Method and system for monitoring and suppressing direct-current magnetic bias current of power transformer based on magnetoelectric coupling sensor

Abstract

The invention relates to the technical field of power equipment state monitoring, in particular to a power transformer direct current magnetic bias current monitoring suppression method and system based on magnetoelectric coupling sensors, and the method comprises the steps: installing the magnetoelectric coupling sensors in monitoring nodes of power transformers, and capturing magnetic field signals in the operation of the power transformers in real time; adaptively decomposing the preprocessed current signal into a plurality of intrinsic mode functions by adopting a successive variational mode decomposition method based on improved information acquisition optimization, and extracting direct current magnetic bias current data of the power transformer from the intrinsic mode functions; a deep recurrent neural network model is adopted to capture a long-term dependency relationship provided by historical data and short-term dynamic changes provided by real-time data, and prediction of direct-current magnetic bias current data at the next moment is completed; according to the invention, the direct current magnetic bias current of the power transformer is accurately detected, the direct current magnetic bias component is effectively inhibited, and the safe and stable operation capability of a power system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment status monitoring, and in particular to a method and system for monitoring and suppressing direct current magnetic bias current of a power transformer based on a magnetoelectric coupling sensor. Background Art

[0002] In the context of accelerating the construction of new power systems and the connection of a high proportion of new energy sources to the grid, power transformers, as core equipment of the power grid, are crucial to accurately monitor their operating status to ensure the safety and stability of the system. Bias current is an important parameter of power transformers. By real-time monitoring of bias current, abnormal conditions of transformers can be detected in time and corresponding measures can be taken to ensure the safe and reliable operation of power equipment.

[0003] Traditional bias current detection methods mainly rely on current transformers or Hall sensors for signal acquisition. However, the measurement accuracy of current transformers is poor and cannot be used for DC detection; Hall sensors are greatly affected by temperature and have low sensitivity. For example, the utility model patent with publication number CN205450103U uses a current transformer and the invention patent with publication number CN114678962B uses a Hall sensor. However, the current transformer can only measure AC current, the accuracy of the Hall sensor is easily affected by temperature drift, the ability to cope with strong electromagnetic interference is limited, and the long-term stability is insufficient.

[0004] 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.

[0005] 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 is combined with a real-time monitoring and processing method of the transformer core, and combined with a data processing method to monitor the health status of the transformer core and suppress the DC bias current. There is still a blank in this regard, and a specific solution cannot be obtained through the existing technology. Summary of the invention

[0006] Purpose of the invention: In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides a method for monitoring and suppressing the DC bias current of a power transformer based on a magnetoelectric coupling sensor. The method solves the problems of low accuracy in monitoring the health status of the transformer core caused by DC bias that may occur during the operation of the transformer core and inability to timely predict and effectively suppress the DC bias. The present invention also provides a system for monitoring and suppressing the DC bias current of a power transformer based on a magnetoelectric coupling sensor.

[0007] Technical solution: According to a first aspect of the present invention, a method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor is provided, the method comprising: The magnetoelectric coupling sensor is installed in the monitoring node of each power transformer to capture the magnetic field signal of the power transformer in real time, thereby obtaining the original current signal and preprocessing the collected original current signal; A successive variational modal decomposition method based on improved information acquisition optimization is adopted to adaptively decompose the preprocessed current signal into a number of intrinsic mode functions, and extract the DC bias current data of the power transformer caused by the stray current. The successive variational modal decomposition method based on improved information acquisition optimization seeks the best penalty factor through the improved information acquisition optimization algorithm IAO, and applies the best penalty factor to the successive variational modal decomposition method, and extracts the direction and amplitude characteristics of the DC bias current according to all the modal components obtained by the decomposition; The historical DC bias current data of the power transformer, the real-time monitored DC bias current data and external variables are combined as the input of the deep recurrent neural network model to capture the long-term dependencies provided by the historical data and the short-term dynamic changes provided by the real-time data, and complete the prediction of the DC bias current data at the next moment. The external variables include: global magnetic field index, grounding pole current and core temperature.

[0008] Furthermore, the method also includes: According to the set augmented objective function without constraint programming, the improved external penalty function method is adopted to solve the corresponding nonlinear programming problem to find the global optimal solution and obtain the neutral point series resistance of each power transformer; the augmented objective function without constraint programming is obtained by minimizing the objective function and penalty term of the nonlinear programming of the bias current suppression parameter; The DC bias current suppression strategy is adjusted in real time according to the obtained neutral point series resistance to reduce the DC bias component.

[0009] Further, including: The improved information acquisition optimization successive variational mode decomposition method seeks the optimal penalty factor through an improved information acquisition optimization algorithm IAO, specifically including: The Circle chaos map is used to initialize the population position, the fitness value is calculated according to the objective function, and the current optimal solution is sought according to the current fitness value; The exploration and development phases of the IAO algorithm are used to optimize the positions of the individuals in the population, and the fitness values ​​are updated during the optimization process, and the current optimal solution is sought based on the calculated fitness values; Iterate according to the given maximum number of iterations and output the global optimal solution, that is, the optimal penalty factor.

[0010] Further, including: The Circle chaotic map is used to initialize the population position, which is expressed as: ; in, Indicates i The chaos value corresponding to each individual in the population; , represents a constant factor; Represents the modulo operator, which is used to limit the value range of a variable; Indicates The initial positions of individuals in the population; , Indicates the upper and lower limits of the search space. Further, including: In the process of calculating the fitness value according to the objective function and seeking the current optimal solution according to the current fitness value, the objective function is to convert the envelope entropy and energy difference Combined multi-objective fitness function , expressed as: ; In the formula, , is the weight coefficient, which is adjusted as needed. Further, it includes: The optimal penalty factor is applied to the successive variational modal decomposition method, and the direction and amplitude characteristics of the DC bias current are extracted according to all modal components obtained by decomposition, including: Input the preprocessed current signal and set relevant parameters, including penalty factor, discrimination accuracy, discrimination precision, noise variance, and initialize modal components, Lagrange multipliers, and center frequencies; Iteratively update the parameter modal components, Lagrange multipliers, and center frequencies until the convergence condition is reached, and output the modal components and center frequencies corresponding to the current iteration; Determine whether all the acquired modes meet the constraints. If not, reinitialize the modal components, Lagrange multipliers, and center frequencies. Otherwise, the iteration ends and all the modal components and their center frequencies are output. When DC bias occurs in the power transformer, there is a DC component in the excitation current, including the fundamental wave, second harmonic components and above. The characteristics of the DC component can effectively characterize whether DC bias occurs in the transformer and its severity. All the modal components obtained by decomposition are analyzed and the direction and amplitude characteristics of the DC bias current are extracted.

