Correction phase synchronization method, system and device based on GIS partial discharge and medium
By collecting partial discharge signal and background noise data in GIS equipment, and using a phase offset prediction model and automatic correction algorithm, combined with the high-frequency resonance principle, the phase of the partial discharge signal is dynamically adjusted, which solves the problem of poor acquisition and processing effect of partial discharge signal under low load and complex environment, and achieves higher precision phase synchronization and fault diagnosis.
Patent Information
- Application Number
- CN202411466850.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-21
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing partial discharge detection systems suffer from poor partial discharge signal acquisition and processing performance under low load conditions and complex environments, especially with a decrease in phase synchronization accuracy.
A GIS-based phase synchronization correction method is adopted. By acquiring the original data of the partial discharge signal and background noise data, the phase of the partial discharge signal is dynamically adjusted using a phase offset prediction model and an automatic correction algorithm, combined with the high-frequency resonance principle. Signal feature comparison is then performed to optimize the phase synchronization model.
It improves the acquisition and processing of partial discharge signals, ensures the accuracy and reliability of phase synchronization under low load and complex environments, and provides a more accurate basis for fault diagnosis.
Smart Images

Figure CN119025829A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of electrical engineering technology, and in particular to a method, system, device and medium for correcting phase synchronization based on GIS partial discharge. Background Art
[0002] Gas insulated switchgear (GIS) plays a key role in the power system. Its operating status directly affects the safety and stability of the power grid. Partial discharge monitoring is an important means to ensure the safe operation of GIS equipment. By monitoring the phase information of partial discharge signals, potential faults of the equipment can be discovered in time.
[0003] Existing partial discharge detection systems usually adopt a fixed phase reference method and an industrial frequency phase synchronization method. The fixed phase reference method aligns the phase of the partial discharge signal with the reference point by setting a fixed phase reference point (such as the peak or trough of the voltage waveform) in the GIS system; however, this method is easily affected by changes in the system operating state (such as voltage fluctuations, frequency offsets), resulting in a decrease in phase synchronization accuracy; the industrial frequency phase synchronization method collects partial discharge signals through sensors and performs phase analysis; however, under low load conditions, the current is insufficient to support the normal collection of industrial frequency phase synchronization, and synchronization problems between multiple sensors will also affect the accuracy of the phase information. Therefore, there is a defect that the collection and processing effect of partial discharge signals of GIS equipment is low, and there is room for improvement. Summary of the invention
[0004] In order to accurately collect and process the phase information of partial discharge signals under low load conditions and complex environments, and improve the collection and processing effects of partial discharge signals of GIS equipment, the present application provides a corrected phase synchronization method, system, equipment and medium based on GIS partial discharge.
[0005] In the first aspect, the invention objective of the present application is achieved by adopting the following technical solutions: The modified phase synchronization method based on GIS partial discharge includes: Collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment, and determine the corresponding reference phase benchmark; Preprocessing the partial discharge signal, and extracting phase information and spectrum characteristics of the preprocessed partial discharge signal; In a preset phase offset prediction model, the phase offset under different environmental conditions is predicted based on the background noise data and the reference phase benchmark to obtain a corresponding phase offset prediction value; According to the phase offset prediction value, an automatic correction algorithm is used to perform phase synchronization processing on the partial discharge signal to obtain corrected phase synchronization data; the automatic correction algorithm combines the high-frequency resonance principle to dynamically adjust the phase of the partial discharge signal at each preset detection point; The corrected phase synchronization data is compared with the corresponding reference phase benchmark in terms of signal characteristics to obtain a characteristic comparison result; and the preset phase offset prediction model is optimized according to the characteristic comparison result.
[0006] In a preferred example of the present application: the steps of establishing the phase offset prediction model include: Obtain historical partial discharge data and synchronous reference data of several preset detection points in GIS equipment, and classify the historical partial discharge data and synchronous reference data according to different load conditions and environmental parameters; Extract key features that affect phase shift from classified historical partial discharge data and synchronous reference data to obtain key feature information; Using machine learning algorithms, the phase offset prediction model is constructed and trained with the extracted key feature information as input and the phase offset as output.
[0007] By adopting the above technical solution, the preset detection points are used to install sensors to collect partial discharge signals and synchronous reference signals, and the predicted detection points can represent the electrical characteristics and environmental conditions of different areas inside the GIS equipment; the historical partial discharge data and synchronous reference data are the partial discharge data and the corresponding synchronous reference data (such as voltage waveform, current waveform, etc.) collected from the preset detection points and recorded in the past period of time. The historical partial discharge data and synchronous reference data are used to analyze the relationship between phase shift and various factors; the load condition classification is to divide the historical data into three categories: low load, medium load and high load according to the current and voltage conditions of the GIS equipment; the environmental parameter classification is to further subdivide the historical data into three categories according to the environmental temperature, humidity, air pressure and other parameters. Different subcategories ensure that the data under each category has similar background conditions; through data classification, it is ensured that the data under each detailed category has similar background conditions, which helps to improve the training effect and prediction accuracy of the model; through feature selection from the classified historical partial discharge data and synchronous reference data, the features related to the phase shift are screened out, the data interference of irrelevant features is reduced, and the training efficiency and prediction accuracy of the model are improved; further, when selecting the model, a suitable machine learning algorithm can be selected, such as support vector machine SVM, random forest RF, neural network NN, etc.) to build a phase shift prediction model. By selecting a suitable machine learning algorithm, it is ensured that the model can effectively capture the law of phase shift and improve the prediction accuracy of the model.
