Rapid protection control method and system for high-voltage ring main unit
By using wavelet transformation and comprehensive fault prediction models in the high-voltage ring cabinet protection control system, fault signal characteristics are extracted and fault type is identified, and the protection action is performed by driving the protection device in combination with the adaptive relay protection conditions, the problem of long system response time is solved, and the fault isolation speed and the safety and reliability of the power system are improved.
Patent Information
- Application Number
- CN202411539222.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-02-25
AI Technical Summary
The high-voltage ring grid cabinet protection control system has a long response time in data acquisition and processing, switching volume output, etc., which leads to an increase in the impact time of the fault current on the power grid and reduces the operating life of the power grid.
By obtaining the AC input signal, sensor data and environmental parameters in the high-voltage ring network cabinet, the AC input signal is analyzed using wavelet transform, fault signal characteristics are extracted, and multi-source data fusion is carried out, the trained comprehensive fault prediction model is input, the fault type is identified, and the protection action is performed in combination with the adaptive relay protection conditions drive the protection device to perform protection actions.
Reduces the response time of the protection control system, improves the fault isolation speed, and enhances the safety and reliability of the power system.
Smart Images

Figure CN119518623A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of power system protection, and in particular to a rapid protection control method and system for a high-voltage ring network cabinet. Background Art
[0002] Ring main unit is a set of electrical equipment with high voltage switchgear installed in a steel plate metal cabinet or made into an assembled interval ring main unit. Its core part uses load switches and circuit breakers, which have the advantages of simple structure, small size, low price, improved power supply parameters and performance, and power supply safety. It is widely used in distribution stations and box-type substations in urban residential areas, high-rise buildings, large public buildings, factories and enterprises and other load centers.
[0003] The high-voltage ring main unit protection control system has the functions of monitoring, protection, communication, data storage, remote control, etc. For example, the patent document with the publication number CN201616712U monitors the various status parameters of the ring main unit in real time, and can actively record, report, and store fault information, intelligently analyze historical faults or status and output the analysis results. By monitoring the operating status of the ring main unit, faults can be discovered in time to protect the ring main unit from damage. The system can also realize remote communication, allowing monitoring personnel to remotely monitor and operate the ring main unit, thereby improving the efficiency of operation and maintenance.
[0004] At present, the high-voltage ring main unit protection control system has a long response time in data acquisition and processing, switch output, etc., which increases the impact time of fault current on the power grid, reduces the actual operating life of the power grid, and is not conducive to rapid fault isolation. Therefore, how to reduce the response time of the protection control system and increase the speed of fault isolation is an urgent problem to be solved in the current high-voltage ring main unit protection control system. Summary of the invention
[0005] The embodiments of the present application provide a rapid protection control method and system for a high-voltage ring main unit, which can be integrated into existing equipment and software to solve the problem of how to reduce the response time of the protection control system and improve the fault isolation speed.
[0006] This application is implemented through the following technical solutions:
[0007] In a first aspect, an embodiment of the present application provides a rapid protection control method for a high-voltage ring main unit, comprising:
[0008] Obtain AC input signals, multiple sensor data and environmental parameters in the high-voltage ring main unit;
[0009] Use wavelet transform to analyze AC input signal and extract fault signal features;
[0010] Perform multi-source data fusion on fault signal features, multiple sensor data and environmental parameters to obtain fused data;
[0011] Input the fused data into the trained preset comprehensive fault prediction model to obtain the comprehensive prediction result;
[0012] Identify the fault type based on fault signal characteristics and comprehensive prediction results;
[0013] Based on the fault type and combined with the adaptive relay protection conditions, the protection device is driven to perform protection actions and control the high-voltage ring network cabinet.
[0014] In a possible implementation manner of the first aspect, analyzing the AC input signal by using wavelet transform to extract fault signal features includes:
[0015] Performing a fast Fourier transform on the AC input signal to obtain an AC input signal after fast Fourier transform;
[0016] Perform wavelet transform on the AC input signal after fast Fourier transform to obtain the fault signal characteristics.
[0017] In a possible implementation manner of the first aspect, wavelet transform is performed on the AC input signal after fast Fourier transform to obtain the fault signal feature, including:
[0018] The AC input signal after fast Fourier transformation is converted from the time domain to the frequency domain to obtain a series of wavelet coefficients;
[0019] The amplitude and phase of the wavelet coefficients are analyzed to determine the fault signal characteristics.