[0011] Further, including: The augmented objective function without constraint programming according to the setting specifically includes: adding the nonlinear programming minimization objective function of the bias current suppression parameter and the penalty function corresponding to the nonlinear programming constraint condition of the bias current suppression parameter as the augmented objective function; The nonlinear programming minimization objective function of the bias current suppression parameter is expressed as: ; in, is the decision variable; For the The series resistance of the monitoring node of each power transformer; For the The DC bias current of the monitoring node of a power transformer; is the number of monitoring nodes of the power transformer; , is the weight coefficient, which can be adjusted as needed; The nonlinear programming constraint condition of the bias current suppression parameter is expressed as: ;in, The upper and lower limits of the DC bias current of each power transformer node; The augmented objective function is expressed as: ; in, is the penalty parameter; . Further, including: The improved external penalty function method is adopted to solve the corresponding nonlinear programming problem to find the global optimal solution and obtain the neutral point series resistance of each power transformer, including: Step 1: Set the initial penalty parameter , allowable error , any initial point , ; Step 2: As the initial point, the gradient descent method is used to calculate the minimized augmented objective function Optimal solutions to unconstrained problems ; Step 3: If , then the problem ends and the optimal solution of the original problem is output , that is, the neutral point series resistance; otherwise, execute step 4; Step 4: Update the penalty parameter using the penalty parameter update formula. , execute step 2; The penalty parameter update formula is: ; in, is the gain coefficient; is the smoothing term; When the constraint violation is large, the penalty parameter increases faster. At this time, the impact of the penalty term is increased, and the infeasible solution is quickly iterated to a feasible solution. When the constraint violation is small, the penalty parameter increases slower. At this time, the difficulty in solving the problem caused by the rapid increase of the penalty parameter is avoided, and the feasible solution is gradually transitioned to the optimal solution.

[0012] Further, including: The method of adjusting the DC bias current suppression strategy in real time according to the obtained neutral point series resistance to reduce the DC bias component includes: A small resistor is connected in series with the neutral point of the power transformer. When the bias current flows into the transformer, the series resistor limits the DC bias current, and a protective gap is used as a protection device for the small resistor. The expression of the series small resistor is: ; In the formula, For the The adjustable resistor setting value of each power transformer node; To solve the nonlinear programming problem On the other hand, the present invention also provides a power transformer DC bias current monitoring and suppression system based on a magnetoelectric coupling sensor, the system comprising: The measurement module is used to install the magnetoelectric coupling sensor in the monitoring node of each power transformer to capture the magnetic field signal of the power transformer in real time during operation, and then obtain the original current signal; A signal processing module, used for preprocessing the collected original current signal; A data processing module is used to use a successive variational modal decomposition method based on improved information acquisition optimization to adaptively decompose the preprocessed current signal into a plurality of intrinsic mode functions, and extract the DC bias current data of the power transformer caused by the stray current, wherein the successive variational modal decomposition method based on improved information acquisition optimization seeks an optimal penalty factor through an improved information acquisition optimization algorithm IAO, and applies the optimal penalty factor to the successive variational modal decomposition method, and extracts the direction and amplitude characteristics of the DC bias current according to all modal components obtained by the decomposition; The data prediction module is used to combine the historical DC bias current data of the power transformer, the real-time monitored DC bias current data and external variables as the input of the deep recurrent neural network model, capture the long-term dependencies provided by the historical data and the short-term dynamic changes provided by the real-time data, and complete the prediction of the DC bias current data at the next moment. The external variables include: global magnetic field index, grounding pole current and core temperature.

[0013] Furthermore, the system also includes: A data analysis module is used to solve the corresponding nonlinear programming problem by adopting an improved external penalty function method according to the set augmented objective function without constraint programming, so as to find the global optimal solution and obtain the neutral point series resistance of each power transformer; the augmented objective function without constraint programming is obtained by minimizing the objective function and penalty term of the nonlinear programming of the bias current suppression parameter; The dynamic management module is used to adjust the DC bias current suppression strategy in real time according to the obtained neutral point series resistance to reduce the DC bias component.

[0014] Finally, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method for monitoring and suppressing the DC bias current of a power transformer based on a magnetoelectric coupling sensor as described above.

[0015] 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) The present invention uses an improved IAO-SVMD algorithm to perform better modal decomposition of complex data and extract bias current characteristics. It introduces external variables through the DRNN network model and combines historical data with real-time data to achieve accurate prediction. It seeks the optimal suppression parameters of the system through nonlinear programming between multiple transformer nodes. At the same time, it considers DC bias current suppression technology and emphasizes dynamic management. The present invention realizes the accurate detection of DC bias current of power transformers, effectively suppresses DC bias components, and improves the ability of power systems to operate safely and stably. This not only helps to improve the health monitoring of power transformers and improve the operating status of power transformers, but also helps to provide data support for fault warning and emergency response of power systems, thereby enhancing the safety and reliability of power grids.

[0016] (3) The present invention adopts Circle chaotic mapping to initialize the population position, replacing the random initialization of the population position in the original IAO algorithm. This improvement can effectively cover various areas without causing repetition of the initial state. It also avoids falling into the same local optimum when running the algorithm multiple times, thereby improving the optimization efficiency of the algorithm.

[0017] (4) The present invention combines envelope entropy and energy difference as the objective function in the IAO algorithm, which can not only measure the complexity of each modal component after signal decomposition, but also ensure that the total energy of each modal component after decomposition is consistent with the original signal, thus avoiding energy loss. By improving the IAO algorithm, the optimal penalty factor is obtained, thereby improving the decomposition effect of the successive variational mode decomposition method SVMD.

[0018] (5) The present invention performs adaptive modal decomposition of the output complex signal by improving the IAO-SVMD algorithm according to the obtained optimal penalty factor. Since the decomposition result of the successive variational modal decomposition method SVMD is mainly affected by the penalty factor The impact of the optimal penalty factor Since the output accuracy of the algorithm is greatly affected, this application introduces constraint criteria to adaptively implement the intrinsic mode function (IMF) decomposition without setting the number of decomposition levels. .

[0019] (6) The present invention adopts a deep recurrent neural network (DRNN) and introduces external variables to fuse the real-time monitoring signal obtained by decomposition with the historical operation data. The historical operation bias current data of the power transformer, the current real-time monitoring data and the external variables are combined as the input of the DRNN model to capture the long-term dependency provided by the historical data and the short-term dynamic changes provided by the real-time data, and accurately predict the DC bias current data at the next moment. The present invention adopts a deep recurrent neural network (DRNN) to realize the fusion prediction of the historical operation data and the real-time monitoring data of the bias current, and on this basis, based on the system perspective, the optimal bias current suppression parameters are solved through nonlinear programming to achieve global joint optimization, thereby achieving the transition from passive response to active suppression.