[0008] In a preferred example of the present application, the feature comparison result includes a mass analysis comparison result; the signal feature comparison of the corrected phase synchronization data with the corresponding reference phase reference is performed to obtain a feature comparison result, including: Calculating the signal-to-noise ratio of the modified phase synchronization data and the corresponding reference phase reference in each frequency band, and evaluating the signal clarity difference value between the modified phase synchronization data and the corresponding synchronization reference signal based on the signal-to-noise ratio; According to the signal-to-noise ratio result, the proportion of speech components corresponding to each time-frequency point is calculated, and the distortion degree between the corrected phase synchronization data and the current speech and the preset clear speech of the corresponding reference phase benchmark is analyzed one by one to obtain a single-point speech distortion value; The single-point speech distortion values of each time-frequency point are integrated, and the comprehensive speech distortion value of the entire corrected phase synchronization data is estimated to obtain the quality analysis comparison results of the partial discharge signal and the specific value of the phase error.
[0009] By adopting the above technical scheme, the proportion of speech components is used to evaluate the degree of signal distortion; the comprehensive speech distortion value is the comprehensive distortion value of the entire corrected phase synchronization data; the present invention evaluates the clarity of the signal by calculating the signal-to-noise ratio, ensures the quality of the signal in different frequency bands, and provides basic data for subsequent feature comparison; by calculating the proportion of speech components and the degree of distortion, the signal quality of each time-frequency point is refined, and accurate data is provided for the subsequent estimation of the comprehensive distortion value; by the integrated calculation of the comprehensive speech distortion value, the accuracy of the specific numerical value of the phase error is ensured, and a reliable basis is provided for subsequent signal processing and fault diagnosis.
[0010] In a preferred example of the present application, the collecting of the original data and background noise data of the partial discharge signals of several preset detection points in the GIS device and determining the corresponding reference phase benchmark includes: According to the structural characteristics of the GIS device, the interior of the GIS device is divided into multiple monitoring areas, and the monitoring areas are associated with area identifiers; The local discharge signal and background noise signal are collected by sensors installed in different monitoring areas of the GIS equipment to obtain the original data of the local discharge signal and background noise data of each monitoring area; Based on the regional identification, each monitoring area is associated with an independent phase synchronization reference, the phase information of the partial discharge signal in each monitoring area is analyzed, and compared with the phase synchronization reference of each monitoring area to calculate the phase error; According to the magnitude of the phase error and the environmental impact characteristics of the GIS equipment, the phase correction parameters required for each monitoring area are calculated; According to the calculated phase correction parameters, a phase correction instruction is sent to each monitoring area, and the phase synchronization benchmark of the corresponding monitoring area is optimized to determine the corresponding reference phase benchmark.
[0011] By adopting the above technical scheme, the original data of the partial discharge signal refers to the partial discharge signal data collected by the sensor in the monitoring area; the phase synchronization benchmark refers to the independent phase synchronization standard set for each monitoring area, which is used to calibrate the phase information of the partial discharge signal; through reasonable area division, the data independence and traceability of each monitoring area are ensured; the present invention calculates the phase error of each monitoring area through sensor installation, data collection and phase analysis, so as to provide accurate error data for subsequent phase correction, and through error analysis and correction parameter calculation, ensures the accuracy and rationality of the phase correction parameters of each monitoring area, provides a scientific basis for subsequent phase optimization, and sends a phase correction instruction so as to send the phase correction quality to each monitoring area through the control system, and the instruction content includes the phase correction parameter and the execution time, so as to improve the phase synchronization accuracy of the partial discharge signal.
[0012] In a preferred example of the present application: after the phase synchronization processing of the partial discharge signal is performed using an automatic correction algorithm according to the phase offset prediction value and the corrected phase synchronization data is obtained, the method further includes: Acquire partition phase detection information, compare the partition phase detection information with the phase value of the phase synchronization reference of the corresponding monitoring area, and obtain a partition difference value; The partition difference value is compared with a preset phase synchronization threshold, and if the partition difference value exceeds the preset phase synchronization threshold, a partition phase error detection instruction is triggered; and adjustment parameter information is obtained according to the partition phase error detection instruction; An adjustment instruction is triggered according to the adjustment parameter information.
[0013] In a preferred example of the present application, the step of obtaining adjustment parameter information according to the partition phase error detection instruction specifically includes: According to the partition phase error detection instruction, phase error information of each monitoring area is obtained; When it is detected that the phase error information meets the preset correction condition, a partition phase change information collection instruction is triggered; Obtain phase change information and sensor distribution information of each monitoring area, and obtain distance information between each sensor and the partial discharge source in each monitoring area according to the sensor distribution information; The phase adjustment parameter information of each monitoring area is calculated by combining the phase change information and the distance information, as well as the electrical characteristics of the GIS equipment and the preset phase synchronization standard.
[0014] By adopting the above technical solution, the phase error information refers to the difference between the phase value of the partition phase detection information and the phase synchronization reference, including the magnitude and direction of the phase error; the preset correction condition refers to a preset upper limit value of the phase error, which is used to determine whether the phase error needs to be corrected; the phase change information refers to the phase change information of the partial discharge signal collected in real time in the sensor in each monitoring area, including the speed and amplitude of the phase change; the sensor distribution information refers to the location and quantity information of the sensor in each monitoring area; the phase adjustment parameter information includes the phase adjustment amount, the gain adjustment, etc.; the present invention detects and records the phase error information in real time to facilitate timely discovery and processing of phase synchronization problems, and ensures that the collection of phase change information is triggered in time when the phase error exceeds the corresponding threshold through phase error and correction condition judgment and instruction generation, and ensures that the distance information between each sensor and the partial discharge source can be accurately obtained through phase change detection and sensor distribution recording, so as to provide accurate parameter support for subsequent phase adjustment; finally, through data integration and parameter calculation, the accuracy and rationality of the calculated phase adjustment parameter information are ensured, a scientific basis is provided for subsequent phase adjustment, and the phase synchronization accuracy of the partial discharge signal is improved.
