A method and system for online rapid evaluation of transformer mechanical status

Abstract

The present invention relates to the technical field of transformers and discloses a method and system for online rapid assessment of the mechanical state of a transformer. The method comprises: installing N pairs of signal generators and signal receivers on the oil tank wall of the transformer to be tested, and assessing whether the mechanical state of the transformer to be tested has changed by determining a model discrimination result of a scattered signal transfer matrix. The method can intuitively and accurately assess whether the mechanical state of the transformer has changed without relying on indirect parameters, significantly improving the intuitiveness and accuracy of the assessment. At the same time, the method also enhances the ability to assess the mechanical state of the iron core without combining with other specialized methods, effectively solving the problems in the prior art of non-intuitive assessment results, limited accuracy, and weak ability to assess the mechanical state of the iron core.

Description

Technical Field

[0001] The present invention relates to the technical field of transformers, and in particular to a method and system for online rapid evaluation of a transformer's mechanical state. Background Art

[0002] Transformers are essential components of power systems, with their core function being the transmission and distribution of electrical energy. However, transformers can encounter a variety of faults during operation, particularly mechanical winding and core failures, which pose a serious threat to the stable operation of power systems.

[0003] Currently, the industry has developed a variety of transformer mechanical condition assessment methods, such as short-circuit impedance, vibration frequency response, and vibration detection. However, these methods rely on indirect evaluation of the transformer's electrical and mechanical parameters. This leads to limited intuitiveness and accuracy, and they are also weak in assessing the core's mechanical condition, often requiring integration with other specialized methods. Summary of the Invention

[0004] Based on this, it is necessary to address the above-mentioned problems and propose an online rapid evaluation method and system for the mechanical state of a transformer. This method can intuitively and accurately evaluate whether the mechanical state of the transformer has changed without relying on indirect parameters, significantly improving the intuitiveness and accuracy of the evaluation. At the same time, this method also enhances the ability to evaluate the mechanical state of the core without combining other specialized methods, effectively solving the problems of non-intuitive evaluation results, limited accuracy, and weak ability to evaluate the mechanical state of the core in the existing technology.

[0005] To achieve the above objectives, the present invention provides, in a first aspect, a method for online rapid evaluation of a transformer's mechanical state, the method comprising:

[0006] When the transformer under test is in operation, controlling N signal generators to emit N scattered signals of different frequencies, and obtaining N×N scattered signals received by N signal receivers, wherein N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer under test, and N is greater than or equal to 2;

[0007] Determine a sent scattered signal matrix based on N scattered signals of different frequencies, and determine a received scattered signal matrix based on N×N scattered signals;

[0008] Determine a scattered signal transfer matrix according to the emitted scattered signal matrix and the received scattered signal matrix;

[0009] Inputting the scattered signal transfer matrix into a preset machine learning model to obtain a discrimination result;

[0010] According to the determination result, it is evaluated whether the mechanical state of the transformer to be tested has changed.

[0011] Optionally, the received scattered signal matrix includes a received scattered signal amplitude matrix and a received scattered signal phase matrix, the transmitted scattered signal matrix includes a transmitted scattered signal amplitude matrix and a transmitted scattered signal phase matrix, and the scattered signal transfer matrix includes a scattered signal amplitude transfer matrix and a scattered signal phase transfer matrix. Determining the scattered signal transfer matrix based on the transmitted scattered signal matrix and the received scattered signal matrix includes:

[0012] The scattered signal amplitude transfer matrix is determined according to the received scattered signal amplitude matrix and the transmitted scattered signal amplitude matrix, and the scattered signal phase transfer matrix is determined according to the received scattered signal phase matrix and the transmitted scattered signal phase matrix.

[0013] Optionally, determining the scattered signal amplitude transfer matrix according to the received scattered signal amplitude matrix and the transmitted scattered signal amplitude matrix, and determining the scattered signal phase transfer matrix according to the received scattered signal phase matrix and the transmitted scattered signal phase matrix, comprises:

[0014] Using the formula Determining the scattered signal amplitude transfer matrix and the scattered signal phase transfer matrix;

[0015] in, , ;

[0016] In the above formula, is the nth row and nth column element in the received scattered signal amplitude matrix, is the nth row and 1st column element in the emitted scattered signal amplitude matrix, is the nth row and nth column element in the received scattered signal phase matrix, is the nth row and nth column element in the phase matrix of the emitted scattered signal, is the nth row and nth column element in the scattered signal amplitude transfer matrix, is the element in the nth row and nth column of the scattered signal phase transfer matrix.

[0017] Optionally, the method further includes:

[0018] Constructing a transformer physical simulation model of the transformer to be tested;

[0019] When the transformer physical simulation model is running, controlling N simulation signal generators to emit N simulation scattered signals of different frequencies, and obtaining N×N scattered signals received by N simulation signal receivers, wherein N pairs of simulation signal generators and simulation signal receivers are installed on the oil tank wall of the transformer physical simulation model;

[0020] Determining a simulated scattered signal matrix based on N simulated scattered signals of different frequencies, and determining a simulated scattered signal matrix based on N×N scattered signals;

[0021] Determine a simulated scattered signal transfer matrix according to the simulated emitted scattered signal matrix and the simulated received scattered signal matrix;

[0022] Adjusting the simulation parameters of the transformer physical simulation model according to the normal mechanical state variation range of the transformer under normal electromotive force, and returning to the step of controlling the N simulation signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by the N simulation signal receivers during each adjustment until the adjustment is completed, thereby obtaining multiple simulated scattered signal transfer matrices, and using the multiple simulated scattered signal transfer matrices as normal scattered signal transfer matrices;

[0023] Adjusting the simulation parameters of the transformer physical simulation model according to the range of abnormal mechanical state changes of the transformer under test when the transformer exceeds the normal electromotive force, and returning to the step of controlling N simulation signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by N simulation signal receivers during each adjustment until the adjustment is completed, thereby obtaining multiple simulated scattered signal transfer matrices, and using the multiple simulated scattered signal transfer matrices as abnormal scattered signal transfer matrices;

[0024] A plurality of normally adjusted scattered signal transfer matrices and a plurality of abnormally adjusted scattered signal transfer matrices are input into an initial machine learning model for training to obtain the preset machine learning model.

[0025] Optionally, before controlling the N simulated signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by the N simulated signal receivers, the method further includes:

[0026] The simulation parameters of the transformer physical simulation model are calibrated according to the reference scattered signal transfer matrix.

[0027] Optionally, the method further includes:

[0028] When the transformer to be tested is not in operation, controlling N signal generators to emit N scattered signals of different frequencies, obtaining N×N scattered signals received by N signal receivers, and using the N scattered signals of different frequencies as references to emit scattered signals, and using the N×N scattered signals as references to receive scattered signals;

[0029] Determine a reference transmitted scattered signal matrix based on N reference transmitted scattered signals of different frequencies, and determine a reference received scattered signal matrix based on N×N reference received scattered signals;

[0030] The reference scattered signal transfer matrix is determined according to the reference transmitted scattered signal matrix and the reference received scattered signal matrix.

[0031] Optionally, determining a transmitted scattered signal matrix according to N scattered signals of different frequencies, and determining a received scattered signal matrix according to N×N scattered signals, includes:

[0032] Extracting the amplitude and phase of each of the N scattered signals with different frequencies to obtain N emitted scattered signal amplitudes and N emitted scattered signal phases;

[0033] Determining an N×1 transmitted scattered signal amplitude matrix based on the N transmitted scattered signal amplitudes, and determining an N×N transmitted scattered signal phase matrix based on the N transmitted scattered signal phases;

[0034] Taking an N×1 emitted scattered signal amplitude matrix and an N×N emitted scattered signal phase matrix as the emitted scattered signal matrix;

[0035] Amplitude and phase extraction are performed on each of the N×N scattered signals to obtain N×N received scattered signal amplitudes and N×N received scattered signal phases;

[0036] Determining an N×1 received scattered signal amplitude matrix based on the N×N received scattered signal amplitudes, and determining an N×N received scattered signal phase matrix based on the N×N received scattered signal phases;

[0037] An N×1 received scattered signal amplitude matrix and an N×N received scattered signal phase matrix are used as the received scattered signal matrix.

