On-line monitoring method and system for alternating current and direct current mixed current of transformer iron core based on magnetoelectric coupling sensor

Abstract

The invention relates to the technical field of power equipment state monitoring, in particular to a transformer iron core alternating current and direct current mixed current on-line monitoring method and system based on a magnetoelectric coupling sensor, and the method comprises the steps: monitoring the change of magnetic flux generated by the vibration of an iron core in a transformer in real time through a magnetoelectric coupling sensor array; the magnetic flux change is converted into an original electric signal, the original electric signal is processed, an alternating current signal component and a direct current signal component in the mixed current are extracted, and historical operation data and real-time environment parameters of the alternating current signal component and the direct current signal component are input into a deep recurrent neural network to be trained; and the deep recurrent neural network outputs the enhanced stray current and the direct current signal after the environmental influence is eliminated after iterative training. According to the invention, high-precision prediction of the temperature of the iron core is realized by using a method of combining a deep recurrent neural network and adaptive decomposition; and the neural network is trained by using the dynamic data, so that the dynamic processing capability of the network is enhanced and the operation reliability of the transformer can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment status monitoring, and in particular to an online monitoring method and system for transformer core AC / DC mixed current based on a magnetoelectric coupling sensor. Background Art

[0002] The transformer core may generate DC current during operation due to reasons such as unbalanced current in the high-voltage DC transmission system, and these DC currents are an important cause of the generation of DC bias current. The DC bias current and AC current mix to cause local overheating and increased vibration of the core, threatening the safe operation of the equipment. The traditional measurement method is to use current transformers and Hall sensors. For example, the utility model patent with publication number CN205450103U uses current transformers for collection and the invention patent with publication number CN114678962B uses Hall sensors. However, current transformers can only measure AC current, and the accuracy of Hall sensors is easily affected by temperature drift, and the ability to cope with strong electromagnetic interference is limited, and the long-term stability is insufficient.

[0003] At present, most sensors used in online monitoring of transformer cores are active sensors, which have the following shortcomings when measuring transformer core current: (1) Reliance on external power supply: Active sensors require additional power to support the operation of their internal circuits, which increases system complexity and potential failure points. Especially when working in harsh environments such as high voltage or outdoors for a long time, reliability is affected. (2) Sensitive to temperature. The electronic components inside the active sensor are easily affected by temperature fluctuations, resulting in measurement drift. (3) Insufficient electromagnetic compatibility. Active sensors may be subject to electromagnetic interference in strong electromagnetic fields or complex high-frequency harmonic conditions, resulting in signal distortion or measurement errors. (4) High cost. The manufacturing cost of active sensors is significantly higher than that of passive sensors, which limits their large-scale application in low-cost monitoring scenarios. In addition, the accuracy of the monitoring and processing methods used in existing technologies is not guaranteed.

[0004] The magnetoelectric coupling sensor, such as the invention patent JP6131601B2, discloses a magnetic sensor, which discloses the specific principle of the magnetic sensor converting magnetic flux into electrical signals, and the utility model patent with publication number CN218766979U discloses a circuit using a magnetoelectric sensor for signal processing. However, the magnetoelectric coupling sensor combined with the real-time monitoring and processing method of the transformer core has no accuracy and adaptability for online evaluation of the health status of the transformer core, and the specific solution cannot be predicted by the existing technology. Summary of the invention

[0005] Purpose of the invention: In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides an online monitoring method for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor. The method solves the problem of low decomposition accuracy of the AC / DC mixed current generated during operation of the transformer core, thereby causing low accuracy and poor adaptability in monitoring the health status of the transformer core. The present invention also provides an online monitoring system for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor.

[0006] Technical solution: According to a first aspect of the present invention, a method for online monitoring of AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor is provided, the method comprising: Since the change of magnetic flux inside the transformer causes the vibration change of the transformer core, a magnetoelectric coupling sensor array is used to monitor the vibration change in real time and indirectly obtain DC bias. Among them, the magnetoelectric coupling sensor converts mechanical vibration into electrical signals by detecting the magnetostrictive effect of the core vibration on itself. The vibration mode of the core is directly related to the magnetic flux distribution: when there is no DC bias, the positive and negative cycles of the core flux are symmetrical, and the vibration is mainly based on the fundamental frequency. When there is DC bias, the positive and negative cycles of the core flux are asymmetrical, resulting in changes in the frequency components in the vibration spectrum. By analyzing the changes in the frequency components in the electrical signal output by the sensor, especially the energy of the high and low frequency band electrical signals, the degree of DC bias can be quantified. The multiple magnetoelectric coupling sensors in the magnetoelectric coupling sensor array are evenly distributed on the surface of the core inside the transformer; Performing gain adjustment and digital processing on the original electrical signal to form an output form of a processed standard current, wherein the standard current includes a mixed current formed by alternating current and direct current; Adaptively decompose the standard current, extract the AC signal component and the DC signal component in the mixed current, and input them into the deep recurrent neural network to be trained along with historical operation data and real-time environmental parameters, wherein the AC signal component includes stray current, and the deep recurrent neural network outputs the enhanced stray current and the DC current signal after eliminating the environmental influence after iterative training; A reverse harmonic current of a certain intensity is applied through the filter, and the reverse harmonic current is used to offset the amplitude and phase of the enhanced stray current in real time, and the effective value of the stray current after the offset is calculated.

[0007] Furthermore, the method also includes: Based on the relationship between the three types of current signal data and the core temperature, a dynamic relationship between the current and the core temperature is constructed, and the predicted core temperature is displayed in real time. The three types of current signal data include the DC signal after eliminating environmental influences, the AC signal component after adaptive decomposition, and the effective value of the stray current after enhancement.

[0008] Further, including: The dynamic relationship between the build current and the core temperature is expressed as: in, The real-time temperature of the core; is the DC signal after eliminating the environmental influence, is the effective value of the AC current, which is obtained by adaptive decomposition of the AC current components , and its root mean square is calculated; is the stray current temperature rise coefficient; is the effective value of the stray current after enhancement; is the DC temperature rise coefficient; is the AC temperature rise coefficient; is the initial temperature of the core; It is the correction term for ambient temperature rise, which is determined by the ambient temperature rise; is the DC resistance of the core, which is calculated based on the core material properties and geometric dimensions; is the heat dissipation coefficient, which is related to the heat dissipation structure; is the material loss coefficient, which is determined by the hysteresis loss and eddy current loss characteristics of the core material; is the frequency; is the saturation flux density, which is an inherent property of the core material and is determined based on the material magnetization curve.

[0009] Furthermore, the method further includes: setting a dynamic alarm threshold, which is used to determine whether the core temperature or current inside the transformer is in a dangerous state, and dynamically adjusting the intensity of the processing strategy according to the obtained dangerous state; The dynamic alarm threshold is expressed as: ;in, It is the average of historical temperature data, which is calculated based on the historical operating data of the last few days. is the standard deviation of historical temperature data, which reflects the temperature fluctuation range; is the temperature rise rate weight factor; is the real-time temperature rise rate, which is obtained through the dynamic relationship between current and core temperature.

[0010] Further, including: After calculating the effective value of the stray current after the current offset, it also includes: If the effective value of the stray current after the current offset is less than the preset threshold, the core temperature change is monitored in real time; Otherwise, if the effective value of the stray current after the current offset is still greater than or equal to the preset threshold, the parameter value of the reverse harmonic current is readjusted again to achieve dynamic suppression of the stray current until its effective value is less than the preset threshold.