[0015] In a preferred example of the present application: the method further includes: Environmental sensors are used to collect environmental information such as temperature, humidity and air pressure in real time to obtain environmental parameters; According to the environmental parameters, dynamically compensating the phase information of the partial discharge signal by a preset environmental compensation algorithm; A self-calibration module is added to each sensor of the GIS equipment to perform self-calibration operations on the sensor according to the specified calibration cycle.
[0016] In the second aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A modified phase synchronization system based on GIS partial discharge is used to execute the modified phase synchronization method based on GIS partial discharge as described above, and the system comprises: The phase reference determination module is used to collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment and determine the corresponding reference phase reference; A signal preprocessing module, used to preprocess the partial discharge signal and extract phase information and spectrum characteristics of the preprocessed partial discharge signal; A phase offset prediction module, used to predict the phase offset under different environmental conditions based on the background noise data and the reference phase benchmark in a preset phase offset prediction model, and obtain a corresponding phase offset prediction value; An automatic correction synchronization module is used to perform phase synchronization processing on the partial discharge signal using an automatic correction algorithm according to the phase offset prediction value to obtain corrected phase synchronization data; the automatic correction algorithm dynamically adjusts the phase of the partial discharge signal at each preset detection point in combination with the high-frequency resonance principle; The correction result tracking module is used to compare the signal characteristics of the corrected phase synchronization data with the corresponding reference phase benchmark to obtain a characteristic comparison result; and optimize the preset phase offset prediction model according to the characteristic comparison result.
[0017] By adopting the above technical solution, In the third aspect, the invention objective of this application is achieved by adopting the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned modified phase synchronization method based on GIS partial discharge when executing the computer program.
[0018] In a fourth aspect, the invention objective of the present application is achieved by adopting the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned modified phase synchronization method based on GIS partial discharge.
[0019] In summary, the present application includes at least one of the following beneficial technical effects: 1. By acquiring and analyzing background noise data and original data, the signal characteristics of partial discharge signals under different low-load conditions and complex environments are considered, which is conducive to improving the accuracy of phase correction in the future; a number of preset detection points should cover the key areas of GIS equipment in actual application to comprehensively detect the partial discharge activities of GIS equipment; the reference phase benchmark is used to calibrate and synchronize the partial discharge signals collected by different preset detection points, and the phase offset of the partial discharge signal under different environmental conditions (including low-load conditions) can be predicted through the preset phase offset prediction model, and then the phase of the partial discharge signal is dynamically adjusted through the automatic correction algorithm. The automatic correction algorithm uses the high-frequency resonance characteristics to accurately adjust the signal phase. The present invention is based on the original partial discharge signal. The initial data and background noise data are used to determine whether it is a low-load condition, and the corresponding reference phase benchmark can be determined for low-load conditions and / or complex environments, and pre-processing operations such as denoising and filtering are performed based on the pre-processed partial discharge signal to improve the signal quality, and the phase of the partial discharge signal of each preset detection point is dynamically adjusted, thereby improving the collection and processing effects of the partial discharge signal of the GIS equipment; further, the signal characteristics of the corrected phase synchronization data are compared with the corresponding synchronization reference signal to obtain the characteristic comparison result; finally, according to the characteristic comparison result, it is determined whether the preset phase offset prediction model needs to be optimized to further improve the prediction accuracy of the phase offset prediction model, and indirectly improve the phase synchronization processing effect; 2. The phase synchronization benchmark refers to an independent phase synchronization standard set for each monitoring area, which is used to calibrate the phase information of the partial discharge signal; the partition phase error detection instruction refers to an instruction for detecting and adjusting the phase error that is triggered when the partition difference value exceeds the phase synchronization threshold; the present invention obtains the partition phase detection information to monitor the phase synchronization of each monitoring area in real time through partition detection and benchmark comparison; and then presets a phase synchronization threshold for each monitoring area one by one to determine whether the phase synchronization error is within an acceptable range; so as to timely discover the monitoring area with a large phase synchronization error through threshold comparison, and then ensure the accuracy and rationality of the adjustment parameters through error detection and parameter calculation; 3. Environmental parameters refer to environmental factors that affect the phase of partial discharge signals; environmental compensation algorithms refer to algorithms used to eliminate the influence of environmental parameters on the phase of partial discharge signals, such as linear compensation, polynomial compensation or neural network compensation; compensation parameters refer to parameters calculated based on environmental parameters for adjusting the phase of partial discharge signals; self-calibration module refers to a module installed in each sensor for automatically calibrating sensor performance. In actual applications, the self-calibration module needs to include a calibration circuit and a control unit; the calibration content of the self-calibration operation includes the sensitivity, response characteristics and zero drift of the sensor; the present invention ensures that the environmental parameters that affect the partial discharge signal can be obtained in real time through the collection of environmental information, so as to solve the environmental compensation parameters and perform environmental compensation through a suitable environmental compensation algorithm, which is beneficial to eliminate the influence of environmental parameters on the phase of partial discharge signals and improve the phase synchronization accuracy and reliability of partial discharge signals. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] Figure 1 It is a flow chart of a method for correcting phase synchronization based on GIS partial discharge in one embodiment of the present application; Figure 2 It is a flowchart of step S5 in the phase synchronization method based on GIS partial discharge correction in one embodiment of the present application; Figure 3 It is a flowchart of step S1 in the phase synchronization method based on GIS partial discharge correction in one embodiment of the present application; Figure 4 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION
[0021] The present application is further described in detail below in conjunction with the accompanying drawings.