[0038] Optionally, controlling N signal generators to emit N scattered signals of different frequencies and obtaining N×N scattered signals received by N signal receivers includes:

[0039] Divide the preset frequency domain range into N frequency domain ranges equally;

[0040] Extract the jth frequency in each frequency domain range to obtain the scattered signal frequency group, where the initial value of j is 1;

[0041] According to the scattered signal frequency group, controlling N signal generators to emit N scattered signals of different frequencies, and obtaining N×N scattered signals received by N signal receivers;

[0042] The step of evaluating whether the mechanical state of the transformer to be tested has changed according to the determination result includes:

[0043] Returning to the steps of determining a sent scattered signal matrix based on N scattered signals of different frequencies, and determining a received scattered signal matrix based on N×N scattered signals, until the discrimination result is obtained;

[0044] Let j = j + 1, and return to the step of extracting the jth frequency in each frequency domain range to obtain a scattered signal frequency group, until j equals the maximum number of frequency sweeps, and a plurality of the discrimination results are obtained;

[0045] Based on all the determination results, it is evaluated whether the mechanical state of the transformer to be tested has changed.

[0046] Optionally, controlling N signal generators to emit N scattered signals of different frequencies and obtaining N×N scattered signals received by N signal receivers includes:

[0047] Control N signal generators to emit N scattered signals of different frequencies, and obtain N×N intermediate scattered signals received by N signal receivers at the i-th time, where the initial value of i is 1;

[0048] Let i = i + 1, and return to the step of controlling the N signal generators to emit N scattered signals of different frequencies, and obtaining the N×N intermediate scattered signals received by the N signal receivers for the i-th time, until the intermediate scattered signal attenuation value corresponding one-to-one between the N×N intermediate scattered signals received for the i-th time and the N×N intermediate scattered signals received for the first time is less than the attenuation threshold, thereby obtaining the N×N intermediate scattered signals received multiple times;

[0049] Among the N×N intermediate scattered signals received multiple times, the N×N intermediate scattered signals received at any one time are regarded as the N×N scattered signals.

[0050] To achieve the above object, the present invention provides, in a second aspect, a system for online rapid evaluation of a transformer mechanical state, the system comprising N signal generators, N signal receivers, and a processor;

[0051] N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer to be tested;

[0052] The processor is configured to execute the method as described in any one of the first aspects.

[0053] To achieve the above-mentioned object, the present invention provides, in a third aspect, a device for online rapid evaluation of a transformer mechanical state, the device comprising:

[0054] A control module is configured to control N signal generators to emit N scattered signals of different frequencies when the transformer under test is in operation, and obtain N×N scattered signals received by N signal receivers, wherein N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer under test, and N is greater than or equal to 2;

[0055] A first determining module is configured to determine a sent scattered signal matrix based on N scattered signals of different frequencies, and to determine a received scattered signal matrix based on N×N scattered signals;

[0056] A second determining module is configured to determine a scattered signal transfer matrix according to the emitted scattered signal matrix and the received scattered signal matrix;

[0057] A model discrimination module, configured to input the scattered signal transfer matrix into a preset machine learning model to obtain a discrimination result;

[0058] An evaluation module is used to evaluate whether the mechanical state of the transformer to be tested has changed according to the judgment result.

[0059] To achieve the above-mentioned objectives, the present invention provides, in a fourth aspect, a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the method as described in any one of the first aspects.

[0060] To achieve the above-mentioned objectives, the present invention provides a computer device in a fifth aspect, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method as described in any one of the first aspects.

[0061] The embodiment of the present invention has the following beneficial effects: the above method controls N signal generators to emit N scattered signals of different frequencies when the transformer to be tested is running, obtains N×N scattered signals received by N signal receivers, wherein N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer to be tested, and N is greater than or equal to 2, and then determines the emitted scattered signal matrix according to the N scattered signals of different frequencies, and determines the received scattered signal matrix according to the N×N scattered signals, and then determines the scattered signal transfer matrix according to the emitted scattered signal matrix and the received scattered signal matrix, and inputs the scattered signal transfer matrix into a preset machine learning model to obtain a discriminant. As a result, it is finally evaluated whether the mechanical state of the transformer to be tested has changed based on the discrimination result; that is, by installing N pairs of signal generators and signal receivers on the oil tank wall of the transformer to be tested, and by determining the model discrimination result of the scattered signal transfer matrix, it is evaluated whether the mechanical state of the transformer to be tested has changed. This can intuitively and accurately evaluate whether the mechanical state of the transformer has changed without relying on indirect parameters, which significantly improves the intuitiveness and accuracy of the evaluation. At the same time, this method also enhances the ability to evaluate the mechanical state of the core, without the need to combine other special methods, and effectively solves the problems in the existing technology of non-intuitive evaluation results, limited accuracy and weak ability to evaluate the mechanical state of the core. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] in:

[0064] Figure 1 Schematic diagram of a method for online rapid evaluation of transformer mechanical status in an embodiment of the present application.

[0065] Figure 2 Schematic diagram of the installation relationship between the transformer to be tested, the signal generator and the signal receiver as exemplified in the embodiment of the present application;

[0066] Figure 3 This is a schematic diagram of an online rapid evaluation device for a transformer mechanical state according to an embodiment of the present application;

[0067] Figure 4 1 is a diagram of the internal structure of a computer device in some embodiments. DETAILED DESCRIPTION

[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0069] Transformers are essential components of power systems, with their core function being the transmission and distribution of electrical energy. However, transformers can encounter a variety of faults during operation, particularly mechanical winding and core failures, which pose a serious threat to the stable operation of power systems.

[0070] Currently, the industry has developed a variety of transformer mechanical condition assessment methods, such as short-circuit impedance, vibration frequency response, and vibration detection. However, these methods rely on indirect evaluation of the transformer's electrical and mechanical parameters. This leads to limited intuitiveness and accuracy, and they are also weak in assessing the core's mechanical condition, often requiring integration with other specialized methods.

[0071] In response to the above problems, the present application proposes a method and system for online rapid evaluation of the mechanical state of a transformer, which can intuitively and accurately evaluate whether the mechanical state of the transformer has changed without relying on indirect parameters, significantly improving the intuitiveness and accuracy of the evaluation. At the same time, this method also enhances the ability to evaluate the mechanical state of the core, without the need to combine other specialized methods, and effectively solves the problems in the prior art of non-intuitive evaluation results, limited accuracy, and weak ability to evaluate the mechanical state of the core. The specific implementation principle will be described in detail in the following embodiments.

[0072] In a first aspect, the present application provides a method for online rapid evaluation of a transformer's mechanical state.

[0073] See also Figure 1 , is a schematic diagram of a method for online rapid evaluation of a transformer mechanical state in an embodiment of the present application, the method comprising:

[0074] Step 110: When the transformer under test is in operation, control N signal generators to emit N scattered signals of different frequencies, and obtain N×N scattered signals received by N signal receivers, where N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer under test, and N is greater than or equal to 2.

[0075] The transformer to be tested refers to a transformer that requires online evaluation of its mechanical condition.

[0076] It should be noted that after controlling N signal generators to emit N scattered signals of different frequencies, the N scattered signals of different frequencies will be reflected in the oil tank of the transformer under test until they are received by N signal receivers to obtain N×N scattered signals.

[0077] It should be further explained that the frequencies of the N signal generators must be different so as to emit scattered signals of N different frequencies, and the frequency band of each signal receiver must include the frequencies of the N signal generators so as to receive scattered signals of all frequencies.

[0078] Regarding the installation method of N signal generators and N signal receivers, in some embodiments, a preset number of windows can be cut out on the oil tank wall of the transformer to be tested, and these windows can be filled with insulating material to form insulation detection windows. Finally, the N signal generators and N signal receivers are installed on the oil tank wall of the transformer to be tested; wherein, the specific number of the preset windows can be obtained and pre-set by the operator based on a large amount of experience, experiments or statistics, and of course, can also be set by the operator according to actual needs.

[0079] In some embodiments, the specific number of preset windows may be 2N or N, depending on the circumstances.

[0080] In the present application, the paired signal generator and signal receiver are preferably arranged on diagonal lines of the oil tank of the transformer to be tested.

[0081] For example, assuming the number of pairs of signal generators and signal receivers is 2, refer to Figure 2 , is a schematic diagram of the installation relationship between the transformer to be tested, the signal generator and the signal receiver as illustrated in the embodiment of the present application. The schematic diagram shows 210 as the oil tank of the transformer to be tested, 220 as the signal generator, 230 as the signal receiver, and 240 as the insulation detection window.

[0082] Step 120: Determine a transmitted scattered signal matrix according to N scattered signals of different frequencies, and determine a received scattered signal matrix according to N×N scattered signals.