[0020] (7) The present invention adjusts the DC bias current suppression strategy in real time according to the optimization parameters solved by nonlinear programming, and reduces the DC bias current component in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a specific flow chart of the method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor as described in Example 1 of the present invention; Figure 2 This is a parameter optimization flow chart of the improved IAO algorithm described in Example 1 of the present invention; Figure 3 This is a schematic diagram of the structure of a power transformer DC bias current monitoring and suppression system based on a magnetoelectric coupling sensor as described in Example 2 of the present invention. DETAILED DESCRIPTION

[0022] 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.

[0023] Example 1 The present invention provides a method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor, such as Figure 1 As shown, the method comprises the following steps: S1 installs magnetoelectric coupling sensors in the monitoring nodes of each power transformer to capture the magnetic field signals of the power transformer in real time and obtain the original current signals; In this embodiment, the magnetoelectric coupling sensors of the measurement module are arranged in a multi-channel array and distributed on the surface of the core of the power transformer to achieve the conversion from magnetic field signals to mechanical signals and then to electrical signals.

[0024] Optionally, the magnetoelectric coupling sensor is composed of magnetostrictive material and piezoelectric material. Under the magnetization of an external magnetic field, the size of the magnetostrictive material changes in one or some directions to generate force, specifically one of Fe-Ga, Terfenol-D, Metglas and NiFe2O4.

[0025] Optionally, an external force is applied to the piezoelectric material in a specific direction, causing the material to deform and generate electric charge, specifically one of quartz, LiNbO3, BaTiO3, PZT, PVDF, and PMN-PT.

[0026] Optionally, the structure of the magnetoelectric coupling sensor is determined by the composite form of two materials, specifically one of a 0-3 type granular composite material, a 2-2 type layered composite material, and a 1-3 type columnar composite material.

[0027] S2 pre-processes the collected original current signal; The preprocessing in this embodiment includes: filtering, gain amplification, phase synchronization and digital processing of the original current signal to eliminate noise interference and improve the signal-to-noise ratio, specifically including: By using a standard current source to inject a known current into the transformer winding and recording the output current of the magnetoelectric coupling sensor, a relationship curve between the two is established. Based on the relationship curve between the actual current of the transformer winding and the output current of the magnetoelectric coupling sensor, the current signal output by the magnetoelectric coupling sensor is converted into the actual current signal of the transformer. On this basis, the signal is filtered, gain amplified, phase synchronized and digitized.

[0028] (a) Filter circuit, whose input is the collected signal of the magnetoelectric coupling sensor, adopts a low-pass filter with a cut-off frequency set to 2kHz to eliminate high-frequency noise in the collected signal, such as switching noise; (b) Gain amplifier, whose input is the noise reduction signal after the filtering circuit, is used to amplify the weak current signal in multiple stages, dynamically adjust the gain according to the signal amplitude, and ensure that the analog-to-digital converter (ADC) input signal is in the optimal range. Its gain is set to 10dB-40dB; (c) A signal synchronization unit, whose input is the amplified signal after the gain amplifier, adopts a phase-locked detection circuit, detects the phase information of the amplified signal and the signal source, compares and analyzes the phase difference between the two signals, and adjusts the signal phase to achieve signal synchronization; (d) The analog-to-digital conversion unit, whose input is the synchronization signal passed through the signal synchronization unit, is used to convert the analog signal into a digital signal. It uses the AD7606 chip, which is a SAR type chip with 16-bit synchronous sampling, a single 5V power supply, and a full-channel throughput rate of 200kSPS.

[0029] S3 adopts a successive variational modal decomposition method based on improved information acquisition optimization to adaptively decompose the preprocessed current signal into several intrinsic mode functions, and extract the DC bias current data of the power transformer caused by stray current. The successive variational modal decomposition method with improved information acquisition optimization seeks the optimal penalty factor through an improved information acquisition optimization algorithm IAO, and applies the optimal penalty factor to the successive variational modal decomposition method, and extracts the direction and amplitude characteristics of the DC bias current based on all modal components obtained by decomposition.

[0030] Specifically, in this embodiment, the successive variational mode decomposition (improved IAO-SVMD) based on improved information acquisition optimization is adopted, such as Figure 2 As shown in the figure, the optimal penalty factor is sought by improving the IAO algorithm to improve the decomposition effect of SVMD. The complex output signal of the signal processing module is adaptively decomposed into several intrinsic mode functions, and the DC bias current characteristics of the power transformer caused by stray current, that is, the direction and amplitude of the DC bias current, are extracted therefrom.

[0031] The above-mentioned IAO algorithm is the Information Acquisition Optimizer (IAO), which solves the increasingly complex challenges in the field of continuous nonlinear optimization. The algorithm is inspired by human information acquisition behavior and consists of three key strategies: information collection, information filtering and evaluation, and information analysis and organization to adapt to different optimization needs. The results show that IAO is highly competitive in terms of convergence rate, solution accuracy and stability. In addition, time comparison analysis experiments show its high efficiency.

[0032] Sequential Variational Mode Decomposition (SVMD) is a method used in signal processing and data analysis. It can decompose a complex signal into a series of modal functions, each of which represents a specific frequency component in the signal. The main goal of SVMD is to extract the different frequency components in the signal and reconstruct them into the original signal.

[0033] The basic principle of SVMD is to decompose the signal into multiple mode functions by variational mode decomposition. In each iteration, SVMD updates the mode function by minimizing the difference between the signal and the mode function. This process is repeated until convergence. The final mode function can be used to reconstruct the original signal.

[0034] Another key feature of SVMD is successive decomposition. In each iteration step, SVMD extracts a major frequency component from the signal and removes it from the signal. In this way, each iteration step extracts a frequency component from the signal until all frequency components are extracted. This successive decomposition method can better capture the different frequency components in the signal.

[0035] SVMD has a wide range of applications in signal processing and data analysis. It can be used in many fields such as denoising, feature extraction, and spectrum analysis. By decomposing the signal into modal functions, SVMD can better understand and describe the frequency characteristics of the signal. This is very important for signal processing and data analysis.

[0036] Data reconstruction of SVMD is the process of recombining the decomposed modal functions into the original signal. The reconstructed signal can be obtained by weighted addition of each modal function. This process can be used to restore the frequency characteristics of the original signal, and further analysis and processing can be performed as needed.

