determine the first coordinate of the partial discharge source inside the target transformer in a first preset coordinate system. Based on the preset original point cloud data of the target transformer, the first coordinate is converted into a second coordinate in a second preset coordinate system, and the position of the second coordinate is displayed in the second preset coordinate system. This achieves the purpose of accurately mapping the abstract electroacoustic location coordinates to the three-dimensional real scene model of the actual equipment on site, thereby realizing the technical effect of transparent, visual, and accurate location of the partial discharge source in the transformer body structure. This solves the technical problems of traditional methods relying on drawings, large errors in manual calibration, and invisible location results, which lead to low location accuracy and poor maintenance efficiency. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0021] Figure 1 A hardware block diagram of a computer terminal for implementing a partial discharge location method for transformers is shown.

[0022] Figure 2 This is a schematic flowchart of a partial discharge location method for a transformer provided according to an embodiment of the present invention;

[0023] Figure 3 This is a structural block diagram of a partial discharge locating device for a transformer provided according to an embodiment of the present invention. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] According to an embodiment of the present invention, a method embodiment for locating partial discharge in a transformer is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a partial discharge location method for transformers is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0028] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the partial discharge location method for transformers in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned application program for the partial discharge location method for transformers. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0031] Figure 2 This is a flowchart illustrating a partial discharge location method for a transformer according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0032] Step S201: Obtain the pulse current signals of the target transformer at multiple first preset positions.

[0033] This step involves deploying high-frequency current sensors (HFCTs) at multiple key grounding nodes of the transformer (e.g., the high-voltage side A / B / C three-phase bushing end screens, neutral point, core, clamps, and low-voltage side auxiliary grounding point) to simultaneously acquire microampere-level pulse current signals generated by partial discharge. HFCTs are non-invasive sensors, and their sensing direction is uniformly defined as pointing towards the transformer body as positive, used to accurately capture the current flow direction. This step provides the raw time-domain signal input for subsequent polarity identification.

[0034] Step S202: Based on the pulse current signals at multiple first preset positions, determine the polarity feature vector, wherein the polarity feature vector represents the polarity state of the pulse current at multiple preset positions.

[0035] This step performs synchronous window locking and first pulse polarity extraction on the 8-channel HFCT signal acquired in step S201, generating an eight-dimensional polarity feature vector. ,in These represent whether the pulse in this channel is positive, negative, or has no significant signal, respectively. This polarity eigenvector is a "topological fingerprint" reflecting the loop structure of the partial discharge current in the transformer grounding system, providing a quantitative basis for subsequent determination of the discharge source based on the physical loop model.

[0036] Step S203: Based on the polarity feature vector, determine whether there is partial discharge inside the target transformer.

[0037] Based on the polarity characteristic vector determined in step S202, this step makes a logical judgment based on the difference in current loops formed by internal partial discharge and external interference in the grounding system: if the high-voltage side (p1–p3) in the polarity characteristic vector is positive (outflow) while the neutral point / core / clamp (p4–p6) is negative (inflow), it is determined to be internal partial discharge, and its current forms a closed loop from the transformer body to the ground and back to the transformer body; if all signal channels are positive (all outflow), it is determined to be external corona discharge or electromagnetic interference. This judgment mechanism is based on the electrical topology of the transformer body and has strong physical meaning and anti-false alarm capability.

[0038] Step S204: In the case of partial discharge inside the target transformer, obtain the arrival time of the acoustic signal at multiple second preset positions of the target transformer.

[0039] After confirming the internal partial discharge in step S203, the ultrasonic sensor (AE) positioning module is activated to record the arrival time of the acoustic waves from each sensor relative to the zero point of the ultra-high frequency (UHF) signal. The UHF sensor is installed at the transformer oil valve port to capture the electromagnetic wave signal generated by the partial discharge, serving as the time reference for acoustic-electric joint positioning. The ultrasonic sensor (AE) is magnetically attached to the transformer tank wall surface to capture the acoustic wave signal generated by the partial discharge. This step acquires the time difference data required for acoustic positioning, which is the input parameter for subsequent three-dimensional spatial positioning.

[0040] In this step, the electromagnetic wave signal acquired by the ultra-high frequency (UHF) sensor can be used as the zero point of time. The spatial coordinates of 12 ultrasonic sensors (AEs) have been pre-calibrated and fixed in a first preset coordinate system (i.e., the sensor array coordinate system), forming the spatial reference points of the positioning network. The times when the 12 ultrasonic sensors capture sound wave signals are obtained. .

[0041] Step S205: Based on the arrival time of the acoustic signals of the target transformer at multiple second preset positions, determine the first coordinate of the partial discharge power source inside the target transformer in the first preset coordinate system.

