Dry-type air-core reactor fault detection method and system, terminal and storage medium

By performing attenuation oscillation voltage testing and feature extraction on dry hollow reactors, using LSTM and random forest models, the problem of difficult detection of fine insulation defects in the existing technology is solved, high-accurate fault diagnosis is achieved, and the power system is reduced risk of downtime.

CN119044705AActive Publication Date: 2024-11-29BINZHOU POWER SUPPLY COMPANY OF STATE GRID SHANDONG ELECTRIC POWER

Patent Information

Application Number
CN202411534136.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-31
Publication Date
2024-11-29
Estimated Expiration
2044-10-31

AI Technical Summary

Technical Problem

The prior art is difficult to effectively detect subtle insulation defects in dry hollow reactors, resulting in the power system facing the risk of shutdown and accidents, and the accuracy of fault detection is insufficient.

Method used

By performing attenuation oscillation voltage test on the target dry hollow reactor, the oscillation voltage waveform and inductance value are obtained, the peak difference sequence and the zero-crossing time difference sequence are calculated, and the waveform characteristics and inductance difference are extracted using pre-trained LSTM model and random forest model. value to realize fault diagnosis.

Benefits of technology

It greatly improves the accuracy of fault detection of dry hollow reactors, can accurately capture small abnormalities, and improves the reliability and accuracy of detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119044705A_ABST
    Figure CN119044705A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of data processing, and particularly provides a dry-type air-core reactor fault detection method and system, a terminal and a storage medium, and the method comprises the steps: carrying out the damped oscillation voltage test of a target dry-type air-core reactor, and obtaining the oscillation voltage waveform and inductance value generated by the target dry-type air-core reactor in the test process; obtaining a pre-stored standard voltage waveform and a standard inductance value of the target dry-type air-core reactor; calculating a wave crest difference sequence and a zero crossing point time difference sequence of the oscillation voltage waveform and a standard voltage waveform; inputting the wave crest difference sequence and the zero crossing point time difference sequence into a pre-trained LSTM model to obtain waveform features; and inputting a difference value between the inductance value and the standard inductance value and the waveform feature into a pre-trained random forest model to obtain a fault diagnosis result. According to the invention, the fault detection accuracy of the dry-type air-core reactor is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a dry-type air-core reactor fault detection method, system, terminal and storage medium. Background Art

[0002] As an inductive high-voltage electrical appliance, the air-core reactor plays a key role in limiting short-circuit current, achieving reactive power compensation and phase shifting in the power system. Its uniqueness lies in the fact that the magnetic flux path forms a loop through the air, hence the name air-core reactor. However, dry-type air-core reactors frequently encounter challenges in actual operation, especially fire incidents caused by insulation damage. These major faults often originate from tiny inter-turn insulation defects, which are even latent when the reactor leaves the factory. If these insulation hazards are not detected in time, the power system may face the risk of downtime or even more serious accidents, resulting in significant economic losses to the power operation department. In view of this, it is particularly urgent and important to implement strict factory inspection of reactors in order to identify potential insulation defects as early as possible.

[0003] Currently, the industry uses the oscillation voltage detection method to diagnose insulation faults, which involves manually observing the oscillation voltage waveform displayed on an oscilloscope. However, this method has limitations and can only make judgments when there are obvious signs of faults, but it is difficult to capture subtle abnormalities. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a dry-type air-core reactor fault detection method, system, terminal and storage medium to solve the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a dry-type air-core reactor fault detection method, comprising: Performing a damped oscillation voltage test on the target dry-type air-core reactor, and obtaining an oscillation voltage waveform and an inductance value generated by the target dry-type air-core reactor during the test; Obtaining a pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value; Calculating a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform; Inputting the peak difference sequence and the zero-crossing time difference sequence into a pre-trained LSTM model to obtain waveform features; The difference between the inductance value and the standard inductance value and the waveform feature are input into a pre-trained random forest model to obtain a fault diagnosis result.

[0006] In an optional implementation, obtaining a pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value includes: According to the model information of the target dry-type air-core reactor, the corresponding standard voltage waveform and standard inductance value are retrieved from a database, wherein the database stores the standard voltage waveforms and standard inductance values ​​of various models of dry-type air-core reactors.

[0007] In an optional implementation, calculating the peak difference sequence and the zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform includes: The peak difference and zero-crossing time difference of the corresponding periods of the oscillating voltage waveform and the standard voltage waveform are calculated, and the peak difference and zero-crossing time difference are sorted in order of period to obtain the peak difference sequence and the zero-crossing time difference sequence.

