A transformer winding axial displacement detection system, method and related equipment

Abstract

The embodiment of the present application relates to the technical field of power equipment monitoring, and discloses a transformer winding axial displacement detection system, method and related equipment. By utilizing the characteristics of high spatial resolution and strong penetration ability of pulse waves, through the use of signal transmitters and receivers, the changes of pulse waves in different states are compared, and combined with the pattern recognition ability of a preset model, the axial displacement amount of the winding can be accurately determined, realizing the online monitoring of the axial displacement of the transformer winding, without the need for professional technical operations, and avoiding related electrical risks and economic losses.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and particularly to a transformer winding axial displacement detection system, method and related equipment. Background Art

[0002] High short-circuit current is the main cause of radial deformation of transformer windings. These mechanical damages do not necessarily lead to immediate transformer failures, but will significantly reduce its ability to withstand future mechanical and dielectric stresses. In recent years, several offline methods such as short-circuit test method, low-voltage impulse method and frequency response analysis method have been proposed to detect winding deformation. However, all of the above methods are offline and require the transformer to be disconnected for measurement. This not only requires professional technicians to operate, but also may lead to related electrical risks and economic losses. Summary of the Invention

[0003] In view of this, the present invention provides a transformer winding axial displacement detection system, method and related equipment.

[0004] The specific technical solution of the first embodiment of the present invention is: a transformer winding axial displacement detection system, the system includes: a signal generator, a signal receiver, a first displacement platform, a second displacement platform and a host computer; the signal generator is arranged on the first displacement platform, the signal receiver is arranged on the second displacement platform, the first displacement platform and the second displacement platform are arranged on the same side of the transformer winding, and the distance between the first displacement platform and the transformer is the same as the distance between the second displacement platform and the transformer; the first displacement platform and the second displacement platform are used to move within a preset range; the signal generator is used to send pulse waves to the winding target point of the transformer within different moving ranges; the signal receiver is used to receive the pulse waves reflected by the winding target point; the host computer is used to obtain the time difference, the time difference is the time difference between the time when the signal generator sends the pulse wave and the time when the signal receiver receives the reflected pulse wave, and use a preset model to identify all the time differences and all the reflected pulse waves to obtain the transformer winding axial displacement data.

[0005] The specific technical solution of the second embodiment of the present invention is as follows: A method for detecting the axial displacement of a transformer winding, which is applied to the transformer winding axial displacement detection system described in the first embodiment of the present application. The method includes: controlling the first displacement platform and the second displacement platform to move within a preset range, so that the signal generator moves as the first displacement platform moves, and the signal receiver moves as the second displacement platform moves; controlling the signal generator to send a pulse wave to the target point of the winding of the transformer; controlling the signal receiver to receive the pulse wave reflected by the target point of the winding; obtaining a time difference, where the time difference is the time difference between the time when the signal generator sends the pulse wave and the time when the signal receiver receives the reflected pulse wave, and using a preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the winding of the transformer.

[0006] Preferably, the preset range includes the total positive displacement range and the total negative displacement range when the winding of the transformer has not failed.

[0007] Preferably, the using the preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the winding of the transformer includes: obtaining the Euclidean distance of each reflected pulse wave; using the preset model to identify all the Euclidean distances and all the time differences to obtain the axial displacement data of the winding.

[0008] Preferably, the preset model is used to output the axial displacement data of the winding according to different time differences and different Euclidean distances; then the using the preset model to identify all the Euclidean distances and all the time differences to obtain the axial displacement data of the winding includes: matching each time difference with the Euclidean distance corresponding to the time difference to form a feature data group; inputting all the feature data groups into the preset model, and the preset model outputs the axial displacement data according to all the feature data groups.

[0009] Preferably, the obtaining the Euclidean distance of each reflected pulse wave includes: obtaining the initially reflected pulse wave when the signal generator is at the initial position; the initial position is the position where the signal generator has not moved; obtaining the Euclidean distance of each reflected pulse wave according to all the reflected pulse waves and the initially reflected pulse wave.

[0010] Preferably, the obtaining the Euclidean distance of each reflected pulse wave according to all the reflected pulse waves and the initially reflected pulse wave includes: obtaining the first amplitude of the initially reflected pulse wave; obtaining the second amplitudes of all the reflected pulse waves; obtaining the Euclidean distance of each reflected pulse wave according to the first amplitude, all the second amplitudes and the number of reflected pulse waves.

