Method for testing unbalanced current of alternating current filter capacitor bank

Abstract

The invention relates to the technical field of current testing, and particularly discloses an alternating current filter capacitor bank unbalanced current testing method, which comprises the following steps of: applying a test voltage smaller than a normal operation voltage to a to-be-tested alternating current filter capacitor bank by using a voltage regulator; according to the method, signal component filtering and reconstruction based on signal distribution guidance are carried out on an unbalanced test current signal between bridge buttocks of an alternating current filter capacitor bank to obtain a more accurate unbalanced current measurement value, and an unbalanced current protection constant value is converted based on a ratio between a normal operation voltage and a test voltage of the alternating current filter capacitor bank to obtain a more accurate unbalanced current protection constant value. And generating a test result according to a current difference value between the unbalanced current measurement value and the unbalanced current protection constant value. Through the mode, noise components such as electromagnetic interference and harmonic waves in unbalanced test current signals can be effectively filtered out, the accuracy and reliability of test results are improved, and a powerful guarantee is provided for the maintenance quality of an alternating current filter capacitor bank.

Description

Technical Field

[0001] This application relates to the technical field of current testing, and more specifically, to a method for testing unbalanced current of an AC filter capacitor bank. Background Art

[0002] In the converter station of UHV DC transmission project, the AC filter, as a key device, undertakes the important functions of compensating the reactive power consumed by the converter valve operation and filtering the harmonics of the DC system. As the core component of the AC filter, the operating state of the capacitor directly affects the stability of the system. However, due to the long-term exposure of the capacitor bank to the harsh environment of high voltage and strong electromagnetic interference, it is prone to abnormal unbalanced current caused by faults such as bird damage, bushing leakage, and capacitance value exceeding the standard.

[0003] Currently, unbalanced protection is generally configured in the project to detect capacitor faults, including unbalanced stage I alarm, unbalanced stage II long-time delay tripping, and unbalanced stage III short-time delay tripping. After the replacement and maintenance operations of defective and faulty capacitors, it is required that the unbalanced current is less than 20% of the operating protection value. Therefore, it is necessary to test the arm unbalanced current of the corresponding AC filter capacitor bank to inspect the maintenance quality and provide a basis for the commissioning of the equipment.

[0004] In the early stage, there was a lack of a dedicated complete set of testing devices for accurately measuring the unbalanced current of the capacitor bank at the converter station maintenance site, and the method of self-built circuit was used for testing. This method requires disconnecting the lead connection points of multiple devices, resulting in a relatively high risk of high-altitude operation and a long maintenance time. In addition, in the test of the unbalanced current of the AC filter capacitor bank, the measured current signal (lub_measured) is often not a pure power frequency sine wave, and may include electromagnetic interference from surrounding operating equipment, noise of the test instrument itself, transient interference caused by switch operations, start-stop operations of nearby equipment, etc., resulting in a relatively large actual test error. It often requires multiple tests to obtain a more accurate conclusion, and the test efficiency is relatively low.

[0005] Currently, some existing digital filters (such as Butterworth, Chebyshev) or methods based on Fourier transform (FFT) have certain effects in dealing with signal interference problems, but they have requirements for the signal stability, and are easily affected by spectral leakage and fence effect, and have poor effects on non-stationary noise (noise characteristics change with time). When the useful signal (fundamental wave) and the noise frequency are close or overlapping, it is difficult to perfectly separate them.

[0006] Therefore, an optimized method for testing the unbalanced current of the AC filter capacitor bank is expected. Summary of the Invention

[0007] To solve the above technical problems, the present application is proposed. An embodiment of the present application provides a method for testing the unbalanced current of an AC filter capacitor bank, which uses a voltage regulator to apply a test voltage less than the normal operating voltage to the AC filter capacitor bank to be tested. Under the test voltage condition, signal component filtering and reconstruction based on signal distribution guidance are performed on the unbalanced test current signal between the bridge arms of the AC filter capacitor bank to filter out the noise and interference components in the current signal, obtain a more accurate unbalanced current measurement value, and based on the ratio between the normal operating voltage and the test voltage of the AC filter capacitor bank, the unbalanced current protection setting value is converted, and then according to the current difference between the unbalanced current measurement value and the converted unbalanced current protection setting value, a test result is generated. In this way, electromagnetic interference, harmonics and other noise components in the unbalanced test current signal can be effectively filtered out, the accuracy and reliability of the test result can be improved, and a strong guarantee can be provided for the maintenance quality of the AC filter capacitor bank.

[0008] According to one aspect of the present application, there is provided a method for testing the unbalanced current of an AC filter capacitor bank, which includes:

[0009] Using a voltage regulator to apply a test voltage to the AC filter capacitor bank to be tested, the test voltage being less than the normal operating voltage;

[0010] Under the condition of applying the test voltage, measuring the unbalanced current value between the bridge arms of the AC filter capacitor bank;

[0011] Generating a test result based on the comparison between the unbalanced current measurement value and the converted unbalanced current protection setting value;

[0012] Wherein, under the condition of applying the test voltage, measuring the unbalanced current value between the bridge arms of the AC filter capacitor bank includes: performing signal component filtering and reconstruction based on signal distribution guidance on the unbalanced test current signal to obtain an enhanced unbalanced test current signal; and obtaining the unbalanced current value based on the enhanced unbalanced test current signal.

