Positioning method and device for partial discharge position of transformer and electronic equipment

Abstract

The invention discloses a method and a device for positioning a partial discharge position of a transformer, and electronic equipment. Relates to the field of intelligent power grids, and the method comprises the steps: obtaining an ultrasonic propagation time delay data set which comprises structure parameters of transformers of various structures and partial discharge ultrasonic signal propagation time delay data corresponding to the transformers of various structures; obtaining a target structure parameter of the target transformer; based on the ultrasonic propagation time delay data set and the target structure parameters, determining an ultrasonic propagation time delay prediction result of the target transformer; and determining the partial discharge position of the target transformer based on the ultrasonic propagation time delay prediction result. According to the method, the technical problem that the partial discharge ultrasonic positioning precision is insufficient due to the fact that the problems of sound wave propagation path and wave velocity change cannot be fully solved in the face of a complex structure in a transformer is solved.

Description

Technical Field

[0001] This invention relates to the field of smart grids, and more specifically, to a method, apparatus, and electronic device for locating the partial discharge location of a transformer. Background Technology

[0002] In power systems, transformers, as critical power conversion and transmission equipment, require careful monitoring and maintenance of their operational status. Partial discharge, a common early fault phenomenon in transformer insulation systems, can be located using ultrasonic detection technology to predict potential equipment failures and ensure the stable operation of the power grid. However, related technologies have significant shortcomings in ultrasonic localization of partial discharge, mainly in the following aspects:

[0003] The ultrasonic time-of-flight positioning method based on constant wave velocity assumes that sound waves propagate in a straight line at a constant speed in transformer oil. However, the presence of multi-layered and non-uniform media inside actual transformers, including the core, windings, and insulation components, leads to complex and variable sound wave propagation paths, affecting wave velocity. Therefore, the positioning accuracy of this method is usually limited, with a large error margin, failing to meet the high-precision positioning requirements of modern power systems. Simulation-based wave velocity correction methods, to overcome the limitations of the constant wave velocity assumption, have attempted to use computer simulations, employing finite element analysis or multiphysics simulation software to establish a refined three-dimensional model of the transformer, simulating the propagation path of ultrasound in complex media. While this method theoretically improves positioning accuracy, the accuracy of the simulation model is highly dependent on the precision of the input parameters. The acoustic characteristic parameters of actual transformers are often difficult to obtain, resulting in a "simulation that is not entirely accurate," limiting the correction effect and hindering widespread application in practical engineering scenarios. Calibration methods based on simple experiments, to simplify experimental operations, have employed simple experimental setups (such as water tanks) with obstacles placed around them, measuring the propagation time of sound waves around the obstacles to summarize correction formulas. However, this experimental setup is overly simplified and cannot reproduce the complex acoustic environment of the multi-layered, anisotropic media inside a transformer. Therefore, the conclusions and correction formulas derived in this way have extremely poor universality and are difficult to apply to a wide range of transformer models and structures, limiting their engineering application value. Although related ultrasonic partial discharge localization methods can provide a rough location of partial discharge sources within a certain range, when faced with the complex internal structure of transformers, the failure to accurately compensate for the additional time delay of sound wave propagation leads to a significant decrease in the accuracy of ultrasonic partial discharge localization, making it difficult to meet the requirements of high-precision detection.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, and electronic device for locating the partial discharge location of a transformer, in order to at least solve the technical problem of insufficient ultrasonic positioning accuracy of partial discharge caused by the failure to fully address the changes in sound wave propagation path and wave velocity when dealing with the complex internal structure of a transformer.

[0006] According to one aspect of the present invention, a method for locating the partial discharge location of a transformer is provided, comprising: acquiring an ultrasonic propagation delay dataset, wherein the ultrasonic propagation delay dataset includes: structural parameters of transformers with various structures, and propagation delay data of partial discharge ultrasonic signals corresponding to the transformers with various structures respectively; acquiring target structural parameters of a target transformer, wherein the target structural parameters include at least the diameter of the core, the height of the winding, the distance between the winding and the core, and the number of insulating partitions; determining an ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structural parameters, wherein the ultrasonic propagation delay prediction result represents a set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations, the ultrasonic sensor combination representing any two ultrasonic sensors in an ultrasonic sensor array, wherein a first ultrasonic sensor is used to transmit partial discharge ultrasonic signals, and a second ultrasonic sensor is used to receive partial discharge ultrasonic signals; and determining the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction result.

[0007] According to another aspect of the present invention, a device for locating the partial discharge location of a transformer is also provided, comprising: an ultrasonic propagation delay dataset acquisition module, configured to acquire an ultrasonic propagation delay dataset, wherein the ultrasonic propagation delay dataset includes: structural parameters of transformers with various structures, and propagation delay data of partial discharge ultrasonic signals corresponding to transformers with various structures respectively; a target structural parameter acquisition module, configured to acquire target structural parameters of a target transformer, wherein the target structural parameters include at least the diameter of the core, the height of the winding, the distance between the winding and the core, and the number of insulating partitions; an ultrasonic propagation delay prediction result determination module, configured to determine the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structural parameters, wherein the ultrasonic propagation delay prediction result represents a set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations, the ultrasonic sensor combination represents any two ultrasonic sensors in an ultrasonic sensor array, wherein the first ultrasonic sensor is used to emit partial discharge ultrasonic signals, and the second ultrasonic sensor is used to receive partial discharge ultrasonic signals; and a partial discharge location determination module, configured to determine the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction result.

[0008] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium storing a plurality of instructions adapted for loading by a processor and executing the method for locating the partial discharge location of a transformer as described in any one of the embodiments.

[0009] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method for locating the partial discharge location of a transformer as described in any one of the present invention.

[0010] 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 the steps of the method for locating the partial discharge location of a transformer as described in any one of the present invention.