[0011] Preferably, the Euclidean distance of each reflected pulse wave is obtained by the following formula:

[0012]

[0013] where is the Euclidean distance of the x-th reflected pulse wave, is the number of reflected pulse waves, is the second amplitude of the x-th reflected pulse wave, is the first amplitude.

[0014] The specific technical solution of the third embodiment of the present invention is: A transformer winding axial displacement detection device includes a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor executes the steps of the method described in any one of the second embodiments of the present application.

[0015] The specific technical solution of the fourth embodiment of the present invention is: A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the steps of the method described in any one of the second embodiments of the present application.

[0016] Implementing the embodiments of the present invention will have the following beneficial effects:

[0017] The present invention includes a signal generator, a signal receiver, a first displacement platform, a second displacement platform, and a host computer; the first displacement platform and the second displacement platform are used to move within a preset range; the signal generator sends pulse waves to the winding target point of the transformer within different moving ranges; the signal receiver receives the pulse waves reflected by the winding target point; the host computer obtains the time difference, which is the time difference between the time when the signal generator sends the pulse wave and the time when the signal receiver receives the reflected pulse wave, and uses a preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the transformer winding. By utilizing the characteristics of high spatial resolution and strong penetration ability of pulse waves, through the use of signal transmitters and receivers, comparing the changes of pulse waves in different states, and combining the pattern recognition ability of the preset model, the present invention can accurately determine the axial displacement of the winding, realize the on-line monitoring of the axial displacement of the transformer winding, without the need for professional technical operations, and avoid related electrical risks and economic losses. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0019] Figure 1 It is a top view of an axial displacement detection system for a transformer winding;

[0020] Figure 2 It is a schematic diagram of the displacement direction of a signal generator and a signal receiver;

[0021] Figure 3 It is a step flowchart of a method for detecting the axial displacement of a transformer winding;

[0022] Figure 4 It is a step diagram for obtaining the Euclidean distance of each reflected pulse wave;

[0023] Figure 5 It is an internal structure diagram of a computer device;

[0024] Among them, 101 is a signal generator; 102 is a signal receiver; 103 is a first displacement platform; 104 is a second displacement platform; 105 is a fixed bracket. Detailed implementation manners

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0026] The terms "first", "second", etc. in the specification, claims and drawings of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally further includes steps or modules not listed, or optionally further includes other steps or modules inherent to these processes, methods, products or devices.

[0027] References to "embodiments" in this specification mean that the particular features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0028] The first embodiment of the present application provides a schematic structural diagram of a transformer winding axial displacement detection system to achieve online monitoring of the axial displacement of the transformer winding. The system includes: a signal generator 101, a signal receiver 102, a first displacement platform 103, a second displacement platform 104, and a host computer. The signal generator 101 is disposed on the first displacement platform 103, the signal receiver 102 is disposed on the second displacement platform 104. The first displacement platform 103 and the second displacement platform 104 are disposed on the same side of the transformer winding, and the distance between the first displacement platform 103 and the transformer is the same as the distance between the second displacement platform 104 and the transformer. The first displacement platform 103 and the second displacement platform 104 are used to move within a preset range. The signal generator 101 is used to send pulse waves to the winding target point of the transformer within different moving ranges. The signal receiver 102 is used to receive the pulse waves reflected by the winding target point. The host computer is used to obtain the time difference, which is the time difference between the time when the signal generator 101 sends the pulse wave and the time when the signal receiver 102 receives the reflected pulse wave, and uses a preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the transformer winding.

[0029] Specifically, please refer to Figure 1 , the signal generator is a UWB signal generator, the signal receiver is a UWB signal receiver. A window is cut out on the transformer oil tank wall and filled with insulating material to form an insulation monitoring window. On the insulation monitoring window, the UWB signal generator and the UWB receiver are installed. The UWB signal generator emits UWB Gaussian single-cycle pulse waves to the target point on the winding at regular time intervals, and after being reflected by the winding target point, it reaches the UWB signal receiver. Due to the radial electrodynamic force on the winding, the winding will undergo slight radial displacement during operation. Therefore, first, a piezoelectric ceramic displacement platform is used to change the positions of the UWB signal generator, the UWB receiver, and the winding target point in the non-operating state of the transformer to simulate the radial displacement of the transformer winding.