[0020] In a possible implementation manner of the first aspect, before identifying the fault type based on the fault signal feature and the comprehensive prediction result, the method further includes:
[0021] Obtain historical AC input signals when a fault occurs in a high-voltage ring main unit;
[0022] Use wavelet transform to analyze historical AC input signals and extract historical fault signal features;
[0023] Based on the historical fault signal characteristics, a mapping relationship between the historical fault signal characteristics and the fault type is constructed.
[0024] In a possible implementation of the first aspect, based on the fault type and in combination with the adaptive relay protection condition, driving the protection device to perform a protection action includes:
[0025] Based on the fault type and combined with the adaptive relay protection conditions, the corresponding protection action exit signal is output;
[0026] Based on the protection action output signal, the protection device is driven to perform the protection action.
[0027] In a possible implementation of the first aspect, based on the fault type and in combination with the adaptive relay protection condition, outputting a corresponding protection action exit signal includes:
[0028] Under the fault type, if the change rate of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is lower than the change rate threshold, the corresponding protection action output signal is output;
[0029] Under the fault type, if the rate of change of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is equal to or greater than the rate of change threshold, the setting value of the protection device's activation and deactivation and action will be immediately reduced, and the corresponding protection action output signal will be output at the same time.
[0030] In a possible implementation of the first aspect, constructing a mapping relationship between historical fault signal features and fault types based on historical fault signal features includes:
[0031] Based on the historical fault signal characteristics, the machine learning algorithm is used to construct the mapping relationship between the historical fault signal characteristics and the fault type.
[0032] In a possible implementation manner of the first aspect, the protection device includes a circuit breaker and an isolating switch.
[0033] In a possible implementation manner of the first aspect, driving the protection device to perform a protection action includes:
[0034] Before driving the isolating switch to open or close, the circuit breaker must be driven to cut off the load current.
[0035] In a second aspect, an embodiment of the present application provides a fast protection control system for a high-voltage ring main unit, which executes a fast protection control method for a high-voltage ring main unit as in the first aspect, including:
[0036] A signal acquisition module is used to acquire AC input signals, multiple sensor data and environmental parameters in the high-voltage ring network cabinet;
[0037] A fault signal extraction module is used to analyze the AC input signal using wavelet transform and extract fault signal features;
[0038] A data fusion module is used to fuse fault signal features, multiple sensor data and environmental parameters to obtain fused data;
[0039] A comprehensive fault prediction module is used to input the fusion data into a trained preset comprehensive fault prediction model to obtain a comprehensive prediction result;
[0040] A fault type identification module is used to identify the fault type based on the fault signal characteristics and comprehensive prediction results;
[0041] The control output module is used to drive the protection device to perform protection actions and control the high-voltage ring network cabinet based on the fault type and in combination with the adaptive relay protection conditions.
[0042] Compared with the related art, the embodiments of the present application have the following beneficial effects:
[0043] The rapid protection control method and system of the high-voltage ring network cabinet of the embodiment of the present application use wavelet transform to analyze the AC input signal. Wavelet transform has better local properties in signal analysis and can decompose the signal into local information in the time domain and frequency domain, so as to have stronger time-frequency positioning ability, can accurately extract the characteristics of the fault signal, and provide accurate basis for subsequent fault type identification. The comprehensive fault prediction model is used to comprehensively analyze and predict not only the fault signal characteristics, but also the data from multiple sensors inside the high-voltage ring network cabinet and the environmental factor data, so as to improve the accuracy and timeliness of fault prediction. At the same time, the comprehensive prediction results obtained based on the comprehensive factors and the fault signal characteristics obtained based on the key factors are comprehensively considered to identify the fault type, which is of great significance for quickly, accurately and comprehensively locating faults and reducing downtime. Especially in key power facilities such as high-voltage ring network cabinets, rapid fault identification is crucial to ensure the stable operation of the power system. Combined with the adaptive relay protection conditions, the protection device is driven to perform the protection action according to the fault type. The adaptive technology can adjust the protection strategy according to various changes in the power system, ensure that the protection device can accurately and quickly respond to the fault, reduce the response time of the protection control system, improve the fault isolation speed, and improve the safety and reliability of the power system.
