A method, device, terminal and medium for detecting voltage sag events in distribution network

Abstract

The present invention discloses a method, device, terminal and medium for detecting voltage sag events in a distribution network, wherein a method for detecting voltage sag events in a distribution network includes collecting voltage sag data and voltage sag simulation data, and selecting reference data; extracting features from the voltage sag data and the reference data; performing hash calculation on the extracted features to generate a hash sequence; defining a first threshold and a second threshold, and preliminarily detecting potential voltage sag events based on the hash sequence, the first threshold and the second threshold; and performing secondary detection on the preliminarily detected potential voltage sag events in combination with the preliminary recognition results and waveform changes. The present invention performs error correction on voltage sag data by designing a correction unit, thereby reducing data measurement deviations caused by errors, and significantly improves the detection accuracy and robustness of voltage sag events by combining hash operations and multi-level detection mechanisms, thereby overcoming the limitation of relying on a single data source.

Description

Technical Field

[0001] The present invention relates to the technical field of power system fault detection, and in particular to a method, device, terminal and medium for detecting a voltage sag event in a distribution network. Background Art

[0002] In the distribution network system, voltage sag events refer to the phenomenon that the grid voltage drops significantly in a short period of time, which may have a negative impact on the stability of power equipment and power systems. Voltage sags are usually caused by a sudden increase in grid load, faults, or the start-up of electrical equipment. With the expansion of the scale of power systems and the diversification of loads, voltage sag events have become more frequent and complex, which puts higher requirements on the stable operation of distribution networks. Therefore, accurate and timely detection of voltage sag events is crucial to ensure the reliability of power systems and the normal operation of power equipment.

[0003] Existing voltage sag detection technologies are mainly based on time domain and frequency domain analysis of voltage signals. These methods usually determine whether the voltage has a sag by setting a fixed voltage threshold, and detect sag events by observing changes in the voltage waveform. However, this simple threshold-based method has certain limitations. First, the amplitude and duration of voltage sag events may vary depending on the operating state of the system, so fixed thresholds are difficult to adapt to all situations, which may lead to false detection or missed detection. Secondly, although time domain analysis can capture changes in voltage waveforms, it is not sensitive enough for short-term, small-amplitude sag events. Although frequency domain analysis can provide spectral characteristics of voltage signals, it has poor adaptability to noise interference and data changes when processing complex voltage waveforms. In addition, existing technologies usually lack a feedback mechanism for detection results, making it difficult to dynamically adjust and optimize the detection results. Summary of the invention

[0004] The object of the present invention is to provide a method for detecting voltage sag events in a distribution network, so as to solve the problems of inaccurate detection and high false alarm in the prior art under complex voltage waveform and noise environment.

[0005] To solve the above technical problems, the present invention provides the following technical solutions, including: collecting voltage sag data and voltage sag simulation data, and selecting benchmark data from the voltage sag data and the voltage sag simulation data; performing feature extraction on the voltage sag data and the benchmark data; performing hash calculation on the extracted features to generate a hash sequence; defining a first threshold and a second threshold, and preliminarily detecting potential voltage sag events based on the hash sequence, the first threshold and the second threshold; and performing secondary detection on the preliminarily detected potential voltage sag events in combination with the preliminary recognition results and waveform changes.

[0006] As a preferred solution of the method for detecting voltage sag events in a distribution network described in the present invention, it includes: establishing a power system simulation model according to the power grid topology, component parameters and operating conditions of the distribution network; defining a fault model; setting simulation parameters, wherein the simulation parameters include fault conditions and random variables; performing simulation and outputting voltage sag simulation data.

[0007] As a preferred solution of the method for detecting voltage sag events in a distribution network described in the present invention, it also includes: performing error correction on voltage sag data through a correction unit, the correction unit includes a capacitive voltage transformer, multiple current sensors, a compensation reactor, an amplifier, an LMS filter, an impedance compensator and a corrector; collecting voltage signals and current signals through the capacitive voltage transformer and the current sensor respectively; weighted fusion of the current signal is input into the compensation reactor for preliminary compensation; the current signal after preliminary compensation is input into the amplifier for amplification, and then the noise is eliminated through the LMS filter; the processed current signal is input into the impedance compensator, secondary compensation is performed based on the KVL theorem, and a secondary compensated voltage signal is output; the secondary compensated voltage signal is superimposed on the voltage signal collected by the capacitive voltage transformer, and a corrected voltage value is output.