[0011] In this embodiment of the invention, an ultrasonic propagation delay dataset is acquired, comprising: structural parameters of transformers with various structures, and propagation delay data of partial discharge ultrasonic signals corresponding to the transformers with various structures; target structural parameters of the target transformer are acquired, wherein the target structural parameters include at least the diameter of the core, the height of the winding, the distance between the winding and the core, and the number of insulating partitions; based on the ultrasonic propagation delay dataset and the target structural parameters, the ultrasonic propagation delay prediction result of the target transformer is determined, wherein the ultrasonic propagation delay prediction result represents a set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations, and the ultrasonic sensor combination represents the ultrasonic sensor array... Any two ultrasonic sensors are used, with the first ultrasonic sensor transmitting partial discharge ultrasonic signals and the second ultrasonic sensor receiving partial discharge ultrasonic signals. Based on the ultrasonic propagation delay prediction results, the partial discharge location of the target transformer is determined. This achieves the goal of accurately determining the partial discharge location of the target transformer by acquiring an ultrasonic propagation delay database and combining it with the target structural parameters of the target transformer, thereby improving the technical effect of ultrasonic positioning accuracy for partial discharge. This solves the technical problem of insufficient ultrasonic positioning accuracy for partial discharge caused by the failure to fully address the changes in sound wave propagation path and wave velocity when facing the complex internal structure of the transformer. Attached Figure Description

[0012] 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:

[0013] Figure 1This is a flowchart of a method for locating the partial discharge location of a transformer according to an embodiment of the present invention;

[0014] Figure 2 This is a flowchart of an optional method for locating the partial discharge location of a transformer according to an embodiment of the present invention;

[0015] Figure 3 This is a schematic diagram of a device for locating the partial discharge position of a transformer according to an embodiment of the present invention. Detailed Implementation

[0016] 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.

[0017] 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.

[0018] Partial discharge refers to the phenomenon of discharge occurring in localized areas of the insulation system of high-voltage power equipment due to uneven electric field distribution or other factors. Although the energy is small, its long-term existence may gradually damage the insulation performance and eventually lead to equipment failure.

[0019] Ultrasonic positioning utilizes the propagation characteristics of ultrasonic signals in a medium. When partial discharge occurs inside a device, it generates ultrasonic waves, which propagate outward through the medium inside the device. Multiple ultrasonic sensors are arranged on the device casing, and these sensors can receive ultrasonic signals from the partial discharge point at different times.

[0020] Time difference positioning (TDRP) is a technology widely used in acoustics, radar, wireless communication, and other fields, primarily for determining the location of signal sources. Its basic principle is to compare the time differences between the reception of the same signal at multiple receiving points, and then, by combining this with the signal propagation speed and the geometric relationship between the receiving points, deduce the actual location of the signal source.

[0021] According to an embodiment of the present invention, a method for locating the partial discharge location of 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.

[0022] Figure 1 This is a flowchart of a method for locating the partial discharge position of a transformer according to an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes the following steps:

[0023] Step S102: Obtain the ultrasonic propagation delay dataset, which includes: structural parameters of transformers with various structures, and propagation delay data of partial discharge ultrasonic signals corresponding to transformers with various structures.

[0024] Optionally, the process of acquiring the ultrasonic propagation delay dataset aims to accurately understand the propagation characteristics of ultrasonic signals within transformers of different structures. This dataset contains detailed structural parameter information for transformers with various structures, covering diverse structural layouts, and corresponding partial discharge ultrasonic signal propagation delay data. This delay data was collected under a series of carefully designed experimental conditions, simulating how sound waves propagate in environments with complex dielectric structures, thereby obtaining the ultrasonic signal propagation delay data. Constructing the ultrasonic propagation delay dataset is the cornerstone for achieving high accuracy, high reliability, and wide applicability, and can provide an innovative solution for partial discharge localization in complex environments.

[0025] In one optional embodiment, obtaining an ultrasonic propagation delay dataset includes: establishing an ultrasonic propagation simulation platform, wherein the ultrasonic propagation simulation platform includes a sealed container for simulating a transformer tank, materials for simulating the transformer structure, obstacles for simulating the shape of the transformer, and an ultrasonic sensor array for measuring partial discharge ultrasonic signals; obtaining a structural parameter space, wherein the structural parameter space is obtained based on preset structural parameters of the transformer, preset variation ranges of the preset structural parameters, and preset step sizes within the preset variation ranges; determining transformers with various structures based on the ultrasonic propagation simulation platform and the structural parameter space; acquiring partial discharge ultrasonic signals from transformers with various structures based on the ultrasonic propagation simulation platform to determine multiple partial discharge ultrasonic signal propagation delay data, wherein the multiple partial discharge ultrasonic signal propagation delay data correspond one-to-one with transformers with various structures; and obtaining an ultrasonic propagation delay dataset based on transformers with various structures and multiple partial discharge ultrasonic signal propagation delay data.

[0026] Optionally, the process of acquiring ultrasonic propagation delay datasets aims to accurately understand and quantify the propagation behavior of ultrasonic signals within transformers of different structures through simulation and experimentation. First, a high-fidelity ultrasonic propagation simulation platform is designed and built. This platform includes, but is not limited to, the following core components: a sealed container, serving as a closed enclosure simulating a transformer tank, filled with standard transformer oil to simulate the acoustic environment of a real transformer tank; simulated materials, which can be, but are not limited to, modules made from materials used in actual transformers, such as silicon steel sheets, copper wires, and insulating cardboard, to realistically represent the structural characteristics and acoustic properties of the transformer; obstacles, which can be designed with different shapes and sizes to represent the core, windings, and insulation components of the transformer. These obstacles can be flexibly positioned to simulate transformers with different structural layouts; and an ultrasonic sensor array, consisting of high-precision optical scales and servo motor-driven linear modules mounted in the X, Y, and Z directions outside the sealed container. The ultrasonic sensors are mounted on the modules using clamps, and their positions can be accurately read and controlled by the control system. A sensor network deployed outside the sealed container is used to accurately capture and record the propagation time of ultrasonic signals generated by partial discharge events. An ultrasonic signal acquisition system can also be configured. By configuring the ultrasonic signal acquisition hardware, high-speed, high-resolution data recording can be ensured. Software design enables automated control, including signal triggering, acquisition, and storage, simplifying experimental procedures. After the ultrasonic propagation simulation platform is built, an open-field test needs to be conducted without obstacles to measure the platform's latency, which will be subtracted in subsequent experiments to ensure data accuracy and reliability.