[0044] The beneficial effects of the above-mentioned second aspect embodiment refer to the beneficial effects of the first aspect embodiment, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0046] Figure 1 It is a structural schematic diagram of a circuit breaker control box provided in one embodiment of the present application;
[0047] Figure 2 It is a flow chart of a rapid protection control method for a high-voltage ring main unit provided in one embodiment of the present application;
[0048] Figure 3 It is a structural schematic diagram of a rapid protection control system for a high-voltage ring main unit provided in one embodiment of the present application. DETAILED DESCRIPTION
[0049] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0050] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0051] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0052] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0053] References to "an embodiment", "one embodiment" or "some embodiments" described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0054] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings and specific implementation methods. 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 making creative work are within the scope of protection of the present invention.
[0055] According to the regulations of the power grid company, the reaction time of a substation's outgoing switch to judge a fault is generally between 60 and 80 ms. Once the microcomputer protection of the substation's outgoing switch completes the fault judgment and outputs a trip signal, the signal is irreversible, so the "distribution firewall" switch must remove and isolate the fault before 60 ms. However, the outdoor overhead line pole switches with spring operating mechanisms or ring network boxes with spring operating mechanisms currently used by power grid companies cannot meet this condition. This is because their tripping times are basically relatively long, ranging from 50 to 120 ms, and the time dispersion of each trip is relatively large, and they do not have the ability to quickly remove and isolate faults. Therefore, in order to shorten the time for fault removal and isolation, in addition to increasing the movement speed of the hardware mechanism, it is also necessary to reduce the time for the control system to identify and respond, such as Figure 1 Circuit breaker control box shown.
[0056] Wavelet transform has the advantage of time-frequency localization. Traditional Fourier transform cannot provide time domain and frequency domain information of the signal at the same time, while wavelet transform can analyze simultaneously in the time and frequency domain. This enables wavelet transform to capture the instantaneous characteristics of the signal more quickly in time-frequency analysis, and to describe the time-frequency changes of the signal more accurately.
[0057] Therefore, this application analyzes high-precision sampling data, extracts the transient characteristics of the signal through the wavelet algorithm, and uses wavelet changes to convert the fault signal from the time domain to the frequency domain for research. At the same time, the opening and closing drive circuit adopts an electronic opening and closing drive circuit, combined with an adaptive relay protection model, to reduce the response time of the opening and closing drive circuit and achieve rapid fault response and protection measures.
[0058] Figure 2 is a flow chart of a rapid protection control method for a high-voltage ring network cabinet provided by an embodiment of the present application, with reference to Figure 2 The rapid protection control method of the high-voltage ring network cabinet comprises:
[0059] Step 101, obtaining an AC input signal, multiple sensor data and environmental parameters in a high-voltage ring main unit.
[0060] The original AC input signal of the high-voltage ring main unit may include operating parameters of switchgear control devices and protection devices, such as lines, transformers, power factor compensation devices, etc.
[0061] Multiple sensor data may include sensor data such as temperature, humidity, vibration, insulation status, etc. within the high-voltage ring main unit; environmental parameters may include external environmental conditions such as temperature, humidity, wind speed, etc. These data are crucial for fully understanding the equipment status and predicting potential failures.
[0062] Exemplarily, the original AC input signal obtained from the high-voltage ring main unit is preprocessed to obtain an AC input signal, thereby improving the accuracy of the following feature extraction process.
[0063] The preprocessing process includes filtering, denoising, etc., and also includes: obtaining the AC input signals of each equipment line and the AC input signals within a preset time period before the AC input signals, and using the characteristic value analysis method to calculate the frequency deviation △f of the AC input signals within the preset time period as the reference oscillation frequency, and the preset time period can be 10 minutes. The high-voltage ring network cabinet is provided with a storage device, and the AC input signals within a period of time are stored in the storage device. Therefore, the AC input signals within the preset time period before the AC input signals can be easily obtained.