[0022] In one embodiment, if Figure 1 As shown, the present application discloses a method for correcting phase synchronization based on GIS partial discharge, which specifically includes the following steps: S1: Collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment, and determine the corresponding reference phase benchmark.
[0023] In this embodiment, a plurality of sensors are installed at key locations of different monitoring areas of the GIS equipment to collect raw data of partial discharge signals and background noise data in real time.
[0024] Specifically, the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment are collected in real time through sensors; the reference phase benchmark refers to the phase synchronization standard set for each detection point, which is used to calibrate the phase information of the partial discharge signal.
[0025] S2: Preprocess the partial discharge signal and extract phase information and spectrum characteristics of the preprocessed partial discharge signal.
[0026] In this embodiment, the collected partial discharge signal is preprocessed, including noise removal, missing value filling and standardization. Phase information extraction is to extract phase information from the preprocessed partial discharge signal, including phase angle and phase difference, such as using Fourier transform (FFT) or Hilbert transform to extract phase information. Spectral feature extraction is to perform spectral analysis on the preprocessed partial discharge signal to extract spectral features, such as amplitude, frequency and bandwidth.
[0027] S3: In a preset phase offset prediction model, the phase offset under different environmental conditions is predicted based on the background noise data and the reference phase benchmark to obtain a corresponding phase offset prediction value.
[0028] In this embodiment, the relationship between the environmental parameters and the phase offset is constructed in the phase offset prediction model. The model predicts the phase offset under different environmental conditions based on the input data to obtain the predicted value of the phase offset.
[0029] Specifically, the steps of establishing the phase offset prediction model include: 1) Obtain the historical partial discharge data and synchronous reference data of several preset detection points in the GIS equipment, and classify the historical partial discharge data and synchronous reference data according to different load conditions and environmental parameters.
[0030] Specifically, historical partial discharge data refers to the partial discharge signal data of GIS equipment collected by sensors in different time periods and under different load conditions; synchronous reference data refers to the reference signal data collected synchronously with the partial discharge signal, which is used to calibrate the phase information of the partial discharge signal; data classification is to classify historical partial discharge data and synchronous reference data according to different load conditions (such as low load, medium load, high load) and environmental parameters (such as temperature, humidity, air pressure, etc.) to ensure that the data in each category has similar background conditions; the classified data is preprocessed, including noise removal, missing value filling and standardization.
[0031] 2) Extract key features that affect phase shift from the classified historical partial discharge data and synchronous reference data to obtain key feature information.
[0032] Specifically, feature selection is to select features related to phase shift from the classified historical partial discharge data and synchronous reference data, such as the amplitude, frequency, phase, duration, ambient temperature, humidity, etc. of the partial discharge signal; first use the feature extraction algorithm (such as principal component analysis PCA, independent component analysis ICA, etc.) to extract key feature information from the selected features, and then verify the validity and reliability of the extracted key feature information through cross-validation and correlation analysis.
[0033] 3) Using machine learning algorithms, with the extracted key feature information as input and the phase offset as output, a phase offset prediction model is constructed and trained.
[0034] S4: According to the predicted value of the phase offset, the automatic correction algorithm is used to perform phase synchronization processing on the partial discharge signal to obtain corrected phase synchronization data; the automatic correction algorithm is combined with the high-frequency resonance principle to dynamically adjust the phase of the partial discharge signal of each preset detection point.
[0035] In this embodiment, the high-frequency resonance principle refers to the use of the resonance characteristics of high-frequency signals at specific frequencies to achieve precise signal adjustment. In the phase synchronization of partial discharge signals, high-frequency resonance can be used to amplify tiny phase changes, thereby achieving more precise phase adjustment; through resonance amplification, tiny phase numbers are enhanced, so that partial discharge signals under low load conditions can still be collected and processed with high accuracy; then the resonantly amplified signal is used to achieve precise phase locking and adjustment.
[0036] Specifically, the automatic correction algorithm combines the high-frequency resonance principle and mainly includes the following steps: 1) Phase offset prediction value input: The phase offset prediction value obtained from the phase offset prediction model is used as input to obtain the initial phase information of the current partial discharge signal.
[0037] 2) High-frequency resonance signal generation: Select a suitable resonance frequency , so that it can effectively amplify tiny phase changes; then perform signal modulation: the mixer is used to modulate the partial discharge signal to the resonant frequency On the top, a high-frequency resonant signal is generated, and the formula is as follows: in, It is a partial discharge signal. It is the modulated high frequency resonant signal.
[0038] 3) Resonant amplification: First design a resonant amplifier that The resonant amplifier has a higher gain at the position where the transfer function can be expressed as: Among them, Q is the quality factor, which determines the width of the resonance peak.
[0039] 4) Signal amplification, the modulated high-frequency resonant signal Input into the resonant amplifier to obtain the amplified signal : .
[0040] 5) Phase detection, using a phase detector to detect the amplified signal The phase information is used to calculate the phase error between the current phase and the reference phase. .
[0041] 6) Automatic correction algorithm: based on phase error , use the automatic correction algorithm to dynamically adjust the phase of the partial discharge signal; this embodiment adopts the PID control algorithm, where the phase adjustment formula of the automatic correction algorithm is expressed as: in, is the corrected phase, is the current phase, , , They are the gains of the proportional, integral, and differential terms respectively.