[0011] Further, including: Adaptively decomposing the standard current to obtain a plurality of intrinsic mode functions, each of which represents a signal component in a different frequency band, thereby extracting the corresponding AC signal component and DC signal component, including: The signal components of different frequency bands include high-frequency harmonic components and fundamental wave components. The high-frequency harmonic components come from: when there is a DC bias current in the transformer core, the half-cycle magnetic density increases, the saturation increases, the magnetic permeability decreases, and the leakage increases, which leads to an increase in the vibration of the transformer core and generates significant high-frequency harmonic components in the vibration signal; The eigenmode function corresponding to the fundamental wave component is recorded as F1, and the eigenmode functions corresponding to the 2nd to 15th harmonics are recorded as F2-F 15 ; Low frequency is defined as below 120Hz, and high frequency is defined as above 120Hz, so the low frequency component is the fundamental wave and the second harmonic, and the high frequency component is the 3rd to 15th harmonics.

[0012] Further, including: The historical operation data and real-time environmental parameters are input into the deep recurrent neural network to be trained, the AC signal component includes stray current, and the deep recurrent neural network outputs the enhanced stray current and the DC current signal after eliminating the environmental influence after iterative training, specifically including: The attention mechanism is used to assign weights to different frequency bands of the signal, giving high weights to the frequency bands where the fundamental wave, harmonics and stray current in the AC signal component are located, and low weights to the noise frequency bands. Iteratively optimize the deep recurrent neural network to be trained, and feed its output back to the input layer for multiple rounds of feature extraction, that is, further strengthen the key frequency band features corresponding to high weights through each round of iteration; The DC temperature rise coefficient in the historical operation data is input into the deep recurrent neural network for iterative training in combination with the dynamically adjusted heat dissipation coefficient. The deep recurrent neural network analyzes the sensor drift in the historical operation data through the attention mechanism to obtain a correction value of the DC temperature rise coefficient, and finally obtains a DC current signal that eliminates environmental influences. The DC temperature rise coefficient is obtained by multiplying the DC resistance of the core and the heat dissipation coefficient. The dynamically adjusted heat dissipation coefficient is obtained by collecting the ambient temperature rise correction term in real time, and adjusting the value of the heat dissipation coefficient accordingly in combination with the current ambient temperature changes.

[0013] Further, including: The reverse harmonic current of a certain intensity is applied through the filter, and the reverse harmonic current of a certain intensity is applied through the filter. The reverse harmonic current is correspondingly expressed as: ;in, nis the harmonic order, ranging from 2 to 15, that is, the stray current is formed by the 2nd to 15th order AC harmonic components, and the AC harmonic components are obtained by the trained deep recurrent neural network. For the n Subharmonic suppression weight; For the n Subharmonic current amplitude; For the n The original phase angle of the subharmonics; is the phase compensation amount, which is adjusted in real time according to the core operating status and environmental interference to ensure that the compensation current is opposite to the phase of the corresponding harmonic. , The power frequency is 50Hz.

[0014] On the other hand, the present invention also provides a transformer core AC / DC mixed current online monitoring system based on a magnetoelectric coupling sensor, the system comprising: An electrical signal acquisition module is used to monitor the vibration changes of the transformer core in real time by using a magnetoelectric coupling sensor array, and indirectly obtain DC bias magnetism; wherein the magnetoelectric coupling sensor converts mechanical vibration into an electrical signal by detecting the magnetostrictive effect of the core vibration on itself, and a plurality of magnetoelectric coupling sensors in the magnetoelectric coupling sensor array are evenly distributed on the surface of the core inside the transformer; A signal conditioning module, used for performing gain adjustment and digital processing on the original electrical signal, so as to form an output form of a standard current, wherein the standard current includes a mixed current formed by alternating current and direct current; A data processing module, used for adaptively decomposing the standard current, extracting the AC signal component and the DC signal component in the mixed current, and inputting them into a deep recurrent neural network to be trained along with historical operation data and real-time environmental parameters, wherein the AC signal component includes stray current, and the deep recurrent neural network outputs enhanced stray current and a DC current signal after eliminating environmental influence after iterative training; The stray current suppression module is used to apply a reverse harmonic current of a certain intensity through a filter, use the reverse harmonic current to offset the amplitude and phase of the enhanced stray current in real time, and calculate the effective value of the stray current after the current offset.

[0015] Furthermore, the system also includes: The temperature prediction module is used to construct a dynamic relationship between current and core temperature based on the relationship between three types of current signal data and core temperature, and to display the predicted core temperature in real time. The three types of current signal data include a DC signal after eliminating environmental influences, an AC signal component after adaptive decomposition, and the effective value of stray current after enhancement.

[0016] Furthermore, the system also includes: An alarm module is used to set a dynamic alarm threshold, determine whether the core temperature or current inside the transformer is in a dangerous state, and dynamically adjust the intensity of the processing strategy according to the obtained dangerous state; The dynamic threshold is expressed as: ;in, It is the average of historical temperature data, which is calculated based on the historical operating data of the last few days. is the standard deviation of historical temperature data, which reflects the temperature fluctuation range; is the temperature rise rate weight factor; is the real-time temperature rise rate, which is obtained through the dynamic relationship between current and core temperature.

[0017] Further, including: The upper and lower layers of the magnetoelectric coupling sensor are magnetostrictive materials, which are used to receive magnetic signals in a magnetic field to generate deformation caused by magnetostriction. The middle layer is piezoelectric material, which is used to receive the strain generated by the upper and lower layers due to magnetostriction, thereby generating a piezoelectric effect and converting the magnetic signal into an electrical signal. The adjacent layers are bonded with epoxy resin to fix and transfer the strain between the materials.

[0018] Further, including: The piezoelectric material is a sheet structure, which includes an upper electrode surface and a lower electrode surface. The upper electrode surface and the lower electrode surface are externally connected to wires for conducting output signals. An excitation coil is wound around the periphery of the magnetoelectric coupling sensor element, and the excitation coil is electrically connected to the signal conditioning module.

[0019] In a third aspect, the present invention also provides an online monitoring device for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor, the device comprising: a memory, a processor, and an online monitoring program for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor stored in the memory and executable on the processor, wherein the online monitoring program for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor implements the steps of the online monitoring method for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor as described above when executed by the processor.

[0020] Beneficial effects: Compared with the prior art, the present invention has the following advantages: (1) The present invention uses a combination of composite sensing materials and a sensor array to deploy data acquisition sensors, which can improve detection accuracy and anti-interference capabilities; (2) When using a neural network algorithm to separate DC signals from AC signals, the present invention takes into account the effects of sensor drift and environmental interference on DC signals, dynamically adjusts the DC temperature rise coefficient in combination with the DC temperature rise coefficient in historical operating data and real-time environmental parameters, and uses dynamic data to train the neural network, thereby improving the flexibility and processing capability of the neural network. The signal output by the trained neural network is a DC current signal that eliminates environmental influences, thereby improving the separation accuracy of AC signals and DC signals. On this basis, the health status of the transformer core is verified through a current-temperature model.

[0021] (3) The present invention aims to solve the problem that the stray current characteristics in the original electrical signal may not be obvious, and adopts adaptive decomposition and neural network algorithm to enhance the characteristics, laying a foundation for improving the stray current suppression effect later. Then, the present application constructs a reverse harmonic current to suppress the enhanced stray current in real time, and adjusts the main transformer stray current suppression strategy in real time, thereby improving the effect of the suppression strategy and ensuring the safe operation of the transformer; (4) Under the premise that stray current is suppressed, this application constructs a current-temperature correlation model based on the dynamic relationship between current and core temperature, so as to monitor the change of core temperature in real time. On this basis, a dynamic alarm threshold is set to determine whether the core temperature or current parameter is in a dangerous state, and the intensity of the processing strategy is dynamically adjusted accordingly, so that this method can monitor the health status of the transformer core with higher accuracy.