[0008] In an optional embodiment, the method further comprises: Dry-type air-core reactors with tiny defects are collected as defective samples, and attenuated oscillation voltage tests are performed on the defective samples to obtain oscillation voltage waveforms and inductance values ​​of the defective samples under various oscillation voltages; Normal dry-type air-core reactors are collected as normal samples, and attenuated oscillation voltage tests are performed on the normal samples to obtain oscillation voltage waveforms and inductance values ​​of the normal samples under various oscillation voltages; Mark the oscillation voltage waveform and inductance value of the defective sample as defective test data and save them in the data set, and mark the oscillation voltage waveform and inductance value of the normal sample under various oscillation voltages as normal test data and save them in the data set; The dataset is used to train and validate the LSTM model and random forest model.

[0009] In a second aspect, the present invention provides a dry-type air-core reactor fault detection system, comprising: A data acquisition module is used to perform an attenuated oscillation voltage test on the target dry-type air-core reactor and obtain an oscillation voltage waveform and an inductance value generated by the target dry-type air-core reactor during the test; A standard acquisition module is used to acquire a pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value; A difference calculation module, used for calculating a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform; A feature extraction module is used to input the peak difference sequence and the zero-crossing time difference sequence into a pre-trained LSTM model to obtain waveform features; The result diagnosis module is used to input the difference between the inductance value and the standard inductance value and the waveform characteristics into a pre-trained random forest model to obtain a fault diagnosis result.

[0010] In an optional implementation, the standard acquisition module includes: The standard acquisition unit is used to retrieve the corresponding standard voltage waveform and standard inductance value from a database according to the model information of the target dry-type air-core reactor, wherein the database stores the standard voltage waveforms and standard inductance values ​​of various models of dry-type air-core reactors.

[0011] In an optional implementation, the difference calculation module includes: The difference calculation unit is used to calculate the peak difference and zero-crossing time difference of the corresponding cycles of the oscillating voltage waveform and the standard voltage waveform, and sort the peak difference and zero-crossing time difference in order of cycle to obtain the peak difference sequence and the zero-crossing time difference sequence.

[0012] In an optional embodiment, the system further includes: The first collection module is used to collect dry-type air-core reactors with tiny defects as defective samples, perform attenuated oscillation voltage tests on the defective samples, and obtain oscillation voltage waveforms and inductance values ​​of the defective samples under various oscillation voltages; The second collection module is used to collect normal dry-type air-core reactors as normal samples, perform attenuated oscillation voltage tests on the normal samples, and obtain oscillation voltage waveforms and inductance values ​​of the normal samples under various oscillation voltages; A data marking module, used to mark the oscillation voltage waveform and inductance value of the defective sample as defective test data and save them in a data set, and mark the oscillation voltage waveform and inductance value of the normal sample under various oscillation voltages as normal test data and save them in a data set; The training execution module is used to train and verify the LSTM model and random forest model using the dataset.

[0013] In a third aspect, a terminal is provided, including: processor, memory, wherein: The memory is used to store computer programs. The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.

[0014] According to a fourth aspect, a computer storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the methods described in the above aspects.

[0015] The beneficial effect of the present invention lies in that the dry-type air-core reactor fault detection method, system, terminal and storage medium provided by the present invention extract the difference parameters between the oscillation voltage waveform and the standard voltage waveform, and use the LSTM model to extract the difference timing characteristics from the difference parameters, and use the random forest model to accurately capture small anomalies based on the inductance difference and the difference timing characteristics, thereby greatly improving the accuracy of dry-type air-core reactor fault detection.

[0016] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0019] Figure 2 It is a schematic diagram of a decay oscillation voltage testing device according to an embodiment of the present invention.

[0020] Figure 3 is a schematic block diagram of a system according to an embodiment of the present invention.

[0021] Figure 4 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0024] The dry-type air-core reactor fault detection method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the dry-type air-core reactor fault detection system runs in the computer device.

[0025] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be a dry-type air-core reactor fault detection system. According to different requirements, the order of the steps in the flow chart may be changed, and some may be omitted.

[0026] like Figure 1 As shown, the method includes: Step 110, performing a damped oscillation voltage test on the target dry-type air-core reactor, and obtaining an oscillation voltage waveform and an inductance value generated by the target dry-type air-core reactor during the test; Step 120, obtaining a pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value; Step 130, calculating a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform; Step 140, inputting the peak difference sequence and the zero-crossing time difference sequence into a pre-trained LSTM model to obtain waveform features; Step 150, inputting the difference between the inductance value and the standard inductance value, and the waveform feature into a pre-trained random forest model to obtain a fault diagnosis result.

[0027] To facilitate understanding of the present invention, the dry-type air-core reactor fault detection method provided by the present invention is further described below based on the principle of the dry-type air-core reactor fault detection method of the present invention and the process of performing fault detection on the dry-type air-core reactor in the embodiment.

