Residual magnetism detection method and equipment of power transformer, medium and product

Abstract

The invention provides a residual magnetism detection method and device of a power transformer, a medium and a product, and relates to the technical field of transformer residual magnetism detection. The method comprises the following steps: applying preset sinusoidal voltage excitation to an excitation winding of a to-be-detected power transformer; the excitation current waveform of the excitation winding is collected, and power transformer temperature data corresponding to the collection time is recorded; based on the temperature data of the power transformer, temperature compensation is carried out on the excitation current waveform; determining the peak difference of the exciting current in each alternating current period from the exciting current waveform subjected to temperature compensation; and determining the residual magnetism state of the power transformer based on the peak difference. According to the invention, the residual magnetism detection precision is improved.

Description

Technical Field

[0001] The present application relates to the technical field of transformer residual magnetism detection, and in particular to a residual magnetism detection method, equipment, medium and product for power transformers. Background Art

[0002] Power transformers are key components in power systems, and their safe and stable operation is crucial to the entire power grid. After a transformer is put into operation or shut down, residual magnetic flux, known as remanence, may remain in the core. This remanence can cause large inrush currents at the moment of closing the transformer, adversely affecting the transformer, relay protection devices, and the power grid. Therefore, accurately detecting and evaluating remanence in power transformers is of great engineering significance and practical value.

[0003] Currently, residual magnetism detection methods for power transformers typically record the line voltage waveform at the moment the power transformer is tripped, then integrate the voltage waveform to calculate the residual magnetism value in the transformer core. However, this method suffers from low residual magnetism detection accuracy. Summary of the Invention

[0004] The present application provides a residual magnetism detection method, equipment, medium and product for power transformers to improve the residual magnetism detection accuracy.

[0005] In a first aspect, the present application provides a method for detecting residual magnetism of a power transformer, comprising:

[0006] Applying a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be tested;

[0007] Collect the excitation current waveform of the excitation winding and record the power transformer temperature data corresponding to the collection time;

[0008] Based on the temperature data of the power transformer, the excitation current waveform is temperature compensated;

[0009] Determine the peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform;

[0010] Based on the peak value difference, the residual magnetism state of the power transformer is determined.

[0011] In one possible implementation, determining the residual magnetism state of the power transformer based on the peak value difference includes:

[0012] The peak difference and the frequency corresponding to the peak difference are input into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer. The residual magnetism determination model adopts a hybrid neural network model that integrates physical constraints.

[0013] In one possible implementation, the residual magnetism determination model includes: a feature extraction module, a physical constraint module, and a decision output module. The peak difference and the frequency corresponding to the peak difference are input into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer, including:

[0014] The peak difference and the frequency corresponding to the peak difference are input into the feature extraction module to obtain the feature vector;

[0015] Input the feature vector into the physical constraint module to obtain the physically constrained feature vector;

[0016] The physically constrained feature vector is input into the decision output module to determine the current residual magnetic polarity and the corresponding magnetic flux of the power transformer.

[0017] In one possible implementation, temperature compensation is performed on the excitation current waveform based on the power transformer temperature data, including:

[0018] The power transformer temperature data is input into a pre-trained compensation model to obtain the temperature compensation value. The compensation model is a neural network model trained based on the mapping relationship between historical power transformer temperature data and the corresponding excitation current waveform deviation;

[0019] The excitation current waveform is corrected using the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

[0020] In a possible implementation, the excitation current waveform is corrected using a temperature compensation amount to obtain a temperature-compensated excitation current waveform, including:

[0021] The amplitude of the excitation current waveform is adjusted according to the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

[0022] In a possible implementation, the method further includes:

[0023] Based on the residual magnetization state, a corresponding excitation inrush current suppression strategy is generated and output.

[0024] In a second aspect, the present application provides a residual magnetism detection device for a power transformer, comprising:

[0025] An excitation module, used for applying a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be tested;

[0026] A processing module, used to collect the excitation current waveform of the excitation winding and record the temperature data of the power transformer corresponding to the collection time;

[0027] A compensation module, used to perform temperature compensation on the excitation current waveform based on the temperature data of the power transformer;

[0028] The determination module is configured to determine a peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform; and determine a residual magnetism state of the power transformer based on the peak value difference.

[0029] In a possible implementation, the determination module is specifically configured to:

[0030] The peak difference and the frequency corresponding to the peak difference are input into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer. The residual magnetism determination model adopts a hybrid neural network model that integrates physical constraints.