[0042] This step utilizes the time difference of arrival (TDOA) information of sound waves collected by an ultrasonic sensor array to calculate the three-dimensional position of the partial discharge source in the first preset coordinate system (local spatial coordinate system) defined by the sensor array using the time difference of arrival (TDOA) principle. This provides the basic positioning results for subsequent coordinate registration with the real-world 3D model. This coordinate system is independent of the transformer's physical structure and is only related to the relative layout of the sensors, serving as an intermediate bridge connecting the electroacoustic detection data and the spatial visualization system.

[0043] Step S206: Based on the original point cloud data of the preset target transformer, the first coordinate is converted into the second coordinate in the second preset coordinate system, and the position of the second coordinate is displayed in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

[0044] This step utilizes a SLAM (Simultaneous Localization and Mapping) system to scan the transformer body using LiDAR and an RGB-D camera before inspection, constructing a high-precision 3D point cloud model that includes the outer shell, radiator, bushings, oil conservator, and other structures. This model, based on the real-world coordinate system, achieves "what you see is what you get" 3D visualization of the real-world scene. The portable SLAM scanning terminal is used for spatial reconstruction of the transformer's on-site environment, including an environmental perception module integrating a multi-line LiDAR and an RGB-D depth camera. The LiDAR acquires high-precision spatial point clouds, while the depth camera acquires texture information and identifies visual labels on the sensor surfaces. The inertial measurement unit (IMU) provides attitude data during the scanning process to assist the SLAM algorithm in mapping.

[0045] This application discloses a method and apparatus for locating partial discharge in a transformer. By acquiring pulse current signals of the target transformer at multiple first preset locations, a polarity feature vector is constructed to determine whether there is partial discharge inside the target transformer. After confirming internal partial discharge, the arrival times of acoustic signals at multiple second preset locations of the target transformer are acquired to determine the first coordinate of the partial discharge source inside the target transformer in a first preset coordinate system. Based on the preset original point cloud data of the target transformer, the first coordinate is converted into a second coordinate in a second preset coordinate system, and the position of the second coordinate is displayed in the second preset coordinate system. This method achieves for the first time a three-dimensional real-scene location of partial discharge in a transformer that is "without drawings, without manual calibration, and with anti-interference and accurate perspective".

[0046] As an optional embodiment, the multiple first preset locations include: the end screen grounding wire of the high-voltage side three-phase bushing of the target transformer, the neutral point grounding wire of the target transformer, the core grounding wire of the target transformer, the clamp grounding wire of the target transformer, the auxiliary grounding point of the target transformer housing, and the low-voltage side grounding wire of the target transformer housing.

[0047] In this step, before performing the judgment, the installation positions and sensing directions of the eight high-frequency current sensors (HFCTs) must be clearly defined, as this is the basis for polarity determination. Installation positions (8 monitoring points): Monitoring points 1-3 are installed on the final screen grounding wires of the three-phase bushings (A, B, and C phases) on the high-voltage side of the transformer; monitoring point 4 is installed on the neutral point grounding wire of the transformer. Monitoring point 5 is installed on the transformer core grounding wire; monitoring point 6 is installed on the transformer clamp grounding wire; monitoring points 7-8 are installed on the auxiliary grounding point of the transformer tank / oil tank or the low-voltage side grounding wire. Simultaneously, it is uniformly stipulated that the polarity end of all HFCT sensors points towards the transformer body side, and the non-polarity end points towards the ground side (grounding grid). When the high-frequency pulse current flows from the transformer body to the ground, the sensor output is a positive polarity pulse; conversely, when it flows from the ground to the transformer body, the output is a negative polarity pulse.

[0048] As an optional embodiment, the polarity feature vector is determined based on the pulse current signals at multiple first preset locations, including: within a preset time window, determining the first pulse waveform corresponding to the pulse current signals at each of the multiple first preset locations; extracting the polarity of the first pulse waveform to form a polarity feature vector, wherein the polarity includes positive polarity, negative polarity, or no polarity, positive polarity indicates that the pulse current flows from the target transformer to the ground, negative polarity indicates that the pulse current flows from the ground to the target transformer, and no polarity indicates that there is no significant signal.

[0049] This step uses a high-speed data acquisition system to synchronously sample the pulse current signals collected by eight high-frequency current sensors (HFCTs). When the signal amplitude of any channel first exceeds a preset threshold (e.g., 50mV), a microsecond-level time window (typically 10–50μs) is automatically locked to capture the first valid pulse waveform of each channel within that window. Then, the polarity of the first pulse waveform of each extracted channel is determined: if the first peak is a positive peak, indicating current flowing from the transformer body through the HFCT to the grounding grid, it is determined to be "positive polarity" (+); if the first trough is a negative peak, indicating current flowing from the grounding grid back into the transformer body, it is determined to be "negative polarity" (-); if the signal amplitude does not reach the threshold or there are no obvious pulse characteristics, it is marked as "no polarity" (0). The first pulse waveform of each channel within the time window is analyzed to extract the polarity of its first peak / trough. A polarity feature vector is generated. ,in The positive and negative distribution of this polarity eigenvector directly maps the physical path of the discharge current—flowing out from the high-voltage side and flowing into the neutral point / core—and is an important criterion for distinguishing between real partial discharge and external electromagnetic interference.