[0064] The oscillation frequency and damping ratio of the AC input signal are calculated using the eigenvalue analysis method, and the oscillation frequency deviation is obtained based on the reference oscillation frequency. The oscillation frequency deviation and damping ratio are used to evaluate the dynamic stability of each equipment line in the power grid system. Since the larger the damping ratio, the faster the decay rate of the line oscillation and the better the stability, when the oscillation frequency deviation is large, the line may have instability problems. Therefore, a larger damping ratio threshold and a larger oscillation frequency deviation threshold are set. If the line is very stable, it will be screened out. If the line is unstable or not very stable, the line will not be missed due to the large threshold, and the AC input signal with fault characteristics will not be affected.
[0065] Once the oscillation frequency deviation of the AC input signal exceeds the oscillation frequency deviation threshold and the damping ratio exceeds the damping ratio threshold, it indicates that the device line is very stable. In this case, the AC input signal of the device line is removed to reduce the usage of computing resources and the subsequent calculation time for extracting fault signal features.
[0066] Step 102: Analyze the AC input signal using wavelet transform to extract fault signal features.
[0067] Exemplarily, step 102 includes:
[0068] Step 1021, perform fast Fourier transform on the AC input signal to obtain an AC input signal X(t) after fast Fourier transform.
[0069] Here, the AC input signal is the AC input signal after the AC input signal of the stable device line is removed in step 101.
[0070] Step 1022, performing wavelet transform on the AC input signal X(t) after the fast Fourier transform to obtain the fault signal feature.
[0071] Step 1022 includes:
[0072] The AC input signal after fast Fourier transformation is converted from time domain to frequency domain to obtain a series of wavelet coefficients. The amplitude and phase of the wavelet coefficients are analyzed to determine the fault signal feature X j (t).
[0073] The db N series of wavelet functions can be selected as the basis functions of wavelet transform to decompose the power grid fault signal X(t) and decompose the X(t) signal into a series of low-frequency signals and high-frequency signals. Generally, the difference in extracting the main features of each wavelet function in the low-frequency aspect is not very obvious, but in the decomposition of high-frequency coefficients, the difference in extracting the main features is large. The wavelet function with rich reflection and many changing features is selected as the basis function of wavelet transform.
[0074]
[0075] Where J is the number of decomposition levels; C 0 (k) is the initial scale factor, d j (k) is the wavelet coefficient; is the scale function, ψ(2 j tk) is the wavelet function, 2 j / 2 is the resolution. Among them, k is the position coordinate, which determines the position of each function along the t-axis; j is the scale coordinate, which corresponds to the scale of each layer of decomposition and determines the width of each function.
[0076]
[0077] d j (k)=[u(t),ψ j,k (t)] (3)
[0078]
[0079] Among them, C j (k) is the function of the AC input signal after the fast Fourier transform of the scale coordinate j with respect to the position k; u(t) is the decomposition factor of the AC input signal after the fast Fourier transform at time t; is the scale function of the AC input signal after fast Fourier transformation at scale coordinate j at position coordinate k at time t; ψ j,k (t) is the wavelet function of the AC input signal after fast Fourier transformation at scale coordinate j and position coordinate k at time t; C j-1 (k) is the function of the AC input signal after the fast Fourier transform of the scale coordinate j-1 with respect to the position k; h(n-2k) is the low-pass filter coefficient; g(n-2k) is the high-pass filter coefficient; C j (n) is the function of the AC input signal after fast Fourier transformation of scale coordinate j with respect to the number of oscillations n.
[0080] The signal of the corresponding frequency band can be obtained by wavelet reconstruction based on the wavelet coefficients and the frequency band to be extracted. The extracted frequency band signal is used as the fault signal feature as shown in formula (6):
[0081]
[0082] Among them, h j is the jth decomposition low-pass filter coefficient, g j is the j-th decomposition high-pass filter coefficient.
[0083] Step 103 , multi-source data fusion is performed on the fault signal feature, multiple sensor data and environmental parameters to obtain fused data.
[0084] Exemplarily, multiple sensor data and environmental parameters are preprocessed before fusion, which can be done through preprocessing steps such as data cleaning and feature extraction. For example, characteristic parameters closely related to the health status of the equipment are extracted from sensors such as temperature, humidity, vibration, and insulation status, such as temperature change trends, vibration spectrum characteristics, insulation resistance values, etc. Considering the impact of the external environment on the equipment, characteristic parameters such as ambient temperature, humidity, wind speed, etc. that may affect the operation of the equipment are extracted.