[0031] In one possible implementation, the residual magnetization determination model includes: a feature extraction module, a physical constraint module, and a decision output module, wherein the determination module is specifically configured to:

[0032] The peak difference and the frequency corresponding to the peak difference are input into the feature extraction module to obtain the feature vector;

[0033] Input the feature vector into the physical constraint module to obtain the physically constrained feature vector;

[0034] The physically constrained feature vector is input into the decision output module to determine the current residual magnetic polarity and the corresponding magnetic flux of the power transformer.

[0035] In a possible implementation manner, the compensation module is specifically configured to:

[0036] The power transformer temperature data is input into a pre-trained compensation model to obtain the temperature compensation value. The compensation model is a neural network model trained based on the mapping relationship between historical power transformer temperature data and the corresponding excitation current waveform deviation;

[0037] The excitation current waveform is corrected using the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

[0038] In a possible implementation manner, the compensation module is specifically configured to:

[0039] The amplitude of the excitation current waveform is adjusted according to the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

[0040] In a possible implementation, the processing module is further configured to:

[0041] Based on the residual magnetization state, a corresponding excitation inrush current suppression strategy is generated and output.

[0042] In a third aspect, the present application provides an electronic device, comprising: a memory, a processor;

[0043] Memory stores computer-executable instructions;

[0044] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the above first aspect and / or various possible implementation methods of the first aspect.

[0046] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed, implements the above first aspect and / or various possible implementations of the first aspect.

[0047] The present application provides a method, device, medium, and product for detecting residual magnetism of a power transformer, which relates to the technical field of residual magnetism detection of transformers. The method comprises: applying a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be detected; collecting the excitation current waveform of the excitation winding and recording the temperature data of the power transformer corresponding to the collection time; performing temperature compensation on the excitation current waveform based on the temperature data of the power transformer; determining the peak difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform; and determining the residual magnetism state of the power transformer based on the peak difference. The present application can avoid errors caused by grid fluctuations and circuit breaker operation uncertainty and enhance anti-interference capability by applying a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be detected; collecting the excitation current waveform of the excitation winding and recording the temperature data of the power transformer corresponding to the collection time; performing temperature compensation on the excitation current waveform based on the temperature data of the power transformer to correct the excitation current waveform; determining the peak difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform, and determining the residual magnetism state of the power transformer based on the peak difference, thereby improving the accuracy of residual magnetism detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] Figure 1 Schematic diagram of the residual magnetism detection method of the power transformer provided in this application Figure 1 ;

[0050] Figure 2 Schematic diagram of the residual magnetism detection method of the power transformer provided in the embodiment of the present application Figure 2 ;

[0051] Figure 3 Schematic diagram of sinusoidal voltage excitation injection and magnetic flux waveform provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of the residual magnetic flux-current peak difference curve corresponding to different sinusoidal voltage excitations provided in an embodiment of the present application;

[0053] Figure 5 A schematic structural diagram of a residual magnetism detection device for a power transformer provided in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application.

[0055] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0056] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0057] Power transformers are extremely expensive and critical electrical equipment. Due to the saturation characteristics of the transformer's ferromagnetic material, closing an unloaded transformer often generates a magnetizing inrush current in the transformer's windings. On-site, this inrush current can reach several times, or even ten times, the rated current. This poses multiple hazards to the power system and the transformer itself, causing malfunction of the transformer's relay protection devices, increasing maintenance costs and severely impacting the safety and stability of the power system. Overcurrent can also impact transformers, switches, and current transformers, reducing the performance and life of circuit components and degrading power quality and supply quality. If transformers are operating in parallel, this inrush current can also induce malfunction of the differential protection of adjacent transformers.

[0058] In summary, the hazards of transformer excitation inrush current are multifaceted, including causing false operation of relay protection devices, equipment damage, voltage surges, affecting power quality and power supply quality, and causing combined excitation inrush current.

[0059] Currently, the commonly used method to suppress excitation inrush current is the phase-controlled closing method. By controlling the circuit breaker to close at an appropriate electrical angle, the pre-induced magnetic flux is made as equal as possible to the residual magnetism of the transformer core, avoiding magnetic flux saturation and thus suppressing the excitation inrush current.

[0060] This requires that an effective transformer core residual magnetism detection device be equipped to efficiently detect the residual magnetism size, and based on this, the appropriate closing angle range can be selected to fully ensure that the inrush current suppression device can achieve the suppression effect.