[0083] In some embodiments, the phases of N scattered signals of different frequencies can be combined to form an emitted scattered signal phase matrix, the amplitudes of N scattered signals of different frequencies can be combined to form an emitted scattered signal amplitude matrix, the integral values of N scattered signals of different frequencies can be combined to form an emitted scattered signal integral value matrix, or the data point average values of N scattered signals of different frequencies can be combined to form an emitted scattered signal data point average value matrix, and then at least one of the emitted scattered signal phase matrix, the emitted scattered signal amplitude matrix, the emitted scattered signal integral value matrix and the emitted scattered signal data point average value matrix can be used as the emitted scattered signal matrix; similarly, the method for determining the received scattered signal matrix is similar.

[0084] Step 130: Determine a scattered signal transfer matrix based on the sent scattered signal matrix and the received scattered signal matrix.

[0085] It should be noted that the scattered signal transfer matrix corresponds to the emitted scattered signal matrix and the received scattered signal matrix; for example, when the scattered signal transfer matrix includes the emitted scattered signal phase matrix and the received scattered signal matrix includes the received scattered signal phase matrix, the scattered signal transfer matrix includes the scattered signal phase transfer matrix; when the scattered signal transfer matrix includes the emitted scattered signal phase matrix and the emitted scattered signal amplitude matrix, and the received scattered signal matrix includes the received scattered signal phase matrix and the received scattered signal amplitude matrix, the scattered signal transfer matrix includes the scattered signal phase transfer matrix and the scattered signal amplitude transfer matrix.

[0086] Regarding the method for determining the scattered signal transfer matrix, in some embodiments, it can be determined by using two known numbers to solve one unknown number, that is, it can be determined by using a column equation.

[0087] Step 140: Input the scattered signal transfer matrix into a preset machine learning model to obtain a discrimination result.

[0088] Among them, the preset machine learning model here refers to a machine learning model that has been trained and can be directly used to predict the output discrimination result based on the input scattering signal transfer matrix.

[0089] In some embodiments, a large number of scattered signal transfer matrices and the discrimination results corresponding to the scattered signal transfer matrices can be used, and then all the scattered signal transfer matrices and the discrimination results corresponding to the scattered signal transfer matrices can be input into the initial machine learning model in sequence for training. After training to a certain extent, a trained preset machine learning model can be obtained; wherein, the discrimination results corresponding to the scattered signal transfer matrices can be used as the true value of the initial machine learning model, that is, by comparing the true value with the discrimination results output during the training process one by one, it can be determined whether the initial machine learning model is well trained and has met the expected requirements.

[0090] In some embodiments, the determination result may be 1 or 0 (or close to 1 or 0), true or false, or right or wrong, etc., so as to clearly evaluate whether the mechanical state of the transformer under test has changed.

[0091] Step 150: Evaluate whether the mechanical state of the transformer to be tested has changed based on the determination result.

[0092] It should be noted that since the scattered signal matrix is obtained by reflecting N scattered signals of different frequencies in the oil tank of the transformer to be tested, the scattered signal matrix can reflect the mechanical conditions in the oil tank of the transformer to be tested, and the scattered signal transfer matrix is also obtained based on the scattered signal matrix. Therefore, the model judgment result of the scattered signal transfer matrix can be used to evaluate whether the mechanical state of the transformer to be tested has changed.

[0093] In some embodiments, if the determination result is 1 or close to 1, it indicates that the mechanical state of the transformer under test has changed; if the determination result is 0 or close to 0, it indicates that the mechanical state of the transformer under test has not changed.

[0094] It should also be noted that, in addition to evaluating whether the mechanical state of the winding and the mechanical state or position of the core have changed, the method of the present application can also evaluate whether the mechanical state or position of other mechanical components in the transformer to be tested has changed; for example, the pads, clamps, fasteners, etc. of the transformer to be tested.

[0095] In an embodiment of the present application, by installing N pairs of signal generators and signal receivers on the oil tank wall of the transformer to be tested, and by determining the model discrimination result of the scattered signal transfer matrix, it is possible to evaluate whether the mechanical state of the transformer to be tested has changed. This allows for intuitive and accurate evaluation of whether the mechanical state of the transformer has changed without relying on indirect parameters, significantly improving the intuitiveness and accuracy of the evaluation. At the same time, this method also enhances the ability to evaluate the mechanical state of the iron core without the need to combine other specialized methods, effectively solving the problems in the prior art of non-intuitive evaluation results, limited accuracy, and weak ability to evaluate the mechanical state of the iron core.

[0096] In addition, the online rapid evaluation method for the mechanical state of the transformer proposed in this application, in addition to the above-mentioned ability to intuitively and accurately evaluate the mechanical state of the transformer and enhance the evaluation ability of the mechanical state of the iron core, also has the following advantages: Real-time monitoring and early warning: Through online rapid evaluation, the mechanical state of the transformer can be monitored in real time, potential fault hazards can be discovered in time, the expansion of faults can be avoided, and power outage time and economic losses can be reduced. Based on the judgment results, the system can set an early warning threshold. When the judgment result approaches or exceeds the threshold, the early warning mechanism is automatically triggered to notify the operation and maintenance personnel to take timely measures; Improve operation and maintenance efficiency: Traditional transformer mechanical state evaluation often requires manual inspections, which is time-consuming and labor-intensive. The method of this application can realize automated evaluation, reduce the frequency and intensity of manual inspections, and improve operation and maintenance efficiency. Through the analysis of the scattered signal transmission matrix, the fault location can be located more accurately, and detailed fault information can be provided to the operation and maintenance personnel for rapid repair; Enhance system reliability: Through real-time monitoring and early warning, potential faults of the transformer can be discovered in advance, preventive maintenance can be carried out, the service life of the transformer can be extended, and power can be improved. The reliability of the system and the timely detection and treatment of mechanical failures of the transformer can avoid power outages caused by failures and ensure the continuity and stability of the power supply; reduce operation and maintenance costs: through preventive maintenance and precise fault location, the maintenance costs and power outage losses caused by failures can be reduced. The method of the present application can realize the automated assessment of the mechanical state of the transformer, reduce the dependence on professional operation and maintenance personnel, and optimize the allocation of human resources; strong adaptability: the method of the present application does not depend on the specific type or model of the transformer, has strong versatility and adaptability, and can be widely applied to different types of transformers. In addition to the mechanical state of the winding and the mechanical state of the core, it can also assess whether the mechanical state or position of other mechanical components in the transformer under test has changed, such as spacers, clamps, fasteners, etc.; technological advancement: the present application adopts a machine learning model for judgment and uses a large amount of data for training, which improves the accuracy and reliability of the assessment, while also achieving rapid assessment. In addition, the mechanical state information of the transformer is obtained through scattered signal technology, which is a novel and effective technical means with high technical content and innovation.

[0097] In a feasible implementation, the received scattered signal matrix in the above embodiment includes a received scattered signal amplitude matrix and a received scattered signal phase matrix, the emitted scattered signal matrix includes an emitted scattered signal amplitude matrix and an emitted scattered signal phase matrix, and the scattered signal transfer matrix includes a scattered signal amplitude transfer matrix and a scattered signal phase transfer matrix.

[0098] Step 130 in the above embodiment determines the scattered signal transfer matrix based on the emitted scattered signal matrix and the received scattered signal matrix, including: determining the scattered signal amplitude transfer matrix based on the received scattered signal amplitude matrix and the emitted scattered signal amplitude matrix, and determining the scattered signal phase transfer matrix based on the received scattered signal phase matrix and the emitted scattered signal phase matrix.

[0099] In the embodiment of the present application, by separately processing the amplitude and phase information of the scattered signal, not only the comprehensiveness and accuracy of the transformer mechanical condition assessment are improved, but also the sensitivity and reliability of the assessment are enhanced, providing a strong guarantee for the safe and stable operation of the transformer.

[0100] It can be understood that improving the comprehensiveness of the evaluation: by simultaneously considering the amplitude and phase information of the scattered signal, the mechanical state of the transformer can be more comprehensively reflected. The amplitude information can reflect the strength of the signal, while the phase information can reflect the timing characteristics of the signal. The combination of the two can provide richer state information; enhancing the accuracy of the evaluation: processing the amplitude and phase information separately can avoid the evaluation deviation caused by a single parameter. For example, some mechanical faults may mainly affect the amplitude of the signal, while other faults may mainly affect the phase of the signal. By comprehensively considering the two, the mechanical state of the transformer can be judged more accurately; improving the sensitivity of the evaluation: since the amplitude and phase information are sensitive to the mechanical state, the mechanical state of the transformer can be judged more accurately. Changes have different sensitivities, so separate processing can more easily detect tiny state changes. This high sensitivity helps to detect and take measures in time at the early stage of the fault to prevent the fault from expanding; enhance the reliability of the evaluation: separate processing of amplitude and phase information can verify the evaluation results with each other. If the evaluation results of the two are consistent, the reliability of the evaluation can be increased. If there is a difference between the two, the cause can be further analyzed to improve the accuracy of the evaluation; adapt to different fault types: different mechanical faults may have different effects on the amplitude and phase of the scattered signal. By processing the two separately, it can be easier to adapt to different types of fault assessment needs, thereby improving the versatility and adaptability of the evaluation.