[0050] As an optional embodiment, determining whether there is partial discharge inside the target transformer based on the polarity feature vector includes: determining that there is no partial discharge inside the target transformer when all elements in the polarity feature vector are positive; or determining that there is partial discharge inside the target transformer when the elements in the polarity feature vector include both positive and negative polarities.

[0051] In this step, based on the polarity eigenvector determined in step S202, when all channels with significant signals in the polarity eigenvector exhibit "positive polarity," it indicates that the pulse signal has not formed a closed loop. Its energy source is not internal insulation defects in the transformer, but more likely originates from external electromagnetic interference, such as corona discharge from nearby lines, transient switching operations, or partial discharge of GIS. External interference signals typically enter through transmission lines or are simultaneously induced on all conductors as spatial electromagnetic waves. These signals flow uniformly to the ground through all grounding channels of the transformer (bushings, neutral point, core). If the eigenvector... In the process, all channels with signals are displayed as positive polarity (or all are in the same direction). Based on this, the system determines that the event is external interference and filters it out, without triggering subsequent positioning procedures.

[0052] When a mixed characteristic of "positive polarity" and "negative polarity" appears in the polarity eigenvector, it indicates that the discharge pulse occurred at a weak point in the transformer's internal insulation, such as a winding to ground fault, tap changer insulation failure, or damage to the lead shielding layer, forming a closed loop of high-frequency current: the current flows out of the transformer body from the high-voltage side (such as the end screen of the A / B / C phase bushing) through capacitive coupling (HFCT detection shows positive polarity). To maintain current continuity, it must flow back into the transformer body through the grounding grid via a low-impedance path such as the neutral point, core, or clamps (corresponding to negative polarity detected by HFCT). This coexistence of positive and negative polarities is a unique electrical topology characteristic of partial discharge inside the transformer, distinguishing it from the unidirectional conduction mode of any external interference. If the eigenvector... The system exhibits a clear mixture of positive and negative polarities. High-voltage bushing monitoring points (monitoring points 1-3) show positive polarity (outflow); while the neutral point (monitoring point 4) or the core / clamp (monitoring points 5-6) shows negative polarity (inflow). This is determined to be a genuine internal partial discharge, activating the subsequent acoustic-electric joint localization and 3D real-scene mapping process. This criterion is based on the physical structure of the transformer grounding system and the principle of electromagnetic circuit conservation, possessing strong robustness, high specificity, and engineering feasibility.

[0053] As an optional embodiment, determining the first coordinate of the partial discharge source inside the target transformer in a first preset coordinate system based on the arrival time of the acoustic signals at multiple second preset locations of the target transformer includes: constructing and solving a set of nonlinear positioning equations to obtain the first coordinate, wherein the mathematical expression of the set of nonlinear positioning equations is as follows:

[0054] ,

[0055] As the first coordinate, The coordinates of the ultrasonic sensor used to acquire sound wave signals are given, and the ultrasonic sensor is positioned at a second preset position. The speed of sound wave signal propagation. The arrival time of the sound wave signal. This is the first arrival time of the pulse current signal. This is the preset delay time.

[0056] In this step, after confirming the internal discharge, the position of the discharge source in the "sensor array coordinate system" is calculated:

[0057] First, based on the arrival times of the acoustic signals from the target transformer at multiple second preset positions, a system of nonlinear equations is constructed:

[0058]

[0059] in, Let the coordinates of the local point be to be determined. For the first The relative coordinates of the ultrasonic sensors Let be the speed of sound propagation in oil. Then, the equations are solved using Newton's iteration method or a genetic algorithm to obtain the partial discharge source. Coordinates in the first coordinate system (sensor relative coordinate system) This is the first coordinate, which reflects the relative spatial position of the discharge source with respect to the sensor array.

[0060] As an optional embodiment, based on the original point cloud data of a preset target transformer, the first coordinates are converted into second coordinates in a second preset coordinate system, and the position of the second coordinates is displayed in the second preset coordinate system. This includes: locating the positions of multiple ultrasonic sensors used to acquire acoustic signals in the original point cloud data based on preset feature identifiers, obtaining the centroid coordinates of multiple point cloud clusters; matching the centroid coordinates of the multiple point cloud clusters with the coordinates of the multiple ultrasonic sensors in the first preset coordinate system, obtaining multiple point pairs; calculating the rotation matrix and translation vector for coordinate transformation based on the multiple point pairs; and converting the first coordinates into the second coordinates based on the rotation matrix and translation vector.