[0028] Specifically, the dry-type air-core reactor fault detection method includes: S1. Perform an attenuated oscillation voltage test on the target dry-type air-core reactor, and obtain the oscillation voltage waveform and inductance value generated by the target dry-type air-core reactor during the test.

[0029] Attenuated oscillation voltage test device such as Figure 2 As shown, it includes a first resistor R1, a second resistor R2, and a voltage divider resistor R H And the voltage divider resistor R L , ball gap switch S, capacitor C C , capacitor C H , capacitor C L , capacitor C, inductor L and diode D; diode D, first resistor R1 and spherical gap switch S are connected in series at both ends of the output side of the target dry-type air-core reactor, second resistor R2, voltage divider resistor R H And the voltage divider resistor R L In series and in parallel with the ball gap switch S; capacitor C C , capacitor C H , capacitor C L The branches connected in series with the voltage divider resistor R H And the voltage divider resistor R L The series branches are connected in parallel; inductor L and capacitor C H , capacitor C L The series branches are connected in parallel; capacitor C and inductor L are connected in parallel.

[0030] The resistor divider is used to measure the main capacitor C C The DC charging voltage value of the capacitor voltage divider is used to measure the exponentially decaying oscillation voltage output by the device. The impedance values ​​of both are very large, and their existence is ignored when analyzing the voltage and current relationship of the circuit. The working process of the original circuit is described as follows: the ball gap switch is controlled to conduct once in each power frequency voltage cycle, that is, the main capacitor discharges to the inductor once in each power frequency power cycle, which just meets the standard requirement of 4000 discharges per minute. In the negative half cycle of the output voltage of the test transformer, the test transformer charges the main capacitor through the protection resistor, damping resistor, and inductor coil. Compared with the impedance of the capacitor, the impedance of the protection resistor, damping resistor and inductor coil can be ignored, so the main capacitor is charged with the peak voltage of the test transformer, the left plate potential is a negative peak, and the right plate potential is zero. In the positive half cycle of the output voltage of the test transformer, the components on the left side of the ball gap switch are all open. At this time, a trigger signal is given, the ball gap switch discharges and turns on, the voltage drop on the damping resistor is ignored, the potential of the left plate of the main capacitor is forced to zero, and because the energy stored in the capacitor cannot change suddenly, the potential of the right plate of the main capacitor jumps to the positive peak value, and the main capacitor discharges to the inductor coil through the damping resistor (the capacitance is very small and can be ignored). After that, the energy is converted between the electric field energy of the main capacitor and the magnetic field energy of the inductor coil until it is completely absorbed by the damping resistor and the loop resistor, and an exponentially decaying oscillation voltage is obtained on the inductor coil and the model sample connected in parallel with it.

[0031] From the analysis of the test principle, it can be seen that in the negative half cycle of the test transformer output voltage, the ball gap switch is disconnected, and the principle circuit works in the charging state. The components involved in the work include the voltage regulator, test transformer, protection resistor, damping resistor, main capacitor and inductor. The impedance of the inductor under DC can be ignored, so the amplitude of the voltage charged on the main capacitor depends on the test transformer output voltage and the resistance values ​​of the protection resistor and damping resistor.

[0032] In order to ensure that the recovery time of the air insulation between the spherical gaps is long enough after the damping resistor completely absorbs the electric field energy in the main capacitor (the arc in the spherical gap is extinguished) and to ensure the controllability of the spherical gap switch, the triggering moment of the spherical gap breakdown is selected at the zero-crossing moment when the output voltage of the test transformer changes from negative to positive.

[0033] PSCAD software is used to simulate and analyze the circuit principle in the above figure, and a simulation study of inter-turn fault discrimination is conducted on an inductor with an inductance of 75mH. Existing studies have shown that if there are short-circuited turns in a dry-type air-core reactor, the following changes will occur: a short-circuited coil appears in the reactor, which reduces the number of effective turns and causes the overall inductance of the reactor to decrease. At the same time, an induced electromotive force will be generated in the short-circuited turn, and the circulating current caused by the induced electromotive force will have a demagnetizing effect on the reactor, reducing the inductance. The circulating current in the short-circuited turn will also increase the overall loss of the reactor.