[0085] Since the feature dimensions and ranges of different data sources may be different, in order to unify the processing and analysis, the extracted features need to be normalized and standardized to make them in the same order of magnitude and range. Then the feature vectors from different data sources are processed comprehensively. Methods such as feature concatenation, principal component analysis (PCA), and linear discriminant analysis (LDA) can be used to merge multiple feature vectors into a comprehensive feature vector to form fused data for subsequent fault prediction, providing high-quality comprehensive data input for subsequent prediction models.
[0086] Step 104, input the fused data into the trained preset comprehensive fault prediction model to obtain a comprehensive prediction result.
[0087] Based on the historical fusion data formed by the AC input signal in the high-voltage ring main unit, historical multiple sensor data and historical environmental parameters, a comprehensive fault prediction model is constructed using machine learning (such as random forest, gradient boosting tree) or deep learning (such as LSTM, CNN-LSTM) algorithms. The model is trained by historical fusion data to enable it to learn and identify various fault modes and their precursor characteristics.
[0088] The real-time collected fusion data is input into the trained comprehensive fault prediction model to perform real-time calculation and prediction of the fault probability to obtain a comprehensive prediction result. The comprehensive prediction result may include multiple fault categories and the corresponding fault probability of each fault category. Among them, the corresponding fault probability of each fault category must be greater than the preset threshold.
[0089] Step 105: Identify the fault type based on the fault signal characteristics and the comprehensive prediction result.
[0090] Exemplarily, before identifying the fault type based on the fault signal feature, the following steps are included:
[0091] Obtain historical AC input signals when faults occur in high-voltage ring main units.
[0092] The historical AC input signal is analyzed by wavelet transform to extract the historical fault signal characteristics.
[0093] Based on the historical fault signal characteristics, a mapping relationship between the fault signal characteristics and the fault type is constructed.
[0094] Among them, based on the historical fault signal characteristics, a mapping relationship between the historical fault signal characteristics and the fault type is constructed, including: based on the historical fault signal characteristics, a mapping relationship between the historical fault signal characteristics and the fault type is constructed using a machine learning algorithm.
[0095] The machine learning algorithm can be a support vector machine, a neural network, etc., which trains fault samples with known historical fault signal characteristics to establish a mapping relationship between fault types and characteristics. For example, for arc faults, since they usually produce high-frequency components, the mapping relationship between the amplitude of high-frequency wavelet coefficients and arc faults can be established. Similarly, short-circuit faults may produce low-frequency components, so the mapping relationship between the amplitude of low-frequency wavelet coefficients and short-circuit faults can be established.
[0096] When the system detects a power grid fault, the wavelet transform unit extracts the fault signal features and inputs them into the trained classifier. The classifier will filter out the fault type corresponding to the fault signal features at the current moment based on the mapping relationship between the fault signal features and the fault type.
[0097] At the same time, the comprehensive prediction results include multiple current fault categories and the fault probabilities corresponding to each fault category. The fault probability of each fault category is used to correct and confirm the fault type corresponding to the fault signal characteristics at the current moment.
[0098] For example, if the fault type corresponding to the fault signal feature at the current moment is not in the currently obtained comprehensive prediction result, it is necessary to repeat step 101. If the fault type corresponding to the fault signal feature at the current moment is in the currently obtained comprehensive prediction result, the fault probability of the fault type corresponding to the fault signal feature at the current moment in the currently obtained comprehensive prediction result is used for correction, and the fault type corresponding to the fault signal feature is used as the first output fault type, and the rest are output from high to low according to the fault probability. If the fault type corresponding to the fault signal feature at the current moment has the highest fault probability in the currently obtained comprehensive prediction result, the fault type is output from high to low according to the fault probability.
[0099] Step 106: Based on the fault type and in combination with the adaptive relay protection condition, the protection device is driven to perform the protection action to control the high-voltage ring main unit.
[0100] For example, the fault type may include but is not limited to overload, short circuit, overvoltage and undervoltage. The protection device includes a circuit breaker and an isolating switch. The protection action may be to cut off the circuit, put into a backup power supply or change the operation mode of the power system.