[0061] In this step, firstly, using the 3D raw point cloud data of the transformer acquired by the SLAM scanning terminal, the physical locations of 12 ultrasonic sensors (AEs) are identified in a second preset coordinate system (real-world coordinate system). The operator moves the SLAM scanning terminal around the transformer, using a lidar odometry system and mapping algorithm to generate a sparse or dense point cloud map of the transformer casing and its auxiliary components (radiator, oil tank, pipes) in real time. The generated model is defined as the second coordinate system. To achieve automatic identification, multimodal feature markers are pre-set on the surface of the 12 ultrasonic sensor casings. These markers include geometric features (cylindrical protrusions) and optical features (highly reflective annular reflective bands). The system acquires the raw point cloud data obtained from the SLAM scan, uses a pass-through filter to remove background noise (such as ground and wall surfaces), and retains only the point cloud of the main transformer area. Using the lidar echo intensity information, a high intensity threshold is set to quickly extract the set of highly reflective point clouds on the sensor surfaces. Euclidean clustering is performed on the candidate point clouds to filter out points with a number within a preset range (…). to Point cloud clusters with cylindrical geometric shapes are selected as "candidate sensor points." Next, a spatial correspondence is established between the centroid coordinates of the identified sensors in the real-world coordinate system and the known physical coordinates of the ultrasonic sensors in the sensor array coordinate system. Since SLAM scanning may result in some sensors not being fully identified due to occlusion, motion blur, or sensor installation deviations (e.g., only 10 sensors are identified), the system does not rely on the physical identification labels of the sensors. Instead, it achieves unique association through topological matching: calculating the mutual spatial distance matrix between all identified centroid points and performing subgraph isomorphic matching with a preset "standard sensor layout distance matrix." Using graph matching algorithms (such as edge-weighted graph edit distance or RANSAC graph matching), the system can uniquely determine which sensor number corresponds to each point cloud cluster based solely on the relative spatial relationships of some points (e.g., point cloud cluster A corresponds to sensor number 3, B corresponds to sensor number 7, etc.), and assign the centroid coordinates of the identified point cloud clusters... With sensor logical number Bind them together to form a set of point-to-point pairs. This provides the minimum necessary matching points for subsequent rigid body transformations. Then, the system employs a robust registration algorithm, inputting the set of point pairs into the coordinate transformation solution module. First, the SVD (Singular Value Decomposition) algorithm is used to perform initial coarse registration of the point pair set, calculating the initial rotation matrix. (3×3) translation vector (1×3) to achieve global alignment of the two coordinate systems. Since SLAM mapping may suffer from drift, point cloud noise, or individual sensor recognition errors, the system further introduces the RANSAC (Random Sample Consensus) algorithm to remove outliers: three sets of point pairs are randomly selected to calculate the transformation model, and the reprojection error of the remaining point pairs after transformation is verified; this process is repeated multiple times, retaining those with errors less than a preset threshold. A set of interior points (e.g., 2mm) is established. Then, based on the high-quality interior points after outlier removal, the ICP (Iterative Closest Point) algorithm is used for nonlinear fine registration to optimize the matrix. and This minimizes the registration error. Finally, the obtained optimal transformation parameters are used... and The first coordinate of the local discharge power source calculated in step S205 in the first preset coordinate system is converted into the second coordinate in the second preset coordinate system (real scene three-dimensional coordinate system).

[0062] In addition, the system increases its reliability through dynamic error assessment and calibration feedback, and calculates the final root mean square error (RMSE):

[0063]

[0064] Feedback mechanisms include: If If the distance is 1.5cm, then registration is considered successful, and the coordinate system is locked. If the system determines that the registration is unreliable (possibly due to incomplete scanning or excessive movement), it will issue a prompt on the interactive interface saying "Please rescan the key areas" and highlight the sensor position with the largest deviation in different colors.

[0065] In addition, the central processing and visualization host is connected (wired) to the aforementioned sensors and terminals, and internally runs a polarity identification module, a TDOA calculation module, a point cloud registration module, and a 3D rendering engine. The system loads a semi-transparent transformer point cloud model into the visualization interface, and... A bright sphere or heat map is rendered at the location, with its color / size corresponding to the discharge amplitude (dB), achieving a "what you see is what you get" 3D real-world perspective display. Maintenance personnel can rotate and zoom the model at will, intuitively perceiving the specific physical areas where the discharge source is located, such as the upper part of the high-voltage winding, near the tap changer lead, or close to the tank wall, greatly improving the efficiency of fault diagnosis.

[0066] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0067] This application acquires pulse current signals from multiple first preset locations of the target transformer and constructs polarity feature vectors to determine whether partial discharge exists inside the target transformer. After confirming internal partial discharge, it acquires the arrival times of acoustic signals from multiple second preset locations of the target transformer and determines the first coordinate of the partial discharge source inside the target transformer in a first preset coordinate system. Based on the preset original point cloud data of the target transformer, the first coordinate is converted into a second coordinate in a second preset coordinate system, and the position of the second coordinate is displayed in the second preset coordinate system. This innovatively integrates three major technology modules: SLAM real-time mapping, automatic recognition of sensor visual features, and multi-terminal HFCT polarity identification. For the first time, it achieves three-dimensional real-scene positioning of transformer partial discharge that is "without drawings, without manual calibration, and with anti-interference and accurate perspective".