[0034] The high-frequency pulse oscillation test device charges the main capacitor Cc in the negative half-wave of the power supply and is triggered in the positive half-wave of the power supply. The advantage of this is that 1 / 2 of the time in each cycle is used to charge the capacitor Cc, ensuring that the capacitor charging voltage reaches the predetermined value. When the capacitor Cc is charged to the predetermined value, the ignition controller sends a trigger signal, which is transmitted to the trigger controller through the optical fiber, triggering the controller to ignite, and the ball gap S breaks down. At this time, the main capacitor Cc and the equivalent inductance L of the test reactor form a damped oscillation circuit. The oscillating discharge current gradually decays. When the current decays to a level that is not enough to maintain arc burning, a damped oscillation is completed. This damped oscillation process is less than 5ms. In the negative half-wave of the next power frequency cycle, the main capacitor C is charged again. When the voltage reaches the predetermined value, the discharge ball gap is triggered at the set time, the ignition ball gap is turned on again, and the RLC circuit forms a damped oscillation again.

[0035] In order to improve the accuracy of the test voltage applied to the reactor, the detection system does not use the natural breakdown discharge method. The triggering moment of the ignition controller is precisely adjustable, and the triggering of the discharge ball gap of the detection system is controlled by the ignition controller. When the detection system is working, it generates a lot of electromagnetic interference to the surrounding electronic equipment, so the ignition controller does not use any electronic devices, and all high-voltage devices are selected to improve the stability and reliability of the ignition controller.

[0036] Through analysis, it can be known that during the damped oscillation process between the pulse capacitor Cc and the test reactor, if the reactor has inter-turn insulation defects, the fixed reactance rate of the entire reactor will change due to the reduction in the number of turns of the reactor coil and the demagnetization effect, and the oscillation frequency of the entire oscillation circuit will change accordingly; the circulating current in the short-circuit turn will increase the loss of the reactor, and the aluminum wire in the short-circuit ring will heat up seriously. The voltage and current decay rate of the entire oscillation circuit is accelerated. Therefore, by comparing the voltage or current waveform frequency and zero-crossing point changes at both ends of the test reactor under the system rated voltage and the oscillation wave test voltage, it can be determined whether the reactor coil has inter-turn insulation defects.

[0037] The pulse capacitor is used to discharge the smoothing reactor by adjusting the ball gap, and a high-frequency oscillation voltage with an oscillation frequency of about 100 kHz is formed on the UHV dry-type smoothing reactor. The polarity of the capacitor charging voltage is negative, and the high-frequency oscillation test sequence is as follows: 1 negative polarity half voltage; 3 negative polarity full voltage; 1 negative polarity half voltage.

[0038] On the premise of completing the medium-frequency oscillation test sequence required by the standard, add a half-voltage test at the end, observe the half-voltage waveform frequency, and check whether the previous medium-frequency oscillation full-voltage test causes damage to the reactor winding.

[0039] S2. Obtain the pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value.

[0040] According to the model information of the target dry-type air-core reactor, the corresponding standard voltage waveform and standard inductance value are retrieved from a database, wherein the database stores the standard voltage waveforms and standard inductance values ​​of various models of dry-type air-core reactors.

[0041] Specifically, according to the specific model information of the target dry-type air-core reactor, we can accurately retrieve the standard voltage waveform and standard inductance value that match it from the carefully constructed database. This database is a comprehensive information resource library that stores a wide range of standard voltage waveform data and standard inductance value data for different models of dry-type air-core reactors in a comprehensive and detailed manner. These data not only cover various common models on the market, but also include information on some special customized or historical models, ensuring wide applicability and high accuracy.

[0042] During the retrieval process, the system will first parse the input dry-type air-core reactor model information, which includes but is not limited to its manufacturer, series number, rated capacity, rated voltage and other key parameters. Then, using an efficient retrieval algorithm, the database will quickly locate the data record that completely corresponds to the model. In these records, the standard voltage waveform is presented in high-precision digital or graphical form, detailing the law of voltage change over time under normal working conditions of the reactor; and the standard inductance value provides a quantitative indicator of the reactor's resistance to alternating current, which is an important parameter for evaluating its electrical performance.

[0043] In addition, the database also has a dynamic update mechanism, which can be continuously updated with the launch of new product models or the technical upgrade of existing models, ensuring the timeliness and reliability of the information provided. Users can not only obtain the required data through direct query, but also use the analysis tools provided by the database to further compare, analyze and optimize the standard voltage waveform and standard inductance value, providing strong support for the design, selection and maintenance of dry-type air-core reactors.

[0044] S3. Calculate a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform.

[0045] The peak difference and zero-crossing time difference of the corresponding periods of the oscillating voltage waveform and the standard voltage waveform are calculated, and the peak difference and zero-crossing time difference are sorted in order of period to obtain the peak difference sequence and the zero-crossing time difference sequence.