[0008] As a preferred solution of the method for detecting voltage sag events in a distribution network described in the present invention, the feature extraction includes: selecting data with the shortest data length from the voltage sag data and the voltage sag start segment of the voltage sag simulation data as reference data; extracting time domain, frequency domain and statistical features of the voltage sag data and the reference data.

[0009] As a preferred solution of the method for detecting voltage sag events in distribution network described in the present invention, the hash calculation includes: converting the extracted features into vector form; performing hash operation on the feature vector through SHA-256 algorithm to generate a 64-bit binary hash sequence.

[0010] As a preferred solution of the method for detecting voltage sag events in a distribution network described in the present invention, the preliminary detection of potential voltage sag events includes: adjusting the first threshold and the second threshold according to the real-time operating status of the distribution network, and preliminarily detecting potential voltage sag events based on the hash sequence, the first threshold and the second threshold; comparing the hash sequence of the voltage sag data with the hash sequence of the reference data by calculating the Hamming distance between the two, if the Hamming distance is greater than or equal to the first threshold, marking it as a potential voltage sag event, otherwise not marking it; comparing the Hamming distance with the second threshold, if it is less than or equal to the second threshold, confirming it as a potential voltage sag event, otherwise not confirming it as a potential voltage sag event.

[0011] As a preferred solution of the method for detecting voltage sag events in distribution network described in the present invention, the secondary detection includes: extracting features from the preliminary detected potential voltage sag events and the known voltage sag event waveforms; and inputting the extracted features into the ELM classifier to finally confirm the voltage sag event.

[0012] The present invention also provides a distribution network voltage sag event detection device, which is used to implement the distribution network voltage sag event detection method as described in any of the above items, and the distribution network voltage sag event detection device includes: a data acquisition module, configured to execute the acquisition of voltage sag data and voltage sag simulation data, and select reference data from the voltage sag data and voltage sag simulation data; a feature extraction module, configured to execute feature extraction of the voltage sag data and the reference data; a hash operation module, configured to execute hash calculation of the extracted features to generate a hash sequence; a first detection module, configured to execute the definition of a first threshold and a second threshold, and preliminarily detect potential voltage sag events based on the hash sequence, the first threshold and the second threshold; a second detection module, configured to perform a secondary detection of the preliminarily detected potential voltage sag events in combination with the preliminary recognition result and the waveform change.

[0013] The present invention also provides a terminal device, comprising:

[0014] one or more processors;

[0015] A memory, coupled to the processor, for storing one or more programs;

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting a voltage sag event in a power distribution network as described in any one of the above items.

[0017] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method for detecting a voltage sag event in a distribution network as described in any one of the above items.

[0018] Beneficial effects of the present invention: The present invention performs error correction on voltage sag data by designing a correction unit, thereby reducing data measurement deviations caused by errors, and significantly improves the detection accuracy and robustness of voltage sag events by combining hash operations and multi-level detection mechanisms, thereby overcoming the limitations of reliance on a single data source. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0020] Figure 1 It is a flow chart of a method for detecting a voltage sag event in a distribution network according to a first embodiment of the present invention;

[0021] Figure 2 A schematic diagram of a process for correcting voltage sag data according to a first embodiment of the present invention;

[0022] Figure 3 It is a schematic diagram of the process of initially detecting a potential voltage sag event according to the first embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0024] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0025] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0026] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0027] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0028] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0029] Example 1

[0030] Reference Figure 1 to Figure 3 , which is the first embodiment of the present invention, provides a method for detecting a voltage sag event in a distribution network, comprising:

[0031] S1: collecting voltage sag data and voltage sag simulation data, and selecting reference data from the voltage sag data and voltage sag simulation data;

[0032] (1) Collecting voltage sag data, that is, collecting voltage signals through a capacitive voltage transformer. In order to reduce the error impact caused by parameter deviation and improve the collection accuracy of voltage sag data, the present application performs error correction on the voltage sag data through a correction unit. Specifically, the correction unit includes a capacitive voltage transformer, multiple current sensors, a compensating reactor, an amplifier, an LMS filter, an impedance compensator and a corrector;

[0033] First, refer to Figure 2 , respectively collecting voltage signals and current signals (current signals related to voltage sag) through capacitive voltage transformers and current sensors;

[0034] Furthermore, the current signal is weighted fused:

[0035]

[0036] In the formula, is the current signal after weighted fusion, t is the time, The weight factor is dynamically adjusted according to the accuracy of the current sensor and the error of historical data. The weight of each current sensor is automatically adjusted through an adaptive optimization algorithm (Kalman filter or gradient descent method), so that the system can automatically remove unreliable data when the current sensor fails or the signal is abnormal, ensuring that accurate data can still be provided when individual sensors fail; is the measurement signal of the kth current sensor, and N is the number of current sensors.

