A series fault arc detection and positioning method, system, terminal and medium

Abstract

The present invention discloses a method for detecting and locating a series arc fault, and discloses a system, terminal, and medium having the method. The method comprises a measurement section, a data preprocessing section, and a decision-making section. The measurement section is used for current and voltage data acquisition. The data preprocessing section performs analysis in the time domain, divides the signal into separate cycles, constructs current and voltage arrays, and extracts arc fault features of the current and voltage signals. The decision-making section uses a random forest classifier to classify and detect single-cycle signals and adopts a scoring system for arc fault diagnosis. Arc fault location (line selection) is achieved based on the MVC50 feature vector and the k-nearest neighbor algorithm. The method achieves high-accuracy detection and high-precision fault location of low-voltage series arc faults, thereby improving the safety and reliability of the power grid.

Description

Technical Field

[0001] The present invention relates to the field of power system detection technology, and in particular to a series fault arc detection and positioning method and system. Background Art

[0002] Arc faults are a serious problem in low-voltage power grids and a major cause of household fires. For 220V / 50Hz AC power used behind the meter, parallel arc and ground arc faults have distinct characteristics and are easy to detect. However, due to the influence of dynamic arc resistance and load characteristics, when a low-voltage AC series arc fault occurs, arc current characteristics vary significantly under different load types. For example, the degree of waveform distortion and the length of the "zero-off period" during zero crossing vary, increasing the difficulty of arc fault detection and location. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method for detecting and locating series fault arcs, which can be applied to arc detection in low-voltage AC home networks. The method includes a measurement part, a data preprocessing part and a decision-making part; the measurement part is used for current and voltage data acquisition, the data preprocessing part performs analysis in the time domain, divides the signal into separate cycles, constructs current and voltage arrays, and extracts arc fault features of current and voltage signals; the decision-making part uses a random forest classifier to classify and detect single-cycle signals, and adopts a scoring system for arc fault diagnosis; based on MVC 50 The eigenvector and k-nearest neighbor algorithm are used to locate arc faults (line selection). This allows for high-accuracy detection and high-precision fault location of low-voltage series arc faults, improving the safety and reliability of the power grid.

[0004] The present invention also provides a system for detecting and locating the series fault arc.

[0005] The method for detecting and locating a series arc fault according to the first embodiment of the present invention is characterized by comprising the following steps:

[0006] Get the original signal of the main power line;

[0007] Performing low-pass filtering on the original signal to obtain a processed signal;

[0008] obtaining arc fault characteristics in the processed signal;

[0009] Based on the feature vector containing the arc fault feature, a random forest classifier is applied, and the arc fault is detected based on the random forest classifier, if a fault is detected within a single cycle, a fault parameter is increased by one, and if no fault is detected, the fault parameter is decreased by one, and when the fault parameter is greater than a predetermined value, it is considered that a fault exists in the line;

[0010] When a fault occurs, the identification feature vector of the arc fault is calculated;

[0011] The arc fault is located based on the identification feature vector.

[0012] The method for detecting and locating a series fault arc according to an embodiment of the present invention has at least the following beneficial effects: the method provided by the present invention includes a measurement part, a data preprocessing part, and a decision-making part; the measurement part is used for current and voltage data acquisition, the data preprocessing part performs analysis in the time domain, divides the signal into separate cycles, constructs current and voltage arrays, and extracts arc fault features of the current and voltage signals; the decision-making part uses a random forest classifier to classify and detect single-cycle signals, and adopts a scoring system to diagnose arc faults; based on MVC 50 The eigenvector and k-nearest neighbor algorithm are used to locate arc faults (line selection). This achieves high-accuracy detection and high-precision fault location of low-voltage series arc faults, improving the safety and reliability of the power grid.

[0013] According to some embodiments of the present invention, in the step of performing low-pass filtering on the original signal to obtain a processed signal, the collected voltage signal and current signal are further converted into a two-dimensional voltage array U and a two-dimensional current array I, respectively, wherein:

[0014] U k =[u 1,k ,……,u m,k ,……,u M,k ]

[0015] I k =[i 1,k ,……,i m,k ,……,i M,k ].