[0013] Compared with the prior art, the method for testing the unbalanced current of the AC filter capacitor bank provided by this application uses a voltage regulator to apply a test voltage lower than the normal operating voltage to the AC filter capacitor bank to be tested. Under the test voltage condition, signal component filtering and reconstruction based on signal distribution orientation are performed on the unbalanced test current signal between the bridge arms of the AC filter capacitor bank to filter out the noise and interference components in the current signal, obtain a more accurate unbalanced current measurement value, and convert the unbalanced current protection setting value based on the ratio between the normal operating voltage and the test voltage of the AC filter capacitor bank. Furthermore, a test result is generated based on the current difference between the unbalanced current measurement value and the converted unbalanced current protection setting value. In this way, electromagnetic interference, harmonics and other noise components in the unbalanced test current signal can be effectively filtered out, the accuracy and reliability of the test result can be improved, and a strong guarantee for the maintenance quality of the AC filter capacitor bank can be provided. Description of the Drawings

[0014] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present application will become more obvious. The accompanying drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. They are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation to the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0015] Figure 1 It is the electrical principle wiring diagram of the AC filter.

[0016] Figure 2 It is the schematic diagram of the AC filter capacitor bank.

[0017] Figure 3 It is the schematic diagram of the heating defect of the capacitor bushing.

[0018] Figure 4 It is the schematic diagram of the recording wave of the tripping of the third section of the unbalanced protection.

[0019] Figure 5 It is the principle wiring diagram of the unbalanced current test of the capacitor bank.

[0020] Figure 6 It is the schematic diagram of the disconnection point for unbalanced current measurement.

[0021] Figure 7 It is the flowchart of the method for testing the unbalanced current of the AC filter capacitor bank according to the embodiment of the present application.

[0022] Figure 8 It is the principle wiring diagram of the unbalanced current test.

[0023] Figure 9 It is the schematic diagram of the disconnection point for unbalanced current measurement of the new wiring method.

[0024] Figure 10 Schematic diagram showing that the new wiring method does not require disconnecting the marked point and the lead on the opposite side.

[0025] Figure 11 Flowchart of sub-step S2 of the method for testing unbalanced current of AC filter capacitor bank according to an embodiment of the present application.

[0026] Figure 12 Flowchart of sub-step S21 of the method for testing unbalanced current of AC filter capacitor bank according to an embodiment of the present application.

[0027] Figure 13 Schematic diagram of data flow of sub-step S21 of the method for testing unbalanced current of AC filter capacitor bank according to an embodiment of the present application.

[0028] Figure 14 Flowchart of sub-step S212 of the method for testing unbalanced current of AC filter capacitor bank according to an embodiment of the present application.

[0029] Figure 15 Flowchart of sub-step S213 of the method for testing unbalanced current of AC filter capacitor bank according to an embodiment of the present application.

[0030] Figure 16 Flowchart of sub-step S2132 of the method for testing unbalanced current of AC filter capacitor bank according to an embodiment of the present application. Detailed implementation manners

[0031] As shown in the present application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0032] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0033] In the present application, flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to the need, various steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps of operations can be removed from these processes.

[0034] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0035] It should be noted that in the present application, all actions of obtaining data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining authorization from the corresponding device owner.

[0036] In the unbalanced current test of the AC filter capacitor bank:

[0037] 1. Wiring method of the AC filter capacitor bank

[0038] The typical configuration of the filters in the UHV converter station mainly includes SC shunt capacitor banks, HP3 AC filter banks, HP12 / 24 AC filter banks, etc.

[0039] Among them, the capacitors (the principle wiring is shown in the Figure 1 virtual box) are one of the important components of the AC filter, and there are a large number of them. Taking the receiving-end converter station of a certain UHV DC project as an example, its AC filter yard is configured with 20 groups of filters (including shunt capacitor banks), and a total of 19,272 capacitors are in operation. The AC filter capacitor bank generally adopts the "H" type wiring, with a total of 4 bridge arms, and each bridge arm contains several capacitors. Current transformers are installed between the bridge arms. This current transformer is different from the general AC current transformer, with a relatively small transformation ratio, generally 1 / 1 or 1 / 2, which is used to detect the unbalanced current between the bridge arms. The on-site equipment layout is as shown in Figure 2 shown. Among them, 1 - high-voltage capacitor bank; 2 - current transformer; 3 - anchor bolt; 4 - earthing flat steel.

[0040] 2. Protection configuration of the AC filter capacitor bank

[0041] The structure of the AC filter capacitor bank is relatively complex, and the operating environment is relatively harsh. Common faults include tripping caused by bird damage, oil leakage from the bushing, overheating of the joints, bulging of the body, and exceeding the capacitance value standard. Overall, it shows the characteristics of diverse fault types. The overheating of the capacitor bushing joint is as shown in Figure 3 shown.

[0042] According to statistics, from 2016 to 2021, the AC filter in domestic converter stations was out of service more than 80 times due to bird damage, capacitor defects, and faults. The fault tripping oscillogram is as shown in Figure 4 shown.

[0043] At present, unbalance protection is generally configured in engineering to detect capacitor faults, including unbalance stage I alarm, unbalance stage II long-time delay tripping, and unbalance stage III short-time delay tripping.