[0046] The oscillating voltage waveform is divided into cycles, and the waveform of each cycle is marked with serial numbers in chronological order. At the same time, the standard voltage waveform is divided into cycles, and the waveform of each cycle is marked with serial numbers in chronological order. The waveforms with the same serial number are compared to calculate the peak difference and the zero-crossing time difference. The peak difference and the zero-crossing time difference are arranged according to the serial number to obtain the peak difference sequence and the zero-crossing time difference sequence.

[0047] For the oscillating voltage waveform, we use specialized waveform analysis software or algorithms to identify its periodic features, such as peaks, troughs, or specific phase change points, and use this as a basis to divide the waveform into several complete cycles. Then, we assign an increasing serial number to each divided periodic waveform in chronological order, such as cycle 1, cycle 2, ..., and so on.

[0048] For standard voltage waveforms, we use the same method to perform cycle segmentation and serial number marking. Since standard voltage waveforms are usually known and stable waveforms, the process of cycle segmentation and serial number marking may be more direct and accurate.

[0049] After completing the waveform segmentation and serial number marking, the oscillating voltage waveform is then compared with the cycle with the same serial number in the standard voltage waveform. The main purpose of the comparison is to find the differences between the two in terms of peaks and zero crossings.

[0050] For the calculation of the crest difference, the crest values ​​of the two waveforms in the same cycle are compared and the voltage difference between them is calculated. This difference reflects the degree of deviation of the voltage amplitude of the oscillating voltage waveform relative to the standard voltage waveform.

[0051] For the calculation of the zero-crossing time difference, first determine the zero-crossing time of the two waveforms in the same cycle, and then calculate the time difference between the two times. This difference reflects the phase shift of the oscillating voltage waveform relative to the standard voltage waveform.

[0052] After calculating the peak difference and zero-crossing time difference in all cycles, we sort these difference values ​​according to the sequence number (i.e. time order). The purpose of this is to facilitate the observation and analysis of the trend of waveform differences over time.

[0053] After sorting, two sequences are obtained: the peak difference sequence and the zero-crossing time difference sequence. The peak difference sequence shows the voltage difference between the oscillating voltage waveform and the standard voltage waveform at the peak in each cycle, while the zero-crossing time difference sequence reveals the change of the waveform phase offset with the cycle.

[0054] S4. Input the peak difference sequence and the zero-crossing time difference sequence into a pre-trained LSTM model to obtain waveform features.

[0055] The peak difference sequence and the zero-crossing time difference sequence have the same length, and weighted summation is performed on the corresponding elements of the peak difference sequence and the zero-crossing time difference sequence to obtain a comprehensive data sequence. The comprehensive data sequence is normalized to obtain a data sequence.

[0056] The LSTM (Long Short-Term Memory) model is a special recurrent neural network (RNN) architecture that aims to solve the gradient vanishing and gradient exploding problems that exist in traditional RNNs when processing long sequence data. The key to the LSTM model lies in its special cell structure, where each cell contains three gates and a cell state. The three gates are: Forget Gate: controls how much information in the current cell state is retained or forgotten. It determines which information needs to be forgotten based on the hidden state of the previous time step and the input of the current time step.

[0057] Input Gate: Controls how much new information is stored in the cell state. It also determines what new information needs to be added based on the implicit state of the previous time step and the input of the current time step.

[0058] Output Gate: Determines how much information is output from the cell state. It calculates the output based on the current cell state and the hidden state of the previous time step.

[0059] The data sequence is input into the pre-trained LSTM model and the waveform features are extracted from the middle layer of the LSTM model.

[0060] After period segmentation, peak difference and zero-crossing time difference calculation, two sequences of the same length are obtained: the peak difference sequence [d1, d2, ..., dn] and the zero-crossing time difference sequence [t1, t2, ..., tn], where n represents the number of periods.

[0061] In order to combine the information of peak difference and zero-crossing time difference, the corresponding elements of the two sequences are weighted and summed. Assuming that the weight assigned to the peak difference sequence is w1, and the weight assigned to the zero-crossing time difference sequence is w2 (and w1+w2=1 to ensure that the weighted value is still within a reasonable range), the comprehensive data sequence can be calculated by the following formula: The comprehensive data sequence = [w1*d1+w2*t1,w1*d2+w2*t2,...,w1*dn+w2*tn].

[0062] This comprehensive data sequence contains both the voltage information of the peak difference and the phase information of the zero-crossing time difference, providing a more comprehensive description of the waveform characteristics.

[0063] Since the elements in the comprehensive data sequence may have different dimensions and value ranges, in order to eliminate the impact of such differences on model training, the comprehensive data sequence is normalized.

[0064] Select the minimum-maximum normalization method, and the normalized data sequence can be calculated by the following formula: Normalized data sequence = [(element - minimum value) / (maximum value - minimum value) for element in integrated data sequence].