[0061] In response to the above problems, the present application provides a residual magnetism detection method for a power transformer, which applies a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be detected; collects the excitation current waveform of the excitation winding, and records the power transformer temperature data corresponding to the collection time; based on the power transformer temperature data, temperature compensates the excitation current waveform; determines the peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform; and determines the residual magnetism state of the power transformer based on the peak value difference, thereby accurately detecting the residual magnetism of the power transformer.

[0062] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0063] Figure 1 Schematic diagram of the residual magnetism detection method of the power transformer provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0064] S101 : Apply a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be tested.

[0065] In this step, it can be understood that when performing residual magnetism testing on a power transformer, it is necessary to determine the excitation winding of the power transformer to be tested, and use the excitation winding as an input end to input a preset sinusoidal voltage excitation to the excitation winding. The frequency of the preset sinusoidal voltage excitation needs to be lower than the operating frequency of the power transformer, for example, a low frequency of 0.1 Hz to 5 Hz is selected.

[0066] This low-frequency sinusoidal voltage excitation can make the magnetization process of the power transformer core more complete and slow, thereby more effectively revealing or reflecting the residual magnetism state inside the power transformer core.

[0067] Step S101 applies the sinusoidal AC voltage of the specific frequency, which can cause the hysteresis loop of the power transformer core to fully expand, so that the residual magnetism state of the power transformer core can be accurately analyzed by subsequently collecting the excitation current waveform.

[0068] Furthermore, the non-excited windings of the power transformer to be tested must be open-circuited or isolated. This means that these non-excited windings must be completely disconnected from any external circuits, loads, or ground wires to prevent them from forming an inductive loop with any external circuits, loads, or ground wires, introducing additional loads or generating unexpected induced voltages, which would interfere with the purity and accuracy of the residual magnetism test on the power transformer.

[0069] S102 : Collect the excitation current waveform of the excitation winding, and record the temperature data of the power transformer corresponding to the collection time.

[0070] After applying a preset sinusoidal voltage excitation to the excitation winding at S101, the excitation winding generates a corresponding excitation current waveform due to the magnetization characteristics of the power transformer. This excitation current waveform carries key information about the magnetization state of the power transformer core. Therefore, the excitation current waveform of the excitation winding needs to be collected in real time, for example, using a current sensor and data acquisition equipment.

[0071] Furthermore, when S101 applies a preset sinusoidal voltage to the excitation winding, the temperature of the power transformer changes. The temperature of the power transformer is a key environmental factor affecting its electrical characteristics. It significantly influences the excitation current waveform of the excitation winding and also affects the shape of the hysteresis loop and saturation characteristics of the iron core. Therefore, it is necessary to record the power transformer temperature data corresponding to the acquisition time.

[0072] S103. Perform temperature compensation on the excitation current waveform based on the power transformer temperature data.

[0073] Since the magnetic properties of the power transformer core and the winding resistivity are sensitive to temperature, the excitation current waveform will drift with temperature changes.

[0074] Therefore, in order to ensure accurate analysis of the excitation current waveform, the embodiment of the present application uses the power transformer temperature data recorded in S102 to perform temperature compensation on the excitation current waveform to eliminate the influence of the power transformer temperature data on residual magnetism detection.

[0075] S104 : Determine the peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform.

[0076] To accurately assess the residual magnetism (RMS) of a power transformer based on temperature compensation, a periodic analysis of the temperature-compensated excitation current waveform is required. Specifically, the peak value difference of the excitation current within each AC cycle is determined from the temperature-compensated excitation current waveform. Specifically, within each AC voltage cycle, the positive and negative peak values of the excitation current waveform are determined, and the difference between the positive and negative peak values is calculated. The magnitude and trend of this peak value difference can reflect the residual magnetism (RMS) state of the power transformer core, providing a quantitative basis for residual magnetism detection.

[0077] S105 : Determine the residual magnetism state of the power transformer based on the peak value difference.

[0078] The peak difference determined by S104 is used as a quantitative indicator to determine the residual magnetism state of the power transformer. When residual magnetism exists in the power transformer core, the magnetization characteristics of the core will exhibit asymmetric characteristics, causing the positive and negative peak values of the excitation current waveform to no longer be equal, resulting in a significant peak difference.