[0101] In one feasible implementation, the above embodiment determines the scattered signal amplitude transfer matrix based on the received scattered signal amplitude matrix and the transmitted scattered signal amplitude matrix, and determines the scattered signal phase transfer matrix based on the received scattered signal phase matrix and the transmitted scattered signal phase matrix, including:

[0102] Using the formula determining a scattered signal amplitude transfer matrix and a scattered signal phase transfer matrix;

[0103] in, , ;

[0104] In the above formula, is the nth row and nth column element in the received scattered signal amplitude matrix, is the nth row and 1st column element in the scattered signal amplitude matrix, is the nth row and nth column element in the phase matrix of the received scattered signal, is the nth row and nth column element in the phase matrix of the emitted scattered signal, is the nth row and nth column element in the scattered signal amplitude transfer matrix, is the nth row and nth column element in the scattered signal phase transfer matrix.

[0105] In some embodiments, It can also be expressed as the amplitude of the n×nth scattered signal in the received scattered signal amplitude matrix, It can also be expressed as the amplitude of the nth scattered signal in the scattered signal amplitude matrix, It can also be expressed as the phase of the n×nth scattered signal in the received scattered signal phase matrix, It can also be expressed as the phase of the nth scattered signal in the scattered signal phase matrix.

[0106] In the embodiment of the present application, by clarifying the formula to determine the scattered signal amplitude transfer matrix and the scattered signal phase transfer matrix, a specific and quantifiable calculation method is provided for the online rapid evaluation of the transformer mechanical state, thereby enhancing the accuracy and reliability of the evaluation.

[0107] It can be understood that providing a quantitative calculation method: in the actual transformer mechanical state assessment process, how to accurately calculate the scattered signal amplitude transfer matrix and the scattered signal phase transfer matrix is a key issue. This implementation method provides a specific calculation formula, so that the assessment process has a clear quantitative basis, avoiding subjectivity and uncertainty in the assessment process; enhancing assessment accuracy: through precise formula calculation, the values of the scattered signal amplitude transfer matrix and the scattered signal phase transfer matrix can be obtained more accurately. The values of these matrices directly reflect the information of the mechanical state in the transformer oil tank. Accurate matrix values help to more accurately assess whether the mechanical state of the transformer has changed, thereby improving the accuracy of the assessment; improving assessment reliability: the various parameters in the formula are clearly defined, such as the meaning of the elements such as the received scattered signal amplitude matrix, the emitted scattered signal amplitude matrix, the received scattered signal phase matrix, and the emitted scattered signal phase matrix. This clear definition and calculation method reduces the source of error in the assessment process, making the assessment results more reliable. At the same time, the subsequent judgment results based on accurate matrix values are also more credible, providing a stronger guarantee for the safe and stable operation of the transformer.

[0108] In a feasible implementation, the method in the above embodiment also includes: constructing a transformer physical simulation model of the transformer to be tested; when the transformer physical simulation model is running, controlling N simulation signal generators to emit N simulated scattered signals of different frequencies, and obtaining N×N scattered signals received by N simulation signal receivers, wherein N pairs of simulation signal generators and simulation signal receivers have been installed on the oil tank wall of the transformer physical simulation model; determining a simulated scattered signal matrix based on the N simulated scattered signals of different frequencies, and determining a simulated scattered signal matrix based on the N×N scattered signals; determining a simulated scattered signal transmission matrix based on the simulated scattered signal matrix and the simulated received scattered signal matrix; adjusting the simulation parameters of the transformer physical simulation model according to the normal mechanical state variation range of the transformer to be tested under normal electromotive force, and returning to execute the control of the N simulation signal generators to emit N different The method comprises the following steps: adjusting the simulated scattered signals of the same frequency, obtaining N×N scattered signals received by N simulated signal receivers, and taking multiple simulated scattered signal transfer matrices until the adjustment is completed, and taking the multiple simulated scattered signal transfer matrices as normal scattered signal transfer matrices; adjusting the simulation parameters of the transformer physical simulation model according to the abnormal mechanical state change range of the transformer under the action of the normal electromotive force, and returning to the execution of controlling N simulated signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by N simulated signal receivers during each adjustment, and taking multiple simulated scattered signal transfer matrices as abnormal scattered signal transfer matrices until the adjustment is completed; inputting multiple normal adjusted scattering signal transfer matrices and multiple abnormal adjusted scattering signal transfer matrices into the initial machine learning model for training to obtain a preset machine learning model.

[0109] The normal mechanical state variation range and the abnormal mechanical state variation range can be obtained and set by the operator based on a large amount of experience, experiments or statistics. Of course, the operator can also set them according to actual needs.

[0110] In some embodiments, the present application preferably sets the abnormal mechanical state change range to [-3M, -M) and (+M, +3M] when the normal mechanical state change range is set to [-M, +M]; wherein M is a positive integer.

[0111] Regarding the adjustment method of the simulation parameters, in some embodiments, the simulation parameters of the transformer physical simulation model can be adjusted incrementally according to a preset step size within the range of mechanical state change; wherein the preset step size can be obtained and set by the operator based on a large amount of experience, experiments or statistics. Of course, it can also be set by the operator according to actual needs, for example, it can be set to 1 mm.

[0112] Regarding the limiting conditions for the end of adjustment, in some embodiments, the range of mechanical state variation may be used as the basis. For example, within the range of mechanical state variation, the simulation parameters of the transformer physical simulation model are adjusted incrementally according to a preset step size. When the adjustment has been completed from the lower limit of the mechanical state variation range to the upper limit of the mechanical state variation range, it is indicated that the adjustment has been completed.

[0113] In an embodiment of the present application, by constructing a physical simulation model of the transformer and simulating the scattered signal transfer matrix under different mechanical states, rich and accurate training data is provided for the preset machine learning model, which significantly improves the prediction accuracy and generalization ability of the preset machine learning model, thereby enhancing the overall performance of the online rapid evaluation method of the transformer mechanical state, and effectively solving the problems of insufficient training data and limited prediction accuracy of the preset machine learning model.

[0114] It is understandable that providing rich and accurate training data: In the training process of the preset machine learning model, how to obtain rich and accurate training data is a key issue. This implementation method simulates the different mechanical states of the transformer to be tested under normal electrodynamic force and under the action of breakthrough normal electrodynamic force by constructing a physical simulation model of the transformer, and obtains the corresponding scattering signal transfer matrix as training data, so that the training process of the preset machine learning model has a clear quantitative basis, avoiding the subjectivity and uncertainty in the training process; enhancing prediction accuracy: by accurately simulating the scattering signal transfer matrix under different mechanical states, it can more accurately reflect the information of the mechanical state in the transformer tank. These accurate scattering signal transfer matrices are input into the preset machine learning model as training data, which helps the preset machine learning model to more accurately learn the mapping relationship between the mechanical state and the scattering signal transfer matrix, thereby improving the prediction accuracy of the preset machine learning model; improving generalization ability: the physical simulation model of the transformer can simulate a variety of different mechanical state change ranges, including normal and abnormal states. By using these different By obtaining the scattered signal transfer matrix under the same state as training data, the preset machine learning model can learn a wider range of mechanical state change patterns, thereby improving its generalization ability, so that the preset machine learning model can more accurately predict and judge when facing the actual transformer mechanical state assessment; reducing dependence on actual data: In actual applications, obtaining a large amount of accurate transformer mechanical state data often faces many difficulties, such as high data acquisition cost and inaccurate data labeling. This implementation method simulates the scattered signal transfer matrix under different mechanical states through the transformer physical simulation model, reducing the dependence of the preset machine learning model on actual data, reducing the cost of data acquisition and labeling, and improving the accuracy and reliability of training data; accelerating the model training process: Since the transformer physical simulation model can quickly simulate the scattered signal transfer matrix under different mechanical states, it can accelerate the training process of the preset machine learning model. Compared with the time required for actual data acquisition and labeling, the transformer physical simulation model can generate a large amount of accurate training data in a short time, thereby improving the training efficiency of the preset machine learning model.