[0027] Next, a structural parameter space is defined. This is a multi-dimensional concept, including but not limited to parameters such as the core diameter, the spacing between the windings and the core, the winding height, and the number of insulators. The establishment of the structural parameter space is based on preset ranges and step sizes for these parameters, allowing for the systematic exploration and coverage of a large number of possible structural configurations, thus laying the foundation for subsequent experimental design and data analysis. Furthermore, based on the structural parameter space, a large number of structural configuration scenarios can be generated within the parameter space, but not limited to full-factor experimental design or Latin hypercube sampling. By changing the values ​​of various parameters, a series of transformer models with different structural characteristics can be virtually constructed. These transformers with different structural characteristics represent the diversity and complexity of real-world transformer structures, providing diverse experimental scenarios for subsequent signal acquisition and time delay data acquisition. Using the established ultrasonic propagation simulation platform, partial discharge ultrasonic signals are acquired for each virtually constructed transformer structure. This process involves controlling the emission of ultrasonic waves, followed by recording and analyzing the time difference of the signal reaching different sensors. Through precise measurement techniques and data analysis algorithms, the actual propagation time of the ultrasonic signal through the complex internal path of the transformer can be calculated, thereby obtaining the partial discharge ultrasonic signal propagation time delay data corresponding to each structural configuration. Finally, all structural parameter configurations and their corresponding ultrasonic propagation delay data are compiled to form an ultrasonic propagation delay dataset. This dataset not only contains detailed structural descriptions but also delay data obtained directly from experiments, providing necessary correction information for high-precision positioning algorithms. It helps time-difference positioning models more accurately understand the propagation patterns of sound waves in specific structures, thereby significantly improving the positioning accuracy of partial discharge. The ultrasonic propagation delay dataset can be stored, but is not limited to, using relational databases or scientific data storage formats to ensure efficient data management and rapid access, forming a comprehensive and systematic data resource library. The ultrasonic propagation delay dataset constructed through the above steps provides solid data support for high-precision positioning of transformer partial discharge, bridging the gap between model assumptions and the real physical environment in related positioning methods.

[0028] In one optional embodiment, based on an ultrasonic propagation simulation platform, partial discharge ultrasonic signals are acquired for transformers of various structures to determine multiple partial discharge ultrasonic signal propagation delay data. This includes: acquiring partial discharge ultrasonic signals for any transformer structure using the ultrasonic propagation simulation platform in the following manner to obtain propagation delay data for any partial discharge ultrasonic signal: Based on the ultrasonic propagation simulation platform, multiple ultrasonic pulse transmitters are determined according to a preset ultrasonic sensor array layout rule, wherein each ultrasonic pulse transmitter corresponds one-to-one with multiple ultrasonic sensors in the ultrasonic sensor array; acquiring partial discharge ultrasonic signals for any transformer structure using the multiple ultrasonic pulse transmitters to obtain multiple ultrasonic propagation waveform data, wherein the ultrasonic propagation waveform data is the set of signals received by the remaining sensors when any ultrasonic sensor is used as any ultrasonic pulse transmitter to transmit a partial discharge ultrasonic signal to the remaining sensors, and the remaining sensors are the sensors other than any ultrasonic sensor among the multiple ultrasonic sensors; determining the propagation delay data for any partial discharge ultrasonic signal based on the multiple ultrasonic propagation waveform data; and obtaining multiple partial discharge ultrasonic signal propagation delay data using the same method as obtaining the propagation delay data for any partial discharge ultrasonic signal.

[0029] Optionally, based on an ultrasonic propagation simulation platform, partial discharge ultrasonic signals are acquired and analyzed for transformers with different structural characteristics to determine the propagation delay data of ultrasonic signals in these structures. The goal of this method is to construct a comprehensive, structured ultrasonic propagation delay dataset. First, multiple ultrasonic pulse transmitters are positioned on the simulation platform according to a pre-defined ultrasonic sensor array layout rule, with each transmitter corresponding to one ultrasonic sensor. This one-to-one correspondence ensures the standardization and repeatability of signal acquisition, laying the foundation for subsequent delay data extraction. Next, for each transformer with a structural configuration, at the start of the experiment, the ultrasonic pulse transmitter emits partial discharge ultrasonic signals to the other sensors. Each transmitter takes turns as the starting point of the signal, while the other sensors act as the receiving end. During this process, the complete waveform data of the signal emitted from each transmitter reaching the other sensors is recorded, thus obtaining multiple ultrasonic propagation waveform data. In this way, a set of ultrasonic propagation waveform data related to any sensor combination (transmitter and receiver) can be obtained. Based on the acoustic propagation waveform data of any sensor combination, the propagation delay data of any partial discharge ultrasonic signal is determined, i.e., the actual time delay experienced by the ultrasonic signal as it propagates inside a transformer with a specific structure. This yields multiple partial discharge ultrasonic signal propagation delay data. These partial discharge ultrasonic signal propagation delay data will be used as key correction parameters in subsequent localization algorithms to compensate for the additional time difference caused by structural complexity in the sound wave propagation path. This method not only provides a powerful tool for understanding and simulating the propagation behavior of ultrasonic waves in complex environments but also lays a solid data foundation for high-precision localization technology of transformer partial discharge, significantly reducing localization errors and improving the efficiency and accuracy of power equipment fault diagnosis.

[0030] In one optional embodiment, determining the propagation delay data of any partial discharge ultrasonic signal based on multiple ultrasonic propagation waveform data includes: determining the target ultrasonic propagation time of any ultrasonic propagation waveform data, wherein the target ultrasonic propagation time represents the set of times when the partial discharge ultrasonic signal is emitted from any ultrasonic pulse transmitter and first arrives at the other sensors respectively; determining the target ultrasonic propagation time corresponding to each of the multiple ultrasonic propagation waveform data; determining an ultrasonic propagation time matrix and a waveform data amplitude matrix based on the multiple ultrasonic propagation waveform data and the target ultrasonic propagation time corresponding to each of the multiple ultrasonic propagation waveform data, wherein any element in the ultrasonic propagation time matrix represents the time it takes for the partial discharge ultrasonic signal to be emitted from any ultrasonic pulse transmitter to any other ultrasonic sensor, and any element in the waveform data amplitude matrix represents the amplitude intensity of the partial discharge ultrasonic signal received by any other ultrasonic sensor; and determining the propagation delay data of any partial discharge ultrasonic signal based on the ultrasonic propagation time matrix and the waveform data amplitude matrix.