[0068] Compared with current technologies, the aforementioned method embodiments have the following advantages:

[0069] (1) Automatic high-precision registration of heterogeneous coordinate systems is achieved, completely eliminating manual calibration errors. Existing technology relies on maintenance personnel manually measuring the installation position of ultrasonic sensors on the transformer surface with a measuring tape and manually inputting the data into the host computer software. This operation is cumbersome, inefficient, and prone to centimeter-level or even decimeter-level spatial positioning deviations due to measurement errors and human oversights. This invention innovatively utilizes the high-reflectivity ring mark and cylindrical geometric features pre-set on the ultrasonic sensor shell to automatically identify its spatial position in the 3D point cloud reconstructed by SLAM, constructing a set of corresponding point pairs of the sensor between the first and second coordinate systems. Combined with robust algorithms of SVD initial registration, RANSAC outlier removal, and ICP fine registration, the rigid body transformation matrix is ​​automatically calculated, achieving seamless alignment of the two heterogeneous coordinate systems at the hardware and software levels. This process requires no manual intervention, improving the coordinate fusion accuracy from the traditional "coarse" to "fine," significantly enhancing the reliability of the local discharge power source positioning results.

[0070] (2) It eliminates the reliance on factory drawings, enabling "scan-and-use" real-scene modeling and dynamic adaptation. Existing visualization systems heavily rely on factory CAD or BIM drawings of transformers. For older equipment without electronic drawings, or transformers that have undergone on-site modifications resulting in discrepancies between the drawings and reality, the system cannot map them correctly, easily leading to misleading displays. This invention innovatively introduces SLAM (Simultaneous Localization and Mapping) technology, using a portable LiDAR and RGB-D depth camera to scan the transformer body and its auxiliary structures in real time, autonomously constructing a high-precision 3D point cloud model that is completely consistent with the actual object on site, achieving the real-scene reconstruction capability of "scanning to model, modeling to use". Regardless of the age of the equipment, whether electronic drawings are available, or whether structural modifications have occurred, model reconstruction can be completed within 5–10 minutes, accurately restoring the current operating status of the equipment, fundamentally solving the two major industry problems of missing drawings and discrepancies between drawings and reality.

[0071] (3) Transforming abstract location data into intuitive three-dimensional perspective information significantly improves fault diagnosis efficiency. Traditional detection systems output only abstract three-dimensional coordinate values ​​(XYZ) or two-dimensional waveforms. Maintenance personnel need to rely on experience to construct three-dimensional spatial relationships in their minds, which is time-consuming and has a high error rate. This invention directly maps and renders the coordinate-registered local discharge source location into the semi-transparent SLAM real-world three-dimensional point cloud model, and uses color gradients, light sphere size, or heat map forms to characterize the discharge intensity (dB), achieving a "what you see is what you get" perspective visualization effect. Maintenance personnel can intuitively see whether the discharge source is located on the upper part of the winding, at the tap changer, or near the lead wire, thereby quickly formulating maintenance strategies and reducing reliance on personnel experience.

[0072] (4) The joint anti-interference mechanism based on multi-source information fusion significantly reduces the false alarm rate. Existing equipment often only focuses on the strength of the partial discharge signal itself. In the high-interference environment of substations, it is easy to mistake external corona interference for internal faults. This invention combines the polarity discrimination logic of 8-channel HFCT. By comparing the polarity characteristics (inflow / outflow relationship) of the signals at each port, it can effectively distinguish the real partial discharge signal inside the transformer from the interference signal from the external line or space. Before starting the three-dimensional positioning, the physical level signal screening is performed to ensure that the system "only models the real internal partial discharge", effectively filtering out the false partial discharge points generated by external space electromagnetic interference, and ensuring the authenticity of the visualization results and the accuracy of the diagnosis.

[0073] (5) The algorithm is robust and adaptable to complex industrial environments. Traditional sensor identification methods based on visual markers are sensitive to occlusion, changes in lighting, and installation tilt. Once some sensors are occluded or reflective markers fail, the system fails. This invention uses a topology matching algorithm based on the distance matrix and a RANSAC outlier removal algorithm. Even if some sensors are occluded (blind zone) during the scanning process, or if some sensors are not installed evenly, the system can still uniquely determine the sensor ID and correct the position error through topological relationships, ensuring stable operation in complex industrial environments.

[0074] Through the above description of the embodiments, those skilled in the art can clearly understand that the transformer partial discharge location method according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0075] According to embodiments of the present invention, an apparatus for implementing the above-described method for locating partial discharge in a transformer is also provided. Figure 3 This is a structural block diagram of a partial discharge locating device for a transformer according to an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes: a first acquisition module 31, a first determination module 32, a judgment module 33, a second acquisition module 34, a second determination module 35, and a conversion module 36. The device will be described below.

[0076] The first acquisition module 31 is used to acquire the pulse current signals of the target transformer at multiple first preset positions;

[0077] The first determining module 32, connected to the first acquiring module 31, is used to determine a polarity feature vector based on the pulse current signals at multiple first preset positions, wherein the polarity feature vector represents the polarity state of the pulse current at the multiple preset positions.