[0044] The basic principles of unbalance stage I and stage III protections are:

[0045] I ub >I ubqd

[0046]

[0047] Among them, Iub is the unbalance current of the capacitor bank, that is, Figure 2 the current flowing through the current transformer T1 in ; Iubqd is the unbalance starting setting value, which is fixed at 10 mA inside the device, Itro is the through current of the AC filter, that is, Figure 2 the current flowing through the current transformer T2 in, Kubzd is the protection setting value of the unbalance proportional coefficient, stage I delays for 10 s to alarm, and stage III delays for 20 ms to trip.

[0048] The basic principle of unbalance stage II protection:

[0049]

[0050] Among them, ΔIub is the transient unbalance current of the AC filter, that is, Figure 2 the sudden change in current of the current transformer T1 in, Itro is the transient through current of the AC filter, that is, Figure 2 the current flowing through the current transformer T2 in, ΔKubzd is the protection setting value of the unbalance proportional coefficient, and the delay is 120 min to trip.

[0051] 3. Principle and method for testing the unbalance current of capacitor bank

[0052] After replacing and repairing defective or faulty capacitors, the unbalance current should be less than 20% of the operating protection value. It is necessary to test the arm unbalance current of the corresponding AC filter capacitor bank to check the quality of the repair work and provide a basis for the equipment to be put into operation. The principle of testing the unbalance current of the capacitor bank is as Figure 5 shown.

[0053] During the test, a test voltage of a certain amplitude is input through a voltage regulator, and the unbalance current value between the arms is measured. At the same time, the operating protection setting value is converted to the test voltage and compared with the test value to judge the balance degree of the capacitor bank.

[0054] In the early stage, there was no dedicated complete set of test equipment capable of accurately measuring the unbalanced current of capacitor banks. At the overhaul site of the converter station, a self-built circuit was used for testing. Using the above-mentioned test circuit, it was necessary to disconnect the lead connection points of multiple devices, such as Figure 6 as shown in the red frame. Since there were too many equipment disconnection points, the risk of working at heights was relatively high and the overhaul took a long time.

[0055] Due to the insufficient stability and anti-interference performance of the self-built circuit, and the large electromagnetic interference generated by other filters operating in the vicinity in the environment, during the actual test process, the test error was relatively large. Often, multiple tests were required to obtain a relatively accurate conclusion, and there was a certain probability of error in data conversion, resulting in low test efficiency.

[0056] In view of the above technical problems, the present application proposes a method for testing the unbalanced current of an AC filter capacitor bank. It uses a voltage regulator to apply a test voltage lower than the normal operating voltage to the AC filter capacitor bank to be tested. Under the test voltage condition, signal component filtering and reconstruction based on signal distribution guidance are performed on the unbalanced test current signal between the bridge arms of the AC filter capacitor bank to filter out the noise and interference components in the current signal, obtain a more accurate measurement value of the unbalanced current, and based on the ratio between the normal operating voltage and the test voltage of the AC filter capacitor bank, convert the unbalanced current protection setting value. Then, based on the current difference between the measured value of the unbalanced current and the converted unbalanced current protection setting value, a test result is generated. In this way, electromagnetic interference, harmonics and other noise components in the unbalanced test current signal can be effectively filtered out, the accuracy and reliability of the test result can be improved, and a strong guarantee can be provided for the overhaul quality of the AC filter capacitor bank.

[0057] Figure 7 It is a flowchart of the method for testing the unbalanced current of an AC filter capacitor bank according to an embodiment of the present application. As Figure 7 shown, the method for testing the unbalanced current of an AC filter capacitor bank includes the steps of: S1, using a voltage regulator to apply a test voltage to the AC filter capacitor bank to be tested, and the test voltage is lower than the normal operating voltage; S2, under the condition of applying the test voltage, measuring the value of the unbalanced current between the bridge arms of the AC filter capacitor bank; S3, generating a test result based on the comparison between the measured value of the unbalanced current and the converted unbalanced current protection setting value.

[0058] In the above method for testing the unbalanced current of the AC filter capacitor bank, in step S1, a test voltage is applied to the AC filter capacitor bank to be tested by a voltage regulator, and the test voltage is less than the normal operating voltage. It should be understood that after the capacitor bank is replaced and repaired, its balance needs to be verified. However, directly applying the normal operating voltage poses a safety risk, and it is difficult to meet the high-voltage test requirements on-site. According to the "State Maintenance Test Regulations for Transmission and Substation Equipment", it is allowed to verify the matching of protection settings through an equivalent test with reduced voltage. Therefore, in this application, a test voltage less than the normal operating voltage is applied to the AC filter capacitor bank to be tested, simulating the operating conditions in a safe and controllable low-voltage environment, and obtaining current signals reflecting the true unbalanced state of the capacitor bank, which helps to avoid potential hazards to equipment and personnel caused by high-voltage operations.

[0059] In particular, without departing from the basic principle of the test, this application optimizes the wiring method. The new wiring method only requires disconnecting the lead at the low-voltage side of the capacitor bank. There is no need to disconnect the lead at the high-voltage side of the capacitor bank, nor to open the grounding switch at the high-voltage side. Using the grounding switch at the high-voltage end of the AC filter, a part of the test wiring loop for earth operation is formed. The test voltage application method is similar to that of measuring the dielectric capacitance of the equipment by the reverse connection method. During the test, the test voltage is applied to the low-voltage side of the capacitor bank, and a complete loop is formed through the capacitor tower, the grounding switch at the high-voltage side, and the instrument grounding. The test wiring is as Figure 8 shown.