[0030] In a specific embodiment, please refer to Figure 2, a signal generator and a signal receiver are installed on a fixed bracket 105. The UWB signal generator and the signal receiver are respectively placed on two piezoelectric ceramic displacement platforms. The two piezoelectric ceramic displacement platforms are adjusted synchronously to change the length d4 of the piezoelectric ceramics simultaneously, so as to finely adjust the positions of the WUB signal generator and the receiver synchronously. The total range needs to be determined according to the maximum displacement caused by the radial electrodynamic force during the normal operation of the winding, and can be determined according to physical structure parameters such as the electrical parameters of the transformer and the yield strength of the winding. Since the winding will receive outward and inward radial electrodynamic forces that change periodically during operation, the total range of the positive displacement of the winding is set as D1 (mm), the total range of the negative displacement is D2 (mm), and the initial position in the non-operating state is 0. The signal generator moves within the range of (-D2, D1) with the initial position as the coordinate origin and sends a pulse wave to the winding target point of the transformer; the signal receiver is used to receive the pulse wave reflected by the winding target point; the upper computer obtains the time difference between the pulse wave received by each signal receiver and the pulse wave sent by the signal generator, and uses a preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the transformer winding.

[0031] The system in this embodiment utilizes the characteristics of high spatial resolution and strong penetration ability of the pulse wave. By using signal transmitters and receivers, comparing the changes of the pulse waves in different states, and combining the pattern recognition ability of the preset model, the axial displacement of the winding can be accurately determined, realizing the online monitoring of the axial displacement of the transformer winding, without the need for professional technical operations, and avoiding related electrical risks and economic losses.

[0032] In a specific embodiment, please refer to Figure 3 , which is the step flow chart of a method for detecting the axial displacement of a transformer winding in the second embodiment of the present application, and is applied to the transformer winding axial displacement detection system as described in the first embodiment of the present application. The method is characterized in that the method includes:

[0033] Step 201, control the first displacement platform and the second displacement platform to move within a preset range, so that the signal generator moves with the movement of the first displacement platform, and the signal receiver moves with the movement of the second displacement platform;

[0034] Step 202, control the signal generator to send a pulse wave to the winding target point of the transformer;

[0035] Step 203, control the signal receiver to receive the pulse wave reflected by the winding target point;

[0036] Step 204: Obtain the time difference, which is the time difference between the time when the signal generator sends the pulse wave and the time when the signal receiver receives the reflected pulse wave, and use a preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the transformer winding.

[0037] Specifically, adjust the piezoelectric ceramic displacement platform so that the UWB signal generator performs a step-by-step scan within the range of (-D2, D1) with a step size of 1 mm. After each distance adjustment, the UWB signal generator emits a UWB Gaussian single-cycle pulse wave, which is received by the signal receiver after being reflected by the winding target point. Record the time difference ∆t spent from when the signal generator emits the signal to when the signal receiver receives the UWB signal after each distance adjustment, and the UWB pulse wave A(x) received by the signal receiver, where the UWB pulse wave received at the initial position is A(0). Based on all the time differences ∆t, all the A(x) and A(0), and using a preset model for identification, obtain the axial displacement data of the transformer winding.

[0038] This method utilizes the characteristics of high spatial resolution and strong penetration ability of the pulse wave. By using signal transmitters and receivers, comparing the changes in the pulse waves in different states, and combining the pattern recognition ability of the preset model, it can accurately determine the axial displacement of the winding, realize the online monitoring of the axial displacement of the transformer winding, without the need for professional technical operations, and avoid relevant electrical risks and economic losses.