[0037] On the basis of the above-mentioned prior art, the present application first obtains the optimal penalty factor required in SVMD based on the improved IAO algorithm of Circle chaos mapping, and the steps include: Step 1: Set the objective function of the IAO algorithm as the fitness function and initialize relevant parameters, including population size, number of iterations, etc. Step 2: Circle chaos mapping is used to initialize the population position, replacing the random initialization of the population position in the original IAO algorithm. It effectively covers each area without causing the initial state to be repeated. When the algorithm is run multiple times, it avoids falling into the same local optimum and improves the optimization efficiency of the algorithm. It is expressed as: In the formula, Indicates i The chaos value corresponding to each individual in the population; , represents the constant factor, take , ; Represents the modulo operator, which is used to limit the value range of a variable; Indicates The initial positions of individuals in the population; , Indicates the upper and lower limits of the search space; Step 3: Calculate the fitness value according to the objective function, and seek the current optimal solution based on the calculated fitness value; Step 4: Optimize the IAO algorithm in two stages, including the exploration stage and the development stage; (a) The filtering and evaluation of information is regarded as the exploration phase of the IAO algorithm, which can be expressed as: In the formula, Indicates the current iteration number; Indicates The number of iterations The location of individuals in a population; Indicates The updated position of each individual in the population; is a random number between [0,1]; represents the random position of individuals in the population; It represents the error caused by subjective factors in the process of information filtering and evaluation and is defined by the following formula: In the formula, represents the subjective influencing factor, which affects the final acquisition and application of information and is defined by the following formula: In the formula, , , and is a random number between [0,1]; represents the modulo operator; represents the reliability factor, which describes the ability of the algorithm to self-adjust according to the quality of information at different iteration stages to optimize its behavior and is defined by the following formula: In the formula, Indicates the maximum number of iterations; represents the information quality factor and is defined by the following formula: In the formula, is a random number between [0,1]; (b) The development phase of the IAO algorithm is represented by the information analysis and organization process as follows: In the formula, Represents the best population individual position generated in the previous iteration; Represents the average value of the best population individual positions generated in the previous iteration; , , and is a random number between [0,1]; Represents the controlling factor in analyzing and organizing information and is defined by the following formula: Step 5: Update the fitness value through the IAO optimization process, and seek the current optimal solution based on the calculated fitness value; Step 6: Determine whether the given maximum number of iterations has been reached. If not, go to step 3. Otherwise, output the global optimal solution. , which is the optimal penalty factor.

[0038] Among them, in step 3 of this embodiment, a multi-objective fitness function is used as the objective function, which is expressed as follows: Envelope Entropy It represents the sparseness of the original signal. The smaller the value, the stronger the signal sparsity and the less noise. The envelope signal is obtained by Hilbert demodulation , Defined by: In the formula, Represents the normalized form of the envelope signal; energy difference Indicates the accuracy of extracting the main resonant component. The closer the energy difference is to zero, the better the decomposition effect. Assuming is the original signal, After decomposition modal components, Defined by: In the formula, is the original signal energy; is the sum of the energy of the modal components after decomposition; Combine envelope entropy and energy difference into a multi-objective fitness function , which can not only measure the complexity of each modal component after signal decomposition, but also ensure that the total energy of each modal component after decomposition is consistent with the original signal, thus avoiding energy loss. Defined by: In the formula, , is the weight coefficient, which can be adjusted as needed.

[0039] Secondly, after obtaining the optimal penalty factor, the improved IAO-SVMD is used to perform adaptive modal decomposition on the complex output signal of the signal processing module. The steps include: Step 1: Input the pre-processed current signal And set relevant parameters, including penalty factors , Discrimination Accuracy , Discrimination Accuracy , Noise Variance wait; Step 2: Initialize the modal components , Lagrange multipliers , center frequency ; Step 3: Update the parameters by the following formulas respectively , , ; In the formula, represents the noise margin; Defined by: Step 4: Repeat step 3 until convergence condition is reached and output the modal components and their center frequencies, the convergence condition is defined by: Step 5: Determine whether all the acquired modes meet the constraints. If not, return to step 2. Otherwise, the iteration ends and all the modal components and their center frequencies are output. The constraints are defined by the following formula: In the formula, express The sampling length of Step 6: When DC bias occurs in the power transformer, there is a DC component in the excitation current, including the fundamental wave, second harmonic components and above. The characteristics of the DC component can effectively characterize whether DC bias occurs in the transformer and its severity. All the modal components obtained by decomposition are analyzed and the direction and amplitude characteristics of the DC bias current are extracted.

[0040] Therefore, in this step, SVMD is used to decompose the complex signal. Regarding the parameter selection of SVMD, the discrimination accuracy , Discrimination Accuracy , Noise Tolerance The impact on the decomposition results is relatively limited, and the commonly used discrimination accuracy is selected , Value, that is , and the noise margin Set to 0, the result of SVMD decomposition is mainly affected by the penalty factor The influence of the constraint criteria is introduced to adaptively realize the intrinsic mode function (IMF) decomposition without setting the number of decomposition levels. , penalty factor The selection is optimized by the improved IAO algorithm.

[0041] S4 combines the historical DC bias current data of the power transformer, the real-time monitored DC bias current data and external variables as the input of the deep recurrent neural network model, captures the long-term dependency provided by the historical data and the short-term dynamic changes provided by the real-time data, and completes the prediction of the DC bias current data at the next moment. The external variables include: global magnetic field index, grounding pole current and core temperature; In this embodiment, a deep recurrent neural network (DRNN) is used to realize the fusion prediction of historical operation data and real-time monitoring data of bias current, and the optimal bias current suppression parameters are solved through nonlinear programming from a system perspective to achieve global joint optimization, thereby achieving a transition from passive response to active suppression.

[0042] This embodiment does not provide a specific description of the training and testing process of the deep recurrent neural network, including but not limited to steps such as data set acquisition, preprocessing, and data set division.

[0043] A deep recurrent neural network (DRNN) is used and external variables are introduced to fuse the real-time monitoring signals and historical operation data obtained by decomposition. The historical operation bias current data of the power transformer, the current real-time monitoring data and the external variables are combined as the input of the DRNN model to capture the long-term dependencies provided by historical data and the short-term dynamic changes provided by real-time data, and to accurately predict the DC bias current data at the next moment.

[0044] Specifically, the DRNN model enhances the characteristics of the bias current by introducing external variables to achieve accurate prediction of the bias current. The external variables include: (a) Global Magnetic Field Index The geomagnetic storms generated by the interaction between the geomagnetic field and the solar plasma wind cause the geomagnetic field to change, generate potential gradients on the earth's surface, and low-frequency induced currents flow into the transformer windings. The global magnetic field index reflects the DC bias magnetic source caused by geomagnetic storms, and is measured by geomagnetic stations.