[0016] According to some embodiments of the present invention, there are 12 arc fault features, with six pairs of features corresponding to the current two-dimensional array I and the voltage two-dimensional array U, respectively. The current two-dimensional array includes:

[0017] The sum of the differences between adjacent periods of array I:

[0018]

[0019] The sum of the absolute values ​​of adjacent periods of array I:

[0020]

[0021] Maximum Euclidean distance:

[0022]

[0023] Euclidean distance ED:

[0024]

[0025] Maximum single sample distance MSSD:

[0026] MSSD I (k)=max(|I k+1 (m)-I k (m)|),m∈<1,2,...,M>

[0027] Maximum slip difference MSD:

[0028]

[0029] By replacing the current two-dimensional array I in the above characteristics with the voltage two-dimensional array U, the remaining six arc fault characteristics are obtained.

[0030] According to some embodiments of the present invention, the minimum value of the fault parameter is 0, the maximum value is 50, and the fault parameter will no longer decrease when it reaches the minimum value, and will no longer increase when it reaches the maximum value.

[0031] According to some embodiments of the present invention, the random forest classifier divides the collected data into a training set and a test set; the training set has 7 sequences, in 6 sequences, only one device is connected to the fault line, and during the seventh run, when connected to the fault line, a maximum of 6 devices work; in the test set, the test set contains sequences of pairs, three groups, four groups, five groups, and all 6 groups of devices.

[0032] According to some embodiments of the present invention, the process of calculating an identification feature vector of an arc fault includes:

[0033] For each cycle k in which the random forest classifier detects an arc fault, the value of the fault parameter ALS is incremented and the vector ΔI is calculated. k :ΔI k =I k -I k-1 , stored in the VC array in the i-th column, where i is equal to k modulo 50; if no arc fault is detected, the value of the fault parameter ALS is decremented and a 0 vector is stored in the i-th column of the VC array;

[0034] Only ΔI during the period when the arc fault is detected k Vector Calculation MVC 50 Eigenvector, calculate MVC from VC array and fault parameter ALS 50 Eigenvectors:

[0035]

[0036] MVC 50 The number of attributes in the vector is reduced from 5000 to 50, and the average of every 100 values ​​is calculated to obtain the MVC 50-mean :

[0037]

[0038] According to some embodiments of the present invention, in the step of locating the arc fault based on the identification feature vector and the monitoring data, a k-nearest neighbor algorithm is used, where k=6; the feature used for classification is MVC 50-mean The average and maximum values ​​of .

[0039] A series arc fault detection and location system according to a second embodiment of the present invention is characterized by comprising:

[0040] Signal acquisition module, capable of acquiring the original signal of the main power line;

[0041] A data processing module, capable of performing low-pass filtering on the original signal to obtain a processed signal;

[0042] a feature extraction module capable of obtaining arc fault features in the processed signal;

[0043] a fault detection module, capable of applying a random forest classifier based on a feature vector containing the arc fault feature, and detecting the arc fault based on the random forest classifier, incrementing a fault parameter by one if a fault is detected within a single cycle, and decrementing the fault parameter by one if no fault is detected, and determining that a fault exists in the line if the fault parameter is greater than a predetermined value;

[0044] The characteristic vector calculation module can calculate the identification characteristic vector of the arc fault when a fault occurs;

[0045] The fault location module can locate the arc fault based on the identification feature vector.

[0046] According to the terminal of the third embodiment of the present invention, the terminal includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned series fault arc detection and location method is implemented.

[0047] According to a fourth aspect of the present application, a computer-readable storage medium is provided, which stores computer-executable instructions for executing the above-mentioned series fault arc detection and location method.

[0048] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments with reference to the accompanying drawings, in which:

[0050] Figure 1 A schematic diagram of the steps of a method for detecting and locating a series arc fault according to an embodiment of the present invention;

[0051] Figure 2 4 is a structural block diagram of a series fault arc detection and location system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0053] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention.

[0054] In the description of the present invention, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0055] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0056] Reference Figure 1 , an embodiment of the present application provides a method for detecting and locating a series arc fault, comprising:

[0057] Step S100: Acquire the original signal of the main power line.