[0079] The residual magnetism state of the power transformer can be determined based on the peak difference. For example, by comparing the peak difference with a preset peak threshold, the residual magnetism of the power transformer can be accurately assessed and the residual magnetism polarity of the power transformer can be inferred.

[0080] The residual magnetism detection method for a power transformer provided in an embodiment of the present application applies a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be detected, thereby avoiding errors caused by grid fluctuations and uncertainty in circuit breaker operation and enhancing anti-interference capability; collects the excitation current waveform of the excitation winding and records the power transformer temperature data corresponding to the collection time; based on the power transformer temperature data, performs temperature compensation on the excitation current waveform to correct the excitation current waveform; determines the peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform, and determines the residual magnetism state of the power transformer based on the peak value difference, thereby improving the accuracy of residual magnetism detection.

[0081] On the basis of the above embodiment, S105 describes determining the residual magnetism state of the power transformer based on the peak difference, including: inputting the peak difference and the frequency corresponding to the peak difference into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer. The residual magnetism determination model adopts a hybrid neural network model that integrates physical constraints.

[0082] In this embodiment, it can be understood that to determine the residual magnetism state of the power transformer, the peak difference and the frequency corresponding to the peak difference need to be input as input data into a pre-built residual magnetism determination model. The residual magnetism determination module will output the current residual magnetism polarity and the corresponding magnetic flux of the power transformer.

[0083] Furthermore, the residual magnetism determination model includes: a feature extraction module, a physical constraint module and a decision output module, which inputs the peak difference and the frequency corresponding to the peak difference into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer, including: inputting the peak difference and the frequency corresponding to the peak difference into the feature extraction module to obtain a feature vector; inputting the feature vector into the physical constraint module to obtain a feature vector subject to physical constraints; and inputting the feature vector subject to physical constraints into the decision output module to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer.

[0084] It can be understood that in order to extract valuable information for residual magnetism detection of the power transformer from the peak difference and the frequency corresponding to the peak difference, the embodiment of the present application uses the peak difference and the frequency corresponding to the peak difference as input data, and inputs the input data into the feature extraction module. The feature extraction module identifies and extracts information that can reflect the residual magnetism state of the power transformer from the input data, and this information is combined into a characteristic vector.

[0085] In one example, a bidirectional long short-term memory (LSTM) network is used as a feature extraction module to learn and extract features from input data. The BLSTM network consists of a forward LSTM network and a reverse LSTM network connected in parallel. It processes input data in both sequential and reverse directions via a bidirectional information flow, then outputs a feature vector through a feature fusion layer. The input, forget, and output gate mechanisms of the BLSTM network facilitate capturing dependencies in the input data, resulting in highly discriminative output feature vectors.

[0086] In another example, a graph neural network is used as a feature extraction module to model the graph structure of the input data, thereby achieving learning and feature extraction of the input data. Specifically, the input data is mapped into a graph structure representation, where the graph structure representation includes multiple nodes and edges connecting the nodes. The nodes correspond to entities or feature units in the input data, and the edges are used to represent the association relationship or interaction between entities or feature units. The message passing mechanism of the graph neural network is used to learn the features of the graph structure representation. By aggregating the information of neighboring nodes, a hierarchical feature representation containing topological structure features and semantic association information is generated, and the corresponding feature vector is output.

[0087] After obtaining the feature vector through the feature extraction module, it must be input into the physical constraint module to obtain a physically constrained feature vector. In other words, after obtaining the feature vector, it is necessary to determine whether the feature vector satisfies the physical constraints and filter out feature vectors that do not. The physical constraints can be set according to actual needs. For example, the physical constraints can be set as energy conservation constraints or boundary condition constraints. This is just an example.

[0088] After obtaining the physically constrained feature vector through the physical constraint module, the physically constrained feature vector is input into the decision output module to determine the current residual magnetic polarity and corresponding magnetic flux of the power transformer. The decision output module includes two output branches connected in parallel, the first output branch is used to output the current residual magnetic flux of the power transformer, and the second output branch is used to output the current residual magnetic polarity of the power transformer.

[0089] The present embodiment utilizes a hybrid neural network structure with mixed physical constraints to more accurately and robustly determine the current residual magnetization polarity and corresponding magnetic flux of a power transformer. This not only effectively overcomes the limitations of traditional integration methods, such as susceptibility to noise interference and limited accuracy, but also provides a residual magnetization state assessment method independent of the closing operation, significantly improving the reliability of residual magnetization detection in power transformers.