[0022] (5) Compared with the traditional fixed parameter setting method, the present invention designs a dynamic threshold and adopts a dynamic adjustment method to dynamically optimize the system operation status according to the real-time temperature rise rate, AC and DC current characteristics and historical data, providing more intelligent and flexible temperature prediction and current monitoring. This mechanism effectively avoids the reaction lag caused by fixed parameters in the traditional method, and enhances the adaptability and response speed of transformer core health prediction under different working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of the structure of the magnetoelectric coupling sensor according to Embodiment 1 of the present invention; Figure 2 This is a flow chart of the method for online monitoring of AC / DC mixed current in transformer core based on magnetoelectric coupling sensor according to Embodiment 1 of the present invention; Figure 3 This is a flow chart of the method for online monitoring of AC / DC mixed current in transformer core based on magnetoelectric coupling sensor according to Embodiment 2 of the present invention; Figure 4 This is a flow chart of the method for online monitoring of AC / DC mixed current in transformer core based on magnetoelectric coupling sensor as described in Example 3 of the present invention.

[0024] Figure 5 Schematic diagram of the structure of the transformer core AC / DC mixed current online monitoring system based on the magnetoelectric coupling sensor according to the fourth embodiment of the present invention Figure 6 This is a schematic structural diagram of an online monitoring system for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor according to Embodiment 5 of the present invention; Figure 7 This is a schematic structural diagram of an online monitoring system for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor according to Embodiment 6 of the present invention; Figure 8 This is a schematic structural diagram of an online monitoring system for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor according to Embodiment 7 of the present invention; Fig. 9 Detailed diagram of the method for online monitoring of AC / DC mixed current in transformer core based on magnetoelectric coupling sensor according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Example 1

[0027] The present invention uses a magnetoelectric coupling sensor to capture the change of the core magnetic field, combines the signal processing algorithm to achieve AC / DC separation, and realizes online evaluation of the health status of the transformer core. Specifically, a method for online monitoring of AC / DC mixed current of the transformer core based on a magnetoelectric coupling sensor is provided. Figure 2 As shown, the method comprises the following steps: S1 uses a magnetoelectric coupling sensor array to monitor the magnetic flux changes caused by the vibration of the iron core inside the transformer in real time, and converts the magnetic flux changes into original electrical signals. Multiple magnetoelectric coupling sensors in the magnetoelectric coupling sensor array are evenly distributed on the surface of the iron core inside the transformer.

[0028] Since the change of magnetic flux inside the transformer causes the vibration change of the transformer core, a magnetoelectric coupling sensor array is used to monitor the vibration change in real time and indirectly obtain the DC bias. Among them, the magnetoelectric coupling sensor converts the mechanical vibration into an electrical signal by detecting the magnetostrictive deformation caused by the vibration of the core. The vibration mode of the core is directly related to the magnetic flux distribution: when there is no DC bias, the positive and negative cycles of the core magnetic flux are symmetrical, and the vibration is mainly based on the fundamental frequency; when there is DC bias, the positive and negative cycles of the core magnetic flux are asymmetrical, resulting in changes in the frequency components in the vibration spectrum. By analyzing the changes in the frequency components in the electrical signal output by the sensor, especially the energy of the high and low frequency band electrical signals, the degree of DC bias can be quantified. The multiple magnetoelectric coupling sensors in the magnetoelectric coupling sensor array are evenly distributed on the surface of the core inside the transformer.

[0029] Specifically, in this embodiment, in order to measure the AC / DC separation accuracy of this method, it is first necessary to generate a corresponding magnetic field in the iron core by injecting a certain amount of current into the transformer. Specifically, this embodiment does not limit the method of adding. A certain amount of AC current can be introduced first, and then a certain amount of DC current can be introduced to cause the vibration change of the transformer core. The magnetoelectric coupling sensor converts the mechanical vibration into an electrical signal by detecting the magnetostrictive effect of the core vibration on itself. A certain amount of mixed AC and DC current can also be introduced at the same time to cause the vibration change of the transformer core. The magnetoelectric coupling sensor converts the mechanical vibration into an electrical signal by detecting the magnetostrictive effect of the core vibration on itself.

[0030] The magnetoelectric coupling sensor used in this embodiment is as follows Figure 1 As shown, the magnetoelectric coupling sensor element is composed of sheet materials in a multi-layer form. The upper and lower layers are magnetostrictive materials, which are used to receive magnetic signals in a magnetic field to generate deformation caused by magnetostriction. The middle layer is a piezoelectric material, which is used to receive the strain generated by the upper and lower layers due to magnetostriction, generate a piezoelectric effect, and convert the magnetic signal into an electrical signal. The layers are bonded with epoxy resin to fix and transfer the strain between the materials. The magnetoelectric coupling sensor element is more sensitive in the length direction, has a more significant magnetostrictive effect than other directions, and can show a better magnetoelectric coupling coefficient.

[0031] The piezoelectric material is a single crystal or polycrystalline ceramic material, specifically one of AlN, quartz, LiNbO3, BaTiO3, ZnO, Pb(Zr, Ti)O3, Pb(Mg, Nb)O3-PbTiO3, Pb(Zn, Nb)O3-PbTiO3 or BiScO3-PbTiO3.

[0032] The magnetostrictive material is an alloy or oxide with magnetostrictive effect or a magnetostrictive composite material formed by combining them with a polymer, and is in the form of a long multi-layer thin sheet; the alloy or oxide with magnetostrictive effect includes Metglas, terbium dysprosium iron alloy [Terfenol-D (Tb0.27-0.30Dy0.73-0.70Fe1.90-1.95)], nickel iron oxide (NiFe2O4), cobalt iron oxide (CoFe2O4), nickel manganese gallium alloy (Ni2MnGa), etc., or a magnetostrictive composite material formed by combining the above magnetostrictive materials with a polymer, and the magnetostrictive material is a single-layer structure or a multi-layer structure.

[0033] In this embodiment, the method for detecting the dynamic bias current of a transformer based on magnetoelectric coupling sensing is mainly composed of the following steps: (1) providing a piezoelectric material, processing the piezoelectric material into a required size and shape, and ultrasonically cleaning the piezoelectric material with ultrapure water; (2) Electrodes are plated on the upper and lower ends of the piezoelectric material surface by annealing, evaporation or magnetron sputtering; (3) The piezoelectric material is polarized along the thickness direction after the electrode is made; (4) The wires are respectively attached to the two electrode end surfaces of the two piezoelectric materials to conduct electrical signals; (5) Provide magnetostrictive materials, process the magnetostrictive materials into the required size and shape, and clean them with alcohol; (6) Using an adhesive to bond the magnetostrictive material to the surface of the piezoelectric material to form a magnetoelectric coupling sensor element; (7) Signals are drawn out from the wires on both sides of the magnetoelectric coupling sensor element to produce a magnetoelectric coupling sensor element.

[0034] (8) An excitation coil is wound around the periphery of the magnetoelectric coupling sensor element, with its sensitive axis direction along the length direction of the magnetoelectric coupling sensor element.

[0035] (9) The two ends of the coil are connected to the signal driving circuit module, and the two electrodes of the magnetoelectric coupling sensor element are connected to the filter amplifier circuit module for preliminary signal processing.

[0036] In this embodiment, preferably, the magnetoelectric coupling sensor array is formed by the magnetoelectric coupling sensor, wherein the magnetoelectric coupling sensors are evenly arranged on the surface of the iron core inside the transformer. The sensor is a passive sensor, which realizes "magnetic-mechanical-electrical" signal conversion through magnetostriction and piezoelectric effect. A single sensor unit is composed of a magnetostrictive material layer composed of Fe-Ga alloy sheets, a piezoelectric sensor element composed of PTZ-5H ceramic sheets, and an electromagnetic shielding cover made of Permalloy, with an additional annular yoke structure for directional capture of stray magnetic fields and reduction of leakage magnetic interference.