[0060] The new test wiring method does not require removing the lead at the high-voltage side of the capacitor, nor hanging the high-voltage side test wire during the test, greatly reducing the demand for special vehicles for the operation and the intensity and danger of working at heights. During the test, the lead disconnection points are as Figure 9 、 Figure 10 shown.

[0061] At the same time, since the lead at the high-voltage side of the capacitor bank is not disconnected, the measurement of the capacitance of the high-voltage side bridge arm can be completed by means of the grounding loop. For example, when measuring the capacitance of bridge arm 2, one end of the capacitance meter can be connected to the ground, and the other end can be connected between bridge arm 1 and bridge arm 2. Compared with before the improvement, it is possible to avoid hanging a dedicated test wire at the high-voltage side.

[0062] In the above method for testing the unbalanced current of the AC filter capacitor bank, in step S2, under the condition of applying the test voltage, the measured value of the unbalanced current between the bridge arms of the AC filter capacitor bank is measured. It should be understood that due to the interference such as broadband harmonics and transient pulses generated during the operation of adjacent filters in the converter station environment, the collected unbalanced test current signal contains a large amount of non-power frequency noise, with a low signal-to-noise ratio, and cannot accurately reflect the true unbalanced state of the capacitor bank. Traditional filtering methods have significant limitations in dealing with such non-stationary and non-linear noise signals, and the filtering effect is not good. In response to this, the present application introduces a signal processing algorithm based on deep learning technology. By learning the feature distribution of the unbalanced test current signal, it automatically identifies and extracts the effective components in the signal, and suppresses high-frequency harmonics and transient interference to improve the signal-to-noise ratio and purity of the signal. Among them, Figure 11 is a flowchart of sub-step S2 of the method for testing the unbalanced current of the AC filter capacitor bank according to an embodiment of the present application. As Figure 11 shown, step S2 includes steps: S21, performing signal component filtering and reconstruction based on signal distribution guidance on the unbalanced test current signal to obtain an enhanced unbalanced test current signal; S22, obtaining the unbalanced current value based on the enhanced unbalanced test current signal.

[0063] Figure 12 is a flowchart of sub-step S21 of the method for testing the unbalanced current of the AC filter capacitor bank according to an embodiment of the present application. Figure 13 is a schematic diagram of data flow of sub-step S21 of the method for testing the unbalanced current of the AC filter capacitor bank according to an embodiment of the present application. As Figure 12 and Figure 13 shown, step S21 includes steps: S211, capturing the unbalanced test current signal; S212, performing feature extraction of the current signal based on modal decomposition on the unbalanced test current signal to obtain a set of current signal component feature coding vectors; S213, performing feature filtering based on cluster distribution learning on the set of current signal component feature coding vectors to obtain a filtered set of current signal component feature coding vectors; S214, inputting the filtered set of current signal component feature coding vectors into a current signal reconstruction model to obtain an enhanced unbalanced test current signal.

[0064] More specifically, in step S211, the unbalanced test current signal is captured. Specifically, the unbalanced test current signal generated by the AC filter capacitor bank under the condition of applying the test voltage is collected in real time through a bridge arm current transformer, and the analog signal is converted into a digital signal by using a high-precision ADC module to ensure the integrity and timeliness of signal acquisition.

[0065] In the process of specific implementation, the first thing to consider is how to obtain the original signal efficiently and accurately. By using a voltage regulator to apply a test voltage lower than the normal operating voltage to the AC filter capacitor bank to be tested, the impact on the equipment itself can be effectively reduced, while ensuring that subsequent tests can be carried out within a safe range. On this basis, a high-precision arm current transformer can be used to collect the unbalanced test current signal generated by the AC filter capacitor bank under the condition of applying the test voltage in real time. Such transformers usually have high sensitivity and accuracy, and can accurately sense the current signal with small changes in a complex electromagnetic environment. In order to further improve the quality of signal acquisition, it is often necessary to optimize the layout of the transformer according to the actual situation on site to ensure that all areas where unbalanced current may occur can be comprehensively covered. In addition, considering the complex internal structure of the capacitor bank and the possible differences in electrical characteristics between different parts, when setting multiple transformers, these differences need to be fully considered, and targeted measures should be taken to achieve the best data acquisition effect.

[0066] After the arm current transformer successfully captures the unbalanced test current signal, the next step is to convert these analog signals into digital signals. This link mainly relies on a high-precision ADC module to complete. The role of the ADC module is to convert the analog signal received from the transformer into a digital form that can be processed by a computer, thus laying the foundation for further data analysis and processing. In this conversion process, in order to ensure the integrity and timeliness of signal conversion, the working parameters of the ADC module must be strictly controlled, including key indicators such as the sampling rate and resolution. The sampling rate determines the number of samples collected per unit time, directly affecting whether the finally obtained digital signal can truly reflect the change trend of the original analog signal; while the resolution is related to the signal quantization accuracy, that is, the ability to distinguish two adjacent values, which is of great significance for improving the signal conversion quality.