[0090] During actual operation, the magnetic properties of the transformer core are sensitive to temperature. This means that excitation current waveforms collected at different temperatures will exhibit differences, even when the same sinusoidal voltage is applied. To ensure the accuracy of subsequent residual magnetism testing of the power transformer, a temperature compensation mechanism is introduced.

[0091] In some embodiments, the temperature compensation of the excitation current waveform based on the power transformer temperature data described in S103 includes: inputting the power transformer temperature data into a pre-trained compensation model to obtain a temperature compensation amount, and the compensation model is a neural network model trained based on the mapping relationship between historical power transformer temperature data and corresponding excitation current waveform deviations.

[0092] In this embodiment, it is understood that after determining the power transformer temperature data in S102, the power transformer temperature data is used to perform temperature compensation on the excitation current waveform. Specifically, the power transformer temperature data is input into a pre-trained compensation model, which outputs a corresponding temperature compensation value. The temperature compensation value is then used to correct the excitation current waveform, resulting in a temperature-compensated excitation current waveform.

[0093] For example, using the temperature compensation amount to correct the excitation current waveform to obtain a temperature-compensated excitation current waveform includes adjusting the amplitude of the excitation current waveform based on the temperature compensation amount to obtain the temperature-compensated excitation current waveform. In this example, it can be understood that the amplitude of the excitation current waveform is corrected using the temperature compensation amount, wherein the correction process can be addition, multiplication, or other linear transformations. The specific correction method can be selected according to actual needs and is not limited in this embodiment of the present application.

[0094] Furthermore, in addition to adjusting the amplitude of the excitation current waveform, the temperature compensation amount can also be used to adjust the harmonic content of the excitation current waveform and the waveform distortion rate of the excitation current waveform, so as to more comprehensively eliminate the influence of temperature on the excitation current waveform.

[0095] The embodiment of the present application eliminates the influence of temperature on the excitation current waveform by introducing a temperature compensation mechanism, thereby laying a foundation for subsequent residual magnetism detection of the power transformer.

[0096] Furthermore, after using the peak difference to determine the residual magnetization state of the power transformer, subsequent treatment measures must be determined based on the residual magnetization state to suppress the excitation inrush current and avoid the harm caused by the excitation inrush current to the power transformer. It is understood that the residual magnetization detection method for a power transformer provided in the embodiment of the present application further includes: generating a corresponding excitation inrush current suppression strategy based on the residual magnetization state, and outputting the excitation inrush current suppression strategy. Different residual magnetization states correspond to different excitation inrush current suppression strategies.

[0097] For example, when the residual magnetic flux is less than a preset threshold or the direction of the residual magnetism is opposite to the instantaneous direction of the closing voltage, the excitation inrush current suppression strategy may be zero-voltage closing or low-voltage closing; when the residual magnetic flux is greater than a preset threshold and the direction of the residual magnetism is the same as the instantaneous direction of the closing voltage, the excitation inrush current suppression strategy may be pre-magnetization closing, controlling the closing angle or phase-split closing.

[0098] After determining the excitation inrush current suppression strategy, it is necessary to output the determined excitation inrush current suppression strategy. The specific output method can be set according to actual needs, such as displaying the excitation inrush current suppression strategy on a display screen and / or broadcasting the excitation inrush current suppression strategy through an audio execution module. This is only an example.

[0099] The embodiments of the present application can more effectively reduce the generation of inrush current by adopting different strategies to suppress the excitation inrush current according to different states of residual magnetism.

[0100] Next, an example will be given to illustrate how to use the residual magnetism detection method of the power transformer provided in the embodiment of the present application. Figure 2 Schematic diagram of the residual magnetism detection method of the power transformer provided in the embodiment of the present application Figure 2.like Figure 2 As shown, the method includes the following steps:

[0101] 1. Select one phase of the power transformer as the excitation winding, inject a sinusoidal voltage with an initial phase of 90° into the excitation winding to obtain the excitation current waveform of the excitation winding.

[0102] 2. Collect the excitation current waveform of the excitation winding and record the power transformer temperature data corresponding to the collection time.

[0103] 3. Based on the temperature data of the power transformer, temperature compensation is performed on the excitation current waveform.

[0104] 4. From the temperature-compensated excitation current waveform, determine the peak difference of the excitation current in each AC cycle. The peak difference is determined by the following formula:

[0105] I Δtest =(I test_peak +-I test_peak- );

[0106] Among them, I Δtest Indicates peak difference; I test_peak+ Indicates the positive peak current; I test_peak- Indicates negative peak current.