[0031] Optionally, the exact moment when the partial discharge ultrasonic signal first arrives at each receiving sensor can be extracted from each acquired ultrasonic propagation waveform data. The set of these moments constitutes the target ultrasonic propagation time, reflecting the initial propagation time of the partial discharge ultrasonic signal from the transmitter to different receivers. Using the determined target ultrasonic propagation time, an ultrasonic propagation time matrix can be constructed. The rows and columns of the matrix represent each sensor in the sensor array, and each element in the matrix represents the time required for the signal to propagate from the sensor in the row (transmitter) to the sensor in the column (receiver). Simultaneously, the amplitude of the partial discharge ultrasonic signal received by each receiving sensor is recorded, forming a waveform data amplitude matrix. The elements in the matrix represent signal strength, which helps in analyzing the quality of the partial discharge ultrasonic signal and its attenuation during propagation. Combining the ultrasonic propagation time matrix and the waveform data amplitude matrix, and removing the delay of the simulation platform itself, a time delay matrix purely caused by the transformer structure is obtained, which represents the actual time delay data of the partial discharge ultrasonic signal propagating from one sensor to another inside a transformer with a specific structure. This step not only provides crucial support for subsequent time difference positioning models, but also plays a significant role in deepening the understanding of the internal acoustic environment of transformers and improving the maintenance efficiency of power equipment.

[0032] Step S104: Obtain the target structural parameters of the target transformer, wherein the target structural parameters include at least the core diameter, winding height, distance between the winding and the core, and number of insulating partitions.

[0033] Optionally, in power equipment monitoring and maintenance, to accurately locate partial discharge events inside a target transformer, it is first necessary to accurately obtain the key structural parameters of the target transformer. This can be achieved, but is not limited to, using computer-aided design drawings combined with 3D laser scanning point cloud data obtained after transformer inspection to extract the key structural parameters. Among these, the core is the core component of the transformer; its diameter affects the diffraction and refraction behavior of sound waves, as well as the complexity of the sound wave path. The height of the windings determines the vertical propagation path of sound waves inside the transformer, affecting the signal propagation distance and time. Accurately measuring the winding height helps to establish a vertical propagation model of sound waves, improving positioning accuracy. The distance parameter between the windings and the core affects the direct and indirect propagation paths of sound waves from the windings to the core, directly relating to whether significant multipath propagation occurs, and is crucial to the accuracy of positioning. Insulating partitions are an important component inside the transformer; their number and layout affect the refraction and reflection of sound waves, thus affecting the signal propagation path and time.

[0034] Step S106: Based on the ultrasonic propagation delay dataset and target structural parameters, determine the ultrasonic propagation delay prediction result of the target transformer. The ultrasonic propagation delay prediction result represents the set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations. The ultrasonic sensor combination represents any two ultrasonic sensors in the ultrasonic sensor array. In any two ultrasonic sensors, the first ultrasonic sensor is used to transmit partial discharge ultrasonic signals, and the second ultrasonic sensor is used to receive partial discharge ultrasonic signals.

[0035] Optionally, each sensor combination—that is, any two ultrasonic sensors selected from the ultrasonic sensor array—takes on the roles of transmitter and receiver, respectively. The transmitter sensor is responsible for emitting ultrasonic signals, and the receiver sensor is responsible for receiving the ultrasonic signals emitted by the transmitter. Based on a pre-built ultrasonic propagation delay dataset and the specific structural parameters of the target transformer obtained on-site, the propagation delay between all ultrasonic sensor combinations can be predicted, forming a comprehensive set of ultrasonic propagation delay prediction results. This set of prediction results covers the ultrasonic propagation delay estimation between any two sensors in the sensor array, which can significantly improve the accuracy and reliability of partial discharge localization and provide crucial information support for the condition monitoring and fault diagnosis of on-site equipment.

[0036] In one optional embodiment, determining the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structural parameters includes: converting the target structural parameters into standard structural parameters that match those in the ultrasonic propagation delay dataset; determining the transformers of the target structure using a similarity measurement method based on the standard structural parameters, wherein the transformers of the target structure represent a predetermined number of transformers related to the target structural parameters obtained from the ultrasonic propagation delay dataset; and obtaining the ultrasonic propagation delay prediction result of the target transformer using an interpolation prediction method based on the transformers of the target structure.

[0037] Optionally, this embodiment proposes a method for intelligently predicting the propagation delay of ultrasonic waves inside a target transformer based on a previously accumulated ultrasonic propagation delay dataset and the structural parameters of the target transformer in the field. First, the structural parameters of the target transformer obtained from the field are converted to the same form and units as the parameters recorded in the ultrasonic propagation delay dataset to ensure comparability and matching. This conversion can be performed, but is not limited to, using point cloud processing algorithms. Next, similarity measurement methods (including but not limited to Euclidean distance, Mahalanobis distance, and correlation coefficient methods) are used to find one or more sets (a predetermined number) of transformer records in the ultrasonic propagation delay dataset whose standard structural parameters are closest. Here, the target structure transformer refers to those transformers with structural parameters similar to the target transformer, for which corresponding ultrasonic propagation delay data already exists in the database. Finally, based on the most similar target structure transformer records found, interpolation prediction methods (including but not limited to inverse distance weighted interpolation and Kriging interpolation) are used to calculate the predicted ultrasonic propagation delay of the target transformer. Through these steps, intelligent prediction of the ultrasonic propagation delay of the target transformer can be achieved.