[0067] It is worth noting that while converting analog signals into digital signals, attention should also be paid to the integrity of the signal transmission process. Due to the complex and changeable environment where the capacitor bank is located, there may be strong electromagnetic interference sources, which may affect the signals at the receiving end to varying degrees. Therefore, when designing the signal transmission path, cables with excellent shielding performance should be used as much as possible, and the wiring scheme should be reasonably planned to avoid laying in parallel with other strong interference sources to reduce the interference of external noise on the received signal. In addition, for the problem of signal attenuation that may occur during long-distance transmission, it can be solved by adding signal amplifiers, etc., to ensure that the signal maintains good quality and stability throughout the transmission link.

[0068] To more deeply understand and master the characteristics of unbalanced test current signals, it is sometimes necessary to combine other auxiliary means for comprehensive analysis. For example, some sensors specifically used to monitor environmental conditions (such as temperature, humidity, etc.) can be installed near the acquisition point. By synchronously recording these environmental parameters, it helps to discover special rules or abnormal conditions manifested by the signal under certain specific conditions. This method can not only help technicians better interpret the collected data but also provide valuable reference information for subsequent optimization of the test method.

[0069] Figure 14 It is a flowchart of sub-step S212 of the unbalanced current test method for the AC filter capacitor bank according to an embodiment of the present application. As Figure 14 shown, the step S212 includes steps: S2121, performing CEEMDAN signal decomposition on the unbalanced test current signal to obtain a set of current signal components; S2122, extracting the current signal characteristics of each current signal component in the set of current signal components to obtain a set of current signal component feature coding vectors.

[0070] In a specific example of the present application, in the step S2121, CEEMDAN signal decomposition is performed on the unbalanced test current signal to obtain a set of current signal components. It should be understood that since the unbalanced test current signal is a non-stationary mixed signal, and the traditional Fourier transform has poor performance in dealing with time-varying noise (such as harmonic components that change with time). For this reason, the present application uses CEEMDAN (Complete Ensemble Empirical Mode Decomposition) technology to decompose the unbalanced test current signal, forming a set of current signal components. Specifically, CEEMDAN signal decomposition is an adaptive signal time-frequency analysis method. By adding adaptive white noise to the signal and iterating multiple times, it overcomes the mode mixing problem of the traditional EMD and can achieve high-precision decomposition of the signal. In the present application, the CEEMDAN signal decomposition technology is used to decompose the unbalanced test current signal from a complex non-stationary signal into a series of intrinsic mode functions (IMFs). Each IMF represents an inherent oscillation mode of the signal, with different frequencies and time scales. In this way, the power frequency fundamental component, harmonic component, and noise component in the unbalanced test current signal can be effectively separated, providing a basis for subsequent signal reconstruction and filtering.

[0071] In a specific example of the present application, in step S2122, the current signal features of each current signal component in the set of current signal components are extracted to obtain the set of current signal component feature coding vectors. It should be understood that each IMF component (i.e., the current signal component) contains different physical meanings (such as noise, fundamental wave, harmonic, etc.). In order to further quantitatively describe its characteristics through feature extraction so as to accurately identify effective components in the subsequent feature selection process, the present application adopts a multi-dimensional feature combination to extract the current signal features (such as mean value, variance, peak factor, main frequency, frequency band energy ratio, sample entropy, permutation entropy, etc.) of each current signal component from three dimensions: time domain, frequency domain, and entropy value. A normalization algorithm (such as Z-Score) is used to eliminate the dimension difference, so as to construct a vectorized feature representation of each IMF component and obtain the set of current signal component feature coding vectors, providing a quantitative basis for the subsequent feature filtering operation.

[0072] More specifically, in step S213, the set of current signal component feature coding vectors is subjected to feature filtering based on cluster distribution learning to obtain a filtered set of current signal component feature coding vectors. Specifically, since most traditional feature selection algorithms analyze each component feature independently and ignore the correlation between features and the group distribution characteristics of signal components, it is easy to misdelete useful features or retain redundant noise features in a complex noise environment. To address this problem, the present application proposes a feature filtering method based on cluster distribution learning, which constructs the semantic association between individual current signal component features and the group distribution characteristics of signal components by learning the distribution characteristics of each current signal component feature coding vector and the set of all component features, and then screens out the feature subset that contributes the most to the current unbalanced current test task, that is, the filtered set of current signal component feature coding vectors, providing a more accurate information basis for the subsequent signal reconstruction. Among them, Figure 15 is a flowchart of sub-step S213 of the unbalanced current test method for the AC filter capacitor bank according to an embodiment of the present application. As Figure 15 shown, step S213 includes the steps of: S2131, extracting the i-th current signal component feature coding vector from the set of current signal component feature coding vectors as the current signal component individual feature coding vector; S2132, performing feature modulation on the current signal component individual feature coding vector based on the semantic association distribution pattern of the set of current signal component feature coding vectors to obtain the current signal component individual feature modulation coding vector; S2133, determining whether to delete the i-th current signal component feature coding vector based on the information gain of the current signal component individual feature modulation coding vector relative to the set of current signal component feature coding vectors.

[0073] In a specific example of the present application, the step S2131 is expressed by the formula:

[0074] X = {x1, x2,..., x i ,..., x n}

[0075] where X represents a set of current signal component feature coding vectors, and x1, x2, x i and x n respectively represent the 1st, 2nd, ith, and nth current signal component feature coding vectors in the set of current signal component feature coding vectors. n is the number of current signal component feature coding vectors, and x i is used as the individual feature coding vector of the current signal component.

[0076] That is, by focusing on the unique attributes of a single signal component, such as the amplitude fluctuation of a specific frequency component, the time-varying characteristics of noise interference, etc., a more refined analysis basis is provided for subsequent signal component filtering.