[0037] The magnetoelectric coupling sensor array is used to monitor the magnetic flux changes caused by the core vibration in real time and convert them into electrical signal output. Specifically: Changes in the magnetic flux inside the transformer cause changes in the vibration of the transformer core. The vibration mode of the core is directly related to the magnetic flux distribution: when there is no DC bias, the positive and negative cycles of the core flux are symmetrical, and the vibration is mainly based on the fundamental frequency; when there is DC bias, the positive and negative cycles of the core flux are asymmetrical, resulting in changes in the frequency components in the vibration spectrum; the magnetoelectric coupling sensor detects the magnetostrictive effect of the core vibration on itself, and transmits the deformation of the magnetostrictive material in the sensor to the middle piezoelectric material layer; the piezoelectric material triggers the piezoelectric effect due to mechanical strain, and generates a voltage signal between the upper and lower electrode surfaces that is proportional to the strain amplitude, which is called the original electrical signal.

[0038] AC current in the core Generates an alternating magnetic field , DC current Generate a static magnetic field , the magnetic field generated by the AC / DC mixed current , causing the core to vibrate due to magnetostriction, and the vibration causes the magnetic flux to change. The formula is: In formula (1), is the magnetoelectric coupling coefficient.

[0039] According to Faraday's law of electromagnetic induction, the output voltage V is proportional to the rate of change of magnetic flux, and the formula is: In formula (2), is the sensor sensitivity coefficient, which is an inherent property of the sensor.

[0040] S2 performs gain adjustment and digital processing on the original electrical signal to form an output form of a standard current, wherein the standard current includes a mixed current formed by alternating current and direct current; In this embodiment, the gain adjustment and digital processing method includes pre-amplification, filtering and analog-to-digital conversion to obtain the output form of standard current.

[0041] Specifically, in this embodiment, the electrical signal is gain-adjusted and digitized, and the magnetic flux change is restored from the voltage signal by integration operation. , based on the magnetic properties of the core and the winding parameters, the flux changes Convert to equivalent AC / DC mixed current , the formula is: in, is the magnetic permeability, A is the cross-sectional area of ​​the core, Nis the number of winding turns; thus forming the output form of standard current, which is a mixed current including AC and DC. The important reason why the transformer produces DC bias is the presence of DC current components in the transformer windings. When DC current flows through the transformer windings, it will cause the positive and negative half-cycles of the core magnetic flux to be asymmetric, exacerbating the vibration of the core. Therefore, the presence of DC current is an important reason for the DC bias phenomenon.

[0042] In this embodiment, the high frequency / low frequency ratio may be used for quantitative calculation, and the formula is: Among them, R reflects the proportion of high-frequency energy to low-frequency energy. The larger the DC bias, the more significant the flux asymmetry, and the higher the proportion of high-frequency energy. In other words, this value reflects the possibility of DC bias. The larger the value, the higher the probability of DC bias.

[0043] High-frequency / low-frequency component ratio analysis: When there is a DC bias current in the transformer core, the half-cycle magnetic density increases, saturation increases, magnetic permeability decreases, and leakage increases, which leads to increased vibration of the transformer core and significant high-frequency harmonic components in the vibration signal; the amplitude of the DC bias current is indirectly quantified through the ratio of high-frequency harmonics to fundamental components, avoiding interference problems when directly measuring DC components.

[0044] According to the obtained eigenmode function, the eigenmode function corresponding to the fundamental frequency is recorded as F1, and the eigenmode function corresponding to the 2nd to 15th harmonics is recorded as F2-F 15 , each eigenmode function represents the signal component in different frequency bands.

[0045] The low frequency is defined as below 120 Hz and the high frequency is defined as above 120 Hz, so the low frequency component is the fundamental frequency and the second harmonic, and the high frequency component is the 3rd to 15th harmonics. in, is the RMS of the low frequency component, is the RMS of the high frequency component, M is the number of sampling points, express n The eigenmode function corresponding to the subharmonic i A sample value.

[0046] S3 adaptively decomposes the standard current, extracts the AC signal component and the DC signal component in the mixed current, and inputs them into the deep recurrent neural network to be trained along with historical operation data and real-time environmental parameters. The AC signal component includes stray current. After iterative training, the deep recurrent neural network outputs the enhanced stray current and the DC current signal after eliminating environmental influences.

[0047] Specifically, in this embodiment, the specific steps are: S31 adaptively decomposes the processed signal through Hilbert-Huang transform (HHT) to extract the intrinsic mode function, that is, to preliminarily separate the AC and DC components.

[0048] Specifically, using HHT to process the nonlinear and non-stationary signals of the signal conditioning module input data processing unit can effectively separate the complex components in the AC / DC mixed current, such as the power frequency fundamental wave, harmonics, DC offset and high-frequency noise. The core lies in the local feature adaptability of empirical mode decomposition, which does not require preset basis functions and solves the limitations of traditional Fourier transform for non-stationary signals. Through this step, the system obtains signal components with physical significance, laying the foundation for subsequent component separation and feature enhancement; S32 mixes the decomposed AC and DC signal components and inputs them into the pre-trained DRNN model, and combines the historical operation database to perform frequency domain feature enhancement and dynamic correction of DC offset. Specifically, for AC components such as harmonics and stray currents, the DRNN model uses an attention mechanism to enhance key frequency band features and suppress non-correlated noise such as switching noise.

[0049] In this embodiment, the attention mechanism is a mechanism that allows the model to focus on key parts when processing information and ignore irrelevant information, thereby improving processing efficiency and accuracy. It imitates the characteristics of selective attention when human vision processes information. It determines the attention Q weight by calculating the similarity between the query vector (Query) and the key vector (Key), and then performs weighted summation on the value vector (Value) to obtain the final output.

[0050] In a preferred method of this embodiment, the attention mechanism is concentrated on the input feature processing stage and the hidden layer iteration process in the deep recurrent neural network. Specifically, it mainly performs weight allocation first, enters the DRNN model for circulation, has an attention feedback mechanism during the circulation process, and finally outputs when the requirements are met.

[0051] In a preferred embodiment of the present invention, the data input to the DRNN includes signal components, historical operation data, and real-time environmental parameters. The signal component is the intrinsic mode function after HHT decomposition, including AC components and DC components; the historical operation data includes pre-stored harmonic characteristics, stray current mode, DC temperature rise coefficient, and environmental parameters; and the real-time environmental parameters are environmental temperature rise data.

[0052] Among them, the DC temperature rise coefficient is expressed as: In formula (7), is the DC resistance of the core, which is calculated based on the core material properties and geometric dimensions; is the heat dissipation coefficient, which is related to the heat dissipation structure.

[0053] The model training process includes: S321 signal input. The DC component and AC component separated by HHT are input into the pre-trained DRNN model; S322 Frequency domain feature enhancement driven by attention mechanism. In the frequency domain dimension, the attention mechanism is used to assign weights to different frequency bands of the signal, giving high weights to the frequency bands where the AC fundamental wave, harmonics and stray current are located, and giving low weights to the noise frequency bands; S323 performs multiple rounds of iterative optimization. The output of DRNN is fed back to the input layer for multiple rounds of feature extraction. In each round of iteration, the key frequency band features are further enhanced through the attention mechanism. S324 dynamic correction and parameter adjustment. Combine the DC temperature rise coefficient in historical data and real-time environmental parameters to dynamically adjust the DC temperature rise coefficient to eliminate the influence of sensor drift and environmental interference; use the historical harmonic database to match and calibrate the amplitude and phase of the harmonics extracted in real time to improve separation accuracy.