[0039] In a specific embodiment, the preset range includes the total positive displacement range and the total negative displacement range when the windings of the transformer are not faulty. Specifically, the windings will contract and expand under the action of electrodynamic force, and the amount of contraction and expansion is the total displacement range of the windings. The measurement of winding displacement usually involves accurately capturing and recording the change in the position of the windings. This can be achieved through various sensors and measuring devices, such as displacement sensors, laser rangefinders, etc. These devices can monitor the position change of the windings in real time and convert these changes into electrical signals or other recordable forms. Specifically, select appropriate displacement measuring devices, such as displacement sensors, laser rangefinders, etc., to ensure that the accuracy and precision of the measuring device meet the measurement requirements. Install the measuring device at a position where the displacement change of the windings can be accurately captured, ensure the stable and reliable connection between the measuring device and the windings, and avoid measurement errors. Before the formal measurement, calibrate the measuring device to ensure the accuracy of its measurement results. Start the measuring device and start recording the position change of the windings. According to needs, the displacement data of the windings at different time points can be recorded. Process and analyze the collected displacement data to calculate the total positive displacement range and the total negative displacement range when the windings are not faulty. Statistical methods, data fitting and other techniques can be used to extract and analyze the key information in the data. The total positive displacement range refers to the maximum distance that the winding moves in the positive direction relative to its initial position during normal operation. The total positive displacement range can be obtained by calculating the maximum displacement value during the positive movement of the winding. The total negative displacement range refers to the maximum distance that the winding moves in the negative direction relative to its initial position during normal operation. The total negative displacement range can be obtained by calculating the maximum displacement value during the negative movement of the winding.

[0040] In a specific embodiment, the utilization of the preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the windings of the transformer includes: obtaining the Euclidean distance of each reflected pulse wave; using the preset model to identify all the Euclidean distances and all the time differences to obtain the axial displacement data of the windings. Specifically, the preset model can be a neural network. The neural network can finely process time information, use the time difference of the pulse signal to accurately measure the distance and displacement, so as to achieve high-precision acquisition of the axial displacement data of the windings.

[0041] In a specific embodiment, obtaining the Euclidean distance of each reflected pulse wave includes: obtaining the initially reflected pulse wave when the signal generator is at the initial position; the initial position is the position where the signal generator has not moved; obtaining the Euclidean distance of each reflected pulse wave based on all the reflected pulse waves and the initially reflected pulse wave. Specifically, to simplify the calculation amount during on-site use, based on the feature value of the Magnitude Euclidean Distance (MED) index, the difference points between the reflected pulse waves received by the signal receiver under different displacement conditions and the reflected pulse waves at the initial position are compared.

[0042] In a specific embodiment, refer to Figure 4 , obtaining the Euclidean distance of each reflected pulse wave based on all the reflected pulse waves and the initially reflected pulse wave includes:

[0043] Step 301, obtaining the first amplitude of the initially reflected pulse wave;

[0044] Step 302, obtaining the second amplitudes of all the reflected pulse waves;

[0045] Step 303, obtaining the Euclidean distance of each reflected pulse wave based on the first amplitude, all the second amplitudes, and the number of reflected pulse waves.

[0046] Specifically, the amplitude of a pulse wave reflects the intensity or magnitude of the pulse wave. When a pulse wave encounters different media or obstacles, it will be reflected, and the formed wave is the reflected pulse wave. By calculating the Euclidean distance of each reflected pulse wave, the differences between the pulse waves can be quantitatively analyzed. This quantitative analysis helps to more accurately identify and analyze the characteristics of the pulse wave, such as waveform changes, attenuation degree, etc.; calculating the Euclidean distance by combining the first amplitude, all the second amplitudes, and the number of reflected pulse waves can improve the measurement accuracy. Because this method comprehensively considers multiple characteristic parameters of the pulse wave and can more comprehensively reflect the change situation of the pulse wave.

[0047] In a specific embodiment, the Euclidean distance of each reflected pulse wave is obtained by the following formula:

[0048]

[0049] Wherein, is the Euclidean distance of the x-th reflected pulse wave, is the number of reflected pulse waves, is the second amplitude of the x-th reflected pulse wave, is the first amplitude.

[0050] In a specific embodiment, the preset model is used to output winding axial displacement data according to different time differences and different Euclidean distances; then the use of the preset model to identify all Euclidean distances and all time differences to obtain the winding axial displacement data includes: matching each time difference with the Euclidean distance corresponding to the time difference into a feature data group; inputting all the feature data groups into the preset model, and the preset model outputs the winding axial displacement data according to all the feature data groups.