[0042] 7) Phase synchronization data generation: The adjusted phase Applied to partial discharge signals to generate phase-synchronized data. Reconstruct the final phase synchronization data: Where A is the amplitude of the signal and f is the frequency of the signal.
[0043] S5: performing signal feature comparison between the corrected phase synchronization data and the corresponding reference phase benchmark to obtain feature comparison results; and optimizing a preset phase offset prediction model according to the feature comparison results.
[0044] Specifically, signal feature comparison includes comparison of phase information and spectrum features; correlation coefficient, mean square error and other indicators can be used for feature comparison. Model optimization is to optimize the preset phase shift prediction model based on the feature comparison results, including adjusting model parameters and improving model structure, and can use methods such as cross-validation and grid search to optimize model parameters; the present invention can effectively monitor and adjust the phase synchronization of partial discharge signals at multiple detection points in GIS equipment, ensure accurate prediction and correction of the phase shift of partial discharge signals under different load conditions and environmental parameters, and improve the accuracy and reliability of partial discharge monitoring of GIS equipment.
[0045] In one embodiment, if Figure 2As shown, in step S5, the feature comparison result includes a mass analysis comparison result; the corrected phase synchronization data is compared with the corresponding reference phase reference for signal feature, and the feature comparison result is obtained, including: S51: Calculate the signal-to-noise ratio of the modified phase synchronization data and the corresponding reference phase reference in each frequency band, and evaluate the signal clarity difference value between the modified phase synchronization data and the corresponding synchronization reference signal based on the signal-to-noise ratio.
[0046] In this embodiment, the corrected phase synchronization data and the reference phase reference are divided into multiple frequency bands, such as 0-1kHz, 1-2kHz, 2-3kHz, etc.; the signal-to-noise ratio refers to the ratio of signal power to noise power, which is used to evaluate the clarity and quality of the signal; the higher the signal-to-noise ratio, the clearer the signal; the clarity of the signal is evaluated by calculating the signal-to-noise ratio.
[0047] S52: According to the signal-to-noise ratio result, the proportion of the speech component corresponding to each time-frequency point is calculated, and the distortion degree between the corrected phase synchronization data and the corresponding reference phase benchmark and the preset clear speech is analyzed one by one to obtain the single-point speech distortion value.
[0048] In this embodiment, the speech component ratio refers to the proportion of the speech component in the signal to the total signal at each time-frequency point, which is used to evaluate the degree of distortion of the signal; the single-point speech distortion value refers to the degree of distortion between the corrected phase synchronization data and the reference phase reference at each time-frequency point.
[0049] Specifically, the single-point speech distortion value is the absolute value of the difference between the current speech of the reference phase reference and the preset clear speech.
[0050] S53: Integrate the single-point speech distortion values of each time-frequency point, estimate the comprehensive speech distortion value of the entire corrected phase synchronization data, and obtain the quality analysis comparison result of the partial discharge signal and the specific value of the phase error.
[0051] In this embodiment, the comprehensive speech distortion value refers to the comprehensive distortion value of the entire corrected phase synchronization data obtained by integrating the single-point speech distortion values of each time-frequency point; the specific value of the phase error is the sum of the product of the comprehensive speech distortion value and the reference phase reference.
[0052] Furthermore, the estimation step of the comprehensive speech distortion value includes distortion value integration, comprehensive distortion value calculation, and quality comparison, wherein distortion value integration refers to integrating the single-point speech distortion values of each time-frequency point to form a comprehensive distortion value matrix; comprehensive distortion value calculation is based on the distortion value matrix, estimating the comprehensive speech distortion value of the entire corrected phase synchronization data, the comprehensive speech distortion value is the sum of the distortion values of all time-frequency points and the average of the total number of time-frequency points; quality analysis comparison is based on the comprehensive speech distortion value to obtain the quality analysis comparison result of the local discharge signal and the specific value of the phase error.
[0053] In one embodiment, if Figure 3 As shown, in step S1, the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment are collected, and the corresponding reference phase benchmark is determined, including: S11: Based on the structural characteristics of the GIS device, the interior of the GIS device is divided into multiple monitoring areas, and the monitoring areas are associated with area identifiers.
[0054] Specifically, the monitoring area refers to multiple independent monitoring areas divided according to the structural characteristics of the GIS equipment; the area identifier refers to a unique identifier of each monitoring area.
[0055] S12: collecting partial discharge signals and background noise signals according to sensors installed in different monitoring areas of the GIS equipment, and obtaining original data of partial discharge signals and background noise data of each monitoring area.
[0056] Specifically, sensors are installed at key locations in each monitoring area to collect partial discharge signals and background noise signals in real time, and the collected data are preprocessed, including noise removal, missing value filling and standardization, to obtain the original data of partial discharge signals and background noise data of each monitoring area.
[0057] S13: Associating each monitoring area with an independent phase synchronization reference based on the area identifier, analyzing the phase information of the partial discharge signal in each monitoring area, comparing it with the phase synchronization reference of each monitoring area, and calculating the phase error.
[0058] In this embodiment, an independent phase synchronization reference is set for each monitoring area, and the phase synchronization reference may be a preset standard phase value. The phase information of the local discharge signal in each monitoring area is analyzed and compared with the phase synchronization reference of each monitoring area to calculate the phase error.
[0059] S14: Calculate the phase correction parameters required for each monitoring area according to the magnitude of the phase error and the environmental impact characteristics of the GIS equipment.