[0115] In a feasible implementation, before controlling N simulation signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by N simulation signal receivers, the method in the above embodiment also includes: calibrating the simulation parameters of the transformer physical simulation model according to the reference scattered signal transfer matrix.

[0116] The reference scattered signal transfer matrix refers to the reference scattered signal transfer matrix when there is no fault anomaly, which can be obtained and pre-set by the operator based on a large amount of experience, experiments or statistics. Of course, it can also be set by the operator according to actual needs.

[0117] It should be noted that the matrix categories (such as amplitude matrix and phase matrix) included in the reference scattered signal transfer matrix correspond to the scattered signal transfer matrix. You can refer to the relevant content of the scattered signal transfer matrix in the above embodiment and will not repeat it here.

[0118] In the embodiment of the present application, calibration is performed to ensure the accuracy of the transformer physical simulation model, providing a reliable basis for subsequent training and evaluation based on the model.

[0119] It can be understood that by calibrating the simulation parameters of the transformer physical simulation model with reference to the scattered signal transfer matrix, it can ensure that the simulation model has a high degree of accuracy when simulating the mechanical state of the transformer, which helps to make subsequent training and evaluation based on the model more reliable; reduce errors: the calibration process can eliminate or reduce the error between the simulation model and the actual transformer, so that the simulation results are closer to the actual situation, which helps to improve the training effect and prediction accuracy of the preset machine learning model; improve training efficiency: an accurate simulation model can generate more accurate training data, thereby accelerating the training process of the preset machine learning model. Compared with using inaccurate simulation models or actual data, the calibrated simulation model can more efficiently provide the data required for training; enhance evaluation reliability: the evaluation results based on accurate simulation models are more reliable and can more accurately reflect the actual mechanical state of the transformer, which helps operation and maintenance personnel to promptly discover and deal with potential fault hazards and improve the reliability and stability of the power system.

[0120] In a feasible implementation, the method in the above embodiment also includes: when the transformer to be tested is not in operation, controlling N signal generators to emit N scattered signals of different frequencies, obtaining N×N scattered signals received by N signal receivers, and using the N scattered signals of different frequencies as reference emitted scattered signals, and using the N×N scattered signals as reference received scattered signals; determining a reference emitted scattered signal matrix based on the N reference emitted scattered signals of different frequencies, and determining a reference received scattered signal matrix based on the N×N reference received scattered signals; and determining a reference scattered signal transfer matrix based on the reference emitted scattered signal matrix and the reference received scattered signal matrix.

[0121] It should be noted that the matrix categories (such as amplitude matrix and phase matrix) included in the reference received scattered signal and reference transmitted scattered signal matrices correspond to the received scattered signal and transmitted scattered signal matrices. You can refer to the relevant contents of the received scattered signal and transmitted scattered signal matrices in the above embodiments, and will not be repeated here.

[0122] In the embodiment of the present application, by obtaining a reference scattered signal transfer matrix when the transformer to be tested is not in operation, an accurate benchmark is provided for subsequent evaluation, thereby improving the accuracy and reliability of the evaluation.

[0123] It can be understood that providing an accurate benchmark: obtaining a reference scattered signal transfer matrix when the transformer to be tested is not in operation, which reflects the scattered signal characteristics of the transformer in a normal fault-free state, provides an accurate benchmark for subsequent evaluation of whether the mechanical state of the transformer has changed. During the operation of the transformer, by comparing and analyzing with the reference scattered signal transfer matrix, it is possible to more accurately judge whether the mechanical state is abnormal; improving the accuracy of the evaluation: since the reference scattered signal transfer matrix is obtained when the transformer is not in operation and there is no fault interference, its data has high accuracy and stability. Using this as a benchmark for evaluation can effectively avoid evaluation errors caused by factors such as the transformer's own operating state or external interference, thereby improving the accuracy of the transformer mechanical state evaluation; enhancing the reliability of the evaluation: the accurate reference scattered signal transfer matrix provides a reliable basis for the evaluation process, making the evaluation results more credible. Operation and maintenance personnel can judge the mechanical state of the transformer more confidently based on the evaluation results, and take corresponding maintenance measures in a timely manner to ensure the safe and stable operation of the power system.

[0124] In a feasible implementation, step 120 in the above embodiment, determining a sent scattered signal matrix based on N scattered signals of different frequencies, and determining a received scattered signal matrix based on N×N scattered signals, includes: extracting the amplitude and phase of each scattered signal in the N scattered signals of different frequencies to obtain N sent scattered signal amplitudes and N sent scattered signal phases; determining an N×1 sent scattered signal amplitude matrix based on the N sent scattered signal amplitudes, and determining an N×N sent scattered signal phase matrix based on the N sent scattered signal phases; and converting the N×1 An emitted scattered signal amplitude matrix and an N×N emitted scattered signal phase matrix are used as an emitted scattered signal matrix; amplitude and phase are extracted for each of the N×N scattered signals to obtain N×N received scattered signal amplitudes and N×N received scattered signal phases; an N×1 received scattered signal amplitude matrix is determined based on the N×N received scattered signal amplitudes, and an N×N received scattered signal phase matrix is determined based on the N×N received scattered signal phases; and the N×1 received scattered signal amplitude matrix and the N×N received scattered signal phase matrix are used as a received scattered signal matrix.

[0125] In the embodiment of the present application, a more comprehensive scattered signal matrix is constructed by finely processing the amplitude and phase information of the scattered signal, thereby improving the accuracy and reliability of the transformer mechanical condition assessment.

[0126] It can be understood that a comprehensive scattering signal matrix is constructed: by simultaneously extracting the amplitude and phase of N scattered signals of different frequencies, a comprehensive scattering signal matrix including the emitted scattered signal amplitude matrix, the emitted scattered signal phase matrix, the received scattered signal amplitude matrix and the received scattered signal phase matrix is constructed. This comprehensive matrix construction method can more completely reflect the characteristics of the scattered signal, and provide richer information for the subsequent scattering signal transfer matrix calculation, thereby improving the accuracy and reliability of the evaluation; improving the evaluation accuracy: amplitude and phase are two important parameters of the scattered signal, which respectively reflect the intensity and timing characteristics of the signal. By considering these two parameters at the same time, the evaluation deviation caused by a single parameter can be avoided. For example, some mechanical faults may mainly affect the amplitude of the signal, while other faults may mainly affect the phase of the signal. By comprehensively considering the amplitude and phase information, the mechanical state of the transformer can be more accurately judged, and the accuracy of the evaluation can be improved; enhancing the reliability of the evaluation: there is a certain correlation and complementarity between the amplitude and phase information. By processing them simultaneously These two parameters can verify the evaluation results with each other and increase the reliability of the evaluation. If the evaluation results of the amplitude and phase are consistent, the judgment of the mechanical state of the transformer can be further confirmed. If there are differences, the causes can be further analyzed to improve the accuracy of the evaluation; adapt to different fault types: different mechanical faults may have different effects on the amplitude and phase of the scattered signal. By processing these two parameters at the same time, it is easier to adapt to different types of fault assessment needs. For example, loose windings may cause significant changes in signal amplitude, while core offset may mainly affect the phase of the signal. By comprehensively considering the amplitude and phase information, different types of mechanical faults can be more comprehensively evaluated; provide a solid foundation for subsequent steps: the constructed comprehensive scattered signal matrix is the basis for the subsequent calculation of the scattered signal transfer matrix. An accurate scattered signal matrix can ensure that the calculation results of the scattered signal transfer matrix are more reliable, thereby providing accurate input data for subsequent machine learning model judgment, which helps to improve the accuracy and reliability of the entire evaluation process and provide strong guarantees for the safe and stable operation of the transformer.

[0127] In a feasible implementation, step 110 in the above embodiment, controlling N signal generators to emit N scattered signals of different frequencies to obtain N×N scattered signals received by N signal receivers, includes: equally dividing the preset frequency domain range into N frequency domain ranges; extracting the jth frequency of each frequency domain range to obtain a scattered signal frequency group, where the initial value of j is 1; and according to the scattered signal frequency group, controlling N signal generators to emit N scattered signals of different frequencies to obtain N×N scattered signals received by N signal receivers.

[0128] Step 150 in the above embodiment, evaluating whether the mechanical state of the transformer to be tested has changed based on the judgment result, includes: returning to execute the steps of determining the emitted scattered signal matrix based on N scattered signals of different frequencies, and determining the received scattered signal matrix based on N×N scattered signals, until a judgment result is obtained; setting j=j+1, returning to execute the step of extracting the j-th frequency in each frequency domain range to obtain a scattered signal frequency group, until j equals the maximum number of frequency sweeps, and obtaining multiple judgment results; and evaluating whether the mechanical state of the transformer to be tested has changed based on all the judgment results.