[0051] Specifically, the data group obtained by step-scanning at 1 mm intervals within the range of (-D2, D1) is [P(x)] = [P(-D2), P(-D2 + 1), ··· P(0), ···, P(D1 - 1), P(D1)] = [(∆t(-D2), MED(-D2)), (∆t(-D2 + 1), MED(-D2 + 1)), ···, (∆t(0), 0), ···, (∆t(D1 - 1), MED(D1 - 1)), (∆t(D1), MED(D1))], where (∆t(-D2), MED(-D2)) is a pair of feature data groups, (∆t(-D2 + 1), MED(-D2 + 1)) is a pair of feature data groups, and all the feature data groups are input into the neural network, and the neural network outputs the winding axial displacement data according to all the feature data groups.

[0052] In a specific embodiment, a neural network is trained using a reference data group to enable it to obtain the characteristics of the UWB pulse wave reception time and the Euclidean distance of the signal amplitude after different radial displacements occur under the action of normal radial electrodynamic force in the transformer winding. Multiple scans can be performed when obtaining the reference data to obtain multiple reference data groups, making the training data more accurate. The neural network simplifies the calculation of the radial displacement amount during the operation of the transformer and determines whether the radial displacement amount meets the characteristics of the reference data. Through the judgment of the pre-trained neural network, the computational amount of the system can be greatly reduced, enabling the on-site monitoring results to be obtained more quickly and being more applicable to the substation site.

[0053] The high spatial resolution of the pulse wave enables precise capture of the minute axial displacement changes of the winding. By comparing the pulse waves in different states, high-precision measurement of the winding displacement can be achieved, improving the accuracy of the measurement. This method does not require direct contact with the winding, avoiding errors and interference caused by contact. Non-contact detection is also applicable to complex structures that are difficult to directly access, enhancing the flexibility and safety of the measurement. The pulse wave technology can monitor the axial displacement of the winding in real time, promptly detecting abnormal changes. Combining with the pattern recognition ability of the preset model, early warning of the winding state can be given, potential faults can be detected in advance, and equipment damage and accidents can be avoided. The pulse wave has strong penetration ability, capable of penetrating the complex structures and materials inside the transformer to achieve accurate measurement of the winding displacement. This makes this method applicable to the measurement of transformer winding displacement in various complex environments, expanding the application scope and reliability of the measurement. By collecting and analyzing the pulse wave data, visual images and reports of the winding displacement can be generated. This helps the operation and maintenance personnel intuitively understand the winding state, conduct data analysis and fault diagnosis, providing strong support for the maintenance and management of the equipment. This method can achieve rapid and accurate measurement of the winding displacement, improving the operation and maintenance efficiency. At the same time, through real-time monitoring and early warning, the equipment failure downtime can be reduced, the maintenance cost can be lowered, and the operation reliability and economy of the transformer can be improved. Measuring the axial displacement of the transformer winding using the pulse wave technology has multiple substantial benefits such as high precision, non-contact detection, real-time monitoring and early warning, applicability to complex environments, data visualization and analysis, and improvement of operation and maintenance efficiency. These advantages make this method have broad application prospects and important practical value in the field of transformer winding displacement measurement.

[0054] In a specific embodiment, the third embodiment of the present application provides a transformer winding axial displacement detection device, including a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to execute the steps of the method according to any one of the second embodiments of the present application. The device in this embodiment utilizes the characteristics of the pulse wave with high spatial resolution and strong penetration ability. By using a signal transmitter and receiver, comparing the changes in the pulse waves in different states, and combining with the pattern recognition ability of the neural network, the axial displacement of the winding can be accurately determined, realizing online monitoring of the axial displacement of the transformer winding, without the need for professional technical operations, and avoiding related electrical risks and economic losses.

[0055] In a specific embodiment, the fourth embodiment of the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor causes the processor to execute the steps of the method according to any one of the second embodiments of the present application. The storage medium in this embodiment utilizes the characteristics of high spatial resolution and strong penetration ability of pulse waves. By using a signal transmitter and receiver, comparing the changes in pulse waves in different states, and combining the pattern recognition ability of a neural network, the axial displacement of the winding can be accurately determined, realizing online monitoring of the axial displacement of the transformer winding, without the need for professional technical operations, and avoiding related electrical risks and economic losses.