[0078] The judgment module 33, connected to the first determination module 32, is used to determine whether there is partial discharge inside the target transformer based on the polarity feature vector;

[0079] The second acquisition module 34, connected to the judgment module 33, is used to acquire the arrival time of the acoustic signal of the target transformer at multiple second preset positions when there is partial discharge inside the target transformer.

[0080] The second determining module 35, connected to the second acquiring module 34, is used to determine the first coordinate of the local discharge power source inside the target transformer in the first preset coordinate system based on the arrival time of the acoustic wave signals of the target transformer at multiple second preset positions.

[0081] The conversion module 36, connected to the second determining module 35, is used to convert the first coordinates into second coordinates in a second preset coordinate system based on the original point cloud data of the preset target transformer, and to display the position of the second coordinates in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

[0082] It should be noted that the first acquisition module 31, the first determination module 32, the judgment module 33, the second acquisition module 34, the second determination module 35, and the conversion module 36 mentioned above correspond to steps S201 to S206 in the embodiments. Multiple modules implement the same instances and application scenarios as their corresponding steps, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run on the computer terminal 10 provided in the embodiments.

[0083] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0084] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the partial discharge location method and device for transformers in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned partial discharge location method for transformers. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0085] The processor can invoke information and application programs stored in the memory via a transmission device to perform the following steps: acquiring pulse current signals of the target transformer at multiple first preset locations; determining a polarity feature vector based on the pulse current signals at the multiple first preset locations, wherein the polarity feature vector represents the polarity state of the pulse current at the multiple preset locations; determining whether there is partial discharge inside the target transformer based on the polarity feature vector; acquiring the arrival time of acoustic signals of the target transformer at multiple second preset locations if there is partial discharge inside the target transformer; determining the first coordinate of the partial discharge source inside the target transformer in a first preset coordinate system based on the arrival time of the acoustic signals of the target transformer at the multiple second preset locations; converting the first coordinate into a second coordinate in a second preset coordinate system based on the preset original point cloud data of the target transformer, and displaying the position of the second coordinate in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

[0086] Optionally, the processor may also execute program code for the following steps: multiple first preset locations include: the end screen grounding wire of the three-phase bushing on the high-voltage side of the target transformer, the neutral point grounding wire of the target transformer, the core grounding wire of the target transformer, the clamp grounding wire of the target transformer, the auxiliary grounding point of the target transformer housing, and the low-voltage side grounding wire of the target transformer housing.

[0087] Optionally, the processor may also execute program code for the following steps: determining a polarity feature vector based on the pulse current signals at multiple first preset locations, including: within a preset time window, determining the first pulse waveform corresponding to the pulse current signals at the multiple first preset locations; extracting the polarity of the first pulse waveform to form a polarity feature vector, wherein the polarity includes positive polarity, negative polarity, or no polarity, positive polarity indicates that the pulse current flows from the target transformer to the ground, negative polarity indicates that the pulse current flows from the ground to the target transformer, and no polarity indicates that there is no significant signal.

[0088] Optionally, the processor may also execute program code for the following steps: determining whether there is partial discharge inside the target transformer based on the polarity feature vector, including: determining that there is no partial discharge inside the target transformer when all elements in the polarity feature vector are positive; or determining that there is partial discharge inside the target transformer when the elements in the polarity feature vector include both positive and negative polarities.

[0089] Optionally, the processor may also execute program code for the following steps: determining the first coordinates of the local discharge source inside the target transformer in a first preset coordinate system based on the arrival times of the acoustic signals at multiple second preset locations of the target transformer, including: constructing and solving a set of nonlinear positioning equations to obtain the first coordinates, wherein the mathematical expression of the set of nonlinear positioning equations is as follows:

[0090] ,

[0091] As the first coordinate, The coordinates of the ultrasonic sensor used to acquire sound wave signals are given, and the ultrasonic sensor is positioned at a second preset position. The speed of sound wave signal propagation. The arrival time of the sound wave signal. This is the first arrival time of the pulse current signal. This is the preset delay time.

[0092] Optionally, the processor may also execute program code for the following steps: based on the preset original point cloud data of the target transformer, converting the first coordinates into second coordinates in a second preset coordinate system, and displaying the position of the second coordinates in the second preset coordinate system, including: based on preset feature identifiers, locating the positions of multiple ultrasonic sensors used to acquire acoustic signals in the original point cloud data to obtain the centroid coordinates of multiple point cloud clusters; matching the centroid coordinates of the multiple point cloud clusters with the coordinates of the multiple ultrasonic sensors in the first preset coordinate system to obtain multiple point pairs; calculating the rotation matrix and translation vector for coordinate transformation based on the multiple point pairs; and converting the first coordinates into the second coordinates based on the rotation matrix and translation vector.