[0077] Figure 16 is a flowchart of sub-step S2132 of the unbalanced current test method for the AC filter capacitor bank according to the embodiment of the present application. As Figure 16 shown, the step S2132 includes steps: S21321, calculating the population distribution semantic map of the set of current signal component feature coding vectors to obtain the current signal component feature population distribution semantic map; S21322, mapping the individual feature coding vector of the current signal component to the feature space of the current signal component feature population distribution semantic map to obtain the individual feature modulation coding vector of the current signal component.

[0078] In a specific example of the present application, the step S21321 includes: calculating the semantic correlation degree between any two current signal component feature coding vectors in the set of current signal component feature coding vectors to obtain the current signal component feature population distribution semantic map composed of multiple semantic correlation degrees, which is expressed by the formula:

[0079]

[0080] where R(·,·) represents the semantic correlation degree between the corresponding two current signal component feature coding vectors, [·;·] represents feature concatenation, x j represents the jth current signal component feature coding vector in the set of current signal component feature coding vectors, W r and b respectively represent the weight parameter matrix and the bias term, sigmoid is the activation function, and r i,j represents x i and x jThe semantic association interaction coding vector of the current signal components, T is r i,j The characteristic scale value of, h is the vector r i,j The position index of the eigenvalue in, M represents the semantic graph of the current signal component feature group distribution.

[0081] That is, by constructing a graph-structured representation, the feature coding vectors of each current signal component are placed in the overall context for investigation, mining semantic dependencies and functional complementary relationships beyond simple linear correlations, providing group context information containing prior knowledge such as feature cluster structure and component status differences for subsequent signal processing, obtaining the semantic graph of the current signal component feature group distribution, and using this to provide guidance from a global perspective for accurately designing signal filtering and reconstruction strategies, avoiding the problem of incomplete signal filtering caused by ignoring the non-linear associations between components.

[0082] In a specific example of the present application, the step S21322 is expressed by the formula:

[0083]

[0084] Wherein, v i Represents the individual feature modulation coding vector of the current signal component corresponding to x i .

[0085] That is, by embedding the individual feature coding vector of the current signal component into the feature space of the semantic graph of the current signal component feature group distribution, using the global association information implicit in the graph structure to enhance the context of the individual features, so that the modulated individual feature modulation coding vector of the current signal component not only retains the independent attributes of the individual feature coding vector of a single current signal component, but also incorporates its structural status and functional associations in the overall signal, providing a more comprehensive feature expression for subsequent signal filtering and reconstruction, thereby enhancing the discrimination ability of useful signals and noise components in subsequent signal processing.

[0086] In a preferred example of the present application, the step S2133 includes: First, perform global semantic conjugate distribution universality optimization on the individual feature modulation coding vector of the current signal component to obtain an optimized individual feature modulation coding vector of the current signal component, which is expressed by the formula:

[0087]

[0088] x′ i =ln(v i )⊙[ln(x i ) ⊙-1

[0089]

[0090] ​where, (·) T represents the transpose of a vector, represents vector multiplication, (·) ⊙-1 represents calculating the reciprocal of each eigenvalue in a vector, M′ represents the semantic map of the optimized current signal component feature population distribution, ln(·) represents the logarithmic function with the natural constant e as the base, ⊙ represents dot product, x′ i represents the optimized current signal component individual feature encoding vector corresponding to x i i represents the optimized current signal component individual feature modulation encoding vector corresponding to v i i j

[0091] Here, when the semantic map of the current signal component feature population distribution captures information such as the feature space topological structure of the local correlation of each current signal component feature encoding vector through pairwise calculations of (x i , x j ), there is also inevitably the problem of uneven global universality of local correlation defects, which affects the accuracy of the overall-local difference significance measurement of the current signal component individual feature modulation encoding vector. In response to this, the present application corrects the energy distribution deviation of local correlation defects in the global semantic background by introducing the universality optimization of the global semantic conjugate distribution, so as to enhance the unified representation ability of the current signal component individual feature modulation encoding vector for signal components in a complex electromagnetic environment. The generated optimized current signal component individual feature modulation encoding vector not only retains the local unique attributes of the signal component, but also can accurately map its energy scale relationship in the global signal space, and solves the problem of feature expression deviation caused by local correlation calculation limitations.

[0092] Then, calculate the current signal component individual feature semantic increment operator of the optimized current signal component individual feature modulation encoding vector relative to the set of the current signal component feature encoding vectors, which is expressed by the formula:

[0093]

[0094] where, L represents the vector scale of v i i,k represents the eigenvalue at the k-th position in v i i i i λ represents the semantic increment intermediate parameter corresponding to v i represents the current signal component individual feature semantic increment operator corresponding to v i

[0095] That is, by means of counterfactual reasoning, the causal effect of each optimized current signal component's individual feature modulation coding vector is quantified, and its influence degree on the overall semantic expression ability of the signal is evaluated, so as to provide a quantifiable priority basis for the subsequent selective filtering and reconstruction of signal components. Based on this, a quantization index reflecting the importance of each signal component is generated, that is, the individual feature semantic increment operator of the current signal component. A high value indicates that the individual feature modulation coding vector of this optimized current signal component is the core element maintaining the effective features of the signal, and removing it will significantly damage the signal semantics. A low value corresponds to secondary or interfering components, and removing them has a weak impact on the overall features of the signal, thereby achieving the key retention of useful signals and the precise elimination of noise components.