[0056] Figure 5 The internal structure diagram of a computer device in an embodiment is shown. This computer device can specifically be a terminal or a server. Please refer to Figure 5 , this computer device includes a processor, a memory, etc. connected by a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of this computer device stores an operating system and can also store a computer program, which when executed by the processor can cause the processor to implement the method in this embodiment. The internal memory can also store a computer program, which when executed by the processor can cause the processor to execute the method in this embodiment. Those skilled in the art can understand that Figure 5 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0057] The above embodiments only represent several implementation manners of the present application, and their descriptions are relatively specific and detailed, but should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

[0058] The above is only a preferred embodiment of the present invention, and it is not a limitation of the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as the technical content of the present invention is not departed from, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims

1. A transformer winding axial displacement detection system, characterized in that, The system includes: a signal generator, a signal receiver, a first displacement platform, a second displacement platform, and a host computer; The signal generator is arranged on the first displacement platform, the signal receiver is arranged on the second displacement platform, the first displacement platform and the second displacement platform are arranged on the same side of the transformer winding, and the distance between the first displacement platform and the transformer is the same as the distance between the second displacement platform and the transformer; The first displacement platform and the second displacement platform are moved within a preset range by changing their lengths; The signal generator is used to send pulse waves to the target point of the transformer winding within different moving ranges; The signal receiver is used to receive the pulse waves reflected by the target point of the winding; The host computer is used to obtain the time difference, which is the time difference between the time when the signal generator sends the pulse wave and the time when the signal receiver receives the reflected pulse wave, and uses a preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the transformer winding; The preset range includes the total range of positive radial displacement and the total range of negative radial displacement when the transformer winding is not faulty and undergoes radial positive and negative displacements due to periodic changes in operation under radial electrodynamic forces acting outward or inward; The step of using the preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the transformer winding includes: Obtaining the Euclidean distance of each reflected pulse wave; Using the preset model to identify all the Euclidean distances and all the time differences to obtain the axial displacement data of the winding; The Euclidean distance of each reflected pulse wave is obtained by the following formula: wherein, is the Euclidean distance of the x-th reflected pulse wave, is the number of reflected pulse waves, is the second amplitude of the x-th reflected pulse wave, is the first amplitude.

2. A method for detecting the axial displacement of a transformer winding, which is applied to the transformer winding axial displacement detection system as described in claim 1, and is characterized in that, The method includes: Controlling the first displacement platform and the second displacement platform to move within a preset range, so that the signal generator moves with the movement of the first displacement platform, and the signal receiver moves with the movement of the second displacement platform; Controlling the signal generator to send pulse waves to the target point of the transformer winding; Controlling the signal receiver to receive the pulse waves reflected by the target point of the winding; Obtaining the time difference, which is the time difference between the time when the signal generator sends the pulse wave and the time when the signal receiver receives the reflected pulse wave, and using a preset model to identify all the time differences and all the reflected pulse waves to obtain the axial displacement data of the transformer winding.

3. The method for detecting the axial displacement of a transformer winding according to claim 2, wherein, The preset model is used to output the axial displacement data of the winding according to different time differences and different Euclidean distances; then the step of using the preset model to identify all the Euclidean distances and all the time differences to obtain the axial displacement data of the winding includes: Matching each time difference with the Euclidean distance corresponding to the time difference to form a feature data group; Inputting all the feature data groups into the preset model, and the preset model outputs the axial displacement data of the winding according to all the feature data groups.

4. The transformer winding axial displacement detection method according to claim 3, wherein The step of obtaining the Euclidean distance of each reflected pulse wave includes: Obtain the pulsed wave of the initial reflection when the signal generator is in the initial position; the initial position is the position where the signal generator has not moved. Obtain the Euclidean distance of each reflected pulsed wave based on all the reflected pulsed waves and the pulsed wave of the initial reflection.

5. The transformer winding axial displacement detection method according to claim 4, characterized in that, The obtaining of the Euclidean distance of each reflected pulsed wave based on all the reflected pulsed waves and the pulsed wave of the initial reflection includes: Obtain the first amplitude of the pulsed wave of the initial reflection. Obtain the second amplitudes of all the reflected pulsed waves. Obtain the Euclidean distance of each reflected pulsed wave based on the first amplitude, all the second amplitudes, and the number of the reflected pulsed waves.

6. A transformer winding axial displacement detection device, comprising a memory and a processor, characterized in that, The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to execute the steps of the method according to any one of claims 2 to 5.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the processor is caused to execute the steps of the method according to any one of claims 2 to 5.

Images