[0107] 5. The peak difference and the frequency corresponding to the peak difference are input into a pre-built residual magnetism determination model to determine the current residual magnetism state of the power transformer, that is, to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer. The residual magnetism determination model adopts a hybrid neural network model that integrates physical constraints.

[0108] It should be noted that the sinusoidal voltage excitation expression is as follows:

[0109] u test (t) = U test sin(ωt+90°)V;

[0110] Among them, u test (t) is the sinusoidal voltage excitation expression; U test is the excitation amplitude of the sinusoidal voltage; ω is the excitation angular frequency of the sinusoidal voltage.

[0111] The flux expression for sinusoidal voltage excitation is shown below:

[0112] Φ(t)=-Φ m cos(ωt+90°)+Φ resid +Φ m cos(90°);

[0113] φ(t) is the magnetic flux expression; φ m is the amplitude of the periodic component of the magnetic flux; Φresid is the residual magnetic flux; Φ m cos(90°) is a constant term that ensures that the magnetic flux does not change suddenly. At the initial phase of 90°, this term is zero, allowing the flux expression to directly reflect the residual magnetism. The magnetic flux is generated by the excitation current waveform.

[0114] Furthermore, determining the residual magnetic flux of the power transformer requires determining the peak difference. To determine the peak difference, it is necessary to remove the sinusoidal voltage excitation when the phase of the sinusoidal voltage excitation is 90° within the set measurement time. This ensures that the sinusoidal voltage excitation application time is an integer multiple of the signal period so as not to change the residual magnetic flux, as shown in the following formula:

[0115]

[0116] Where ΔΦ resid Indicates the change in residual magnetic flux; u test represents the sinusoidal voltage excitation; t0 represents the start time of the measurement time; t represents the end time of the measurement time.

[0117] After determining the peak difference, in addition to determining the current residual polarity and corresponding magnetic flux of the power transformer through the residual magnetism determination model, the current residual magnetic flux corresponding to the peak difference can also be determined through the residual magnetic flux-current peak difference curve to realize residual magnetic detection.

[0118] The residual magnetic flux-current peak difference curve of the same type of power transformer to be tested needs to be determined. The residual magnetic flux-current peak difference curve is determined by the following method:

[0119] Using external DC, the power transformer core is magnetized to magnetic flux saturation, and the saturation magnetic flux φ is recorded. * The per-unit value is 1, and the difference between the positive and negative half-wave peak values of the current is I Δsatur ; Select a phase of the power transformer and apply a sinusoidal voltage excitation with an initial phase of 90° to the primary side of the power transformer. The parameters such as the magnitude, frequency, measurement time, and current amplification factor of the sinusoidal voltage excitation are set in advance. During the measurement time, the current signal of the phase is continuously detected, and the difference between the positive and negative half-wave peak values of the current is recorded as I Δtest And according to the linear function fitting, the residual magnetic flux-current peak difference curve is obtained. The residual magnetic flux can be determined by the following formula:

[0120]

[0121] Since the periodic component of the magnetic flux is proportional to the ratio of the sinusoidal voltage to the frequency, as shown in the following formula:

[0122] Φ m ∝∫u test (t)dt∝Utest / ω.

[0123] Figure 3 Schematic diagram of sinusoidal voltage excitation injection and magnetic flux waveform provided in an embodiment of the present application.

[0124] in, Figure 3 (a) is a schematic diagram of the input sinusoidal voltage excitation; Figure 3 (b) is a schematic diagram of the residual magnetic flux of the power transformer after the sinusoidal voltage is injected. Figure 3 (b) It can be seen that when a sinusoidal voltage excitation with an initial phase of 90° is injected and removed at the 90° phase after the measurement time, the flux waveform is a sinusoidal wave with a phase of 0°. The residual magnetic flux of the power transformer remains unchanged after the residual magnetic detection is completed. Figure 3 (c) is a schematic diagram of the current after the injection of sinusoidal voltage excitation. Due to the existence of the hysteresis loop, the current is asymmetric.