[0096] Finally, based on the comparison between the individual feature semantic increment operator of the current signal component and a preset threshold, it is determined whether to delete the i-th current signal component feature coding vector, which is expressed by the formula:

[0097]

[0098] where θ represents the preset mask threshold, and mask(·) is the mask function.

[0099] That is, an objective decision boundary is constructed through the preset threshold to eliminate noise or secondary components that have a weak impact on the overall semantic expression ability of the signal, while retaining the core useful components, achieving noise reduction and truth retention in the feature dimension, retaining high-value components carrying key information such as fundamental wave amplitude and phase, thereby significantly improving the purity of signal components, reducing the interference of non-stationary noise on measurement results, and laying a foundation for accurately calculating the unbalanced current value.

[0100] More specifically, in step S214, the filtered set of the current signal component feature coding vectors is input into the current signal reconstruction model to obtain the unbalanced test current enhanced signal. Specifically, in the current signal reconstruction stage, the autoencoder model under the deep learning architecture is adopted as the current signal reconstruction model in this application. Through unsupervised learning, the autoencoder model can learn the low-dimensional representation of data from the input high-dimensional feature space and reconstruct the high-dimensional features of the original data based on this low-dimensional representation, achieving effective dimensionality reduction and information retention of features. In this application, the autoencoder model receives the filtered set of the current signal component feature coding vectors after feature filtering as input, maps the high-dimensional features to the low-dimensional latent space through its encoding layer, and then reconstructs the high-dimensional feature representation of the current signal from the low-dimensional latent space, that is, the unbalanced test current enhanced signal. This process can not only effectively remove noise components but also retain the key information reflecting the unbalanced state of the capacitor bank, thereby greatly improving the signal-to-noise ratio and interpretability of the signal.

[0101] Specifically, in step S22, based on the unbalanced test current enhancement signal, the unbalanced current value is obtained. It should be understood that the non-stationary noise and interference components have been filtered out from the unbalanced test current enhancement signal, and its amplitude and phase can truly reflect the unbalance degree between the arms of the capacitor bank. Therefore, by calculating the effective value of the unbalanced test current enhancement signal, the unbalanced current value between the arms of the AC filter capacitor bank can be obtained.

[0102] In the above method for testing the unbalanced current of the AC filter capacitor bank, in step S3, based on the comparison between the measured unbalanced current value and the converted unbalanced current protection setting value, a test result is generated. More specifically, step S3 includes: obtaining the unbalanced current protection setting value of the AC filter capacitor bank under the normal operating voltage; based on the ratio between the normal operating voltage and the test voltage, converting the unbalanced current protection setting value to obtain the converted unbalanced current protection setting value; calculating the current difference between the measured unbalanced current value and the converted unbalanced current protection setting value; and generating the test result based on the comparison between the current difference and a preset threshold.

[0103] It should be understood that according to the principle of electromagnetic induction, the voltage regulator generates a low-voltage current proportional to the operating voltage between the arms of the capacitor bank by changing the amplitude of the input voltage. Since the capacitive reactance of the capacitor is inversely proportional to the voltage frequency, under power frequency conditions, the low-voltage test current and the high-voltage operating current are in a linear proportional relationship. Based on this, the unbalanced current protection setting value can be equivalently converted through the voltage ratio, and the conversion formula is as follows:

[0104]

[0105] where I2 represents the unbalanced section I protection current value under the test voltage, that is, the converted unbalanced current protection setting value, U1 represents the test applied voltage value, I1 represents the unbalanced section I protection current setting value, and U n represents the rated line voltage value of the filter operation.

[0106] Then, the calculated unbalanced current value is compared with the converted unbalanced current protection setting value. By quantifying the deviation between the current difference and the preset threshold, the balance state of the capacitor bank is evaluated, providing a reliable basis for the commissioning decision. For example, according to the standard requirements, the measured unbalanced current value needs to be less than 20% of the protection setting value. Then, the threshold can be dynamically set accordingly. By comparing the threshold, it can be determined whether the capacitor bank is in a normal state or needs maintenance, thereby realizing real-time monitoring and early warning of the unbalanced state of the capacitor bank and improving the maintenance efficiency and operation reliability of the power grid.

[0107] In summary, the method for testing the unbalanced current of the AC filter capacitor bank according to the embodiments of the present application is clarified. It uses a voltage regulator to apply a test voltage less than the normal operating voltage to the AC filter capacitor bank to be tested. Under the test voltage condition, signal component filtering and reconstruction based on signal distribution guidance are performed on the unbalanced test current signal between the bridge arms of the AC filter capacitor bank to filter out the noise and interference components in the current signal, obtain a more accurate unbalanced current measurement value, and convert the unbalanced current protection setting value based on the ratio between the normal operating voltage and the test voltage of the AC filter capacitor bank. Then, according to the current difference between the unbalanced current measurement value and the converted unbalanced current protection setting value, a test result is generated. In this way, electromagnetic interference, harmonics and other noise components in the unbalanced test current signal can be effectively filtered out, the accuracy and reliability of the test result can be improved, and a strong guarantee can be provided for the maintenance quality of the AC filter capacitor bank.

[0108] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and easy understanding, rather than limitations. The above details do not limit the present invention to necessarily adopt the above specific details to be implemented.