[0037] Furthermore, the weighted fused current signal is input to the compensation reactor for preliminary compensation to offset part of the voltage error of the system. The current sensor measures the current signal i(t) and transmits it to the signal amplifier.

[0038] Furthermore, the current signal after preliminary compensation is input into the amplifier for amplification, that is, the weak signal is amplified by the low-noise amplifier, and then the noise is eliminated by the LMS filter to ensure the signal purity;

[0039] Further, the processed current signal is input into the impedance compensator, and secondary compensation is performed based on the KVL theorem, and a secondary compensated voltage signal is output; it should be noted that in the existing correction method, the compensation voltage is calculated only based on the equivalent inductance, equivalent capacitance and equivalent resistance parameters, and these parameters are constants, which may change due to factors such as temperature and load changes under actual working conditions, making it difficult to calculate the actual compensation voltage under different working conditions. Therefore, the present application introduces a dynamic adjustment factor , and Ensure the real-time and accuracy of the compensation voltage, as shown below:

[0040]

[0041] In the formula, is the secondary compensation voltage, , and It is a dynamic adjustment factor that is adjusted in real time based on actual working conditions. Used to adjust the effect of capacitance on the compensation voltage, Used to adjust the effect of inductance on compensation voltage, Used to adjust the effect of resistance on the compensation voltage, which can effectively correct the errors caused by component parameter drift and environmental changes; is the processed current signal; is the equivalent capacitance, is the equivalent inductance, is the equivalent resistance, and t is the time.

[0042] Furthermore, the secondary compensation voltage signal The voltage signal collected by the capacitive voltage transformer Superimpose and output the corrected voltage value :

[0043]

[0044] Where δ(t) is the dynamic ratio correction coefficient, which is adaptively adjusted based on historical errors. is a fixed transformation ratio coefficient used to adjust the overall voltage level, m is a normalization coefficient of the compensation voltage used to adjust the scale of voltage compensation, u(t) is the voltage collected by the capacitive voltage transformer, and t is time.

[0045] Preferably, the present application introduces a ratio correction coefficient δ(t) to ensure the accuracy of the ratio under different working conditions and avoid measurement errors caused by ratio drift.

[0046] Furthermore, in order to eliminate the error caused by parameter setting deviation, this application introduces a real-time error estimation model, uses a feedback control system to dynamically optimize key parameters, and calculates the corrected voltage value in each sampling period. With the expected voltage Error , and use it for parameter optimization in the next cycle:

[0047]

[0048] Based on error The size and rate of change of the impedance parameter and ratio correction factor Dynamic adjustment is performed to minimize the error. The adjustment rules are as follows:

[0049]

[0050]

[0051]

[0052]

[0053] In the formula, , , , The adjustment coefficient defines the adjustment step size, which can be adjusted based on the feedback from actual operation. is the capacitance adjustment step size, is the step size of inductance adjustment, is the step size of resistance adjustment, is the step size of ratio correction; is the value of the equivalent capacitance at time t, is the value of the equivalent inductance at time t, is the value of the equivalent resistance at time t, is the value of the dynamic ratio correction coefficient at time t; is the value of the equivalent capacitance at time t+1, is the value of the equivalent inductance at time t+1, is the value of the equivalent resistance at time t+1, is the value of the dynamic ratio correction coefficient at time t+1.

[0054] Preferably, the real-time error estimation model of the present application can ensure that the system can correct itself in real time, avoid long-term accumulation of errors, and improve compensation accuracy.

[0055] (2) Collecting voltage sag simulation data

[0056] According to the power distribution network topology (including busbars, transformers, switches and lines, etc.), component parameters (including transformer rated power and impedance, line resistance, inductance, capacitance, load distribution, etc.) and operating conditions (normal operating state of the system, load level, time-varying characteristics of power generation and load, etc.), and using power system analysis software to establish a power system simulation model;

[0057] Define the fault model and determine the possible fault types of voltage sag, such as short circuit fault, switch operation, load mutation, etc.

[0058] Set simulation parameters, including fault conditions (fault location, fault type, fault duration) and random variables (load fluctuation, equipment failure probability);

[0059] Perform simulations and output voltage sag simulation data; in each simulation, randomly generate fault events and system operating conditions, run the power system simulation model for each random event, and perform multiple simulations to ensure the statistical significance of the data.