[0058] Use a transformer to obtain the voltage u of the main power line total (t), use current transformer to obtain the current i of the main power line total (t). Sampling frequency fs = 250 kHz, a single 50 Hz current and voltage cycle, then a single cycle contains M = 5000 samples.

[0059] Step S200: low-pass filter the original signal to obtain a processed signal.

[0060] For the original voltage signal u total (t) is low-pass filtered with a cut-off frequency of 70 Hz to eliminate the effects of harmonics higher than the fundamental component. The beginning of each cycle is the time instant when the voltage fundamental value crosses from zero to a positive value. Therefore, the beginning of each cycle is the same regardless of the disturbance in the specific power grid.

[0061] The collected signal u total (t), i total (t) are converted into 2D arrays U and I respectively.

[0062] U k =[u 1,k ,……,u m,k ,……,u M,k ]

[0063] I k =[i 1,k ,……,i m,k ,……,i M,k ]

[0064] Step S300: Acquire arc fault characteristics in the processed signal.

[0065] The following signal features are calculated for each signal cycle. The feature vector contains 12 features, and 6 pairs of features are used for voltage and current signals. The following calculations are performed on the current and voltage signals respectively:

[0066] a. The sum of the differences between adjacent periods of array I:

[0067]

[0068] b. The sum of the absolute values ​​of adjacent periods of array I

[0069]

[0070] c. Maximum Euclidean distance

[0071]

[0072] d. Euclidean distance ED

[0073]

[0074] e. Maximum Single Sample Distance (MSSD)

[0075] MSSD I (k)=max(|I k+1 (m)-I k (m)|),m∈<1,2,...,M> (5)

[0076] f. Maximum slip difference (MSD)

[0077]

[0078] By replacing the current two-dimensional array I in the above formulas (1) to (6) with the voltage two-dimensional array U, the remaining six arc fault characteristics can be obtained.

[0079] Step S400: Based on the feature vector containing the arc fault feature, a random forest classifier is applied, and the arc fault is detected based on the random forest classifier. If a fault is detected within a single cycle, a fault parameter is increased by one; if no fault is detected, the fault parameter is decreased by one. If the fault parameter is greater than a predetermined value, it is considered that a fault exists in the line.

[0080] Based on a feature vector consisting of 12 arc fault signatures, a random forest classifier with n=25 trained trees was used to detect a series of arc faults. If an arc fault was detected within a cycle, the value of the ALS parameter was incremented by 1, with a maximum value of 50. If no arc fault was detected within a cycle, the value of the ALS parameter was decremented by 1, with a minimum value of 0. If more than six arc fault cycles (ALS>=7) were detected within the last second, an arc fault was present on the line.

[0081] For the random forest classifier, the collected data was divided into two datasets: a training set and a test set. The training set contained seven sequences, six of which had only one device connected to the fault line. During the seventh run, a maximum of six devices worked when connected to the fault line. The test set contained sequences of pairs, triplets, quadruplets, quintuples, and all six device groups.

[0082] Step S500: When a fault occurs, calculate an identification feature vector of the arc fault.

[0083] For each cycle k in which the random forest classifier detects an arc fault, the value of ALS (the number of cycles in which the arc fault was detected in the last second) is incremented, and the vector ΔI is calculated. k :ΔI k =I k -Ik-1 , stored in the VC array in the i-th column, where i is equal to k modulo 50; if no arc fault is detected, the ALS value is decremented and a 0 vector is stored in the i-th column of the VC array.

[0084] Only ΔI during the period when the arc fault is detected k Vector Calculation MVC 50 Eigenvectors, compute MVC from VC array and ALS 50 Eigenvector.

[0085]

[0086] MVC 50 The number of attributes in the vector is reduced from 5000 (the number of samples in one cycle) to 50, and the average of every 100 values ​​is calculated to obtain the MVC 50-mean .

[0087]

[0088] Step S600: locating the arc fault based on the identification feature vector.