[0101] The switch output circuit usually uses output relays and intermediate relays to realize the opening and closing drive. Since the mechanical output points of the output relays and intermediate relays have a certain response time, the delay time of the output relay is generally 5ms, and the delay time of the intermediate relay is more than 8ms, that is, the protection control system needs at least 30.5ms of delay at the fastest from the fault current output of the analog input circuit to the giving of the opening and closing drive signal, ignoring the software calculation time. This response time increases the impact time of the fault current on the power grid, reduces the actual operating life of the power grid, and is not conducive to rapid fault isolation. At the same time, the system also has malfunctions caused by short-term fluctuations in electrical quantities or measurement errors. For example, no fault is detected at the current moment, but the short-term fluctuation of the electrical quantity exceeds the set value. At this time, it is difficult to solve which signal to execute between the fault-free isolation signal and the signal exceeding the set value.
[0102] Therefore, in the embodiment of the present application, by setting the adaptive relay protection condition, the fault type and the adaptive relay protection condition are used to determine how to perform the protection action.
[0103] Exemplarily, based on the fault type and in combination with the adaptive relay protection condition, driving the protection device to perform the protection action includes:
[0104] Based on the fault type and in combination with the adaptive relay protection conditions, the corresponding protection action output signal is output; based on the protection action output signal, the protection device is driven to perform the protection action.
[0105] Exemplarily, based on the fault type and in combination with the adaptive relay protection condition, the corresponding protection action output signal is output, including:
[0106] Under the fault type, if the change rate of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is lower than the change rate threshold, the corresponding protection action output signal is output.
[0107] Under the fault type, if the rate of change of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is equal to or greater than the change rate threshold, the setting value of the protection device's throw and action will be immediately reduced, and the corresponding protection action output signal will be output at the same time. That is, when there is a fault and there is a transient abnormality, the time for driving the protection device to perform the protection action is reduced.
[0108] Exemplarily, the rapid protection control method of the high-voltage ring main unit also includes:
[0109] If there is no fault and the rate of change of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is lower than the rate of change threshold, the corresponding protection action output signal will not be output.
[0110] If there is no fault and the rate of change of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is equal to or greater than the rate of change threshold, the corresponding protection action output signal is output.
[0111] In this embodiment, when outputting the corresponding protection action output signal, the system will also have a certain action delay time. In the case of overload tripping, the circuit has undergone an overheating operation, resulting in the wire insulation layer, wires, etc. being in a high temperature state. If the power is turned on again immediately, these components will continue to be affected by the high temperature, and the risk of damage will be higher. Therefore, a delay time is required to allow the circuit to cool down and reduce the temperature in order to protect the safety of the circuit and equipment. However, when the circuit is determined to have both a fault and a transient abnormality, necessary risks must be avoided.
[0112] For example, since a general disconnector has no arc extinguishing capability, the protection device is driven to perform a protection action, including: before driving the disconnector to perform an opening and closing operation, the circuit breaker must be driven to cut off the load current to ensure safety and stability.
[0113] In summary, the rapid protection and control method of the high-voltage ring network cabinet provided in the embodiment of the present application analyzes the AC input signal by using wavelet transform. The wavelet transform has better local properties in signal analysis and can decompose the signal into local information in the time domain and frequency domain, so as to have stronger time-frequency positioning ability, and can accurately extract the characteristics of the fault signal, and provide an accurate basis for subsequent fault type identification, which is of great significance for rapid fault positioning and reducing downtime. Especially in key power facilities such as high-voltage ring network cabinets, rapid fault identification is crucial to ensure the stable operation of the power system. By introducing a comprehensive fault prediction model that integrates multi-source data and combining the comprehensive prediction results, the comprehensiveness, accuracy and timeliness of fault prediction are significantly enhanced, thereby improving the safety and reliability of the high-voltage ring network cabinet. Combined with the adaptive relay protection conditions, the protection device is driven to perform protection actions according to the fault type. The adaptive technology can adjust the protection strategy according to various changes in the power system, ensuring that the protection device can accurately and quickly respond to faults, reduce the response time of the protection control system, and improve the fault isolation speed, thereby improving the safety and reliability of the power system.
[0114] See also Figure 3 An embodiment of the present application provides a rapid protection control system for a high-voltage ring main unit, which executes the rapid protection control method for a high-voltage ring main unit as described above. The system includes a signal acquisition module 201, a fault signal extraction module 202, a data fusion module 203, a comprehensive fault prediction module 204, a fault type identification module 205 and a control output module 206.