[0060] S2: Extract features from voltage sag data and reference data.

[0061] Select the data with the shortest data length from the voltage sag start segment of the voltage sag data and the voltage sag simulation data as the benchmark data; specifically, identify the time point when the voltage starts to drop significantly (the start of the sag), for example, when the voltage drop exceeds a certain proportion (such as 10%), mark it as the start of the sag, extract the data in the time window from the start of the sag to the end of the sag, calculate the length of all extracted voltage sag start segments, and select the data segment with the shortest length as the benchmark data. By reducing the length of the processed data, the interference of noise on the detection results is reduced, thereby improving the accuracy of the detection.

[0062] Furthermore, the time domain, frequency domain and statistical features of voltage sag data and benchmark data are extracted to transform the complex data into a more informative and analyzable form for subsequent processing. The time domain features include the voltage sag amplitude, the time for the voltage to return to normal level, and the duration of the voltage sag; the frequency domain features include the spectrum features of the voltage sag signal (main frequency component, frequency band energy); and the statistical features include the voltage mean, standard deviation, kurtosis, and skewness.

[0063] S3: Perform hash calculation on the extracted features to generate a hash sequence.

[0064] Convert the extracted features into vector form;

[0065] The feature vector is hashed using the SHA-256 algorithm to generate a 64-bit binary hash sequence.

[0066] Preferably, high-dimensional complex data is converted into low-dimensional hash values ​​through a hash algorithm. This dimensionality reduction process reduces the reliance on complex waveform details, making subsequent processing more efficient and robust.

[0067] S4: Define a first threshold and a second threshold, and preliminarily detect a potential voltage sag event based on the hash sequence, the first threshold and the second threshold.

[0068] Reference Figure 3 ,(1) adjusting the first threshold and the second threshold according to the real-time operating status of the distribution network, and preliminarily detecting potential voltage sag events based on the hash sequence, the first threshold and the second threshold;

[0069] Applying the sliding window technology to calculate the mean P and standard deviation S of real-time voltage sag data and dynamically adjusting the first threshold T1 and the second threshold T2 can improve the accuracy of event detection and the adaptability of the system, ensuring that the threshold settings are always in line with the actual situation. The first threshold is used to preliminarily screen potential voltage sag events, and the second threshold is used to confirm the authenticity of the event to reduce false alarms:

[0070]

[0071] Where k is the adjustment factor, and its value range is (1.5, 2) so as to capture most voltage sag events.

[0072] (2) Comparing the difference between the hash sequence of the voltage sag data and the hash sequence of the reference data by calculating the Hamming distance between the hash sequence of the voltage sag data and the hash sequence of the reference data, if the Hamming distance is greater than or equal to a first threshold, marking it as a potential voltage sag event, otherwise not marking it;

[0073] (3) Compare the Hamming distance with the second threshold value. If the Hamming distance is less than or equal to the second threshold value, it is confirmed as a potential voltage sag event. Otherwise, it is not confirmed as a potential voltage sag event.

[0074] S5: Perform secondary detection of potential voltage sag events based on the preliminary identification results and waveform changes.

[0075] The voltage sag event types are marked, including transient sag, short-term sag, long-term sag and normal. The marked voltage sag data set is used to train the ELM classifier, and the weights and biases of the hidden layer neurons are randomly generated. The weights of the output layer remain trainable.

[0076] Extract features from the initially detected potential voltage sag events and known voltage sag event waveforms;

[0077] The extracted features are input into the trained ELM classifier to finally confirm the voltage sag event and identify the type of voltage sag event.

[0078] Preferably, the present application realizes accurate detection of voltage sag events by designing a multi-level detection mechanism.

[0079] Example 2

[0080] The present invention provides a distribution network voltage sag event detection device, which is used to implement the steps of a distribution network voltage sag event detection method as described in any of the above embodiments. The distribution network voltage sag event detection device includes:

[0081] A data acquisition module is configured to acquire voltage sag data and voltage sag simulation data, and select reference data from the voltage sag data and the voltage sag simulation data;

[0082] A feature extraction module is configured to perform feature extraction on the voltage sag data and the reference data;

[0083] A hash operation module is configured to perform hash calculation on the extracted features to generate a hash sequence;

[0084] A first detection module is configured to define a first threshold and a second threshold, adjust the first threshold and the second threshold according to the real-time operating state of the distribution network, and preliminarily detect a potential voltage sag event based on the hash sequence, the first threshold and the second threshold;

[0085] The second detection module is configured to perform a secondary detection of a potential voltage sag event by combining the preliminary recognition result and the waveform change.