[0065] The normalized data sequence is input into a pre-trained LSTM model. The LSTM model is a recurrent neural network that is good at processing time series data and can capture long-term dependencies in the data.

[0066] In the LSTM model, the data sequence is input into the input layer of the model in chronological order, and then passes through multiple hidden layers for feature extraction and transformation. In order to extract the waveform features, an output is set on an intermediate layer of the LSTM model (such as the last hidden layer) to obtain the feature vector processed by the model.

[0067] This feature vector not only contains the information in the original data, but also has undergone nonlinear transformation and feature extraction by the LSTM model, so it has stronger expression and generalization capabilities. This feature vector is used in subsequent fault diagnosis, classification or regression tasks.

[0068] S5. Input the difference between the inductance value and the standard inductance value, and the waveform feature into a pre-trained random forest model to obtain a fault diagnosis result.

[0069] The difference between the inductance value and the standard inductance value and the waveform feature are input into a pre-trained random forest model to obtain a fault diagnosis result.

[0070] Inductance difference calculation: Measure the actual inductance of the device, recorded as L_actual. Obtain the standard inductance of the device, recorded as L_standard. Calculate the difference between the inductance and the standard inductance, that is, ΔL = L_actual - L_standard.

[0071] The waveform features extracted from the middle layer of the LSTM model are denoted as F_waveform.

[0072] Combine the inductance difference ΔL and the waveform feature vector F_waveform into a new input vector X_input, that is: X_input = [ΔL, F_waveform]; This input vector contains the device’s inductance value change information and waveform characteristic information, providing comprehensive data support for subsequent fault diagnosis.

[0073] In practical applications, the new input vector X_input is input into the pre-trained random forest model. The model will traverse and vote on the decision tree based on the characteristics of the input vector, and finally give a fault diagnosis result. This result may include information such as the type of fault, the severity of the fault, and the possible cause of the fault, providing strong support for equipment maintenance and management.

[0074] In addition, before using the model, the model needs to be trained. The training methods include: Dry-type air-core reactors with tiny defects are collected as defective samples, and an attenuated oscillation voltage test is performed on the defective samples to obtain the oscillation voltage waveform and inductance value of the defective samples under various oscillation voltages; normal dry-type air-core reactors are collected as normal samples, and an attenuated oscillation voltage test is performed on the normal samples to obtain the oscillation voltage waveform and inductance value of the normal samples under various oscillation voltages; the oscillation voltage waveform and inductance value of the defective samples are marked as defective test data and saved in a data set, and the oscillation voltage waveform and inductance value of the normal samples under various oscillation voltages are marked as normal test data and saved in a data set.

[0075] Defective sample collection: Select the reactors with minor defects from the dry-type air-core reactors on the production line or in use as defective samples. These defects may include loose windings, aging of insulation materials, partial discharge, etc. Detailed records are kept for each defective sample, including information such as defect type, defect location, and defect degree.

[0076] Normal sample collection: Select several dry-type air-core reactors with no obvious defects and operating normally from the same batch or the same production line as normal samples. Ensure that the normal samples are comparable to the defective samples in terms of electrical performance and structural characteristics.

[0077] Test equipment preparation: Prepare a test device that can generate attenuated oscillation voltage and ensure that the equipment accuracy meets the test requirements. Set the parameters of the test equipment, such as voltage amplitude, frequency, attenuation rate, etc., to simulate the voltage fluctuation in actual operation.

[0078] Test process: Perform attenuated oscillation voltage test on each defective sample and normal sample. Record the oscillation voltage waveform and inductance value of each sample under various oscillation voltages (such as different amplitudes, different frequencies, etc.). Ensure that the sample is in a stable state during the test to avoid external interference affecting the test results.

[0079] Data marking: Mark the oscillation voltage waveform and inductance value of the defective sample as defective test data. Mark the oscillation voltage waveform and inductance value of the normal sample as normal test data.

[0080] Data collation: collate the test data to ensure that the data format is uniform, clear and easy to understand. Number each data point to facilitate subsequent data analysis and processing.

[0081] Data preservation: Defect test data and normal test data are saved in dedicated data sets respectively. The data set should contain information such as the original data record, processing process, and analysis results for subsequent research and application.

[0082] Data quality control: Perform quality control on data sets to ensure data accuracy, completeness, and consistency. Abnormal data can be processed by deletion, correction, or retesting.

[0083] The dataset is used to train and validate the LSTM model and random forest model.

[0084] The LSTM model is trained using the training set, and the loss function is minimized by iteratively updating the weights and biases of the model. During the training process, the validation set can be used to monitor the performance of the model so that strategies such as early stopping or adjusting the learning rate can be used to prevent overfitting.