[0093] This invention provides a scheme for locating partial discharge in a transformer. It involves acquiring pulse current signals from multiple first preset locations on the target transformer; determining polarity feature vectors based on these signals, where each feature vector represents the polarity of the pulse current at each preset location; determining whether partial discharge exists inside the target transformer based on these feature vectors; acquiring the arrival times of acoustic signals from multiple second preset locations on the target transformer if partial discharge exists; determining the first coordinates of the partial discharge source inside the target transformer in a first preset coordinate system based on the arrival times of the acoustic signals from the target transformer at the second preset locations; and converting the first coordinates into second coordinates in a second preset coordinate system based on the original point cloud data of the target transformer, and displaying the position of the second coordinates in the second preset coordinate system. This achieves the goal of accurately mapping abstract electroacoustic positioning coordinates to a three-dimensional real-world model of the actual equipment on-site, thus solving the technical problems of traditional methods relying on drawings, large errors in manual calibration, and invisible positioning results, leading to low positioning accuracy and poor maintenance efficiency.

[0094] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0095] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the partial discharge location method for transformers provided in the above embodiments.

[0096] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0097] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: acquiring pulse current signals of the target transformer at multiple first preset locations; determining a polarity feature vector based on the pulse current signals at the multiple first preset locations, wherein the polarity feature vector characterizes the polarity state of the pulse current at the multiple preset locations; determining whether there is partial discharge inside the target transformer based on the polarity feature vector; if there is partial discharge inside the target transformer, acquiring the arrival time of acoustic signals of the target transformer at multiple second preset locations; determining the first coordinate of the partial discharge source inside the target transformer in a first preset coordinate system based on the arrival time of the acoustic signals of the target transformer at the multiple second preset locations; converting the first coordinate into a second coordinate in a second preset coordinate system based on the preset original point cloud data of the target transformer, and displaying the position of the second coordinate in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

[0098] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: The processor can also execute program code for the following steps: Multiple first preset locations include: the end screen grounding wire of the high-voltage side three-phase bushing of the target transformer, the neutral point grounding wire of the target transformer, the core grounding wire of the target transformer, the clamp grounding wire of the target transformer, the auxiliary grounding point of the target transformer housing, and the low-voltage side grounding wire of the target transformer housing.

[0099] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining a polarity feature vector based on pulse current signals at multiple first preset locations, including: within a preset time window, determining the first pulse waveform corresponding to the pulse current signals at each of the multiple first preset locations; extracting the polarity of the first pulse waveform to form a polarity feature vector, wherein the polarity includes positive polarity, negative polarity, or no polarity, positive polarity indicates that the pulse current flows from the target transformer to the ground, negative polarity indicates that the pulse current flows from the ground to the target transformer, and no polarity indicates that there is no significant signal.

[0100] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining whether there is partial discharge inside the target transformer based on the polarity feature vector, including: determining that there is no partial discharge inside the target transformer when all elements in the polarity feature vector are positive; or determining that there is partial discharge inside the target transformer when the elements in the polarity feature vector include both positive and negative polarities.

[0101] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the first coordinates of the partial discharge source inside the target transformer in a first preset coordinate system based on the arrival times of the acoustic signals of the target transformer at multiple second preset locations, including: constructing and solving a set of nonlinear positioning equations to obtain the first coordinates, wherein the mathematical expression of the set of nonlinear positioning equations is as follows:

[0102] ,

[0103] As the first coordinate, The coordinates of the ultrasonic sensor used to acquire sound wave signals are given, and the ultrasonic sensor is positioned at a second preset position. The speed of sound wave signal propagation. The arrival time of the sound wave signal. This is the first arrival time of the pulse current signal. This is the preset delay time.

[0104] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: based on the original point cloud data of the preset target transformer, converting the first coordinates into second coordinates in a second preset coordinate system, and displaying the position of the second coordinates in the second preset coordinate system, including: based on preset feature identifiers, locating the positions of multiple ultrasonic sensors used to acquire acoustic signals in the original point cloud data to obtain the centroid coordinates of multiple point cloud clusters; matching the centroid coordinates of the multiple point cloud clusters with the coordinates of the multiple ultrasonic sensors in the first preset coordinate system to obtain multiple point pairs; calculating the rotation matrix and translation vector for coordinate transformation based on the multiple point pairs; and converting the first coordinates into the second coordinates based on the rotation matrix and translation vector.