[0115] The signal acquisition module 201 is used to acquire the AC input signal, multiple sensor data and environmental parameters in the high-voltage ring network cabinet;
[0116] The fault signal extraction module 202 is used to analyze the AC input signal using wavelet transform to extract the fault signal characteristics;
[0117] The data fusion module 203 is used to fuse the fault signal characteristics, multiple sensor data and environmental parameters to obtain fused data;
[0118] Comprehensive fault prediction module 204, used to input the fusion data into the trained preset comprehensive fault prediction model to obtain a comprehensive prediction result;
[0119] A fault type identification module 205 is used to identify the fault type based on the fault signal characteristics and the comprehensive prediction results;
[0120] The control output module 206 is used to drive the protection device to perform protection actions and control the high-voltage ring main unit based on the fault type and in combination with the adaptive relay protection conditions.
[0121] Exemplarily, the fault signal extraction module 202 is specifically used for:
[0122] Performing a fast Fourier transform on the AC input signal to obtain an AC input signal after fast Fourier transform;
[0123] Perform wavelet transform on the AC input signal after fast Fourier transform to obtain the fault signal characteristics.
[0124] Exemplarily, in the fault signal extraction module 202, wavelet transform is performed on the AC input signal after fast Fourier transform to obtain fault signal features, including:
[0125] The AC input signal after fast Fourier transformation is converted from the time domain to the frequency domain to obtain a series of wavelet coefficients;
[0126] The amplitude and phase of the wavelet coefficients are analyzed to determine the fault signal characteristics.
[0127] Exemplarily, the rapid protection control system of the high-voltage ring network cabinet further includes a mapping relationship building module; before identifying the fault type based on the fault signal characteristics and the comprehensive prediction results, the mapping relationship building module is specifically used to:
[0128] Obtain historical AC input signals when a fault occurs in a high-voltage ring main unit;
[0129] Use wavelet transform to analyze historical AC input signals and extract historical fault signal features;
[0130] Based on the historical fault signal characteristics, a mapping relationship between the historical fault signal characteristics and the fault type is constructed.
[0131] Exemplarily, based on the fault type and in combination with the adaptive relay protection condition, driving the protection device to perform the protection action includes:
[0132] Based on the fault type and combined with the adaptive relay protection conditions, the corresponding protection action exit signal is output;
[0133] Based on the protection action output signal, the protection device is driven to perform the protection action.
[0134] Exemplarily, the control output module 206 is specifically used to:
[0135] Under the fault type, if the change rate of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is lower than the change rate threshold, the corresponding protection action output signal is output;
[0136] Under the fault type, if the rate of change of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is equal to or greater than the rate of change threshold, the setting value of the protection device's activation and deactivation and action will be immediately reduced, and the corresponding protection action output signal will be output at the same time.
[0137] Exemplarily, in the mapping relationship building module, based on the historical fault signal features, a mapping relationship between the historical fault signal features and the fault type is built, including:
[0138] Based on the historical fault signal characteristics, the machine learning algorithm is used to construct the mapping relationship between the historical fault signal characteristics and the fault type.
[0139] Exemplarily, the protection devices include circuit breakers and disconnect switches.
[0140] Exemplarily, in the control output module 206, driving the protection device to perform a protection action includes:
[0141] Before driving the isolating switch to open or close, the circuit breaker must be driven to cut off the load current.
[0142] The beneficial effects of the above-mentioned embodiment of the rapid protection control system of the high-voltage ring main unit can be found in the beneficial effects of the embodiment of the rapid protection control method of the high-voltage ring main unit, which will not be repeated here.
[0143] It should be noted that, although several units / modules or sub-units / modules of the rapid protection control system of the high-voltage ring main unit are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to the embodiment of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.
[0144] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.
[0145] The present application also provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the rapid protection control method of the high-voltage ring network cabinet provided in the above embodiment of the present application is implemented.