[0054] For step S324, the system collects the ambient temperature rise correction item in real time , combined with the current ambient temperature changes, dynamically adjust The value of, for example, when the ambient temperature rises, the heat dissipation efficiency decreases. To eliminate the influence of sensor drift, DRNN analyzes the sensor drift in historical data through the attention mechanism, thereby correcting The value of .

[0055] In the output results, the AC component includes key frequency band characteristics such as AC fundamental wave, harmonics and stray current that have been enhanced by DRNN; the DC component is a DC current signal that eliminates environmental influences by dynamically adjusting the temperature rise coefficient and sensor drift correction terms.

[0056] S325 uses the DRNN model to perform multiple rounds of feature extraction on signal components through the attention mechanism. In each iteration, the time-frequency characteristics of key frequency bands such as harmonics and stray currents are strengthened, while suppressing non-correlated noise. In each cycle, the temperature rise coefficient of the DC component and the sensor drift correction term are dynamically updated in combination with real-time environmental parameters, so that the separation accuracy of AC and DC currents can be improved. This process continues until the AC and DC current separation accuracy error is less than 0.5%.

[0057] This embodiment uses an example to illustrate the processed data: after HHT, DC component, 50Hz fundamental frequency AC, 100Hz harmonics and high-frequency noise above 2kHz are obtained; the weights of 50Hz fundamental frequency AC and 100Hz harmonics are strengthened through the attention mechanism, and high-frequency noise above 2kHz is suppressed; the DC temperature rise coefficient of the DC component is corrected according to the ambient temperature ; Output DC component and AC component.

[0058] In this embodiment, the DC current separation accuracy error is calculated as follows: Before measuring AC and DC current, apply known DC and AC currents, record the output signal of the sensor, and establish the corresponding relationship between the sensor output signal and the applied current. The subsequent monitoring results are based on this calibration relationship; The current signal output by the sensor when there is only AC and DC is considered to be the true value of the current. , AC effective value ; In the process of measuring AC and DC, the separated DC current is recorded as , the effective value of AC current is recorded as ;therefore, DC Error AC Error For a clearer explanation, this application provides an example: The real value of the DC component is 10mA, and the real value of the AC component is 500mA; Separation results: DC 9.97mA; AC effective value 498mA; Calculation error: DC Error AC Error ; Therefore, the above calculation error meets the requirements.

[0059] S4 applies a reverse harmonic current of a certain intensity through the filter, uses the reverse harmonic current to offset the amplitude and phase of the enhanced stray current in real time, and calculates the effective value of the stray current after the offset.

[0060] In this embodiment, a reverse harmonic current is applied to the power grid connected to the transformer through a filter, and this embodiment does not specifically limit the type of the power grid, which may be a transmission network or a distribution network according to the voltage. The reverse harmonic current is correspondingly expressed as: in, n is the harmonic order, ranging from 2 to 15, that is, the stray current is formed by the 2nd to 15th order AC harmonic components, and the AC harmonic components are obtained by the trained deep recurrent neural network. For the n Subharmonic suppression weight; For the n Subharmonic current amplitude; For the n The original phase angle of the subharmonics; is the phase compensation amount, which is adjusted in real time according to the core operating status and environmental interference to ensure that the compensation current is opposite to the phase of the corresponding harmonic. , The power frequency is 50Hz.

[0061] In this embodiment, the 2-15th harmonic components are separated by the HHT and DRNN joint algorithm, and their amplitudes are extracted. and Phase , the algorithm is based on the real-time harmonic amplitude , Phase And historical operation data, so as to dynamically calculate the suppression weight of each harmonic and phase compensation ; The above parameters are passed to the reverse harmonic current formula, and the stray current suppression strategy is adjusted in real time to ensure the stable operation of the transformer core.

[0062] In this embodiment, a preferred calculation step may be: inputting real-time harmonic parameters, ambient temperature, and historical operation data; strengthening the weight of key frequency bands through the attention coordination mechanism of DRNN, suppressing noise interference, and combining historical data to generate preliminary and ; Adopt the gradient descent method to adjust the residual current that is not completely offset by the reverse harmonic current and ; and and Input dynamic processing module to generate reverse harmonic current.

[0063] Therefore, the reverse harmonic current is generated according to the above formula And inject the system through the active filter to offset the stray current. In this embodiment, after calculating the effective value of the stray current after the offset, it also includes: If the effective value of the stray current after the current offset is less than the preset threshold, the core temperature change is monitored in real time; Otherwise, if the effective value of the stray current after the current offset is still greater than or equal to the preset threshold, the parameter value of the reverse harmonic current is readjusted again to achieve dynamic suppression of the stray current until its effective value is less than the preset threshold.

[0064] Specifically, a preferred method of this embodiment is: strengthen the weight of the frequency band where the stray current is located by combining the HHT and DRNN algorithms, perform RMS calculation on the enhanced stray current signal, and obtain the effective value of the stray current. If the effective value of the stray current is less than 10mA / m 2 , the current-temperature correlation model is used to monitor the core temperature change in real time; if the effective value of the stray current is greater than or equal to 10mA / m 2 , then the dynamic optimization solution of the stray current suppression parameters is generated again through the collaborative mechanism between edge computing nodes, thereby suppressing the stray current and ensuring the safe operation of the transformer.

[0065] Therefore, a magnetoelectric coupling sensor array is used to monitor the vibration changes of the transformer core in real time, and the DC bias magnetism is obtained indirectly; the magnetoelectric coupling sensor converts the mechanical vibration into an electrical signal by detecting the magnetostrictive effect of the core vibration on itself; the signal is digitized; the AC and DC current components are separated; a method combining a deep recurrent neural network (DRNN) and machine learning is used to achieve high-precision prediction of the core temperature; and the main transformer stray current suppression technology is used to enhance the dynamic processing capability. The present invention realizes high-precision online monitoring of AC and DC mixed currents, has the advantages of strong anti-interference ability, fast dynamic response speed, high degree of intelligence, etc., and can effectively improve the reliability of transformer operation.

[0066] Example 2 like Figure 3 and Fig. 9 As shown, based on Example 1, the present invention further includes the following steps: S5 constructs a dynamic relationship between current and core temperature based on the relationship between three types of current signal data and core temperature, and displays the predicted core temperature in real time. The three types of current signal data include the DC signal after eliminating environmental influences, the AC signal component after adaptive decomposition, and the effective value of the stray current after enhancement.

[0067] In this embodiment, the current-temperature correlation model used establishes a dynamic relationship between current and core temperature by fusing the output data from the signal conditioning module and the data processing unit. After decoupling the AC and DC current components and synchronously extracting the stray current characteristics through the HHT and RDNN joint algorithm, the system inputs these current signals into the current-temperature correlation model. The model monitors the changes in core temperature in real time based on the relationship between the change in current signal and the core temperature, such as the relationship between the DC current component and the effective value of the AC current and the core temperature. The output of the model serves as the basis for the dynamic processing module to optimize the stray current suppression strategy, and displays the predicted core temperature in real time on the monitoring terminal, further improving the operational safety of the transformer. The expression of the model is as follows: In formula (9), T It is the real-time temperature of the core; is the DC current component, which is separated from the original signal by the HHT and DRNN algorithms; is the effective value of the AC current, and the AC current components are obtained by HHT decomposition , calculated by RMS; is the stray current temperature rise coefficient, which is obtained by dynamically optimizing historical operating data and real-time environmental parameters through a machine learning model; is the effective value of the stray current, which is obtained by RMS calculation after the stray current is extracted by the HHT and DRNN joint algorithm; is the DC temperature rise coefficient, and the calculation formula is shown in formula (7); is the AC temperature rise coefficient, and the calculation formula is shown in formula (11); is the initial temperature of the core, which is the initial value measured by the temperature sensor when the system is started; It is the correction term for ambient temperature rise, which is determined by the ambient temperature rise; In formula (10), is the DC resistance of the core, which is calculated based on the core material properties and geometric dimensions; is the heat dissipation coefficient, which is related to the heat dissipation structure; In formula (11), is the material loss coefficient, which is determined by the hysteresis loss and eddy current loss characteristics of the core material; is the frequency, 50Hz; is the saturation flux density, an inherent property of the core material, determined based on the material magnetization curve.