[0045] (b) Grounding electrode current In the HVDC transmission system, when the single pole loop operation mode is adopted, the DC current flowing back from the earth flows into the transformer with neutral point grounding. The grounding current reflects the core magnetic bias of the power transformer aggravated by the single pole loop of the HVDC transmission system, and the grounding current is measured by a DC shunt.

[0046] (c) Core temperature DC bias magnetization causes severe saturation of the power transformer core, increased losses in metal structural parts, and local overheating. The core temperature reflects the abnormal temperature rise caused by the core saturation caused by the bias magnetization, and the core temperature is measured by a temperature sensor.

[0047] The present invention adopts a deep recurrent neural network (DRNN) and introduces external variables, fuses the real-time monitoring signals obtained by decomposition with the historical operation data, and combines the historical operation bias current data of the power transformer, the current real-time monitoring data and the external variables as the input of the DRNN model, captures the long-term dependency provided by the historical data and the short-term dynamic changes provided by the real-time data, and accurately predicts the DC bias current data at the next moment.

[0048] Example 2

[0049] On the basis of Example 1, the present invention also considers measuring from the perspective of multiple power transformers, constraining the output data of DRNN according to the upper and lower limits of the DC bias current, that is, processing the data predicted by the model, specifically considering the objective function as the sum of the DC bias currents and the total series resistance of the monitoring nodes of all power transformers, and adopting the improved external penalty function method to solve its nonlinear programming problem to find the global optimal solution, that is, the neutral point series resistance, to avoid the global conflict caused by local optimization. Specifically, it includes: S5 uses the improved external penalty function method to solve the nonlinear programming problem of bias current suppression parameters; Specifically, in this embodiment, an improved external penalty function method is used to solve the nonlinear programming problem of the bias current suppression parameters, that is, a penalty function is used to process the constraints, and an adaptive penalty parameter is adopted. According to the degree of constraint violation, that is, the penalty function value, the penalty parameter is adjusted to improve the algorithm's solution efficiency.

[0050] The objective function of the original constrained programming is a combination of the sum of the DC bias current and the total series resistance; the improved external penalty function method converts the constrained programming into an unconstrained programming, converts the original constraints into penalty terms and adds them to the original objective function as an augmented objective function. Specifically: The nonlinear programming minimization objective function of the bias current suppression parameter is: In the formula, is the decision variable; For the The series resistance of the monitoring node of each power transformer; For the The DC bias current of the monitoring node of the power transformer, that is, the current data predicted by the above-mentioned deep neural network model; is the number of monitoring nodes of the power transformer; , is the weight coefficient, which can be adjusted as needed; The nonlinear programming constraints of the bias current suppression parameters are: In the formula, It is the upper and lower limit constraints of the DC bias current of each power transformer node.

[0051] The nonlinear programming minimization objective function of the bias current suppression parameter and the penalty function corresponding to the nonlinear programming constraint condition of the bias current suppression parameter are used as the objective function, which is expressed as: In the formula, is the penalty parameter; .

[0052] The steps of improving the external penalty function method include: Step 1: Set the initial penalty parameter , allowable error , any initial point , ; Step 2: As the initial point, use the gradient descent method to calculate Optimal solutions to unconstrained problems ; Step 3: If , then the problem ends and the optimal solution of the original problem is output , that is, the neutral point series resistance; otherwise, execute step 4; Step 4: Update the penalty parameter, , proceed to step 2.

[0053] The penalty parameter update formula in step 4 is: In the formula, is the gain factor, adjust as needed; is a smoothing term to avoid the denominator being zero.

[0054] When the constraint violation is large, the penalty parameter increases faster, accelerating the impact of the penalty term and quickly iterating the infeasible solution to a feasible solution; when the constraint violation is small, the penalty parameter increases slower, avoiding the difficulty of solving the problem caused by the penalty parameter increasing too quickly, and gradually transitioning the feasible solution to the optimal solution.

[0055] S6 adjusts the DC bias current suppression strategy in real time to reduce the DC bias component based on the neutral point series resistance predicted by the DC bias current constraint planning problem.

[0056] According to the neutral point series resistance solved by the above analysis method, the DC bias current suppression strategy is adjusted in real time to reduce the DC bias component. Dynamic management mainly adopts the method of connecting a small resistor in series with the neutral point of the power transformer. The selected device is mainly composed of an adjustable resistor and a protective gap. When the bias current flows into the transformer, the series resistance limits the size of the DC bias current. The protective gap serves as a protective device for the small resistor. The expression of the series small resistor is: In the formula, For the The adjustable resistor setting value of each power transformer node; The first The series resistance of each power transformer node.

[0057] Example 3

[0058] The present invention also provides a power transformer DC bias current monitoring and suppression system based on magnetoelectric coupling sensor, such as Figure 3 As shown, the system includes: Measurement module: The magnetoelectric coupling sensor is installed at the key monitoring node of the power transformer to capture the magnetic field signal of the power transformer in real time; The magnetoelectric coupling sensors of the measurement module adopt a multi-channel array layout and are distributed on the surface of the iron core of the power transformer to achieve the conversion from magnetic field signals to mechanical signals and then to electrical signals.

[0059] Optionally, the magnetoelectric coupling sensor is composed of magnetostrictive material and piezoelectric material. Under the magnetization of an external magnetic field, the size of the magnetostrictive material changes in one or some directions to generate force, specifically one of Fe-Ga, Terfenol-D, Metglas and NiFe2O4.

[0060] Optionally, an external force is applied to the piezoelectric material in a specific direction, causing the material to deform and generate electric charge, specifically one of quartz, LiNbO3, BaTiO3, PZT, PVDF, and PMN-PT.

[0061] Optionally, the structure of the magnetoelectric coupling sensor is determined by the composite form of two materials, specifically one of a 0-3 type granular composite material, a 2-2 type layered composite material, and a 1-3 type columnar composite material.

[0062] Signal processing module: connected to the magnetoelectric coupling sensor, used to filter, gain amplify, synchronize the phase and digitize the original current signal to eliminate noise interference and improve the signal-to-noise ratio; The signal processing module comprises: By using a standard current source to inject a known current into the transformer winding and recording the output current of the magnetoelectric coupling sensor, a relationship curve between the two is established. Based on the relationship curve between the actual current of the transformer winding and the output current of the magnetoelectric coupling sensor, the current signal output by the magnetoelectric coupling sensor is converted into the actual current signal of the transformer. On this basis, the signal is filtered, gain amplified, phase synchronized and digitized.