[0038] In an optional embodiment, when there are multiple transformers in the target structure, an interpolation prediction method is used to obtain the ultrasonic propagation time delay prediction result of the target transformer based on the transformers in the target structure. This includes: based on multiple transformers in the target structure, an interpolation prediction method is used to determine the ultrasonic propagation time delay prediction result of any combination of ultrasonic sensors in the following manner:

[0039] ;

[0040] in, This represents the predicted ultrasonic propagation delay for any combination of ultrasonic sensors. This represents the propagation delay data of the ultrasonic signal for partial discharge of a transformer with any target structure; i i and j represent the indices of any ultrasonic sensor in the ultrasonic sensor array, respectively. The weight of the transformer representing any target structure, The difference between the transformer and the target structure parameters of any target structure is represented by the similarity measurement method, where n represents the index of the transformer of any target structure and p represents the preset power parameter. The ultrasonic propagation delay prediction results of multiple ultrasonic sensor combinations are obtained by using the method of obtaining the ultrasonic propagation delay prediction results of any ultrasonic sensor combination. Based on the ultrasonic propagation delay prediction results of multiple ultrasonic sensor combinations, the ultrasonic propagation delay prediction result of the target transformer is obtained.

[0041] Optionally, in the interpolation prediction process, firstly, a similarity analysis is performed on the transformers of all target structures to identify the multiple structural configurations most similar to the target transformer on site. Next, the weight of each transformer in any target structure is calculated based on the differences between its parameters and those of the target structure. More similar structural configurations are assigned higher weights, indicating a greater contribution to the prediction results. Finally, the propagation delay data of the partial discharge ultrasonic signal of each target structure transformer is multiplied by its weight, and the weighted delay data of all target structures are summed to obtain the ultrasonic propagation delay prediction result for any combination of ultrasonic sensors. These steps are repeated to predict multiple combinations of ultrasonic sensors, ultimately generating a set of ultrasonic propagation delay prediction results covering all sensor combinations. This interpolation prediction method, even when facing multiple similar target transformers, can generate accurate and adaptable ultrasonic propagation delay prediction results based on data in the database, significantly improving the accuracy of partial discharge localization.

[0042] Step S108: Based on the ultrasonic propagation delay prediction results, determine the partial discharge location of the target transformer.

[0043] Optionally, firstly, the predicted ultrasonic propagation time delay data is incorporated into the time-difference positioning equation to modify the equation, resulting in a time-difference positioning model. This involves introducing a time delay compensation value when calculating the time difference between the arrival of the partial discharge acoustic signal at each sensor. For any combination of ultrasonic sensors, the corresponding time-difference positioning equation is: ,in, and These represent the times when the partial discharge ultrasonic signal arrives at any ultrasonic sensor in the ultrasonic sensor array from the partial discharge location; and Let V represent the distance from the partial discharge ultrasonic signal to any ultrasonic sensor at the partial discharge location, and V represent the propagation speed of the partial discharge ultrasonic signal in the medium. Subsequently, by performing mathematical inversion calculations on the modified model (i.e., the time-of-flight positioning model), the three-dimensional spatial location of the partial discharge event can be accurately determined. This method can significantly improve the accuracy and efficiency of fault diagnosis, effectively reduce the maintenance costs of power equipment, and provide strong technical support for the stable operation of the power system.

[0044] In one optional embodiment, determining the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction results includes: obtaining a time-difference localization model of any combination of ultrasonic sensors in the following form based on the ultrasonic propagation delay prediction results, wherein the time-difference localization model is used to determine the propagation delay of the partial discharge ultrasonic signal in the medium:

[0045] ;

[0046] in, and These represent the times when the partial discharge ultrasonic signal arrives at any ultrasonic sensor in the ultrasonic sensor array from the partial discharge location; and This represents the distance from the partial discharge ultrasonic signal to any ultrasonic sensor at the location of the partial discharge; and These represent the time delay compensation values ​​for the partial discharge ultrasonic signal reaching any ultrasonic sensor from the partial discharge location; that is... and The ultrasonic propagation time delay prediction results for any combination of ultrasonic sensors are represented by , and V represents the propagation speed of the partial discharge ultrasonic signal in the medium. Using the method of obtaining the time difference positioning model for any combination of ultrasonic sensors, time difference positioning models corresponding to multiple ultrasonic sensor combinations are obtained. The time difference positioning models corresponding to multiple ultrasonic sensor combinations are inverted to determine the partial discharge location of the target transformer.

[0047] Optionally, a time-difference positioning model is obtained by incorporating the ultrasonic propagation delay prediction result into the time-difference positioning equation. The key to this model is the addition of a time delay compensation value. For any combination of ultrasonic sensors, and The time delay compensation values ​​are derived from the ultrasonic propagation time delay prediction results, specifically the elements in the i-th row and j-th column of the matrix in the ultrasonic propagation time delay prediction results. Under idealized symmetrical propagation conditions, these two time delay compensation values ​​should be completely equal. However, in the complex acoustic environment of actual transformers, the asymmetry of the sound wave propagation path and the inhomogeneity of the medium may lead to slight differences, thus correcting the main source of error in the time difference localization equation. A series of corrected time difference localization models are formed for the ultrasonic sensor combination in the sensor array. Each equation reflects the time difference relationship between the partial discharge location and a specific ultrasonic sensor combination. All corrected time difference localization models are organized into a set of equations, which contains the time difference information between the partial discharge location and all sensor combinations. The equation set is solved using an inversion algorithm to determine the partial discharge location of the target transformer. Specifically, this includes the following steps: initializing parameters, setting an initial estimate of the partial discharge location, which can be the center of the sensor deployment area or other reasonable predicted location; algorithm selection, including but not limited to using nonlinear optimization algorithms, least squares method, gradient descent method, conjugate gradient method, quasi-Newton method, and genetic algorithm to solve the equation set. Iterative optimization involves substituting the current partial discharge location estimate into each time-difference positioning model equation, calculating the residual between the estimated value and the actual measured time difference, and then iteratively updating the partial discharge location estimate through an optimization algorithm to minimize the overall residual. Convergence is determined by setting a convergence condition, such as the residual being less than a certain threshold or the number of iterations reaching an upper limit. When the convergence condition is met, the algorithm terminates, and the current partial discharge location estimate becomes the positioning result. Result verification involves comparing the obtained partial discharge location with known discharge information (such as artificially introduced discharge points in a laboratory setting) to verify the positioning accuracy. Through these steps, the multi-sensor combined positioning inversion algorithm based on ultrasonic propagation time delay prediction results can overcome positioning errors caused by the complexity of the medium and structure, achieving high-precision real-time positioning of the partial discharge location of the target transformer, providing strong technical support for the maintenance and safe operation of power equipment.