[0086] Example 3

[0087] This embodiment provides a terminal device, including:

[0088] one or more processors;

[0089] A memory, coupled to the processor, for storing one or more programs;

[0090] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting a voltage sag event in a power distribution network as described above.

[0091] The processor is used to control the overall operation of the terminal device to complete all or part of the steps of the above-mentioned method for detecting a voltage sag event in a distribution network. The memory is used to store various types of data to support the operation of the terminal device, and these data may include, for example, instructions for any application or method used to operate on the terminal device, as well as data related to the application. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0092] The terminal device can be implemented by one or more application-specific integrated circuits (Application Specific1n Integrated Circuit, ASC), digital signal processors (Digital Signal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute a distribution network voltage sag event detection method as described in any of the above embodiments, and achieve the same technical effect as the above method.

[0093] Example 4

[0094] This embodiment provides a computer-readable storage medium, and when the program instructions are executed by a processor, the steps of a method for detecting a voltage sag event in a distribution network as described in any of the above embodiments are implemented. For example, the computer-readable storage medium may be the above-mentioned memory including the program instructions, and the above-mentioned program instructions may be executed by a processor of a terminal device to complete a method for detecting a voltage sag event in a distribution network as described in any of the above embodiments, and achieve the same technical effect as the above-mentioned method.

[0095] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in an assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed ASIC for this purpose.

[0096] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that may be executed by one or more processors.

[0097] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, a RAM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or part thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques described in the present invention, the present invention also includes the computer itself. The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on a display.

[0098] As used in this application, the terms "component", "module", "system", etc. are intended to refer to a computer-related entity, which can be hardware, firmware, a combination of hardware and software, software, or software in operation. For example, a component can be, but is not limited to: a process running on a processor, a processor, an object, an executable file, a thread in execution, a program, and / or a computer. As an example, an application running on a computing device and the computing device can both be components. One or more components can exist in a process and / or thread in execution, and a component can be located in a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures thereon. These components can communicate in a local and / or remote process manner, such as according to a signal having one or more data packets (e.g., data from a component that interacts with another component in a local system, a distributed system, and / or interacts with other systems in a signal manner through a network such as the Internet).