[0060] In this embodiment, according to the size of the phase error, the cause of the error is analyzed, and the environmental impact characteristics of the GIS equipment, such as temperature and humidity, are considered; then, based on the phase error and environmental impact characteristics, the phase correction parameters required for each monitoring area are calculated.
[0061] S15: sending a phase correction instruction to each monitoring area according to the calculated phase correction parameter, optimizing the phase synchronization reference of the corresponding monitoring area to determine the corresponding reference phase reference.
[0062] Specifically, the phase correction instruction refers to an instruction including a phase correction parameter and an execution time, and is used to optimize the phase synchronization benchmark of the monitoring area.
[0063] In one embodiment, after step S4, the phase synchronization correction method based on GIS partial discharge further includes: S41: Obtain partition phase detection information, compare the partition phase detection information with the phase value of the phase synchronization reference of the corresponding monitoring area, and obtain the partition difference value.
[0064] In this embodiment, the partition phase detection information is compared with the phase value of the phase synchronization reference of the corresponding monitoring area to calculate the partition difference value.
[0065] S42: Compare the partition difference value with the preset phase synchronization threshold. If the partition difference value exceeds the preset phase synchronization threshold, trigger a partition phase error detection instruction; and obtain adjustment parameter information according to the partition phase error detection instruction.
[0066] Specifically, the phase synchronization threshold refers to a preset upper limit value of the phase synchronization error, which is used to determine whether the phase synchronization error is within an acceptable range; the partition phase error detection instruction refers to an instruction for detecting and adjusting the phase error that is triggered when the partition difference value exceeds the phase synchronization threshold; the adjustment parameter information refers to the parameters for adjusting the phase synchronization benchmark calculated based on the partition difference value and the error detection result.
[0067] S43: triggering an adjustment instruction according to the adjustment parameter information.
[0068] Specifically, the adjustment instruction refers to an instruction including adjustment parameters and execution time, which is used to optimize the phase synchronization benchmark of the monitoring area; the adjustment instruction is sent to the corresponding monitoring area through the control system, and the instruction content includes the adjustment parameters and execution time.
[0069] In one embodiment, in step S42, obtaining adjustment parameter information according to the partition phase error detection instruction specifically includes: S421: According to the partition phase error detection instruction, the phase error information of each monitoring area is obtained.
[0070] In this embodiment, the phase error information refers to the difference between the partition phase detection information and the phase value of the phase synchronization reference; according to the partition phase error detection instruction, the phase error information of each monitoring area is detected in real time, including the size and direction of the phase error.
[0071] S422: When it is detected that the phase error information meets the preset correction condition, a partition phase change information collection instruction is triggered.
[0072] Specifically, the preset correction condition refers to a preset upper limit value of a phase error, which is used to determine whether the phase error needs to be corrected; through conditional judgment and instruction generation, it is ensured that the collection of phase change information is triggered in time when the phase error exceeds the threshold.
[0073] S423: Acquire phase change information and sensor distribution information of each monitoring area, and acquire distance information between each sensor and the partial discharge source in each monitoring area according to the sensor distribution information.
[0074] Specifically, phase change information refers to the phase change information of the partial discharge signal collected in real time in the sensor in each monitoring area, including the speed and amplitude of the phase change; sensor distribution information refers to the location and quantity information of the sensors in each monitoring area; distance information refers to the distance information between each sensor and the partial discharge source.
[0075] S424: Calculate the phase adjustment parameter information of each monitoring area by combining the phase change information and the distance information, as well as the electrical characteristics of the GIS equipment and the preset phase synchronization standard.
[0076] In this embodiment, the phase adjustment parameter information refers to parameters for adjusting the phase synchronization reference calculated according to the phase change information, distance information, electrical characteristics of the GIS equipment and a preset phase synchronization standard, including phase offset, gain adjustment, etc.
[0077] Specifically, the phase change information, distance information, electrical characteristics of GIS equipment and preset phase synchronization standards are integrated to form a comprehensive data set. Then, based on the comprehensive data set, the phase adjustment parameter information of each monitoring area is calculated, including phase offset, gain adjustment, etc.
[0078] In one embodiment, the phase synchronization correction method based on GIS partial discharge further includes: S10: Collect environmental information such as temperature, humidity and air pressure in real time through environmental sensors to obtain environmental parameters.
[0079] In this embodiment, the environmental parameters refer to environmental factors that affect the phase of the partial discharge signal, such as temperature, humidity and air pressure.
[0080] Specifically, the temperature, humidity and air pressure data collected by the environmental sensors are recorded in real time through the data acquisition system to obtain environmental parameters.
[0081] S20: Dynamically compensate the phase information of the partial discharge signal by using a preset environmental compensation algorithm according to the environmental parameters.
[0082] In this embodiment, the parameters used to adjust the phase of the partial discharge signal are calculated based on the environmental parameters to obtain the compensation parameters, and the phase of the corresponding partial discharge signal is compensated; the environmental compensation algorithm refers to an algorithm used to eliminate the influence of environmental parameters on the phase of the partial discharge signal, which includes linear compensation, polynomial compensation or neural network compensation. This embodiment adopts a neural network compensation method to eliminate the influence of environmental parameters on the phase of the partial discharge signal through environmental compensation.
[0083] S30: Add a self-calibration module to each sensor of the GIS device, and perform a self-calibration operation of the sensor according to a specified calibration cycle.