[0048] Through the above steps S102 to S108, the goal of accurately determining the partial discharge location of the target transformer can be achieved by obtaining the ultrasonic propagation delay database and combining it with the target structural parameters of the target transformer to determine the ultrasonic propagation delay prediction result. This improves the technical accuracy of ultrasonic positioning of partial discharge and solves the technical problem of insufficient ultrasonic positioning accuracy of partial discharge caused by the failure to fully address the changes in sound wave propagation path and wave velocity when facing the complex internal structure of the transformer.

[0049] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method. Figure 2 This is a flowchart of an optional method for locating the partial discharge location of a transformer according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes:

[0050] S1: Based on the ultrasonic propagation simulation platform, various transformer structures and multiple ultrasonic propagation delay results are determined to obtain an ultrasonic propagation delay dataset. The specific implementation process is the same as the aforementioned embodiments, and will not be repeated here.

[0051] S2: Obtain the target structural parameters of the target transformer. The specific implementation process is the same as in the previous embodiment, and will not be repeated here.

[0052] S3: Transform the target structural parameters into standard structural parameters that match the ultrasonic propagation delay dataset. The specific implementation process is the same as in the previous embodiment, and will not be repeated here.

[0053] S4: Based on standard structural parameters, determine the transformer with the target structure. The specific implementation process is the same as the previous embodiment, and will not be repeated here.

[0054] S5: Based on the transformer of the target structure, the ultrasonic propagation time delay prediction result of the target transformer is obtained. The specific implementation process is the same as the previous embodiment, and will not be repeated here.

[0055] S6: Based on the ultrasonic propagation delay prediction results, multiple time difference positioning models are obtained. The specific implementation process is the same as the aforementioned embodiments, and will not be repeated here.

[0056] S7: Based on multiple time-difference positioning models, the partial discharge location of the target transformer is determined. The specific implementation process is the same as the aforementioned embodiments, and will not be repeated here.

[0057] This embodiment can achieve at least one of the following effects: (1) Revolutionary improvement in accuracy: This embodiment fundamentally corrects the largest source of error (propagation path), improving the positioning accuracy from >40cm to <10cm. (2) Extremely high reliability: The correction data in this embodiment comes from physical experiments, rather than idealized simulations. The data is real and reliable, and can better reflect the actual propagation behavior of sound waves in complex structures. (3) Strong universality: This embodiment, through systematic parameter scanning and dataset interpolation, can cover an infinite number of structural combinations and is applicable to transformers of different models and structures, solving the fatal problem of poor universality of simple experimental models. (4) Strong feasibility: The dataset can be pre-built, and in field applications, it only requires querying and calculation. It is fast, easy to integrate into existing positioning systems, and has strong engineering application value.

[0058] This embodiment also provides a device for locating the partial discharge position of a transformer. This device is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the terms "module" and "device" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0059] According to an embodiment of the present invention, an apparatus embodiment for implementing the above-described method for locating the partial discharge location of a transformer is also provided. Figure 3 This is a schematic diagram of a device for locating the partial discharge position of a transformer according to an embodiment of the present invention. Figure 3 As shown, the device for locating the partial discharge location of the aforementioned transformer includes: an ultrasonic propagation time delay dataset acquisition module 300, a target structure parameter acquisition module 302, an ultrasonic propagation time delay prediction result determination module 304, and a partial discharge location determination module 306, wherein:

[0060] The ultrasonic propagation delay dataset acquisition module 300 is used to acquire the ultrasonic propagation delay dataset, which includes: structural parameters of transformers with various structures, and propagation delay data of partial discharge ultrasonic signals corresponding to transformers with various structures.

[0061] The target structural parameter acquisition module 302 is connected to the ultrasonic propagation delay dataset acquisition module 300 and is used to acquire the target structural parameters of the target transformer. The target structural parameters include at least the diameter of the iron core, the height of the winding, the distance between the winding and the iron core, and the number of insulating partitions.

[0062] The ultrasonic propagation delay prediction result determination module 304 is connected to the target structure parameter acquisition module 302. It is used to determine the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structure parameters. The ultrasonic propagation delay prediction result represents the set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations. The ultrasonic sensor combination represents any two ultrasonic sensors in the ultrasonic sensor array. In any two ultrasonic sensors, the first ultrasonic sensor is used to transmit partial discharge ultrasonic signals, and the second ultrasonic sensor is used to receive partial discharge ultrasonic signals.

[0063] The partial discharge location determination module 306 is connected to the ultrasonic propagation delay prediction result determination module 304 and is used to determine the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction result.

[0064] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0065] It should be noted that the ultrasonic propagation delay dataset acquisition module 300, target structure parameter acquisition module 302, ultrasonic propagation delay prediction result determination module 304, and partial discharge location determination module 306 mentioned above correspond to steps S102 to S108 in the embodiments. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run on a computer terminal.

[0066] It should be noted that the optional or preferred implementation methods of this embodiment can be found in the relevant descriptions in the embodiments, and will not be repeated here.

[0067] The aforementioned device for locating the partial discharge location of a transformer may also include a processor and a memory. The aforementioned ultrasonic propagation delay dataset acquisition module 300, target structure parameter acquisition module 302, ultrasonic propagation delay prediction result determination module 304, and partial discharge location determination module 306 are all stored in the memory as program modules, and the processor executes the aforementioned program modules stored in the memory to realize the corresponding functions.

[0068] The processor contains a core that retrieves the corresponding program modules from memory. One or more cores may be configured. Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0069] According to an embodiment of this application, an embodiment of a non-volatile storage medium is also provided. Optionally, in this embodiment, the non-volatile storage medium includes a stored program, wherein, when the program runs, it controls the device containing the non-volatile storage medium to execute any of the aforementioned methods for locating the partial discharge position of a transformer.

[0070] 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, and the non-volatile storage medium includes stored programs.