[0125] Figure 4 This is a schematic diagram of the residual magnetic flux-current peak difference curve corresponding to the application of different sinusoidal voltage excitations provided in the embodiment of the present application. Figure 4 It can be seen that the residual flux-current peak difference curves obtained by injecting a sinusoidal voltage excitation of 0.05 times the rated voltage of the power transformer at a frequency of 50 Hz and 0.005 times the rated voltage of the power transformer at a frequency of 5 Hz are very similar. Therefore, the same measurement effect can be achieved by reducing the frequency of the sinusoidal voltage excitation and relaxing the requirements for the sinusoidal voltage excitation amplitude.

[0126] In summary, the embodiments of the present application disclose a method for detecting residual magnetism in a power transformer. This method addresses the problem of residual magnetism in the transformer core after disconnection or various power testing processes. By injecting a 90° low-frequency voltage excitation into the power transformer and measuring the difference between the peak values of the positive and negative half-waves of the power transformer's current waveform, the residual magnetism of the power transformer is detected, thereby effectively suppressing magnetizing inrush current.

[0127] The characteristic of this method is to use low-frequency voltage excitation with an initial phase and an ending phase of 90° to inject into the transformer, and measure the size of the peak value difference between the positive and negative half-wave current waveform of the power transformer. It can effectively detect the residual magnetism of the transformer core without applying excessive voltage amplitude excitation.

[0128] In addition, this method can reduce the signal frequency by adjusting and lowering the requirements for the sinusoidal voltage amplitude, and has higher applicability while ensuring measurement accuracy; the measurement process of this method is clear and simple, and the measurement accuracy is conducive to no-load closing excitation inrush current suppression and other related tests, and the engineering feasibility is high.

[0129] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0130] Figure 5 A schematic diagram of the structure of the residual magnetism detection device for the power transformer provided in the embodiment of the present application is shown as follows: Figure 5 As shown, the residual magnetism detection device 500 for a power transformer provided in this embodiment includes:

[0131] The excitation module 501 is used to apply a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be detected;

[0132] Processing module 502, used to collect the excitation current waveform of the excitation winding and record the power transformer temperature data corresponding to the collection time;

[0133] The compensation module 503 is used to perform temperature compensation on the excitation current waveform based on the temperature data of the power transformer;

[0134] The determination module 504 is configured to determine the peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform; and determine the residual magnetism state of the power transformer based on the peak value difference.

[0135] In a possible implementation, the determining module 504 is specifically configured to:

[0136] The peak difference and the frequency corresponding to the peak difference are input into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer. The residual magnetism determination model adopts a hybrid neural network model that integrates physical constraints.

[0137] In one possible implementation, the residual magnetism determination model includes: a feature extraction module, a physical constraint module, and a decision output module. The determination module 504 is specifically configured to:

[0138] The peak difference and the frequency corresponding to the peak difference are input into the feature extraction module to obtain the feature vector;

[0139] Input the feature vector into the physical constraint module to obtain the physically constrained feature vector;

[0140] The physically constrained feature vector is input into the decision output module to determine the current residual magnetic polarity and the corresponding magnetic flux of the power transformer.

[0141] In a possible implementation, the compensation module 503 is specifically configured to:

[0142] The power transformer temperature data is input into a pre-trained compensation model to obtain the temperature compensation value. The compensation model is a neural network model trained based on the mapping relationship between historical power transformer temperature data and the corresponding excitation current waveform deviation;

[0143] The excitation current waveform is corrected using the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

[0144] In a possible implementation, the compensation module 503 is specifically configured to:

[0145] The amplitude of the excitation current waveform is adjusted according to the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

[0146] In a possible implementation, the processing module 502 is further configured to:

[0147] Based on the residual magnetization state, a corresponding excitation inrush current suppression strategy is generated and output.

[0148] The residual magnetism detection device for the power transformer provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and are not described in detail in this embodiment.

[0149] It should be noted that it should be understood that the division of the various modules of the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called by a processing element; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the processing module can be a separately established processing element, or it can be integrated into a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called by a processing element of the above device to perform the functions of the above processing module. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or by instructions in the form of software.

[0150] For example, the above modules can be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0151] Figure 6 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present application. Figure 6 As shown, the electronic device 600 provided in the embodiment of the present application may include: a processor 601, and a memory 602 communicatively connected to the processor, wherein:

[0152] Memory stores computer-executable instructions;

[0153] The processor executes the computer-executable instructions stored in the memory to implement the method described in the foregoing method embodiment.