[0085] In the model training phase, we use a large amount of historical fault data and normal data to train the random forest model. These data include inductance value difference, waveform feature vector and corresponding fault diagnosis results. Through training, the random forest model can learn the mapping relationship between inductance value difference and waveform features and fault diagnosis results.

[0086] In some embodiments, the dry-type air-core reactor fault detection system may include a plurality of functional modules composed of computer program segments. The computer program of each program segment in the dry-type air-core reactor fault detection system may be stored in a memory of a computer device and executed by at least one processor to execute (see Figure 1 Description) Dry-type air-core reactor fault detection function.

[0087] In this embodiment, the dry-type air-core reactor fault detection system can be divided into multiple functional modules according to the functions it performs, such as Figure 3 As shown. The functional modules of the system 400 may include: a data acquisition module 410, a standard acquisition module 420, a difference calculation module 430, a feature advance module 340 and a result diagnosis module 350. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0088] A data acquisition module is used to perform an attenuated oscillation voltage test on the target dry-type air-core reactor and obtain an oscillation voltage waveform and an inductance value generated by the target dry-type air-core reactor during the test; A standard acquisition module is used to acquire a pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value; A difference calculation module, used for calculating a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform; A feature extraction module is used to input the peak difference sequence and the zero-crossing time difference sequence into a pre-trained LSTM model to obtain waveform features; The result diagnosis module is used to input the difference between the inductance value and the standard inductance value and the waveform characteristics into a pre-trained random forest model to obtain a fault diagnosis result.

[0089] Optionally, as an embodiment of the present invention, the standard acquisition module includes: The standard acquisition unit is used to retrieve the corresponding standard voltage waveform and standard inductance value from a database according to the model information of the target dry-type air-core reactor, wherein the database stores the standard voltage waveforms and standard inductance values ​​of various models of dry-type air-core reactors.

[0090] Optionally, as an embodiment of the present invention, the difference calculation module includes: The difference calculation unit is used to calculate the peak difference and zero-crossing time difference of the corresponding cycles of the oscillating voltage waveform and the standard voltage waveform, and sort the peak difference and zero-crossing time difference in order of cycle to obtain the peak difference sequence and the zero-crossing time difference sequence.

[0091] Optionally, as an embodiment of the present invention, the system further includes: The first collection module is used to collect dry-type air-core reactors with tiny defects as defective samples, perform attenuated oscillation voltage tests on the defective samples, and obtain oscillation voltage waveforms and inductance values ​​of the defective samples under various oscillation voltages; The second collection module is used to collect normal dry-type air-core reactors as normal samples, perform attenuated oscillation voltage tests on the normal samples, and obtain oscillation voltage waveforms and inductance values ​​of the normal samples under various oscillation voltages; A data marking module, used to mark the oscillation voltage waveform and inductance value of the defective sample as defective test data and save them in a data set, and mark the oscillation voltage waveform and inductance value of the normal sample under various oscillation voltages as normal test data and save them in a data set; The training execution module is used to train and verify the LSTM model and random forest model using the dataset.

[0092] Figure 4A schematic diagram of the structure of a terminal 400 provided in an embodiment of the present invention. The terminal 400 can be used to execute the dry-type air-core reactor fault detection method provided in an embodiment of the present invention.

[0093] The terminal 400 may include: a processor 410, a memory 420 and a communication unit 430. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0094] The memory 420 can be used to store the execution instructions of the processor 410, and the memory 420 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 420 are executed by the processor 410, the terminal 400 can perform some or all of the steps in the following method embodiments.

[0095] The processor 410 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 420, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 410 can include only a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0096] The communication unit 430 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0097] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0098] Therefore, the present invention extracts the difference parameters between the oscillating voltage waveform and the standard voltage waveform, uses the LSTM model to extract the difference timing features from the difference parameters, and uses the random forest model to accurately capture slight anomalies based on the inductance difference and the difference timing features, thereby greatly improving the accuracy of dry-type air-core reactor fault detection. The technical effects that can be achieved by this embodiment can be found in the description above and will not be repeated here.

[0099] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0100] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0101] 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 schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0102] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0104] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A dry-type air-core reactor fault detection method, characterized in that: include: Performing a damped oscillation voltage test on the target dry-type air-core reactor, and obtaining an oscillation voltage waveform and an inductance value generated by the target dry-type air-core reactor during the test; Obtaining a pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value; Calculating a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform; Inputting the peak difference sequence and the zero-crossing time difference sequence into a pre-trained LSTM model to obtain waveform features; The difference between the inductance value and the standard inductance value and the waveform feature are input into a pre-trained random forest model to obtain a fault diagnosis result.