[0068] Example 3 On the basis of Example 2, Figure 4 As shown, the present invention also includes the following steps: S6 sets a dynamic alarm threshold, which is used to determine whether the core temperature or current inside the transformer is in a dangerous state, and dynamically adjusts the intensity of the processing strategy according to the obtained dangerous state; The dynamic threshold is expressed as: in, It is the average of historical temperature data, which is calculated based on the historical operating data of the last few days. is the standard deviation of historical temperature data, which reflects the temperature fluctuation range; is the weight factor of temperature rise rate, which is generally 0.5-1.5; is the real-time temperature rise rate, which is obtained through the dynamic relationship between current and core temperature. Specifically, T here is the real-time core temperature in the above formula (9). Specifically, in this embodiment, the present invention continuously records the core temperature data and updates it at fixed intervals. and , generally 1 hour; the data processing unit calculates the temperature rise rate in real time , and combined with Generate dynamic threshold; when the real-time temperature T exceeds , the monitoring terminal triggers an alarm and starts a dynamic processing strategy. Therefore, the present invention adopts a combination of composite sensing materials and sensor array deployment to improve detection accuracy and anti-interference ability. By introducing a collaborative optimization strategy, dynamic adjustment of system parameters such as stray current suppression is achieved. Compared with the traditional fixed parameter setting method, the dynamic threshold designed in this application adopts a dynamic adjustment method to dynamically optimize the system operation status according to the real-time temperature rise rate, AC and DC current characteristics and historical data, and provide more intelligent and flexible temperature prediction and current monitoring. This mechanism effectively avoids the reaction lag caused by fixed parameters in traditional methods, and enhances the adaptability and response speed of the system under different working conditions.

[0069] Example 4 The present invention also provides a transformer core AC / DC mixed current online monitoring system based on a magnetoelectric coupling sensor, such as Figure 5 As shown, the system includes: An electrical signal acquisition module is used to monitor the vibration changes of the transformer core in real time by using a magnetoelectric coupling sensor array, and indirectly obtain DC bias magnetism; wherein the magnetoelectric coupling sensor converts mechanical vibration into an electrical signal by detecting the magnetostrictive effect of the core vibration on itself, and a plurality of magnetoelectric coupling sensors in the magnetoelectric coupling sensor array are evenly distributed on the surface of the core inside the transformer; The signal conditioning module is used to perform gain adjustment and digital processing on the original electrical signal to form an output form of a standard current, wherein the standard current includes a mixed current formed by alternating current and direct current.

[0070] Specifically, the above-mentioned magnetoelectric coupling sensor is connected to the information conditioning module through a shielded twisted pair cable, and an epoxy resin potting sealing kit is used when passing through the transformer tank, and the sealing interface meets the IP68 protection level.

[0071] The signal conditioning module is connected to the sensor array and includes a preamplifier circuit, a bandpass filter and an analog-to-digital conversion unit, and is used for performing gain adjustment and digital processing on the original signal.

[0072] In this embodiment, the gain of the preamplifier circuit is adjustable in the range of 40-80 dB, and the cut-off frequency of the bandpass filter is set to 50 Hz-2 kHz. The analog-to-digital conversion resolution is not less than 16 bits, and the sampling rate is ≥100 kSPS.

[0073] The data processing module is used to adaptively decompose the standard current, extract the AC signal component and the DC signal component in the mixed current, and input them into the deep recurrent neural network to be trained along with historical operation data and real-time environmental parameters. The AC signal component includes stray current. After iterative training, the deep recurrent neural network outputs the enhanced stray current and the DC current signal after eliminating the environmental impact.

[0074] The data processing module in this embodiment adopts an FPGA-DSP architecture, with a built-in AC and DC current component separation algorithm, a current reconstruction model, and a main transformer stray current suppression module. Through a deep recurrent neural network (DRNN) algorithm and a machine learning method, historical operation data and real-time monitoring parameters are integrated, and the DC temperature rise coefficient in the historical data and the real-time environmental parameters are combined to dynamically adjust the DC temperature rise coefficient to eliminate the influence of sensor drift and environmental interference. Thus, through the algorithm set inside the data processing unit, dynamic optimization matching of the suppression parameters is achieved, and the conditioned signal is jointly analyzed in the time domain and frequency domain to calculate the effective value of the AC and DC current of the iron core; Preferably, the processing process of the module corresponding to this embodiment includes: A1: Adaptively decompose the processed signal through HHT to extract the intrinsic mode function, that is, preliminarily separate the AC and DC components. Specifically, using HHT to process the nonlinear and non-stationary signals of the signal conditioning module input data processing unit can effectively separate the complex components in the AC and DC mixed currents, such as the power frequency fundamental wave, harmonics, DC offset and high-frequency noise. The core lies in the local feature adaptability of empirical mode decomposition, which does not require preset basis functions and solves the limitations of traditional Fourier transform for non-stationary signals. Through this step, the system obtains signal components with physical significance, laying the foundation for subsequent component separation and feature enhancement; A2: The decomposed AC and DC signal components are mixed and input into the pre-trained DRNN model, and the frequency domain features are enhanced and the DC offset is dynamically corrected in combination with the historical operation database. Specifically, for AC components such as harmonics and stray currents, DRNN uses the attention mechanism to enhance the key frequency band features and suppress non-correlated noise such as switching noise.

[0075] The data input into DRNN includes signal components, historical operation data and real-time environmental parameters. The signal components are the intrinsic mode functions after HHT decomposition, including AC components and DC components; the historical operation data include pre-stored harmonic characteristics, stray current mode, DC temperature rise coefficient and environmental parameters; the real-time environmental parameters are the environmental temperature rise data.

[0076] The processing steps include: B1: Signal input. The DC component and AC component separated by HHT are input into the pre-trained DRNN model; B2: Frequency domain feature enhancement driven by attention mechanism. In the frequency domain dimension, the attention mechanism is used to assign weights to different frequency bands of the signal, giving high weights to the frequency bands where the AC fundamental wave, harmonics and stray current are located, and giving low weights to the noise frequency band; that is, the high frequency of 2kHz is given a low weight. This embodiment does not make specific restrictions on high and low, as long as the noise frequency band and other frequency bands can be clearly distinguished.

[0077] B3: Perform multiple rounds of iterative optimization. Feed the output of DRNN back to the input layer and perform multiple rounds of feature extraction. In each round of iteration, the key frequency band features are further enhanced through the attention mechanism. B4: Dynamic correction and parameter adjustment. Combine the DC temperature rise coefficient in historical data and real-time environmental parameters to dynamically adjust the DC temperature rise coefficient to eliminate the influence of sensor drift and environmental interference; use the historical harmonic database to match and calibrate the harmonic amplitude and phase extracted in real time to improve separation accuracy.

[0078] For B4, the system collects ambient temperature rise correction items in real time, and dynamically adjusts the value of the heat dissipation coefficient based on the current ambient temperature changes. For example, when the ambient temperature rises, the heat dissipation efficiency decreases, and the heat dissipation coefficient needs to be reduced accordingly. To eliminate the impact of sensor drift, DRNN analyzes the sensor drift in historical data through the attention mechanism and corrects the value of the heat dissipation coefficient.

[0079] In the output results, the AC component includes key frequency band characteristics such as AC fundamental wave, harmonics and stray current that have been enhanced by DRNN, and the noise component is suppressed; the DC component is a DC current signal that eliminates environmental influences by dynamically adjusting the temperature rise coefficient and sensor drift correction terms.