[0084] In this embodiment, a self-calibration module is added to each sensor of the GIS device, and the self-calibration module includes a calibration circuit and a control unit; the self-calibration period of the sensor is set, such as once a day, once a week or once a month; according to the specified calibration period, the self-calibration module automatically starts the calibration operation, and the calibration content includes the sensitivity, response characteristics and zero drift of the sensor. Through sensor self-calibration, the long-term stability and accuracy of the sensor are ensured, and the reliability and accuracy of partial discharge signal monitoring are improved; this solution can effectively monitor and adjust the phase synchronization of partial discharge signals in multiple monitoring areas in the GIS device, and ensure accurate prediction and correction of the phase offset of the partial discharge signal under different load conditions and environmental parameters.
[0085] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0086] In one embodiment, a corrected phase synchronization system based on GIS partial discharge is provided, and the corrected phase synchronization system based on GIS partial discharge corresponds to the corrected phase synchronization method based on GIS partial discharge in the above-mentioned embodiment.
[0087] The phase correction synchronization system based on GIS partial discharge includes a phase reference determination module, a signal preprocessing module, a phase offset prediction module, an automatic correction synchronization module and a correction result tracking module. The detailed description of each functional module is as follows: The phase reference determination module is used to collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment and determine the corresponding reference phase reference; A signal preprocessing module, used to preprocess the partial discharge signal and extract the phase information and spectrum characteristics of the preprocessed partial discharge signal; A phase offset prediction module is used to predict the phase offset under different environmental conditions based on background noise data and a reference phase benchmark in a preset phase offset prediction model to obtain a corresponding phase offset prediction value; The automatic correction synchronization module is used to perform phase synchronization processing on the partial discharge signal using an automatic correction algorithm according to the predicted value of the phase offset to obtain corrected phase synchronization data; the automatic correction algorithm combines the high-frequency resonance principle to dynamically adjust the phase of the partial discharge signal at each preset detection point; The correction result tracking module is used to compare the signal characteristics of the corrected phase synchronization data with the corresponding reference phase benchmark to obtain the characteristic comparison result; and optimize the preset phase offset prediction model according to the characteristic comparison result.
[0088] For the specific limitations of the corrected phase synchronization system based on GIS partial discharge, please refer to the limitations of the corrected phase synchronization method based on GIS partial discharge in the above text, which will not be repeated here; each module in the above-mentioned corrected phase synchronization system based on GIS partial discharge can be fully or partially implemented by software, hardware and their combination; each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.
[0089] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the original data of the partial discharge signal, the background noise data and the predicted value of the phase offset, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a corrected phase synchronization method based on GIS partial discharge is implemented.
[0090] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: S1: Collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment, and determine the corresponding reference phase benchmark; S2: preprocessing the partial discharge signal and extracting the phase information and spectrum characteristics of the preprocessed partial discharge signal; S3: In a preset phase offset prediction model, the phase offset under different environmental conditions is predicted based on the background noise data and the reference phase benchmark to obtain a corresponding phase offset prediction value; S4: According to the predicted value of the phase offset, the automatic correction algorithm is used to perform phase synchronization processing on the partial discharge signal to obtain corrected phase synchronization data; the automatic correction algorithm combines the high-frequency resonance principle to dynamically adjust the phase of the partial discharge signal at each preset detection point; S5: performing signal feature comparison between the corrected phase synchronization data and the corresponding reference phase benchmark to obtain feature comparison results; and optimizing a preset phase offset prediction model according to the feature comparison results.
[0091] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: S1: Collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment, and determine the corresponding reference phase benchmark; S2: preprocessing the partial discharge signal and extracting the phase information and spectrum characteristics of the preprocessed partial discharge signal; S3: In a preset phase offset prediction model, the phase offset under different environmental conditions is predicted based on the background noise data and the reference phase benchmark to obtain a corresponding phase offset prediction value; S4: According to the predicted value of the phase offset, the automatic correction algorithm is used to perform phase synchronization processing on the partial discharge signal to obtain corrected phase synchronization data; the automatic correction algorithm combines the high-frequency resonance principle to dynamically adjust the phase of the partial discharge signal at each preset detection point; S5: performing signal feature comparison between the corrected phase synchronization data and the corresponding reference phase benchmark to obtain feature comparison results; and optimizing a preset phase offset prediction model according to the feature comparison results.
[0092] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0093] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0094] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the features thereof may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A modified phase synchronization method based on GIS partial discharge, characterized in that: include: Collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment, and determine the corresponding reference phase benchmark; Preprocessing the partial discharge signal, and extracting phase information and spectrum characteristics of the preprocessed partial discharge signal; In a preset phase offset prediction model, the phase offset under different environmental conditions is predicted based on the background noise data and the reference phase benchmark to obtain a corresponding phase offset prediction value; According to the phase offset prediction value, an automatic correction algorithm is used to perform phase synchronization processing on the partial discharge signal to obtain corrected phase synchronization data; the automatic correction algorithm combines the high-frequency resonance principle to dynamically adjust the phase of the partial discharge signal at each preset detection point; The corrected phase synchronization data is compared with the corresponding reference phase benchmark in terms of signal characteristics to obtain a characteristic comparison result; and the preset phase offset prediction model is optimized according to the characteristic comparison result.
2. The modified phase synchronization method based on GIS partial discharge according to claim 1 is characterized in that: The step of establishing the phase shift prediction model comprises: Obtain historical partial discharge data and synchronous reference data of several preset detection points in GIS equipment, and classify the historical partial discharge data and synchronous reference data according to different load conditions and environmental parameters; Extract key features that affect phase shift from classified historical partial discharge data and synchronous reference data to obtain key feature information; Using machine learning algorithms, the phase offset prediction model is constructed and trained with the extracted key feature information as input and the phase offset as output.