[0099] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting a voltage sag event in a distribution network, characterized in that: include: Collecting voltage sag data and voltage sag simulation data, and selecting reference data from the voltage sag data and voltage sag simulation data; Extract features from voltage sag data and benchmark data; Perform hash calculation on the extracted features to generate a hash sequence; defining a first threshold and a second threshold, and preliminarily detecting a potential voltage sag event based on the hash sequence, the first threshold and the second threshold; Combine the initial identification results with the waveform changes to conduct a secondary detection of the potential voltage sag event; The collecting of voltage sag data and voltage sag simulation data, and selecting reference data from the voltage sag data and voltage sag simulation data comprises the following steps: (1) collecting voltage sag data, that is, collecting voltage signals through a capacitive voltage transformer, and performing error correction on the voltage sag data through a correction unit, wherein the correction unit includes a capacitive voltage transformer, a plurality of current sensors, a compensating reactor, an amplifier, an LMS filter, an impedance compensator, and a corrector; The voltage signal and the current signal are collected through a capacitive voltage transformer and a current sensor respectively; Furthermore, the current signal is weighted fused: In the formula, is the current signal after weighted fusion, t is the time, is a weight factor that is dynamically adjusted based on the current sensor accuracy and historical data error. is the measurement signal of the kth current sensor, N is the number of current sensors; Furthermore, the weighted fused current signal is input into the compensation reactor for preliminary compensation, and the current sensor measures the current signal i(t) and transmits it to the signal amplifier; Furthermore, the current signal after preliminary compensation is input into the amplifier for amplification, that is, the weak signal is amplified by the low-noise amplifier, and then the noise is eliminated by the LMS filter to ensure the signal purity; Furthermore, the processed current signal is input into the impedance compensator, and secondary compensation is performed based on the KVL theorem, and a secondary compensated voltage signal is output; by introducing a dynamic adjustment factor , and Ensure the real-time and accuracy of the compensation voltage, as shown below: In the formula, is the secondary compensation voltage, , and It is a dynamic adjustment factor that is adjusted in real time based on actual working conditions. Used to adjust the effect of capacitance on the compensation voltage, Used to adjust the effect of inductance on compensation voltage, Used to adjust the effect of resistance on the compensation voltage, which can effectively correct the errors caused by component parameter drift and environmental changes; is the processed current signal; is the equivalent capacitance, is the equivalent inductance, is the equivalent resistance, t is the time; Furthermore, the secondary compensation voltage signal The voltage signal collected by the capacitive voltage transformer Superimpose and output the corrected voltage value : Where δ(t) is the dynamic ratio correction coefficient, which is adaptively adjusted based on historical errors. is a fixed transformation ratio coefficient, used to adjust the overall voltage level, m is a normalization coefficient of the compensation voltage, used to adjust the scale of voltage compensation, u(t) is the voltage collected by the capacitive voltage transformer, and t is time; Furthermore, a real-time error estimation model is introduced to dynamically optimize key parameters using a feedback control system, and the corrected voltage value is calculated in each sampling period. With the expected voltage Error , and use it for parameter optimization in the next cycle: Based on error The size and rate of change of the impedance parameter and ratio correction factor Dynamic adjustment is performed to minimize the error. The adjustment rules are as follows: In the formula, is the capacitance adjustment step size, is the step size of inductance adjustment, is the step size of resistance adjustment, is the step size of ratio correction; is the value of the equivalent capacitance at time t, is the value of the equivalent inductance at time t, is the value of the equivalent resistance at time t, is the value of the dynamic ratio correction coefficient at time t; is the value of the equivalent capacitance at time t+1, is the value of the equivalent inductance at time t+1, is the value of the equivalent resistance at time t+1, is the value of the dynamic ratio correction coefficient at time t+1; (2) Collecting voltage sag simulation data Establish a power system simulation model based on the grid topology, component parameters and operating conditions of the distribution network; Define the fault model; Setting simulation parameters, wherein the simulation parameters include fault conditions and random variables; Perform simulation and output voltage sag simulation data; in each simulation, randomly generate fault events and system operating conditions, run the power system simulation model for each random event, and perform multiple simulations; Wherein, the feature extraction includes: Selecting the data with the shortest data length from the voltage sag data and the voltage sag start segment of the voltage sag simulation data as the reference data; Extract time domain, frequency domain and statistical features of voltage sag data and benchmark data.

2. The method for detecting a voltage sag event in a distribution network according to claim 1, characterized in that: The hash calculation includes: Convert the extracted features into vector form; The feature vector is hashed using the SHA-256 algorithm to generate a 64-bit binary hash sequence.

3. The method for detecting a voltage sag event in a distribution network according to claim 2, characterized in that: The initial detection of potential voltage sag events includes: Adjust the first threshold and the second threshold according to the real-time operating state of the distribution network, and preliminarily detect potential voltage sag events based on the hash sequence, the first threshold and the second threshold; Compare the difference between the hash sequence of the voltage sag data and the hash sequence of the reference data by calculating the Hamming distance between the two, and if the Hamming distance is greater than or equal to a first threshold, mark it as a potential voltage sag event, otherwise do not mark it; The Hamming distance is compared with a second threshold value, and if the Hamming distance is less than or equal to the second threshold value, it is confirmed as a potential voltage sag event, otherwise it is not confirmed as a potential voltage sag event.

4. The method for detecting a voltage sag event in a distribution network according to claim 3, characterized in that: The secondary detection includes: Extract features from the initially detected potential voltage sag events and known voltage sag event waveforms; The extracted features are input into the ELM classifier for final confirmation of the voltage sag event.

5. A distribution network voltage sag event detection device, used to implement the distribution network voltage sag event detection method according to any one of claims 1 to 4, characterized in that: The distribution network voltage sag event detection device comprises: A data acquisition module is configured to acquire voltage sag data and voltage sag simulation data, and select reference data from the voltage sag data and voltage sag simulation data; A feature extraction module is configured to perform feature extraction on the voltage sag data and the reference data; A hash operation module is configured to perform hash calculation on the extracted features to generate a hash sequence; A first detection module is configured to define a first threshold and a second threshold, and preliminarily detect a potential voltage sag event based on the hash sequence, the first threshold and the second threshold; The second detection module is configured to perform a secondary detection of a potential voltage sag event by combining the preliminary recognition result and the waveform change.

6. A terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting a voltage sag event in a distribution network as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the method for detecting a voltage sag event in a distribution network as claimed in any one of claims 1 to 4.

Images