2. The method according to claim 1, characterized in that: Obtain the pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value, including: According to the model information of the target dry-type air-core reactor, the corresponding standard voltage waveform and standard inductance value are retrieved from a database, wherein the database stores the standard voltage waveforms and standard inductance values ​​of various models of dry-type air-core reactors.

3. The method according to claim 1, characterized in that Calculating a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform, including: The peak difference and zero-crossing time difference of the corresponding periods of the oscillating voltage waveform and the standard voltage waveform are calculated, and the peak difference and zero-crossing time difference are sorted in order of period to obtain the peak difference sequence and the zero-crossing time difference sequence.

4. The method according to claim 1, characterized in that: The method further comprises: Dry-type air-core reactors with tiny defects are collected as defective samples, and attenuated oscillation voltage tests are performed on the defective samples to obtain oscillation voltage waveforms and inductance values ​​of the defective samples under various oscillation voltages; Normal dry-type air-core reactors are collected as normal samples, and attenuated oscillation voltage tests are performed on the normal samples to obtain oscillation voltage waveforms and inductance values ​​of the normal samples under various oscillation voltages; Mark the oscillation voltage waveform and inductance value of the defective sample as defective test data and save them in the data set, and mark the oscillation voltage waveform and inductance value of the normal sample under various oscillation voltages as normal test data and save them in the data set; The dataset is used to train and validate the LSTM model and random forest model.

5. A dry-type air-core reactor fault detection system, characterized in that: include: A data acquisition module is used to perform an attenuated oscillation voltage test on the target dry-type air-core reactor and obtain an oscillation voltage waveform and an inductance value generated by the target dry-type air-core reactor during the test; A standard acquisition module is used to acquire a pre-stored target dry-type air-core reactor standard voltage waveform and standard inductance value; A difference calculation module, used for calculating a peak difference sequence and a zero-crossing time difference sequence between the oscillating voltage waveform and the standard voltage waveform; A feature extraction module is used to input the peak difference sequence and the zero-crossing time difference sequence into a pre-trained LSTM model to obtain waveform features; The result diagnosis module is used to input the difference between the inductance value and the standard inductance value and the waveform characteristics into a pre-trained random forest model to obtain a fault diagnosis result.

6. The system according to claim 5, characterized in that The standard acquisition module includes: The standard acquisition unit is used to retrieve the corresponding standard voltage waveform and standard inductance value from a database according to the model information of the target dry-type air-core reactor, wherein the database stores the standard voltage waveforms and standard inductance values ​​of various models of dry-type air-core reactors.

7. The system according to claim 5, characterized in that The difference calculation module comprises: The difference calculation unit is used to calculate the peak difference and zero-crossing time difference of the corresponding cycles of the oscillating voltage waveform and the standard voltage waveform, and sort the peak difference and zero-crossing time difference in order of cycle to obtain the peak difference sequence and the zero-crossing time difference sequence.

8. The system according to claim 5, characterized in that The system further comprises: The first collection module is used to collect dry-type air-core reactors with tiny defects as defective samples, perform attenuated oscillation voltage tests on the defective samples, and obtain oscillation voltage waveforms and inductance values ​​of the defective samples under various oscillation voltages; The second collection module is used to collect normal dry-type air-core reactors as normal samples, perform attenuated oscillation voltage tests on the normal samples, and obtain oscillation voltage waveforms and inductance values ​​of the normal samples under various oscillation voltages; A data marking module, used to mark the oscillation voltage waveform and inductance value of the defective sample as defective test data and save them in a data set, and mark the oscillation voltage waveform and inductance value of the normal sample under various oscillation voltages as normal test data and save them in a data set; The training execution module is used to train and verify the LSTM model and random forest model using the dataset.

9. A terminal, characterized in that: include: A memory, used for storing a dry-type air-core reactor fault detection program; A processor is used to implement the steps of the dry-type air-core reactor fault detection method as described in any one of claims 1 to 4 when executing the dry-type air-core reactor fault detection program.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a dry-type air-core reactor fault detection program, which, when executed by a processor, implements the steps of the dry-type air-core reactor fault detection method according to any one of claims 1 to 4.

Citation Information

Patent Citations

  • Method and system for identifying insulation defect of dry-type air-core reactor and terminal equipment

    CN111610420A

  • BP neural network-based TCR (thyristor controlled reactor) fault protection judgment method for SVC (static var compensator)

    CN118312893A

  • Transformer fault determination method and device and transformer fault detection system

    CN118445731A

  • Online monitoring method for turn-to-turn short circuit fault of dry-type air-core series reactor

    CN118534361A

  • Reactor turn-to-turn short circuit fault diagnosis method and system and medium

    CN118837785A

Cited By

  • Inductance measurement system based on deformation correlation model

    CN120970472A