[0071] Optionally, during program execution, the device containing the non-volatile storage medium performs the following functions: acquiring an ultrasonic propagation delay dataset, wherein the ultrasonic propagation delay dataset includes: structural parameters of transformers with various structures, and partial discharge ultrasonic signal propagation delay data corresponding to transformers with various structures; acquiring target structural parameters of the target transformer, wherein the target structural parameters include at least the core diameter, winding height, distance between the winding and the core, and the number of insulating partitions; determining the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structural parameters, wherein the ultrasonic propagation delay prediction result represents the set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations, and the ultrasonic sensor combination represents any two ultrasonic sensors in the ultrasonic sensor array, wherein the first ultrasonic sensor is used to transmit partial discharge ultrasonic signals, and the second ultrasonic sensor is used to receive partial discharge ultrasonic signals; and determining the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction result.

[0072] According to an embodiment of this application, an embodiment of a processor is also provided. Optionally, in this embodiment, the processor is used to run a program, wherein the program executes any of the above-described methods for locating the partial discharge location of a transformer.

[0073] According to an embodiment of this application, an embodiment of a computer program product is also provided. Optionally, in this embodiment, the computer program product includes a computer program that, when executed by a processor, implements the steps of the method for locating the partial discharge location of a transformer as described above.

[0074] Optionally, when the above-mentioned computer program product is executed on a data processing device, it is suitable to execute an initialization program with the following method steps: acquiring an ultrasonic propagation delay dataset, wherein the ultrasonic propagation delay dataset includes: structural parameters of transformers with various structures, and partial discharge ultrasonic signal propagation delay data corresponding to the transformers with various structures respectively; acquiring target structural parameters of the target transformer, wherein the target structural parameters include at least the diameter of the core, the height of the winding, the distance between the winding and the core, and the number of insulating partitions; determining the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structural parameters, wherein the ultrasonic propagation delay prediction result represents a set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations, the ultrasonic sensor combination represents any two ultrasonic sensors in the ultrasonic sensor array, wherein the first ultrasonic sensor is used to transmit the partial discharge ultrasonic signal, and the second ultrasonic sensor is used to receive the partial discharge ultrasonic signal; and determining the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction result.

[0075] This invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: acquiring an ultrasonic propagation delay dataset, wherein the ultrasonic propagation delay dataset includes: structural parameters of transformers with various structures, and partial discharge ultrasonic signal propagation delay data corresponding to the various structures of transformers; acquiring target structural parameters of a target transformer, wherein the target structural parameters include at least the diameter of the core, the height of the winding, the distance between the winding and the core, and the number of insulating partitions; determining the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structural parameters, wherein the ultrasonic propagation delay prediction result represents a set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations, and the ultrasonic sensor combination represents any two ultrasonic sensors in an ultrasonic sensor array, wherein the first ultrasonic sensor is used to transmit partial discharge ultrasonic signals, and the second ultrasonic sensor is used to receive partial discharge ultrasonic signals; and determining the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction result.

[0076] The order of the above embodiments of the present invention is merely for description and does not represent the superiority or inferiority of the embodiments.

[0077] 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.

[0078] 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 modules described above can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between modules, and may be electrical or other forms.

[0079] The modules described above as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0080] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0081] If the aforementioned integrated modules are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of this 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 non-volatile 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 this invention. The aforementioned non-volatile 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.

[0082] 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 method for locating the partial discharge position of a transformer, characterized in that, include: Obtain an ultrasonic propagation delay dataset, wherein the ultrasonic propagation delay dataset includes: structural parameters of transformers with various structures, and propagation delay data of partial discharge ultrasonic signals corresponding to the transformers with various structures respectively; Obtain the target structural parameters of the target transformer, wherein the target structural parameters include at least the diameter of the core, the height of the winding, the distance between the winding and the core, and the number of insulating partitions; Based on the ultrasonic propagation delay dataset and the target structure parameters, the ultrasonic propagation delay prediction result of the target transformer is determined. The ultrasonic propagation delay prediction result represents a set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations. The ultrasonic sensor combination represents any two ultrasonic sensors in the ultrasonic sensor array. In the any two ultrasonic sensors, the first ultrasonic sensor is used to transmit partial discharge ultrasonic signals, and the second ultrasonic sensor is used to receive the partial discharge ultrasonic signals. Based on the ultrasonic propagation delay prediction results, the partial discharge location of the target transformer is determined.

2. The method according to claim 1, characterized in that, The acquisition of the ultrasound propagation delay dataset includes: An ultrasonic propagation simulation platform is established, wherein the ultrasonic propagation simulation platform includes a sealed container for simulating the transformer tank, a material for simulating the transformer structure, an obstacle for simulating the shape of the transformer, and an ultrasonic sensor array for measuring the partial discharge ultrasonic signal; Obtain the structural parameter space, wherein the structural parameter space is obtained based on the preset structural parameters of the transformer, the preset variation range of the preset structural parameters, and the preset step size within the preset variation range; Based on the ultrasonic propagation simulation platform and the structural parameter space, the transformers of the various structures are determined; Based on the ultrasonic propagation simulation platform, partial discharge ultrasonic signals are acquired for transformers of various structures respectively, and multiple partial discharge ultrasonic signal propagation delay data are determined. The multiple partial discharge ultrasonic signal propagation delay data correspond one-to-one with the transformers of various structures. Based on the transformers of the various structures and the propagation delay data of the multiple partial discharge ultrasonic signals, the ultrasonic propagation delay dataset is obtained.

3. The method according to claim 2, characterized in that, Based on the ultrasonic propagation simulation platform, partial discharge ultrasonic signals are acquired for transformers of various structures to determine multiple partial discharge ultrasonic signal propagation delay data, including: Based on the ultrasonic propagation simulation platform, partial discharge ultrasonic signals of any transformer structure are acquired in the following manner to obtain propagation delay data of any partial discharge ultrasonic signal: Based on the ultrasonic propagation simulation platform, multiple ultrasonic pulse transmitting ends are determined according to the preset ultrasonic sensor array layout rules, wherein the multiple ultrasonic pulse transmitting ends correspond one-to-one with the multiple ultrasonic sensors in the ultrasonic sensor array. Based on the multiple ultrasonic pulse transmitters, partial discharge ultrasonic signals are acquired on a transformer of any structure to obtain multiple ultrasonic propagation waveform data. The ultrasonic propagation waveform data is the set of signals received by the other sensors when any ultrasonic sensor is used as any ultrasonic pulse transmitter to transmit partial discharge ultrasonic signals to the other sensors. The other sensors are the sensors other than any ultrasonic sensor among the multiple ultrasonic sensors. Based on the multiple ultrasonic propagation waveform data, the propagation delay data of any partial discharge ultrasonic signal is determined; The propagation delay data of the multiple partial discharge ultrasonic signals are obtained by using the method of obtaining the propagation delay data of any one of the partial discharge ultrasonic signals.