[0063] (a) Filter circuit, whose input is the collected signal of the magnetoelectric coupling sensor, adopts a low-pass filter with a cut-off frequency set to 2kHz to eliminate high-frequency noise in the collected signal, such as switching noise; (b) Gain amplifier, whose input is the noise reduction signal after the filtering circuit, is used to amplify the weak current signal in multiple stages, dynamically adjust the gain according to the signal amplitude, and ensure that the analog-to-digital converter (ADC) input signal is in the optimal range. Its gain is set to 10dB-40dB; (c) A signal synchronization unit, whose input is the amplified signal after the gain amplifier, adopts a phase-locked detection circuit, detects the phase information of the amplified signal and the signal source, compares and analyzes the phase difference between the two signals, and adjusts the signal phase to achieve signal synchronization; (d) The analog-to-digital conversion unit, whose input is the synchronization signal passed through the signal synchronization unit, is used to convert the analog signal into a digital signal. It uses the AD7606 chip, which is a SAR type chip with 16-bit synchronous sampling, a single 5V power supply, and a full-channel throughput rate of 200kSPS.

[0064] Data processing module: decompose the output of the signal processing module, extract the intrinsic mode function of the signal, and seek the bias current characteristics of the power transformer; The data processing module adopts successive variational modal decomposition (improved IAO-SVMD) based on improved information acquisition optimization, and seeks the optimal penalty factor by improving the decomposition effect of SVMD through the improved IAO algorithm. It adaptively decomposes the complex output signal of the signal processing module into several intrinsic mode functions, and extracts the DC bias current characteristics of the power transformer caused by stray current, that is, the direction and amplitude of the DC bias current.

[0065] The data processing module adopts an improved IAO algorithm based on Circle chaos mapping to obtain the optimal penalty factor of SVMD, and the steps include: Step 1: Set the objective function of the IAO algorithm as the fitness function and initialize relevant parameters, including population size, number of iterations, etc. Step 2: Circle chaos mapping is used to initialize the population position, replacing the random initialization of the population position in the original IAO algorithm. It effectively covers each area without causing the initial state to be repeated. When the algorithm is run multiple times, it avoids falling into the same local optimum and improves the optimization efficiency of the algorithm. It is expressed as: in, Indicates i The chaos value corresponding to each individual in the population; , represents the constant factor, take , ; Represents the modulo operator, which is used to limit the value range of a variable; Indicates The initial positions of individuals in the population; , Indicates the upper and lower limits of the search space; Step 3: Calculate the fitness value according to the objective function, and seek the current optimal solution based on the calculated fitness value; Step 4: Optimize the IAO algorithm in two stages, including the exploration stage and the development stage; (a) The filtering and evaluation of information is regarded as the exploration phase of the IAO algorithm, which can be expressed as: ; In the formula, Indicates the current iteration number; Indicates The number of iterations The location of individuals in a population; Indicates The updated position of each individual in the population; is a random number between [0,1]; represents the random position of individuals in the population; It represents the error caused by subjective factors in the process of information filtering and evaluation and is defined by the following formula: In the formula, represents the subjective influencing factor, which affects the final acquisition and application of information and is defined by the following formula: In the formula, , , and is a random number between [0,1]; represents the modulo operator; represents the reliability factor, which describes the ability of the algorithm to self-adjust according to the quality of information at different iteration stages to optimize its behavior and is defined by the following formula: In the formula, Indicates the maximum number of iterations; represents the information quality factor and is defined by the following formula: In the formula, is a random number between [0,1]; (b) the information analysis and organization process is used as the development stage of the IAO algorithm, expressed as: In the formula, Represents the best population individual position generated in the previous iteration; Represents the average value of the best population individual positions generated in the previous iteration; , , and is a random number between [0,1]; Represents the controlling factor in analyzing and organizing information and is defined by the following formula: Step 5: Update the fitness value through the IAO optimization process, and seek the current optimal solution based on the calculated fitness value; Step 6: Determine whether the given maximum number of iterations has been reached. If not, go to step 3. Otherwise, output the global optimal solution. , which is the optimal penalty factor.

[0066] The data processing module uses improved IAO-SVMD to perform adaptive modal decomposition on the complex output signal of the signal processing module, and the steps include: Step 1: Input the pre-processed current signal And set relevant parameters, including penalty factors , Discrimination Accuracy , Discrimination Accuracy , Noise Variance wait; Step 2: Initialize the modal components , Lagrange multipliers , center frequency ; Step 3: Update the parameters by the following formulas respectively , , ; In the formula, represents the noise margin; Defined by: Step 4: Repeat step 3 until convergence condition is reached and output the modal components and their center frequencies, the convergence condition is defined by: ; Step 5: Determine whether all the acquired modes meet the constraints. If not, return to step 2. Otherwise, the iteration ends and all the modal components and their center frequencies are output. The constraints are defined by the following formula: In the formula, express Sampling length; Step 6: When DC bias occurs in the power transformer, there is a DC component in the excitation current, including the fundamental wave, second harmonic components and above. The characteristics of the DC component can effectively characterize whether DC bias occurs in the transformer and its severity. All the modal components obtained by decomposition are analyzed and the direction and amplitude characteristics of the DC bias current are extracted.

[0067] The data processing module adopts a multi-objective fitness function as the objective function, which is expressed as follows: Envelope Entropy It represents the sparseness of the original signal. The smaller the value, the stronger the signal sparsity and the less noise. The envelope signal is obtained by Hilbert demodulation , Defined by: ; In the formula, represents the normalized form of the envelope signal; Energy gap Indicates the accuracy of extracting the main resonant component. The closer the energy difference is to zero, the better the decomposition effect. Assuming is the original signal, After decomposition modal components, Defined by: In the formula, is the original signal energy; is the sum of the energy of the modal components after decomposition; Combine envelope entropy and energy difference into a multi-objective fitness function , which can not only measure the complexity of each modal component after signal decomposition, but also ensure that the total energy of each modal component after decomposition is consistent with the original signal, thus avoiding energy loss. Defined by: In the formula, , is the weight coefficient, which can be adjusted as needed.

[0068] The data processing module uses SVMD to decompose complex signals. The parameters of SVMD are selected and the accuracy of the judgment is , Discrimination Accuracy , Noise Tolerance The impact on the decomposition results is relatively limited, and the commonly used discrimination accuracy is selected , Value, that is , and the noise margin Set to 0, the result of SVMD decomposition is mainly affected by the penalty factor The influence of the constraint criteria is introduced to adaptively realize the intrinsic mode function (IMF) decomposition without setting the number of decomposition levels. , penalty factor The selection is optimized by the improved IAO algorithm.