[0129] The preset frequency domain range and the maximum number of frequency sweeps can be obtained and pre-set by the operator based on a large amount of experience, experiments or statistics. Of course, they can also be set by the operator according to actual needs.

[0130] It should be noted that, for the frequency sweeping process, the reference scattered signal transfer matrix in the above embodiment may not have a frequency sweeping process, that is, only one frequency sweep is required, and multiple frequency sweeps are not required. The normal adjustment scattered signal transfer matrix and the abnormal adjustment scattered signal transfer matrix in the above embodiment may have a frequency sweeping process, that is, multiple frequency sweeps may be performed to obtain multiple groups of normal adjustment scattered signal transfer matrices and multiple groups of abnormal adjustment scattered signal transfer matrices, and each group of normal adjustment scattered signal transfer matrices has multiple normal adjustment scattered signal transfer matrices, and each group of abnormal adjustment scattered signal transfer matrices has multiple abnormal adjustment scattered signal transfer matrices. Then, multiple groups of normal adjustment scattered signal transfer matrices and multiple groups of abnormal adjustment scattered signal transfer matrices are used for model training, and the frequency sweeping process can be referred to, which will not be repeated here.

[0131] Regarding the evaluation method of evaluating whether the mechanical state of the transformer to be tested has changed based on all the discrimination results, in some embodiments, among all the discrimination results, if any one of the discrimination results is 0 or close to 0, then it is evaluated that the mechanical state of the transformer to be tested has changed; in other embodiments, among all the discrimination results, if a preset proportion of the discrimination results is 0 or close to 0, then it is evaluated that the mechanical state of the transformer to be tested has changed; wherein the preset proportion can be obtained and set in advance by the operator based on a large amount of experience, experiments or statistics, and of course, it can also be set by the operator according to actual needs.

[0132] In the embodiment of the present application, multiple groups of discrimination results are obtained through the frequency sweep process, and the mechanical state of the transformer to be tested is comprehensively evaluated, which significantly improves the comprehensiveness and accuracy of the evaluation.

[0133] It can be understood that improving the comprehensiveness of the evaluation: evaluation based on a single scattered signal frequency or a limited set of frequencies may result in incomplete evaluation results and ignore the possible mechanical state changes at other frequencies. This implementation method divides the preset frequency domain range into multiple frequency domain ranges through a frequency sweep process, and extracts the frequencies in each frequency domain range in turn to transmit and receive scattered signals, thereby obtaining multiple groups of discrimination results. This method can more comprehensively cover various mechanical state changes that may exist in the transformer under test, improve the comprehensiveness of the evaluation, and also improve the evaluation efficiency; enhancing the accuracy of the evaluation: multiple groups of discrimination results provide richer information, so that the evaluation process can more accurately reflect the mechanical state of the transformer under test. By comprehensively analyzing multiple groups of discrimination results, the errors caused by the evaluation of a single frequency or a limited frequency group can be eliminated or reduced, thereby improving the accuracy of the evaluation. For example, in some cases, certain mechanical faults may only show obvious characteristics at specific frequencies, and the frequency sweep process can capture these characteristics, thereby more accurately judging the mechanical state of the transformer; adapting to different fault types: different mechanical faults may have different effects on different frequency components of the scattered signal. Obtaining multiple groups of discrimination results through the frequency sweep process can more easily adapt Different types of fault assessment requirements, for example, some faults may mainly affect low-frequency components, while other faults may mainly affect high-frequency components. By comprehensively analyzing multiple groups of discrimination results, different types of mechanical faults can be assessed more comprehensively; improving assessment reliability: multiple groups of discrimination results can be mutually verified to increase the reliability of the assessment. If there is consistency between multiple groups of discrimination results, the judgment of the transformer mechanical state can be further confirmed. If there is a difference, the cause can be further analyzed to improve the accuracy of the assessment. This method helps to reduce the risk of misjudgment and missed judgment and improve the reliability of the assessment; optimizing operation and maintenance strategies: based on Based on the evaluation results of multiple sets of discrimination results, operation and maintenance personnel can formulate more optimized operation and maintenance strategies. For example, for frequency ranges where abnormalities frequently occur, monitoring and inspections can be strengthened. For frequency ranges judged to be in normal status, the monitoring frequency can be appropriately reduced, thereby optimizing the configuration of operation and maintenance resources and improving operation and maintenance efficiency; improving system robustness: The frequency sweeping process can cope with the evaluation needs under different environments and working conditions, and improve the robustness of the system. Under different environments and working conditions, the characteristics of the scattered signal may be different. By obtaining multiple sets of discrimination results through the frequency sweeping process, it is possible to adapt to different environments and working conditions, and improve the adaptability and robustness of the system.

[0134] In a feasible implementation, the controlling of N signal generators to emit N scattered signals of different frequencies and obtaining N×N scattered signals received by N signal receivers in the above embodiment includes: controlling the N signal generators to emit N scattered signals of different frequencies and obtaining N×N intermediate scattered signals received by the N signal receivers for the i-th time, where the initial value of i is 1; setting i=i+1, and returning to execute the step of controlling the N signal generators to emit N scattered signals of different frequencies and obtaining the N×N intermediate scattered signals received by the N signal receivers for the i-th time, until the intermediate scattered signal attenuation value corresponding one-to-one between the N×N intermediate scattered signals received for the i-th time and the N×N intermediate scattered signals received for the first time is less than an attenuation threshold, thereby obtaining N×N intermediate scattered signals received multiple times; and using the N×N intermediate scattered signals received at any one time among the N×N intermediate scattered signals received multiple times as the N×N scattered signals.

[0135] The attenuation threshold may be obtained and pre-set by the operator based on a large amount of experience, experiments or statistics. Of course, the operator may also set it based on actual needs.

[0136] In some embodiments, the attenuation threshold may be set to half the scattered signal emitted by the signal generator.

[0137] It should be noted that, since the N scattered signals emitted by the N signal generators are of different frequencies, each signal receiver can identify the number of receptions when receiving the N scattered signals reflected by the oil tank of the transformer under test.

[0138] It should be further explained that the scattered signal emitted by the signal generator will gradually attenuate when reflected in the oil tank of the transformer to be tested; in this application, the scattered signal emitted by the signal generator is attenuated to 0 within a single frequency sweep by default.

[0139] In the embodiment of the present application, a stable scattered signal is obtained through a multiple reflection attenuation process, thereby ensuring the accuracy and reliability of the evaluation data and improving the accuracy and efficiency of the transformer mechanical condition evaluation.

[0140] It can be understood that to ensure the accuracy of the evaluation data: in the transformer tank, the scattered signal will undergo multiple reflections and attenuation until it reaches a stable state. This implementation method controls the signal generator to send out scattered signals multiple times, and obtains the intermediate scattered signal of the signal receiver after multiple reflections, until the attenuation value of the intermediate scattered signal is less than the preset attenuation threshold, thereby ensuring that the obtained scattered signal is stable, avoiding the evaluation error caused by signal instability, and the stable scattered signal can more accurately reflect the mechanical state in the transformer tank, providing a reliable data basis for subsequent signal processing and evaluation, and significantly improving the accuracy of the evaluation; improving evaluation efficiency: by setting the attenuation threshold, it can automatically determine when the scattered signal has reached a stable state, thereby reducing the number of unnecessary signal acquisitions and improving evaluation efficiency. In actual applications, this automated judgment mechanism can significantly shorten the evaluation time, reduce evaluation costs, and improve evaluation efficiency; enhancing evaluation reliability: stable scattered signals can provide more reliable evaluation results, reduce the risk of misjudgment and missed judgment due to signal instability, obtain stable scattered signals through multiple reflection attenuation processes, and use the same The N×N intermediate scattered signals received at one time are used as N×N scattered signals, which can ensure the consistency and reliability of the evaluation results and provide strong protection for the safe and stable operation of the transformer; adapting to different working conditions and environments: Under different working conditions and environments, the attenuation characteristics and stabilization time of the scattered signal may vary. This implementation method obtains a stable scattered signal through a multiple reflection attenuation process, which can adapt to the evaluation needs under different working conditions and environments and improve the versatility and adaptability of the evaluation; optimizing the signal processing process: After obtaining a stable scattered signal, it can be subjected to more precise signal processing and analysis, such as filtering and denoising, to further improve the accuracy and reliability of the evaluation. The stable scattered signal provides better input data for subsequent signal processing processes, which helps to optimize the entire evaluation process and improve the efficiency and quality of the evaluation; reducing equipment requirements: Obtaining a stable scattered signal through a multiple reflection attenuation process can reduce the performance requirements of the signal generator and signal receiver. In practical applications, this can reduce equipment costs and improve the economic efficiency of the evaluation. At the same time, the stable scattered signal also helps to reduce dependence on equipment accuracy and improve the robustness of the evaluation.