4. The method according to claim 3, characterized in that, The step of determining the propagation delay data of any partial discharge ultrasonic signal based on the plurality of ultrasonic propagation waveform data includes: Determine the target ultrasonic propagation time for any ultrasonic propagation waveform data, wherein the target ultrasonic propagation time represents the set of times when the partial discharge ultrasonic signal is emitted from any ultrasonic pulse transmitter and first arrives at the other sensors respectively; Determine the target ultrasound propagation time corresponding to each of the plurality of ultrasound propagation waveform data; Based on the multiple ultrasonic propagation waveform data and the target ultrasonic propagation time corresponding to each of the multiple ultrasonic propagation waveform data, an ultrasonic propagation time matrix and a waveform data amplitude matrix are determined. In the ultrasonic propagation time matrix, any element represents the time it takes for the partial discharge ultrasonic signal to be transmitted from any ultrasonic pulse transmitter to any other ultrasonic sensor. In the waveform data amplitude matrix, any element represents the amplitude intensity of the partial discharge ultrasonic signal received by any other ultrasonic sensor. Based on the ultrasonic propagation time matrix and the waveform data amplitude matrix, the propagation delay data of any partial discharge ultrasonic signal is determined.

5. The method according to claim 1, characterized in that, The step of determining the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structural parameters includes: The target structural parameters are transformed into standard structural parameters that match the ultrasonic propagation delay dataset. Based on the standard structural parameters, a similarity measurement method is used to determine the transformers of the target structure, wherein the transformers of the target structure represent a predetermined number of transformers related to the target structural parameters obtained from the ultrasonic propagation delay dataset; Based on the transformer with the target structure, an interpolation prediction method is used to obtain the predicted ultrasonic propagation time delay of the target transformer.

6. The method according to claim 5, characterized in that, When there are multiple transformers in the target structure, the ultrasonic propagation time delay prediction result of the target transformer is obtained by using an interpolation prediction method based on the transformers in the target structure, including: Based on transformers with multiple target structures, an interpolation prediction method is used to determine the predicted ultrasonic propagation time delay for any combination of ultrasonic sensors in the following manner: ； in, This represents the predicted ultrasonic propagation delay for any of the ultrasonic sensor combinations. This represents the propagation delay data of the ultrasonic signal for partial discharge of a transformer with any target structure; i i and j represent the indices of any ultrasonic sensor in the ultrasonic sensor array, respectively. This represents the weight of the transformer in any of the target structures. The difference between the transformer of any target structure and the parameters of the target structure is represented; based on the similarity measurement method, n represents the index of the transformer of any target structure, and p represents the preset power parameter; By using the method of obtaining the ultrasonic propagation delay prediction result of any ultrasonic sensor combination, the ultrasonic propagation delay prediction results corresponding to each of the multiple ultrasonic sensor combinations are obtained; Based on the ultrasonic propagation delay prediction results corresponding to each of the multiple ultrasonic sensor combinations, the ultrasonic propagation delay prediction results of the target transformer are obtained.

7. The method according to claim 1, characterized in that, Determining the partial discharge location of the target transformer based on the ultrasonic propagation time delay prediction result includes: Based on the predicted ultrasonic propagation delay, a time-difference localization model for any combination of ultrasonic sensors in the following form is obtained, wherein the time-difference localization model is used to determine the propagation delay of the partial discharge ultrasonic signal in the medium: ； in, and These represent the times when the partial discharge ultrasonic signal arrives at any ultrasonic sensor in the ultrasonic sensor array from the partial discharge location; and This represents the distance from the partial discharge ultrasonic signal to each of the ultrasonic sensors, respectively; and These represent the time delay compensation values ​​for the partial discharge ultrasonic signal reaching each of the ultrasonic sensors from the partial discharge location; that is... and These represent the ultrasonic propagation delay prediction results of any combination of ultrasonic sensors in the ultrasonic propagation delay prediction results, respectively, and V represents the propagation speed of the partial discharge ultrasonic signal in the medium; By using the method of obtaining the time difference localization model of any of the ultrasonic sensor combinations, the time difference localization models corresponding to each of the multiple ultrasonic sensor combinations are obtained; The location of partial discharge of the target transformer is determined by inverting the time-difference positioning model corresponding to each of the multiple ultrasonic sensor combinations.

8. A device for locating the partial discharge position of a transformer, characterized in that, include: An ultrasonic propagation delay dataset acquisition module is used to acquire an ultrasonic propagation delay dataset, wherein the ultrasonic propagation delay dataset includes: structural parameters of transformers with various structures, and propagation delay data of partial discharge ultrasonic signals corresponding to the transformers with various structures respectively; The target structural parameter acquisition module is used to acquire the target structural parameters of the target transformer, wherein the target structural parameters include at least the diameter of the core, the height of the winding, the distance between the winding and the core, and the number of insulating partitions; An ultrasonic propagation delay prediction result determination module is used to determine the ultrasonic propagation delay prediction result of the target transformer based on the ultrasonic propagation delay dataset and the target structure parameters. The ultrasonic propagation delay prediction result represents a set of ultrasonic propagation delay prediction results corresponding to multiple ultrasonic sensor combinations. The ultrasonic sensor combination represents any two ultrasonic sensors in an ultrasonic sensor array. In the any two ultrasonic sensors, the first ultrasonic sensor is used to emit partial discharge ultrasonic signals, and the second ultrasonic sensor is used to receive the partial discharge ultrasonic signals. The partial discharge location determination module is used to determine the partial discharge location of the target transformer based on the ultrasonic propagation delay prediction results.

9. A non-volatile storage medium, characterized in that, The non-volatile storage medium stores multiple instructions adapted for loading and execution by a processor of the method for locating the partial discharge location of the transformer according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs for execution, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method for locating the partial discharge location of a transformer as described in any one of claims 1 to 7.

Images