[0146] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0147] The above embodiments 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, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These 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 rapid protection control method for a high-voltage ring main unit, characterized in that: include: Obtain AC input signals, multiple sensor data and environmental parameters in the high-voltage ring main unit; Analyzing the AC input signal using wavelet transform to extract fault signal features; Performing multi-source data fusion on the fault signal feature, the multiple sensor data and the environmental parameters to obtain fused data; Inputting the fused data into a trained preset comprehensive fault prediction model to obtain a comprehensive prediction result; Based on the fault signal characteristics and the comprehensive prediction result, identifying the fault type; Based on the fault type and in combination with the adaptive relay protection condition, the protection device is driven to perform a protection action to control the high-voltage ring main unit.
2. The rapid protection control method for high-voltage ring main unit according to claim 1, characterized in that: The method of analyzing the AC input signal by wavelet transform to extract fault signal features includes: Performing a fast Fourier transform on the AC input signal to obtain an AC input signal after fast Fourier transform; The AC input signal after the fast Fourier transform is subjected to wavelet transform to obtain the fault signal feature.
3. The rapid protection control method for high-voltage ring main unit according to claim 2, characterized in that: The step of performing wavelet transform on the AC input signal after the fast Fourier transform to obtain the fault signal feature includes: Convert the AC input signal after the fast Fourier transform from the time domain to the frequency domain to obtain a series of wavelet coefficients; The amplitude and phase of the wavelet coefficients are analyzed to determine the fault signal characteristics.
4. The rapid protection control method for high-voltage ring main unit according to claim 1, characterized in that: Before identifying the fault type based on the fault signal feature and the comprehensive prediction result, the method further includes: Obtain historical AC input signals when a fault occurs in a high-voltage ring main unit; Analyzing the historical AC input signal using wavelet transform to extract historical fault signal features; Based on the historical fault signal characteristics, a mapping relationship between the historical fault signal characteristics and the fault type is constructed.
5. The rapid protection control method for high-voltage ring main unit according to claim 1, characterized in that: Based on the fault type and in combination with the adaptive relay protection condition, driving the protection device to perform the protection action includes: Based on the fault type and in combination with the adaptive relay protection condition, output a corresponding protection action exit signal; Based on the protection action output signal, the protection device is driven to perform a protection action.
6. The rapid protection control method for high-voltage ring main unit according to claim 5, characterized in that: Based on the fault type and in combination with the adaptive relay protection condition, outputting a corresponding protection action output signal includes: Under the fault type, if the change rate of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is lower than the change rate threshold, the corresponding protection action output signal is output; Under the fault type, if the rate of change of the electrical parameters of the electrical equipment in the high-voltage ring network cabinet within the preset time is equal to or greater than the rate of change threshold, the setting value of the protection device's activation and deactivation and action is immediately reduced, and the corresponding protection action output signal is output at the same time.
7. The rapid protection control method for high-voltage ring main unit according to claim 4, characterized in that: The constructing a mapping relationship between the historical fault signal characteristics and the fault type based on the historical fault signal characteristics includes: Based on the historical fault signal characteristics, a mapping relationship between the historical fault signal characteristics and the fault type is constructed using a machine learning algorithm.
8. The rapid protection control method for a high-voltage ring main unit according to any one of claims 1 to 7, characterized in that: The protection device includes a circuit breaker and an isolating switch.
9. The rapid protection control method for high-voltage ring main unit according to claim 8, characterized in that: The driving protection device performs a protection action, including: Before driving the isolating switch to perform opening and closing operations, the circuit breaker needs to be driven to cut off the load current.
10. A fast protection control system for a high-voltage ring main unit, executing the fast protection control method for a high-voltage ring main unit according to any one of claims 1 to 9, characterized in that: include: A signal acquisition module is used to acquire AC input signals, multiple sensor data and environmental parameters in the high-voltage ring network cabinet; A fault signal extraction module is used to analyze the AC input signal using wavelet transform to extract fault signal features; A data fusion module, used for performing multi-source data fusion on the fault signal feature, the plurality of sensor data and the environmental parameters to obtain fused data; A comprehensive fault prediction module, used for inputting the fusion data into a trained preset comprehensive fault prediction model to obtain a comprehensive prediction result; A fault type identification module, used to identify the fault type based on the fault signal characteristics and the comprehensive prediction result; The control output module is used to drive the protection device to perform protection actions and control the high-voltage ring network cabinet based on the fault type and in combination with the adaptive relay protection conditions.
Citation Information
Patent Citations
Real-time status monitoring device for high-voltage ring main unit
CN201616712U