[0080] The DRNN model is used to perform multiple rounds of feature extraction on signal components through the attention mechanism. In each iteration, the time-frequency characteristics of key frequency bands such as harmonics and stray currents are strengthened, while suppressing non-correlated noise. In each cycle, the temperature rise coefficient of the DC component and the sensor drift correction term are dynamically updated in combination with real-time environmental parameters, so that the separation accuracy of AC and DC currents can be improved. This process continues until the AC and DC current separation accuracy error is less than 0.5%.

[0081] Obviously, after the training process of the neural network described in this embodiment is completed, it is necessary to use test data for testing before putting it into use. This is a basic process in engineering and will not be repeated in this application.

[0082] The stray current suppression module is used to apply a reverse harmonic current of a certain intensity through a filter, use the reverse harmonic current to offset the amplitude and phase of the enhanced stray current in real time, and calculate the effective value of the stray current after the current offset.

[0083] Example 5 On the basis of Example 4, Figure 6 As shown, the system also includes: The temperature prediction module is used to construct a dynamic relationship between current and core temperature based on the relationship between three types of current signal data and core temperature, and to display the predicted core temperature in real time. The three types of current signal data include a DC signal after eliminating environmental influences, an AC signal component after adaptive decomposition, and the effective value of stray current after enhancement.

[0084] Example 6 On the basis of Example 5, Figure 7 As shown, the system also includes: An alarm module is used to set a dynamic alarm threshold, determine whether the core temperature or current inside the transformer is in a dangerous state, and dynamically adjust the intensity of the processing strategy according to the obtained dangerous state; The dynamic threshold is expressed as: in, It is the average of historical temperature data, which is calculated based on the historical operating data of the last few days. is the standard deviation of historical temperature data, which reflects the temperature fluctuation range; is the temperature rise rate weight factor; is the real-time temperature rise rate, which is obtained through the dynamic relationship between current and core temperature.

[0085] Example 7 Based on any one of Embodiment 4, Embodiment 5 and Embodiment 6, Figure 8 As shown, the system also includes a monitoring terminal, which communicates with the data processing unit through the industrial Internet, integrates a human-computer interaction page, a data storage module and an abnormal alarm unit, and realizes real-time temperature display, historical data backtracking, dynamic processing status feedback and temperature abnormality alarm.

[0086] Other technical features of the transformer core AC / DC mixed current online monitoring system based on magnetoelectric coupling sensor described in the present invention are similar to the corresponding method of the present application and will not be repeated here.

[0087] In order to better understand the implementation of the present invention, the present invention is specifically described in the form of examples. This example is only used as a further understanding of the invention scheme and is not intended to limit the claims.

[0088] Take the online monitoring of the main transformer of a 220kV substation as an example: The system consists of the following parts: magnetoelectric coupling sensor array, signal conditioning cabinet, FPGA-DSP all-in-one machine, dynamic processing device, and industrial Internet platform.

[0089] Implementation steps: (1) Install 12 magnetoelectric coupling sensors evenly on the surface of the core, apply 10A / 50Hz AC current to verify the sensor output linearity, and then apply 5A DC bias to test the AC / DC separation accuracy.

[0090] (2) The gain of the preamplifier circuit is set to 60dB, converting the analog signal into a 16-bit digital signal with a sampling rate of 200kSPS.

[0091] (3) The intrinsic mode function is extracted through Hilbert-Huang transform, the fundamental wave, DC component and 2-15 harmonics are separated, and the effective value of each component is calculated.

[0092] (4) When DC bias magnetization causes the core to overheat, parameter optimization and active filter control are performed.

[0093] (5) Accurately predict the core temperature.

[0094] (6) If the temperature exceeds the safety threshold, an alarm will be issued.

[0095] Three processing methods are compared: without DRNN and fixed parameters; with DRNN and fixed parameters, and with DRNN and dynamic parameters, which are the corresponding methods of this application. The specific comparison data indicators are shown in Table 1: Table 1: Comparison data of three methods

[0096] As can be seen from Table 1, the method adopted in this application has significant advantages in terms of AC / DC separation error, temperature prediction error, harmonic suppression efficiency, parameter update time, and anti-interference ability, which verifies the superiority of this application in terms of system structure and algorithm optimization.

[0097] Finally, the present invention also provides an online monitoring device for transformer DC bias based on magnetoelectric coupling sensor, the device comprising: a memory, a processor, and an online monitoring program for transformer DC bias based on magnetoelectric coupling sensor stored in the memory and executable on the processor, wherein the online monitoring program for transformer DC bias based on magnetoelectric coupling sensor implements the steps of the online monitoring method for transformer DC bias based on magnetoelectric coupling sensor as described above when executed by the processor.

[0098] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0100] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for online monitoring of AC / DC mixed current in transformer core based on magnetoelectric coupling sensor, characterized in that: The method includes: Since the change of magnetic flux inside the transformer causes the vibration change of the transformer core, a magnetoelectric coupling sensor array is used to monitor the vibration change in real time. The magnetoelectric coupling sensor converts the mechanical vibration into the original electrical signal by detecting the magnetostrictive effect of the core vibration on itself. Performing gain adjustment and digital processing on the original electrical signal to form an output form of a processed current, wherein the processed current includes a mixed current formed by alternating current and direct current; Adaptively decomposing the processed current to obtain a plurality of intrinsic mode functions, each of which represents a signal component in a different frequency band, thereby extracting the corresponding AC signal component and DC signal component, and inputting them into a deep recurrent neural network to be trained along with historical operation data and real-time environmental parameters, wherein the AC signal component includes stray current, and the deep recurrent neural network outputs enhanced stray current and a DC current signal after eliminating environmental influences after iterative training; A reverse harmonic current is applied to the power grid connected to the transformer through a filter, and the reverse harmonic current is used to offset the amplitude and phase of the enhanced stray current in real time, and the effective value of the stray current after the offset is calculated.

2. The method for online monitoring of AC / DC mixed current of transformer core based on magnetoelectric coupling sensor according to claim 1, characterized in that: The method further includes: Based on the relationship between the three types of current signal data and the core temperature, a dynamic relationship between the current and the core temperature is constructed, and the predicted core temperature is displayed in real time. The three types of current signal data include the DC signal after eliminating environmental influences, the AC signal component after adaptive decomposition, and the effective value of the stray current after enhancement.

3. The method for online monitoring of AC / DC mixed current of transformer core based on magnetoelectric coupling sensor according to claim 2, characterized in that: The dynamic relationship between the build current and the core temperature is expressed as: in, It is the real-time temperature of the core; is the DC signal after eliminating the environmental influence, is the effective value of the AC current, which is obtained by adaptive decomposition of the AC current components , and its root mean square is calculated; is the stray current temperature rise coefficient; is the effective value of the stray current after enhancement; is the DC temperature rise coefficient; is the AC temperature rise coefficient; is the initial temperature of the core; It is the correction term for ambient temperature rise, which is determined by the ambient temperature rise; is the DC resistance of the core, which is calculated based on the core material properties and geometric dimensions; is the heat dissipation coefficient, which is related to the heat dissipation structure; is the material loss coefficient, which is determined by the hysteresis loss and eddy current loss characteristics of the core material; is the frequency; is the saturation flux density, which is an inherent property of the core material.

4. The method for online monitoring of AC / DC mixed current of transformer core based on magnetoelectric coupling sensor according to claim 3 is characterized in that: The method further includes: setting a dynamic alarm threshold, the dynamic alarm threshold being used to determine whether the core temperature inside the transformer is in a dangerous state, and dynamically adjusting the intensity of the processing strategy according to the obtained dangerous state; The dynamic alarm threshold is expressed as: ;in, It is the average of historical temperature data, which is calculated based on the historical operating data of the last few days. is the standard deviation of historical temperature data, which reflects the temperature fluctuation range; is the temperature rise rate weight factor; is the real-time temperature rise rate.