[0141] In a second aspect, the present application provides a system for online rapid evaluation of the mechanical state of a transformer, the system comprising N signal generators, N signal receivers and a processor (not shown in the figure, but may be referred to as Figure 2 Schematic diagram shown as an example).

[0142] In a feasible implementation, N pairs of signal generators and signal receivers are installed on the wall of the oil tank of the transformer to be tested; and the processor is configured to execute any one of the methods in the first aspect.

[0143] In the embodiments of the present application, the online evaluation system for the mechanical condition of a transformer proposed in the present application provides a strong guarantee for the stable operation of the power system through the beneficial effects of integrated design, real-time online monitoring, flexible scalability, efficient data processing capabilities, easy deployment and maintenance, and improved evaluation accuracy and reliability. The system not only solves the problems of non-intuitive evaluation results, limited accuracy, and weak ability to evaluate the mechanical condition of the core in the prior art, but also reduces operation and maintenance costs and improves the overall benefits of the power system.

[0144] It can be understood that system integration and automation: by integrating N signal generators, N signal receivers and processors into one system, the online evaluation of the mechanical state of the transformer is automated. This integrated design makes the evaluation process more efficient and convenient, reduces the need for manual intervention, and improves the accuracy and reliability of the evaluation; real-time and online monitoring: the system can collect and process scattered signal data in real time, and realize online monitoring of the mechanical state of the transformer through real-time analysis of the data by the processor. This real-time performance enables operation and maintenance personnel to understand the operating status of the transformer in a timely manner, discover and deal with potential faults in a timely manner, and avoid greater losses caused by the deterioration of faults; flexibility and scalability: the number of signal generators and signal receivers in the system can be flexibly configured according to actual needs. This flexibility enables the system to adapt to different types of transformers and different evaluation needs. At the same time, with the continuous development of technology, the system can also be easily expanded and upgraded to adapt to new evaluation methods and technologies that may emerge in the future. Technology; Efficient data processing capability: As the core component of the system, the processor has powerful data processing capabilities. It can quickly process large amounts of scattered signal data and extract useful information for evaluating the mechanical condition of the transformer. This efficient data processing capability improves the efficiency and accuracy of the evaluation, enabling the system to obtain reliable evaluation results in a short period of time; Easy to deploy and maintain: The system is relatively simple to deploy. It only requires installing a signal generator and a signal receiver on the oil tank wall of the transformer to be tested and connecting the processor. At the same time, the system is also very convenient to maintain. Due to the high degree of integration and automation of the system, operation and maintenance personnel only need to perform regular inspections and maintenance to ensure the normal operation of the system; Improve the accuracy and reliability of the evaluation: Through the processor's precise analysis and processing of scattered signal data, the system can more accurately evaluate the mechanical condition of the transformer. Compared with traditional evaluation methods, this system does not rely on indirect parameters and can directly reflect the actual operating status of the transformer, thereby improving the accuracy and reliability of the evaluation.

[0145] In a third aspect, the present application provides an online rapid evaluation device for the mechanical state of a transformer.

[0146] See also Figure 3, is a schematic diagram of an online rapid evaluation device for a transformer mechanical state according to an embodiment of the present application, wherein the device 310 includes:

[0147] A control module 311 is configured to control N signal generators to emit N scattered signals of different frequencies when the transformer under test is in operation, and obtain N×N scattered signals received by N signal receivers, wherein N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer under test, and N is greater than or equal to 2;

[0148] A first determining module 312 is configured to determine a transmitted scattered signal matrix based on N scattered signals of different frequencies, and to determine a received scattered signal matrix based on N×N scattered signals;

[0149] A second determining module 313 is configured to determine a scattered signal transfer matrix according to the sent scattered signal matrix and the received scattered signal matrix;

[0150] The model discrimination module 314 is used to input the scattered signal transfer matrix into a preset machine learning model to obtain a discrimination result;

[0151] The evaluation module 315 is used to evaluate whether the mechanical state of the transformer to be tested has changed according to the determination result.

[0152] In the embodiment of the present application, the relevant contents of the control module 311, the first determination module 312, the second determination module 313, the model identification module 314 and the evaluation module 315 can be referred to. Figure 1 The contents of the illustrated embodiments are not described in detail here.

[0153] It should be noted that the device 310 of the present application also includes some other modules. It can be understood that the method of the present application and the device 310 have a one-to-one correspondence. Therefore, the other modules of the device 310 of the present application are the contents corresponding to the method of the present application in the above embodiment.

[0154] In an embodiment of the present application, by installing N pairs of signal generators and signal receivers on the oil tank wall of the transformer to be tested, and by determining the model discrimination result of the scattered signal transfer matrix, it is possible to evaluate whether the mechanical state of the transformer to be tested has changed. This allows for intuitive and accurate evaluation of whether the mechanical state of the transformer has changed without relying on indirect parameters, significantly improving the intuitiveness and accuracy of the evaluation. At the same time, this method also enhances the ability to evaluate the mechanical state of the iron core without the need to combine with other specialized devices, effectively solving the problems in the prior art of non-intuitive evaluation results, limited accuracy, and weak ability to evaluate the mechanical state of the iron core.

[0155] In addition, the online rapid evaluation device for the mechanical state of the transformer proposed in the present application, in addition to the above-mentioned ability to intuitively and accurately evaluate the mechanical state of the transformer and enhance the evaluation ability of the mechanical state of the iron core, also has the following advantages: Real-time monitoring and early warning: Through online rapid evaluation, the mechanical state of the transformer can be monitored in real time, potential fault hazards can be discovered in time, the expansion of faults can be avoided, and power outage time and economic losses can be reduced. Based on the judgment results, the system can set an early warning threshold. When the judgment result approaches or exceeds the threshold, the early warning mechanism is automatically triggered to notify the operation and maintenance personnel to take timely measures; Improve operation and maintenance efficiency: Traditional transformer mechanical state evaluation often requires manual inspections, which is time-consuming and labor-intensive. The device of the present application can realize automated evaluation, reduce the frequency and intensity of manual inspections, improve operation and maintenance efficiency, and through the analysis of the scattered signal transmission matrix, it can more accurately locate the fault location, provide detailed fault information to the operation and maintenance personnel, and facilitate rapid repair; Enhance system reliability: Through real-time monitoring and early warning, potential faults of the transformer can be discovered in advance, preventive maintenance can be carried out, the service life of the transformer can be extended, and power can be improved. The reliability of the system and the timely detection and treatment of mechanical faults in the transformer can avoid power outages caused by faults and ensure the continuity and stability of the power supply; reduce operation and maintenance costs: through preventive maintenance and precise fault location, the maintenance costs and power outage losses caused by faults can be reduced. The device of the present application can realize automatic assessment of the mechanical state of the transformer, reduce the dependence on professional operation and maintenance personnel, and optimize the allocation of human resources; strong adaptability: the device of the present application is independent of the specific type or model of the transformer, has strong versatility and adaptability, and can be widely applied to different types of transformers. In addition to the mechanical state of the winding and the mechanical state of the core, it can also assess whether the mechanical state or position of other mechanical components in the transformer under test has changed, such as spacers, clamps, fasteners, etc.; technological advancement: the present application adopts a machine learning model for judgment and uses a large amount of data for training, which improves the accuracy and reliability of the assessment, while also achieving rapid assessment. In addition, the mechanical state information of the transformer is obtained through scattered signal technology, which is a novel and effective technical means with high technical content and innovation.

[0156] In a fourth aspect, the present application further provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes a method for online rapid evaluation of the mechanical state of a transformer in the above method embodiment.

[0157] In a fifth aspect, the present application further provides a computer device including a memory and a processor, wherein the memory stores a computer program. When the computer program is executed by the processor, the processor executes a method for online rapid evaluation of the mechanical state of a transformer in the above-mentioned method embodiment.

[0158] Figure 4The internal structure diagram of the computer device in some embodiments is shown. The computer device can be a terminal, a server, or a gateway. Figure 4 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus.