[0089] The location of the series arc fault is achieved by identifying the equipment powered by the fault line. For the identification (selection) of the fault line, the k-nearest neighbor algorithm is used, with k=6. The features used for classification are based on MVC 50-mean , the other two features are MVC 50-mean The average and maximum values ​​of .

[0090] Another embodiment of the present application provides a series fault arc detection and location system, such as Figure 2 As shown, the system 20 includes:

[0091] The signal acquisition module 201 is capable of acquiring the original signal of the main power line;

[0092] The data processing module 202 is capable of performing low-pass filtering on the original signal to obtain a processed signal;

[0093] A feature extraction module 203 is capable of obtaining arc fault features in the processed signal;

[0094] The fault detection module 204 can apply a random forest classifier based on the feature vector containing the arc fault feature, and detect the arc fault based on the random forest classifier. If a fault is detected within a single cycle, a fault parameter is incremented by one; if no fault is detected, the fault parameter is decremented by one. If the fault parameter is greater than a predetermined value, it is considered that a fault exists in the line.

[0095] The feature vector calculation module 205 is capable of calculating the identification feature vector of the arc fault when a fault occurs;

[0096] The fault location module 206 can locate the arc fault based on the identification feature vector.

[0097] The embodiment of the present application includes a measurement section, a data preprocessing section, and a decision-making section. The measurement section is used for current and voltage data acquisition. The data preprocessing section performs analysis in the time domain, divides the signal into separate cycles, constructs current and voltage arrays, and extracts arc fault characteristics of the current and voltage signals. The decision-making section uses a random forest classifier to classify and detect single-cycle signals and adopts a scoring system for arc fault diagnosis. Arc fault location (line selection) is achieved based on the MVC50 feature vector and the k-nearest neighbor algorithm. This achieves high-accuracy detection and high-precision fault location of low-voltage series arc faults, improving the safety and reliability of the power grid.

[0098] The jam detection device of the application of this embodiment can execute the series fault arc detection and positioning method provided in the embodiment of this application. Its implementation principle is similar and will not be repeated here.

[0099] Another embodiment of the present application provides a terminal, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned series arc fault detection and location method when executing the computer program.

[0100] Specifically, a processor may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. A processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0101] Specifically, the processor is connected to the memory via a bus. The bus may include a path for transmitting information. The bus may be a PCI bus or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc.

[0102] The memory may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an EEPROM, CD-ROM or other optical disk storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0103] Optionally, the memory is used to store the code of the computer program for executing the solution of the present application, and the execution is controlled by the processor. The processor is used to execute the application code stored in the memory to implement Figure 2 The illustrated embodiment provides the functionality of a series fault arc detection and location system.

[0104] Another embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for executing the above-mentioned Figure 1 The series fault arc detection and location method shown.

[0105] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0106] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0107] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the above implementation mode. Technical personnel familiar with the field can also make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for detecting and locating a series arc fault, characterized in that: The following steps are involved: Get the original signal of the main power line; Performing low-pass filtering on the original signal to obtain a processed signal; The collected voltage signal and current signal are converted into a voltage two-dimensional array U and a current two-dimensional array I respectively, where: IN k =[in 1,k ,……,in m,k ,……,in M,k ] I k =[i 1,k ,……,i m,k ,……,i M,k ]; Obtain arc fault features in the processed signal; wherein, there are 12 arc fault features, with six pairs of features corresponding to the current two-dimensional array I and the voltage two-dimensional array U, respectively, wherein the current two-dimensional array includes: The sum of the differences between adjacent periods of array I: The sum of the absolute values ​​of adjacent periods of array I: Maximum Euclidean distance: Euclidean distance ED: Maximum single sample distance MSSD: MSSD I (k)=max(|I k+1 (m)-I k (m)|),m∈<1,2,...,M> Maximum slip difference MSD: Replacing the current two-dimensional array I in the above characteristics with the voltage two-dimensional array U will yield the remaining six arc fault characteristics. Based on the feature vector containing the arc fault feature, a random forest classifier is applied, and the arc fault is detected based on the random forest classifier, if a fault is detected within a single cycle, a fault parameter is increased by one, and if no fault is detected, the fault parameter is decreased by one, and when the fault parameter is greater than a predetermined value, it is considered that a fault exists in the line; When a fault occurs, the arc fault identification feature vector is calculated, including: For each cycle k in which the random forest classifier detects an arc fault, the value of the fault parameter ALS is incremented and the vector ΔI is calculated. k :ΔI k =I k -I k-1 , stored in the VC array in the i-th column, where i is equal to k modulo 50; if no arc fault is detected, the value of the fault parameter ALS is decremented and a 0 vector is stored in the i-th column of the VC array; Only ΔI during the period when the arc fault is detected k Vector Calculation MVC 50 Eigenvector, calculate MVC from VC array and fault parameter ALS 50 Eigenvectors: MVC 50 The number of attributes in the vector is reduced from 5000 to 50, and the average of every 100 values ​​is calculated to get the MVC 50-mean : The arc fault is located based on the identification feature vector.