[0069] Data prediction module: A deep recurrent neural network (DRNN) is used to achieve fusion prediction of the historical operation data and real-time monitoring data of the bias current, and the optimal bias current suppression parameters are solved through nonlinear programming from a system perspective to achieve global joint optimization, thereby achieving a transition from passive response to active suppression. The data prediction module adopts a deep recurrent neural network (DRNN) and introduces external variables, fuses the real-time monitoring signals obtained by decomposition with historical operation data, and combines the historical operation bias current data of the power transformer, the current real-time monitoring data and the external variables as the input of the DRNN model, captures the long-term dependencies provided by the historical data and the short-term dynamic changes provided by the real-time data, and accurately predicts the DC bias current data at the next moment.

[0070] The DRNN model in the data prediction module enhances the characteristics of the bias current by introducing external variables to achieve accurate prediction of the bias current. The external variables include: (a) Global Magnetic Field Index The geomagnetic storms generated by the interaction between the geomagnetic field and the solar plasma wind cause the geomagnetic field to change, generate potential gradients on the earth's surface, and low-frequency induced currents flow into the transformer windings. The global magnetic field index reflects the DC bias magnetic source caused by geomagnetic storms, and is measured by geomagnetic stations.

[0071] (b) Grounding electrode current In the HVDC transmission system, when the single pole loop operation mode is adopted, the DC current flowing back from the earth flows into the transformer with neutral point grounding. The grounding current reflects the core magnetic bias of the power transformer aggravated by the single pole loop of the HVDC transmission system, and the grounding current is measured by a DC shunt.

[0072] (c) Core temperature DC bias magnetization causes severe saturation of the power transformer core, increased losses in metal structural parts, and local overheating. The core temperature reflects the abnormal temperature rise caused by the core saturation caused by the bias magnetization, and the core temperature is measured by a temperature sensor.

[0073] Data analysis module: From the perspective of multiple power transformers in the system, the output data of DRNN is constrained according to the upper and lower limits of the DC bias current. The objective function is considered to be the sum of the DC bias currents and the total series resistance of the monitoring nodes of all power transformers. The improved external penalty function method is used to solve the nonlinear programming problem to find the global optimal solution, that is, the neutral point series resistance, avoiding the global conflict caused by local optimization.

[0074] The data analysis module adopts an improved external penalty function method to solve the nonlinear programming problem of the bias current suppression parameter, that is, the constraint condition is processed by the penalty function, and an adaptive penalty parameter is adopted. According to the constraint violation degree, that is, the penalty function value, the penalty parameter is adjusted to improve the solution efficiency of the algorithm. Specifically, The nonlinear programming minimization objective function of the bias current suppression parameter is: ; In the formula, is the decision variable; For the The series resistance of the monitoring node of each power transformer; For the The DC bias current of the monitoring node of a power transformer; is the number of monitoring nodes of the power transformer; , is the weight coefficient, which can be adjusted as needed.

[0075] The nonlinear programming constraints of the bias current suppression parameters are: In the formula, is the upper and lower limit constraints of the DC bias current of each power transformer node. The nonlinear programming minimization objective function of the bias current suppression parameter and the penalty function corresponding to the nonlinear programming constraint condition of the bias current suppression parameter are used as the objective function, which is expressed as: In the formula, is the penalty parameter; .

[0076] The steps of improving the external penalty function method include: Step 1: Set the initial penalty parameter , allowable error , any initial point , ; Step 2: As the initial point, use the gradient descent method to calculate Optimal solutions to unconstrained problems ; Step 3: If , then end and output the optimal solution of the original problem , that is, the neutral point series resistance; otherwise, execute step 4; Step 4: Update the penalty parameter, , proceed to step 2.

[0077] The penalty parameter update formula in step 4 is: In the formula, is the gain factor, adjust as needed; is a smoothing term to avoid the denominator being zero.

[0078] When the constraint violation is large, the penalty parameter increases faster, accelerating the impact of the penalty term and quickly iterating the infeasible solution to a feasible solution; when the constraint violation is small, the penalty parameter increases slower, avoiding the difficulty of solving the problem caused by the penalty parameter increasing too quickly, and gradually transitioning the feasible solution to the optimal solution.

[0079] Dynamic management module: According to the optimization parameters output by the data analysis module, the DC bias current suppression strategy is adjusted in real time to reduce the DC bias component in real time.

[0080] The dynamic management module adjusts the DC bias current suppression strategy in real time according to the neutral point series resistance solved by the data analysis module to reduce the DC bias component. The dynamic management mainly adopts the method of connecting a small resistor in series with the neutral point of the power transformer. The selected device is mainly composed of an adjustable resistor and a protection gap. When the bias current flows into the transformer, the series resistance limits the size of the DC bias current. The protection gap serves as a protection device for the small resistor. The expression of the series small resistor is: In the formula, For the The adjustable resistor setting value of each power transformer node; The first The series resistance of each power transformer node.

[0081] Finally, the present invention also provides a computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the above-mentioned method for monitoring and suppressing the DC bias current of a power transformer based on a magnetoelectric coupling sensor is implemented.

[0082] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0083] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0084] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0085] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0086] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0087] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0088] 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.

[0089] 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 monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor, characterized in that: The method includes: The magnetoelectric coupling sensor is installed in the monitoring node of each power transformer to capture the magnetic field signal of the power transformer in real time, thereby obtaining the original current signal and preprocessing the collected original current signal; A successive variational modal decomposition method based on improved information acquisition optimization is used to adaptively decompose the preprocessed current signal into a number of intrinsic mode functions, and extract the DC bias current data of the power transformer caused by the stray current. The successive variational modal decomposition method based on improved information acquisition optimization first seeks the optimal penalty factor through an improved information acquisition optimization algorithm IAO, and applies the optimal penalty factor to the successive variational modal decomposition method. Finally, the direction and amplitude characteristics of the DC bias current are extracted according to all the modal components obtained by the decomposition. The historical DC bias current data of the power transformer, the real-time monitored DC bias current data and external variables are combined as the input of the deep recurrent neural network model to capture the long-term dependencies provided by the historical data and the short-term dynamic changes provided by the real-time data, thereby completing the prediction of the DC bias current data at the next moment. The external variables include: global magnetic field index, grounding pole current and core temperature.

2. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 1 is characterized in that: The method further includes: According to the set augmented objective function without constraint programming, the improved external penalty function method is adopted to solve the corresponding nonlinear programming problem to find the global optimal solution and obtain the neutral point series resistance of each power transformer; the augmented objective function without constraint programming is obtained by minimizing the objective function and penalty term of the nonlinear programming of the bias current suppression parameter; The DC bias current suppression strategy is adjusted in real time according to the obtained neutral point series resistance to reduce the DC bias component.

3. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 1 or 2, characterized in that: The improved information acquisition optimization successive variational mode decomposition method seeks the optimal penalty factor through an improved information acquisition optimization algorithm IAO, specifically including: The Circle chaotic map is used to initialize the population position, the fitness value is calculated according to the objective function, and the current optimal solution is sought according to the current fitness value; The exploration and development phases of the IAO algorithm are used to optimize the positions of the individuals in the population, and the fitness values ​​are updated during the optimization process, and the current optimal solution is sought based on the calculated fitness values; Iterate according to the given maximum number of iterations and output the global optimal solution, that is, the optimal penalty factor.

4. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 3 is characterized in that: The Circle chaotic map is used to initialize the population position, which is expressed as: ； in, Indicates i The chaos value corresponding to each individual in the population; , represents a constant factor; Represents the modulo operator, which is used to limit the value range of a variable; Indicates The initial positions of individuals in the population; , Indicates the upper and lower bounds of the search space.

5. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 4 is characterized in that: In the process of calculating the fitness value according to the objective function and seeking the current optimal solution according to the current fitness value, the objective function is to convert the envelope entropy and energy difference Combined multi-objective fitness function , expressed as: ; In the formula, , is the weight coefficient.

6. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 5, characterized in that: The optimal penalty factor is applied to the successive variational modal decomposition method, and the direction and amplitude characteristics of the DC bias current are extracted according to all modal components obtained by decomposition, including: Input the preprocessed current signal and set relevant parameters, including optimal penalty factor, discrimination accuracy, discrimination accuracy, noise variance, and initialize modal components, Lagrange multipliers, and center frequencies; Iteratively update the parameter modal components, Lagrange multipliers, and center frequencies until the convergence condition is reached, and output the modal components and center frequencies corresponding to the current iteration; Determine whether all the acquired modes meet the constraints. If not, reinitialize the modal components, Lagrange multipliers, and center frequencies. Otherwise, the iteration ends and all the modal components and their center frequencies are output. When DC bias occurs in the power transformer, there is a DC component in the excitation current, including the fundamental wave, second harmonic components and above. The characteristics of the DC component can effectively characterize whether DC bias occurs in the transformer and its severity. All the modal components obtained by decomposition are analyzed and the direction and amplitude characteristics of the DC bias current are extracted.

7. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 2, characterized in that: The augmented objective function without constraint programming according to the setting specifically includes: adding the nonlinear programming minimization objective function of the bias current suppression parameter and the penalty function corresponding to the nonlinear programming constraint condition of the bias current suppression parameter as the augmented objective function; The nonlinear programming minimization objective function of the bias current suppression parameter is expressed as: ; in, is the decision variable; For the The series resistance of the monitoring node of each power transformer; For the The DC bias current of the monitoring node of a power transformer; is the number of monitoring nodes of the power transformer; , is the weight coefficient; The nonlinear programming constraint condition of the bias current suppression parameter is expressed as: ;in, The upper and lower limits of the DC bias current of each power transformer node; The augmented objective function is expressed as: ; in, is the penalty parameter; .

8. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 7, characterized in that: The improved external penalty function method is adopted to solve the corresponding nonlinear programming problem to find the global optimal solution and obtain the neutral point series resistance of each power transformer, including: Step 1: Set the initial penalty parameter , allowable error , any initial point , ; Step 2: As the initial point, the gradient descent method is used to calculate the minimized augmented objective function Optimal solutions to unconstrained problems ; Step 3: If , then the problem ends and the optimal solution of the original problem is output , that is, the neutral point series resistance; otherwise, execute step 4; Step 4: Update the penalty parameter using the penalty parameter update formula. , execute step 2; The penalty parameter update formula is: ; in, is the gain coefficient; is the smoothing term; When the constraint violation is large, the penalty parameter increases faster. At this time, the impact of the penalty term is increased, and the infeasible solution is quickly iterated to a feasible solution. When the constraint violation is small, the penalty parameter increases slower. At this time, the difficulty in solving the problem caused by the rapid increase of the penalty parameter is avoided, and the feasible solution is gradually transitioned to the optimal solution.

9. The method for monitoring and suppressing DC bias current of a power transformer based on a magnetoelectric coupling sensor according to claim 8, characterized in that: The method of adjusting the DC bias current suppression strategy in real time according to the obtained neutral point series resistance to reduce the DC bias component includes: A small resistor is connected in series with the neutral point of the power transformer. When the bias current flows into the transformer, the series resistor limits the DC bias current, and a protective gap is used as a protection device for the small resistor. The expression of the series small resistor is: ; In the formula, For the The adjustable resistor setting value of each power transformer node; To solve the nonlinear programming problem The series resistance of each power transformer node.

10. A power transformer DC bias current monitoring and suppression system based on magnetoelectric coupling sensor, characterized in that: The system includes: The measurement module is used to install the magnetoelectric coupling sensor in the monitoring node of each power transformer to capture the magnetic field signal of the power transformer in real time during operation, and then obtain the original current signal; A signal processing module, used for preprocessing the collected original current signal; A data processing module is used to use a successive variational modal decomposition method based on improved information acquisition optimization to adaptively decompose the preprocessed current signal into a plurality of intrinsic mode functions, and extract the DC bias current data of the power transformer caused by the stray current, wherein the successive variational modal decomposition method based on improved information acquisition optimization seeks an optimal penalty factor through an improved information acquisition optimization algorithm IAO, and applies the optimal penalty factor to the successive variational modal decomposition method, and extracts the direction and amplitude characteristics of the DC bias current according to all modal components obtained by the decomposition; The data prediction module is used to combine the historical DC bias current data of the power transformer, the real-time monitored DC bias current data and external variables as the input of the deep recurrent neural network model, capture the long-term dependencies provided by the historical data and the short-term dynamic changes provided by the real-time data, and complete the prediction of the DC bias current data at the next moment. The external variables include: global magnetic field index, grounding pole current and core temperature.

11. The power transformer DC bias current monitoring and suppression system based on magnetoelectric coupling sensor according to claim 10 is characterized in that: The system also includes: A data analysis module is used to solve the corresponding nonlinear programming problem by adopting an improved external penalty function method according to the set augmented objective function without constraint programming, so as to find the global optimal solution and obtain the neutral point series resistance of each power transformer; the augmented objective function without constraint programming is obtained by minimizing the objective function and penalty term of the nonlinear programming of the bias current suppression parameter; The dynamic management module is used to adjust the DC bias current suppression strategy in real time according to the obtained neutral point series resistance to reduce the DC bias component.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for monitoring and suppressing direct current bias current of a power transformer based on a magnetoelectric coupling sensor as claimed in any one of claims 1 to 8 is implemented.

Images