5. The method for online monitoring of AC / DC mixed current of transformer core based on magnetoelectric coupling sensor according to claim 1, characterized in that: After calculating the effective value of the stray current after the current offset, it also includes: If the effective value of the stray current after the current offset is less than the preset threshold, the core temperature change is monitored in real time; Otherwise, if the effective value of the stray current after the current offset is still greater than or equal to the preset threshold, the parameter value of the reverse harmonic current is readjusted again to achieve dynamic suppression of the stray current until its effective value is less than the preset threshold.

6. The method for online monitoring of AC / DC mixed current of transformer core based on magnetoelectric coupling sensor according to any one of claims 1 to 5, characterized in that: Adaptively decomposing the processed current to obtain a plurality of intrinsic mode functions, each of which represents a signal component in a different frequency band, thereby extracting the corresponding AC signal component and DC signal component, including: The signal components of different frequency bands include high-frequency harmonic components and fundamental wave components. The high-frequency harmonic components come from: when there is a DC bias current in the transformer core, the half-cycle magnetic density increases, the saturation increases, the magnetic permeability decreases, and the leakage increases, which leads to an increase in the vibration of the transformer core and generates significant high-frequency harmonic components in the vibration signal; The eigenmode function corresponding to the fundamental wave component is recorded as F1, and the eigenmode functions corresponding to the 2nd to 15th harmonics are recorded as F2-F 15 ; and the low frequency is defined as below 120Hz, and the high frequency is defined as above 120Hz, so the low frequency component is the fundamental component and the second harmonic, and the high frequency component is the third to fifteenth harmonics.

7. The method for online monitoring of AC / DC mixed current of transformer core based on magnetoelectric coupling sensor according to any one of claims 1 to 5, characterized in that: The historical operation data and real-time environmental parameters are input into the deep recurrent neural network to be trained, the AC signal component includes stray current, and the deep recurrent neural network outputs the enhanced stray current and the DC current signal after eliminating the environmental influence after iterative training, specifically including: Assign weights to different frequency bands of the signal, assign high weights to the key frequency bands where the fundamental wave, harmonics and stray current in the AC signal components are located, and assign low weights to the high-frequency components; Iteratively optimize the deep recurrent neural network to be trained, and feed its output back to the input layer for multiple rounds of feature extraction, that is, further strengthen the key frequency band features corresponding to high weights through each round of iteration; The DC temperature rise coefficient in the historical operation data, combined with the dynamically adjusted heat dissipation coefficient, are input into the deep recurrent neural network for iterative training. The deep recurrent neural network analyzes the sensor drift in the historical operation data to obtain a correction value of the DC temperature rise coefficient, and finally obtains a DC current signal that eliminates environmental influences. The DC temperature rise coefficient is obtained by multiplying the DC resistance of the core and the heat dissipation coefficient. The dynamically adjusted heat dissipation coefficient is obtained by collecting the ambient temperature rise correction term in real time, and adjusting the value of the heat dissipation coefficient accordingly in combination with the current ambient temperature changes.

8. The method for online monitoring of AC / DC mixed current of transformer core based on magnetoelectric coupling sensor according to any one of claims 1 to 5, characterized in that: The reverse harmonic current is applied to the power grid connected to the transformer through the filter, and the reverse harmonic current is correspondingly expressed as: ;in, n is the harmonic order, ranging from 2 to 15, that is, the stray current is formed by the 2nd to 15th order AC harmonic components, and the AC harmonic components are obtained by the trained deep recurrent neural network. For the n Subharmonic suppression weight; For the n Subharmonic current amplitude; For the n The original phase angle of the subharmonics; is the phase compensation amount, which is adjusted in real time according to the core operating status and environmental interference to ensure that the compensation current is opposite to the phase of the corresponding harmonic. , The power frequency is 50Hz.

9. An online monitoring system for AC / DC mixed current of transformer core based on magnetoelectric coupling sensor, characterized in that: The system includes: An electrical signal acquisition module is used to monitor vibration changes in real time using a magnetoelectric coupling sensor array, wherein the vibration changes are caused by changes in the transformer core vibration caused by changes in the internal magnetic flux of the transformer. The magnetoelectric coupling sensor detects the magnetostrictive effect of the core vibration on itself and converts the mechanical vibration into an original electrical signal; A signal conditioning module, used for performing gain adjustment and digital processing on the original electrical signal, so as to form an output form of a processed current, wherein the processed current includes a mixed current formed by alternating current and direct current; A data processing module, used for adaptively decomposing the processed current, extracting the AC signal component and the DC signal component in the mixed current, and inputting them into a deep recurrent neural network to be trained along with historical operation data and real-time environmental parameters, wherein the AC signal component includes stray current, and the deep recurrent neural network outputs enhanced stray current and a DC current signal after eliminating environmental influence after iterative training; The stray current suppression module is used to apply a reverse harmonic current to the power grid connected to the transformer through a filter, use the reverse harmonic current to offset the amplitude and phase of the enhanced stray current in real time, and calculate the effective value of the current stray current after offset.

10. The transformer core AC / DC mixed current online monitoring system based on magnetoelectric coupling sensor according to claim 9, characterized in that: The system also includes: The temperature prediction module is used to construct a dynamic relationship between current and core temperature based on the relationship between three types of current signal data and core temperature, and to display the predicted core temperature in real time. The three types of current signal data include a DC signal after eliminating environmental influences, an AC signal component after adaptive decomposition, and the effective value of stray current after enhancement.

11. The transformer core AC / DC mixed current online monitoring system based on magnetoelectric coupling sensor according to claim 10, characterized in that: The system also includes: An alarm module is used to set a dynamic alarm threshold, determine whether the core temperature inside the transformer is in a dangerous state, and dynamically adjust the intensity of the processing strategy according to the obtained dangerous state; The dynamic alarm threshold is expressed as: ; in, It is the average of historical temperature data, which is calculated based on the historical operating data of the last few days. is the standard deviation of historical temperature data, which reflects the temperature fluctuation range; is the temperature rise rate weight factor; is the real-time temperature rise rate.

12. The transformer core AC / DC mixed current online monitoring system based on magnetoelectric coupling sensor according to claim 9, characterized in that: The upper and lower layers of the magnetoelectric coupling sensor are magnetostrictive materials, which are used to receive magnetic signals in a magnetic field to generate deformation caused by magnetostriction. The middle layer is piezoelectric material, which is used to receive the strain generated by the upper and lower layers due to magnetostriction, thereby generating a piezoelectric effect and converting the magnetic signal into an electrical signal. The adjacent layers are bonded with epoxy resin to fix and transfer the strain between the materials.

13. The transformer core AC / DC mixed current online monitoring system based on magnetoelectric coupling sensor according to claim 12, characterized in that: The piezoelectric material is a sheet structure, which includes an upper electrode surface and a lower electrode surface. The upper electrode surface and the lower electrode surface are externally connected to wires for conducting output signals. An excitation coil is wound around the periphery of the magnetoelectric coupling sensor element, and the excitation coil is electrically connected to the signal conditioning module.

14. An online monitoring device for AC / DC mixed current of transformer core based on magnetoelectric coupling sensor, characterized in that: The device comprises: a memory, a processor and an online monitoring program for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor, which is stored in the memory and can be run on the processor. When the online monitoring program for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor is executed by the processor, the steps of the online monitoring method for AC / DC mixed current of a transformer core based on a magnetoelectric coupling sensor as described in any one of claims 1 to 8 are implemented.

Images