2. The method according to claim 1, characterized in that The minimum value of the fault parameter is 0, and the maximum value is 50. When the minimum value is reached, the fault parameter will not decrease any more, and when the maximum value is reached, the fault parameter will not increase any more.

3. The method according to claim 1, characterized in that The random forest classifier divides the collected data into a training set and a test set; the training set has 7 sequences, in which only one device is connected to the fault line in 6 sequences, and during the seventh run, when connected to the fault line, a maximum of 6 devices work; in the test set, the test set contains sequences of pairs, groups of three, groups of four, groups of five, and all 6 groups of devices.

4. The method according to claim 1, wherein In the step of locating the arc fault based on the identification feature vector and monitoring data, a k-nearest neighbor algorithm is used, where k=6; the feature used for classification is MVC 50-mean The average and maximum values ​​of .

5. A series fault arc detection and location system, characterized in that: include: Signal acquisition module, capable of acquiring the original signal of the main power line; A data processing module, capable of performing low-pass filtering on the original signal to obtain a processed signal; The collected voltage signal and current signal are converted into a voltage two-dimensional array U and a current two-dimensional array I respectively, where: IN k =[in 1,k ,……,in m,k ,……,in M,k ] I k =[i 1,k ,……,i m,k ,……,i M,k ]; The feature extraction module is capable of obtaining arc fault features from the processed signal; wherein, there are 12 arc fault features, with six pairs of features corresponding to the current two-dimensional array I and the voltage two-dimensional array U, respectively, wherein the current two-dimensional array includes: The sum of the differences between adjacent periods of array I: The sum of the absolute values ​​of adjacent periods of array I: Maximum Euclidean distance: Euclidean distance ED: Maximum single sample distance MSSD: MSSD I (k)=max(|I k+1 (m)-I k (m)|),m∈<1,2,...,M> Maximum slip difference MSD: Replacing the current two-dimensional array I in the above characteristics with the voltage two-dimensional array U will yield the remaining six arc fault characteristics. a fault detection module, capable of applying a random forest classifier based on a feature vector containing the arc fault feature, and detecting the arc fault based on the random forest classifier, incrementing a fault parameter by one if a fault is detected within a single cycle, and decrementing the fault parameter by one if no fault is detected, and determining that a fault exists in the line if the fault parameter is greater than a predetermined value; The feature vector calculation module can calculate the identification feature vector of the arc fault when a fault occurs, including: For each cycle k in which the random forest classifier detects an arc fault, the value of the fault parameter ALS is incremented and the vector ΔI is calculated. k :ΔI k =I k -I k-1 , stored in the VC array in the i-th column, where i is equal to k modulo 50; if no arc fault is detected, the value of the fault parameter ALS is decremented and a 0 vector is stored in the i-th column of the VC array; Only ΔI during the period when the arc fault is detected k Vector Calculation MVC 50 Eigenvector, calculate MVC from VC array and fault parameter ALS 50 Eigenvectors: MVC 50 The number of attributes in the vector is reduced from 5000 to 50, and the average of every 100 values ​​is calculated to get the MVC 50-mean : The fault location module can locate the arc fault based on the identification feature vector.

6. A terminal comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 4. 7 . A computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method according to claim 1 .

Images