[0109] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the unit division is only a logical function division, and there can be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claimed invention.

[0111] In addition, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. The multiple elements stated in the system claims can also be implemented by one element through software or hardware.

[0112] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for testing the unbalanced current of an AC filter capacitor bank, characterized in that, Including: Applying a test voltage to the AC filter capacitor bank to be tested by using a voltage regulator, where the test voltage is less than the normal operating voltage; Under the condition of applying the test voltage, measuring the unbalanced current value between the bridge arms of the AC filter capacitor bank; Generating a test result based on the comparison between the measured unbalanced current value and the converted unbalanced current protection setting value; Wherein, under the condition of applying the test voltage, measuring the unbalanced current value between the bridge arms of the AC filter capacitor bank includes: filtering and reconstructing the unbalanced test current signal based on signal distribution guidance to obtain an enhanced unbalanced test current signal; and obtaining the unbalanced current value based on the enhanced unbalanced test current signal.

2. The unbalanced current test method for the AC filter capacitor bank according to claim 1, wherein Generating a test result based on the comparison between the measured unbalanced current value and the converted unbalanced current protection setting value includes: Obtaining the unbalanced current protection setting value of the AC filter capacitor bank under the normal operating voltage; Converting the unbalanced current protection setting value based on the ratio between the normal operating voltage and the test voltage to obtain the converted unbalanced current protection setting value.

3. The method for testing the unbalanced current of the AC filter capacitor bank according to claim 2, wherein Generating a test result based on the comparison between the measured unbalanced current value and the converted unbalanced current protection setting value further includes: Calculating the current difference between the measured unbalanced current value and the converted unbalanced current protection setting value; Generating the test result based on the comparison between the current difference and a preset threshold value.

4. The unbalanced current test method for the AC filter capacitor bank according to claim 1, wherein Filtering and reconstructing the unbalanced test current signal based on signal distribution guidance to obtain an enhanced unbalanced test current signal includes: Capturing the unbalanced test current signal; Extracting the current signal component feature encoding vector set of the unbalanced test current signal by performing current signal feature extraction based on modal decomposition; Performing feature filtering based on cluster distribution learning on the current signal component feature encoding vector set to obtain a filtered set of current signal component feature encoding vectors; Inputting the filtered set of current signal component feature encoding vectors into a current signal reconstruction model to obtain the enhanced unbalanced test current signal.

5. The method for testing the unbalanced current of the AC filter capacitor bank according to claim 4, wherein Extracting the current signal component feature encoding vector set of the unbalanced test current signal by performing current signal feature extraction based on modal decomposition includes: Performing CEEMDAN signal decomposition on the unbalanced test current signal to obtain a set of current signal components; Extracting the current signal features of each current signal component in the set of current signal components to obtain the current signal component feature encoding vector set.

6. The method for testing the unbalanced current of the AC filter capacitor bank according to claim 5, characterized in that, Performing feature filtering based on cluster distribution learning on the current signal component feature encoding vector set to obtain a filtered set of current signal component feature encoding vectors includes: Extracting the i-th current signal component feature encoding vector from the current signal component feature encoding vector set as the individual feature encoding vector of the current signal component; Based on the semantic association distribution pattern of the set of the current signal component feature encoding vectors, perform feature modulation on the individual feature encoding vectors of the current signal components to obtain the individual feature modulation encoding vectors of the current signal components; Based on the information gain of the individual feature modulation encoding vectors of the current signal components relative to the set of the current signal component feature encoding vectors, determine whether to delete the i-th current signal component feature encoding vector.

7. The method for testing the unbalanced current of the AC filter capacitor bank according to claim 6, characterized in that, Based on the semantic association distribution pattern of the set of the current signal component feature encoding vectors, performing feature modulation on the individual feature encoding vectors of the current signal components to obtain the individual feature modulation encoding vectors of the current signal components includes: Calculating the population distribution semantic graph of the set of the current signal component feature encoding vectors to obtain the current signal component feature population distribution semantic graph; Mapping the individual feature encoding vectors of the current signal components to the feature space of the current signal component feature population distribution semantic graph to obtain the individual feature modulation encoding vectors of the current signal components.

8. The unbalanced current test method for the AC filter capacitor bank according to claim 7, wherein Calculating the population distribution semantic graph of the set of the current signal component feature encoding vectors to obtain the current signal component feature population distribution semantic graph includes: Calculating the semantic association degree between any two current signal component feature encoding vectors in the set of the current signal component feature encoding vectors to obtain the current signal component feature population distribution semantic graph composed of multiple semantic association degrees.

9. The method for testing the unbalanced current of the AC filter capacitor bank according to claim 8, characterized in that Based on the information gain of the individual feature modulation encoding vectors of the current signal components relative to the set of the current signal component feature encoding vectors, determining whether to delete the i-th current signal component feature encoding vector includes: Performing global semantic conjugate distribution universality optimization on the individual feature modulation encoding vectors of the current signal components to obtain the optimized individual feature modulation encoding vectors of the current signal components; Calculating the individual feature semantic increment operator of the current signal components of the optimized individual feature modulation encoding vectors of the current signal components relative to the set of the current signal component feature encoding vectors; Based on the comparison between the individual feature semantic increment operator of the current signal components and a preset threshold, determine whether to delete the i-th current signal component feature encoding vector.

Images