[0159] The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the various steps in the above method embodiment. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement the various steps in the above method embodiment. It will be understood by those skilled in the art that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0160] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0161] Among them, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0162] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for rapid online evaluation of transformer mechanical status, characterized in that: The method comprises: When the transformer under test is in operation, controlling N signal generators to emit N scattered signals of different frequencies, and obtaining N×N scattered signals received by N signal receivers, wherein N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer under test, and N is greater than or equal to 2; Determine a sent scattered signal matrix based on N scattered signals of different frequencies, and determine a received scattered signal matrix based on N×N scattered signals; Determine a scattered signal transfer matrix according to the emitted scattered signal matrix and the received scattered signal matrix; Inputting the scattered signal transfer matrix into a preset machine learning model to obtain a discrimination result; According to the determination result, evaluating whether the mechanical state of the transformer to be tested has changed; The received scattered signal matrix includes a received scattered signal amplitude matrix and a received scattered signal phase matrix, the emitted scattered signal matrix includes an emitted scattered signal amplitude matrix and an emitted scattered signal phase matrix, the scattered signal transfer matrix includes a scattered signal amplitude transfer matrix and a scattered signal phase transfer matrix, and determining the scattered signal transfer matrix based on the emitted scattered signal matrix and the received scattered signal matrix includes: The scattered signal amplitude transfer matrix is determined according to the received scattered signal amplitude matrix and the transmitted scattered signal amplitude matrix, and the scattered signal phase transfer matrix is determined according to the received scattered signal phase matrix and the transmitted scattered signal phase matrix.

2. The method for online rapid evaluation of transformer mechanical status according to claim 1, characterized in that: The determining of the scattered signal amplitude transfer matrix according to the received scattered signal amplitude matrix and the transmitted scattered signal amplitude matrix, and the determining of the scattered signal phase transfer matrix according to the received scattered signal phase matrix and the transmitted scattered signal phase matrix, comprises: Using the formula Determining the scattered signal amplitude transfer matrix and the scattered signal phase transfer matrix; in, , ; In the above formula, is the nth row and nth column element in the received scattered signal amplitude matrix, is the nth row and 1st column element in the emitted scattered signal amplitude matrix, is the nth row and nth column element in the received scattered signal phase matrix, is the nth row and nth column element in the phase matrix of the emitted scattered signal, is the nth row and nth column element in the scattered signal amplitude transfer matrix, is the element in the nth row and nth column of the scattered signal phase transfer matrix.

3. The method for online rapid evaluation of transformer mechanical status according to claim 1, characterized in that: The method further comprises: Constructing a transformer physical simulation model of the transformer to be tested; When the transformer physical simulation model is running, controlling N simulation signal generators to emit N simulation scattered signals of different frequencies, and obtaining N×N scattered signals received by N simulation signal receivers, wherein N pairs of simulation signal generators and simulation signal receivers are installed on the oil tank wall of the transformer physical simulation model; Determining a simulated transmitted scattered signal matrix based on N simulated scattered signals of different frequencies, and determining a simulated received scattered signal matrix based on N×N scattered signals; Determine a simulated scattered signal transfer matrix according to the simulated emitted scattered signal matrix and the simulated received scattered signal matrix; Adjusting the simulation parameters of the transformer physical simulation model according to the normal mechanical state variation range of the transformer under normal electromotive force, and returning to the step of controlling the N simulation signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by the N simulation signal receivers during each adjustment until the adjustment is completed, thereby obtaining multiple simulated scattered signal transfer matrices, and using the multiple simulated scattered signal transfer matrices as normal scattered signal transfer matrices; Adjusting the simulation parameters of the transformer physical simulation model according to the range of abnormal mechanical state changes of the transformer under test when the transformer exceeds the normal electromotive force, and returning to the step of controlling N simulation signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by N simulation signal receivers during each adjustment until the adjustment is completed, thereby obtaining multiple simulated scattered signal transfer matrices, and using the multiple simulated scattered signal transfer matrices as abnormal scattered signal transfer matrices; Multiple normal scattering signal transfer matrices and multiple abnormal scattering signal transfer matrices are input into an initial machine learning model for training to obtain the preset machine learning model.

4. The method for online rapid evaluation of transformer mechanical status according to claim 3, characterized in that: Before controlling the N simulated signal generators to emit N simulated scattered signals of different frequencies and obtaining N×N scattered signals received by the N simulated signal receivers, the method further includes: The simulation parameters of the transformer physical simulation model are calibrated according to the reference scattered signal transfer matrix.

5. The method for online rapid evaluation of transformer mechanical status according to claim 4, characterized in that: The method further comprises: When the transformer to be tested is not in operation, controlling N signal generators to emit N scattered signals of different frequencies, obtaining N×N scattered signals received by N signal receivers, and using the N scattered signals of different frequencies as references to emit scattered signals, and using the N×N scattered signals as references to receive scattered signals; Determine a reference transmitted scattered signal matrix based on N reference transmitted scattered signals of different frequencies, and determine a reference received scattered signal matrix based on N×N reference received scattered signals; The reference scattered signal transfer matrix is determined according to the reference transmitted scattered signal matrix and the reference received scattered signal matrix.

6. The method for online rapid evaluation of transformer mechanical status according to claim 1, characterized in that: The method of determining a sent scattered signal matrix based on N scattered signals of different frequencies, and determining a received scattered signal matrix based on N×N scattered signals, includes: Extracting the amplitude and phase of each of the N scattered signals with different frequencies to obtain N emitted scattered signal amplitudes and N emitted scattered signal phases; Determining an N×1 transmitted scattered signal amplitude matrix based on the N transmitted scattered signal amplitudes, and determining an N×N transmitted scattered signal phase matrix based on the N transmitted scattered signal phases; Taking an N×1 emitted scattered signal amplitude matrix and an N×N emitted scattered signal phase matrix as the emitted scattered signal matrix; Amplitude and phase extraction are performed on each of the N×N scattered signals to obtain N×N received scattered signal amplitudes and N×N received scattered signal phases; Determining an N×1 received scattered signal amplitude matrix based on the N×N received scattered signal amplitudes, and determining an N×N received scattered signal phase matrix based on the N×N received scattered signal phases; An N×1 received scattered signal amplitude matrix and an N×N received scattered signal phase matrix are used as the received scattered signal matrix.

7. The method for online rapid evaluation of transformer mechanical status according to claim 1, characterized in that: The controlling N signal generators to emit N scattered signals of different frequencies and obtaining N×N scattered signals received by N signal receivers includes: Divide the preset frequency domain range into N frequency domain ranges equally; Extract the jth frequency in each frequency domain range to obtain the scattered signal frequency group, where the initial value of j is 1; According to the scattered signal frequency group, controlling N signal generators to emit N scattered signals of different frequencies, and obtaining N×N scattered signals received by N signal receivers; The step of evaluating whether the mechanical state of the transformer to be tested has changed according to the determination result includes: Returning to the steps of determining a sent scattered signal matrix based on N scattered signals of different frequencies, and determining a received scattered signal matrix based on N×N scattered signals, until the discrimination result is obtained; Let j = j + 1, and return to the step of extracting the jth frequency in each frequency domain range to obtain a scattered signal frequency group, until j equals the maximum number of frequency sweeps, and a plurality of the discrimination results are obtained; Based on all the determination results, it is evaluated whether the mechanical state of the transformer to be tested has changed.

8. The method for online rapid evaluation of transformer mechanical status according to claim 1 or 7, characterized in that: The controlling N signal generators to emit N scattered signals of different frequencies and obtaining N×N scattered signals received by N signal receivers includes: Control N signal generators to emit N scattered signals of different frequencies, and obtain N×N intermediate scattered signals received by N signal receivers at the i-th time, where the initial value of i is 1; Let i = i + 1, and return to the step of controlling the N signal generators to emit N scattered signals of different frequencies, and obtaining the N×N intermediate scattered signals received by the N signal receivers for the i-th time, until the intermediate scattered signal attenuation value corresponding one-to-one between the N×N intermediate scattered signals received for the i-th time and the N×N intermediate scattered signals received for the first time is less than the attenuation threshold, thereby obtaining the N×N intermediate scattered signals received multiple times; Among the N×N intermediate scattered signals received multiple times, the N×N intermediate scattered signals received at any one time are regarded as the N×N scattered signals.

9. A transformer mechanical status online rapid assessment system, characterized in that: The system includes N signal generators, N signal receivers and a processor; N pairs of signal generators and signal receivers are installed on the oil tank wall of the transformer to be tested; The processor is configured to execute the method according to any one of claims 1 to 8.

Images