[0105] Embodiments of the present invention also provide a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it can: acquire pulse current signals of a target transformer at multiple first preset locations; determine a polarity feature vector based on the pulse current signals at the multiple first preset locations, wherein the polarity feature vector represents the polarity state of the pulse current at the multiple preset locations; determine whether there is partial discharge inside the target transformer based on the polarity feature vector; if there is partial discharge inside the target transformer, acquire the arrival time of acoustic signals of the target transformer at multiple second preset locations; determine the first coordinate of the partial discharge source inside the target transformer in a first preset coordinate system based on the arrival time of the acoustic signals of the target transformer at the multiple second preset locations; convert the first coordinate into a second coordinate in a second preset coordinate system based on the preset original point cloud data of the target transformer, and display the position of the second coordinate in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

[0106] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0107] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0109] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0110] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0112] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A partial discharge positioning method for a transformer, characterized by, include: Acquire the pulse current signals of the target transformer at multiple first preset positions; Based on the pulse current signals at the plurality of first preset positions, a polarity feature vector is determined, wherein the polarity feature vector represents the polarity state of the pulse current at the plurality of preset positions. Based on the polarity feature vector, it is determined whether there is partial discharge inside the target transformer; In the case of partial discharge inside the target transformer, the arrival times of acoustic signals of the target transformer at multiple second preset positions are obtained; Based on the arrival time of the acoustic signals of the target transformer at multiple second preset positions, the first coordinate of the partial discharge power source inside the target transformer in the first preset coordinate system is determined. Based on the preset original point cloud data of the target transformer, the first coordinate is converted into a second coordinate in a second preset coordinate system, and the position of the second coordinate is displayed in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

2. The method of claim 1, wherein, The plurality of first preset locations include: the end screen grounding wire of the high-voltage side three-phase bushing of the target transformer, the neutral point grounding wire of the target transformer, the core grounding wire of the target transformer, the clamp grounding wire of the target transformer, the auxiliary grounding point of the target transformer housing, and the low-voltage side grounding wire of the target transformer housing.

3. The method of claim 1, wherein, The determination of the polarity feature vector based on the pulse current signals at the respective first preset positions includes: Within a preset time window, the first pulse waveform corresponding to the pulse current signal at each of the multiple first preset positions is determined respectively; The polarity of the first pulse waveform is extracted to form the polarity feature vector, wherein the polarity includes positive polarity, negative polarity or no polarity, the positive polarity represents that the pulse current flows from the target transformer to the ground, the negative polarity represents that the pulse current flows from the ground to the target transformer, and the no polarity represents that there is no significant signal.

4. The method of claim 3, wherein, The step of determining whether there is partial discharge inside the target transformer based on the polarity feature vector includes: If all elements in the polarity feature vector are of the positive polarity, it is determined that there is no partial discharge inside the target transformer. Alternatively, if the elements in the polarity feature vector simultaneously include both the positive and negative polarities, it can be determined that a partial discharge exists inside the target transformer.

5. The method of claim 1, wherein, The step of determining the first coordinate in a first preset coordinate system of the partial discharge source inside the target transformer based on the arrival time of the acoustic signals at multiple second preset locations of the target transformer includes: The first coordinate is obtained by constructing and solving a system of nonlinear positioning equations, wherein the mathematical expression of the system of nonlinear positioning equations is as follows: ， Let the first coordinate be... The coordinates of the ultrasonic sensor used to acquire the sound wave signal are provided, and the ultrasonic sensor is arranged at the second preset position. The propagation speed of the sound wave signal. The arrival time of the sound wave signal is [time]. This refers to the first arrival time of the pulse current signal. This is the preset delay time.

6. The method according to claim 1, characterized in that, The process of converting the first coordinates into second coordinates in a second preset coordinate system based on the preset original point cloud data of the target transformer, and displaying the position of the second coordinates in the second preset coordinate system, includes: Based on preset feature identifiers, the positions of multiple ultrasonic sensors used to acquire the acoustic signal are located in the original point cloud data, and the centroid coordinates of multiple point cloud clusters are obtained. The centroid coordinates of the multiple point cloud clusters are matched with the coordinates of the multiple ultrasonic sensors in the first preset coordinate system to obtain multiple point pairs; Based on the multiple point pairs, calculate the rotation matrix and translation vector used for coordinate transformation; Based on the rotation matrix and the translation vector, the first coordinates are converted into the second coordinates.

7. A partial discharge locating device for a transformer, characterized in that, include: The first acquisition module is used to acquire the pulse current signals of the target transformer at multiple first preset positions; The first determining module is used to determine a polarity feature vector based on the pulse current signals at the plurality of first preset positions, wherein the polarity feature vector represents the polarity state of the pulse current at the plurality of preset positions. The judgment module is used to determine whether there is partial discharge inside the target transformer based on the polarity feature vector. The second acquisition module is used to acquire the arrival time of the acoustic signal of the target transformer at multiple second preset positions when there is partial discharge inside the target transformer; The second determining module is used to determine the first coordinate of the partial discharge power source inside the target transformer in the first preset coordinate system based on the arrival time of the acoustic wave signals of the target transformer at multiple second preset positions. The conversion module is used to convert the first coordinates into second coordinates in a second preset coordinate system based on the preset original point cloud data of the target transformer, and to display the position of the second coordinates in the second preset coordinate system, wherein the original point cloud data is located in the second preset coordinate system.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the partial discharge location method for a transformer as described in any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the partial discharge location method for a transformer as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the partial discharge location method for transformers as described in any one of claims 1 to 6.

Images