[0154] It should be understood that the processor 601 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc. The steps of the method disclosed in the application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The memory 602 may include a high-speed random access memory (RAM), and may also include non-volatile storage NVM (non-volatile memory), such as at least one disk storage, and can also be a USB flash drive, a mobile hard disk, a read-only memory, a disk or an optical disk, etc.

[0155] Optionally, the electronic device 600 may further include a communication interface 603. In a specific implementation, if the communication interface 603, the memory 602, and the processor 601 are implemented independently, the communication interface 603, the memory 602, and the processor 601 may be interconnected via a bus and communicate with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc., but this does not mean that there is only one bus or only one type of bus.

[0156] Optionally, in a specific implementation, if the communication interface 603, the memory 602 and the processor 601 are integrated on a chip, the communication interface 603, the memory 602 and the processor 601 can complete communication through an internal interface.

[0157] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed, they are used to implement the method described in any of the aforementioned embodiments.

[0158] It is understood that the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The computer-readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0159] An exemplary computer-readable storage medium is coupled to a processor, such that the processor can read information from and write information to the computer-readable storage medium. Of course, the computer-readable storage medium can also be an integral part of the processor. The processor and the computer-readable storage medium can reside in an ASIC. Of course, the processor and the computer-readable storage medium can also reside as discrete components in an electronic device.

[0160] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a computer-readable storage medium and includes a number of instructions for causing an electronic device (which can be a personal computer, server, or network device, etc.) or a processor to perform some steps of the method described in various embodiments of the present application.

[0161] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method described in any of the aforementioned embodiments when executed.

[0162] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0163] It should be further noted that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0164] In the above embodiments, the description of each embodiment has its own focus. For parts not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order 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.

[0165] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0166] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for detecting residual magnetism of a power transformer, characterized in that: include: Applying a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be tested; Collecting the excitation current waveform of the excitation winding and recording the temperature data of the power transformer corresponding to the collection time; performing temperature compensation on the excitation current waveform based on the power transformer temperature data; Determine the peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform; Based on the peak value difference, a residual magnetization state of the power transformer is determined.

2. The residual magnetism detection method according to claim 1, characterized in that: The determining the residual magnetism state of the power transformer based on the peak value difference includes: The peak difference and the frequency corresponding to the peak difference are input into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer. The residual magnetism determination model adopts a hybrid neural network model that integrates physical constraints.

3. The residual magnetism detection method according to claim 2, characterized in that: The residual magnetism determination model includes: a feature extraction module, a physical constraint module, and a decision output module. The peak difference and the frequency corresponding to the peak difference are input into a pre-built residual magnetism determination model to determine the current residual magnetism polarity and the corresponding magnetic flux of the power transformer, including: Inputting the peak difference and the frequency corresponding to the peak difference into the feature extraction module to obtain a feature vector; Inputting the feature vector into the physical constraint module to obtain a physically constrained feature vector; The physically constrained feature vector is input into a decision output module to determine the current residual magnetic polarity and the corresponding magnetic flux of the power transformer.

4. The residual magnetism detection method according to any one of claims 1 to 3, characterized in that: The step of performing temperature compensation on the excitation current waveform based on the power transformer temperature data includes: Inputting the power transformer temperature data into a pre-trained compensation model to obtain a temperature compensation amount, wherein the compensation model is a neural network model trained based on a mapping relationship between historical power transformer temperature data and corresponding excitation current waveform deviations; The excitation current waveform is corrected using the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

5. The residual magnetism detection method according to claim 4, characterized in that: The method of modifying the excitation current waveform by using the temperature compensation amount to obtain a temperature-compensated excitation current waveform includes: The amplitude of the excitation current waveform is adjusted according to the temperature compensation amount to obtain a temperature-compensated excitation current waveform.

6. The residual magnetism detection method according to any one of claims 1 to 3, characterized in that: Also includes: Based on the residual magnetization state, a corresponding excitation inrush current suppression strategy is generated and output.

7. A residual magnetism detection device for a power transformer, characterized in that: include: An excitation module, used for applying a preset sinusoidal voltage excitation to the excitation winding of the power transformer to be tested; a processing module, configured to collect the excitation current waveform of the excitation winding and record the temperature data of the power transformer corresponding to the collection time; a compensation module, configured to perform temperature compensation on the excitation current waveform based on the temperature data of the power transformer; a determination module for determining a peak value difference of the excitation current in each AC cycle from the temperature-compensated excitation current waveform; And, based on the peak value difference, determining the residual magnetization state of the power transformer.

8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when the computer program is executed.

Images