3. The modified phase synchronization method based on GIS partial discharge according to claim 1 is characterized in that: The feature comparison result includes a mass analysis comparison result; the signal feature comparison of the corrected phase synchronization data and the corresponding reference phase reference is performed, Get feature comparison results, including: Calculating the signal-to-noise ratio of the modified phase synchronization data and the corresponding reference phase reference in each frequency band, and evaluating the signal clarity difference value between the modified phase synchronization data and the corresponding synchronization reference signal based on the signal-to-noise ratio; According to the signal-to-noise ratio result, the proportion of speech components corresponding to each time-frequency point is calculated, and the distortion degree between the corrected phase synchronization data and the current speech and the preset clear speech of the corresponding reference phase benchmark is analyzed one by one to obtain a single-point speech distortion value; The single-point speech distortion values of each time-frequency point are integrated, and the comprehensive speech distortion value of the entire corrected phase synchronization data is estimated to obtain the quality analysis comparison results of the partial discharge signal and the specific value of the phase error.
4. The modified phase synchronization method based on GIS partial discharge according to claim 1 is characterized in that: The collecting of raw data and background noise data of partial discharge signals of a plurality of preset detection points in the GIS equipment and determining corresponding reference phase benchmarks includes: According to the structural characteristics of the GIS device, the interior of the GIS device is divided into multiple monitoring areas, and the monitoring areas are associated with area identifiers; The local discharge signal and background noise signal are collected by sensors installed in different monitoring areas of the GIS equipment to obtain the original data of the local discharge signal and background noise data of each monitoring area; Based on the regional identification, each monitoring area is associated with an independent phase synchronization reference, the phase information of the partial discharge signal in each monitoring area is analyzed, and compared with the phase synchronization reference of each monitoring area to calculate the phase error; According to the magnitude of the phase error and the environmental impact characteristics of the GIS equipment, the phase correction parameters required for each monitoring area are calculated; According to the calculated phase correction parameters, a phase correction instruction is sent to each monitoring area, and the phase synchronization benchmark of the corresponding monitoring area is optimized to determine the corresponding reference phase benchmark.
5. The modified phase synchronization method based on GIS partial discharge according to claim 1 is characterized in that: After the phase synchronization processing of the partial discharge signal is performed using an automatic correction algorithm according to the phase offset prediction value to obtain the corrected phase synchronization data, the method further includes: Acquire partition phase detection information, compare the partition phase detection information with the phase value of the phase synchronization reference of the corresponding monitoring area, and obtain a partition difference value; The partition difference value is compared with a preset phase synchronization threshold, and if the partition difference value exceeds the preset phase synchronization threshold, a partition phase error detection instruction is triggered; and adjustment parameter information is obtained according to the partition phase error detection instruction; An adjustment instruction is triggered according to the adjustment parameter information.
6. The modified phase synchronization method based on GIS partial discharge according to claim 5 is characterized in that: The obtaining adjustment parameter information according to the partition phase error detection instruction specifically includes: According to the partition phase error detection instruction, phase error information of each monitoring area is obtained; When it is detected that the phase error information meets the preset correction condition, a partition phase change information collection instruction is triggered; Obtain phase change information and sensor distribution information of each monitoring area, and obtain distance information between each sensor and the partial discharge source in each monitoring area according to the sensor distribution information; The phase adjustment parameter information of each monitoring area is calculated by combining the phase change information and the distance information, as well as the electrical characteristics of the GIS equipment and the preset phase synchronization standard.
7. The modified phase synchronization method based on GIS partial discharge according to claim 5 is characterized in that: The method further comprises: Environmental sensors are used to collect environmental information such as temperature, humidity and air pressure in real time to obtain environmental parameters; According to the environmental parameters, dynamically compensating the phase information of the partial discharge signal by a preset environmental compensation algorithm; A self-calibration module is added to each sensor of the GIS equipment to perform self-calibration operations on the sensor according to the specified calibration cycle.
8. The corrected phase synchronization system based on GIS partial discharge is characterized by: Used to execute the modified phase synchronization method based on GIS partial discharge according to any one of claims 1 to 7, the system comprises: The phase reference determination module is used to collect the original data and background noise data of the partial discharge signal of several preset detection points in the GIS equipment and determine the corresponding reference phase reference; A signal preprocessing module, used to preprocess the partial discharge signal and extract phase information and spectrum characteristics of the preprocessed partial discharge signal; A phase offset prediction module, used to predict the phase offset under different environmental conditions based on the background noise data and the reference phase benchmark in a preset phase offset prediction model, and obtain a corresponding phase offset prediction value; An automatic correction synchronization module is used to perform phase synchronization processing on the partial discharge signal using an automatic correction algorithm according to the phase offset prediction value to obtain corrected phase synchronization data; the automatic correction algorithm dynamically adjusts the phase of the partial discharge signal at each preset detection point in combination with the high-frequency resonance principle; The correction result tracking module is used to compare the signal characteristics of the corrected phase synchronization data with the corresponding reference phase benchmark to obtain a characteristic comparison result; and optimize the preset phase offset prediction model according to the characteristic comparison result.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the modified phase synchronization method based on GIS partial discharge as described in any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the modified phase synchronization method based on GIS partial discharge as described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Medium-voltage single-phase cable terminal operation voltage phase location method
CN106918743A
Automatic calibration system for infrared receiving head
CN118677521A
Partial discharge detection device, partial discharge detection method, partial discharge detection system, and computer program product
JP2020046202A
Cited By
Electric energy equipment receiving end phase angle deviation correction method based on Z-shaped winding
CN120611170A
Method for correcting phase angle deviation of power receiving end of power equipment based on zigzag winding
CN120611170B
