Methods, devices, electronic equipment, and storage media for identifying mining activities.

Abstract

The present invention provides a method, device, electronic device and storage medium for identifying mining behavior. The method includes: obtaining a mixed electrical signal of at least one power usage parameter of a user; for each mixed electrical signal of a power usage parameter, based on an improved fast independent component analysis method, decomposing the mixed electrical signal of the power usage parameter to obtain M independent electrical signals corresponding to the power usage parameter; for each power usage parameter, respectively calculating the distance value between each independent electrical signal corresponding to the power usage parameter and a preset mining electrical signal corresponding to the power usage parameter to obtain M distance values ​​corresponding to the power usage parameter; judging whether the user has mining behavior according to the M distance values ​​corresponding to each power usage parameter. The present invention can improve the reliability of mining behavior identification.

Description

Technical Field

[0001] The present invention relates to the technical field of mining behavior, and in particular to a method, device, electronic device and storage medium for identifying mining behavior. Background Art

[0002] People's lives are closely related to electricity. For users who implement residential electricity prices, if they participate in virtual currency "mining" activities, it will affect the reliable and stable operation of the power grid.

[0003] Currently, most existing technologies detect whether a user is mining by detecting web page traffic on the user's computer or using mining identification scripts. However, identifying whether a user is mining by monitoring the user's computer has problems such as poor compatibility and inaccurate identification. Summary of the invention

[0004] The present invention provides a method, device, electronic device and storage medium for identifying mining behavior, so as to solve the problems of poor compatibility and inaccurate identification when identifying whether a user is mining by monitoring the user's computer.

[0005] In a first aspect, the present invention provides a method for identifying mining behavior, comprising:

[0006] Acquire a mixed electrical signal of at least one electrical usage parameter of a user;

[0007] For each mixed electrical signal of an electrical parameter, based on an improved fast independent component analysis method, the mixed electrical signal of the electrical parameter is decomposed to obtain M independent electrical signals corresponding to the electrical parameter;

[0008] For each power usage parameter, respectively calculate the distance value between each independent electrical signal corresponding to the power usage parameter and the preset mining electrical signal corresponding to the power usage parameter to obtain M distance values ​​corresponding to the power usage parameter;

[0009] According to the M distance values ​​corresponding to each power consumption parameter, it is determined whether the user has mining behavior.

[0010] In a possible implementation, for each mixed electrical signal of the electrical parameter, based on the improved fast independent component analysis method, the mixed electrical signal of the electrical parameter is decomposed to obtain M independent electrical signals corresponding to the electrical parameter, including:

[0011] For each mixed electrical signal of an electrical parameter, the mixed electrical signal of the electrical parameter is decentralized to obtain a first mixed electrical signal with a mean of zero; the first mixed electrical signal is whitened and denoised using a minimum noise separation method to obtain a second mixed electrical signal; the initial value of the mixing matrix is ​​determined using the steepest descent method, and based on the initial value, the mixing matrix is ​​iteratively obtained using the Newton method; based on the mixing matrix, the second mixed electrical signal is decomposed into M independent electrical signals corresponding to the mixed electrical signal of the electrical parameter.

[0012] In a possible implementation, judging whether the user has engaged in mining behavior based on the M distance values ​​corresponding to each power usage parameter includes:

[0013] For each power usage parameter, the M distance values ​​corresponding to the power usage parameter are compared with the preset distance value corresponding to the power usage parameter. If the distance value of the power usage parameter is less than the preset distance value corresponding to the power usage parameter, it is determined that the power usage parameter is in an abnormal state.

[0014] If the number of power usage parameters in an abnormal state is greater than a preset number, it is determined that the user has engaged in mining behavior.

[0015] In one possible implementation, the mixed electrical signal of at least one electrical parameter includes at least one of a mixed electrical signal of current, a mixed electrical signal of voltage, a mixed electrical signal of active power, a mixed electrical signal of reactive power, a mixed electrical signal of frequency, and a mixed electrical signal of power factor.

[0016] In a possible implementation, after determining whether the user has engaged in mining behavior based on the M distance values ​​corresponding to each power usage parameter, the method further includes:

[0017] If the user is determined to be engaged in mining, an alarm signal will be sent to the power supply company.

[0018] In a second aspect, the present invention provides a mining behavior identification device, comprising:

[0019] An acquisition module, used to acquire a mixed electrical signal of at least one electrical usage parameter of a user;

[0020] A decomposition module, for decomposing the mixed electrical signal of each electrical parameter based on an improved fast independent component analysis method to obtain M independent electrical signals corresponding to the electrical parameter;

[0021] A calculation module, for calculating, for each power usage parameter, a distance value between each independent electrical signal corresponding to the power usage parameter and a preset mining electrical signal corresponding to the power usage parameter, to obtain M distance values ​​corresponding to the power usage parameter;

[0022] The judgment module is used to judge whether the user has mining behavior according to the M distance values ​​corresponding to each power consumption parameter.

[0023] In a possible implementation, the decomposition module is further used to:

[0024] For each mixed electrical signal of an electrical parameter, the mixed electrical signal of the electrical parameter is decentralized to obtain a first mixed electrical signal with a mean of zero; the first mixed electrical signal is whitened and denoised using a minimum noise separation method to obtain a second mixed electrical signal; the mixing matrix is ​​determined using the steepest descent method, and based on the initial value, the mixing matrix is ​​iteratively obtained using the Newton method; based on the mixing matrix, the second mixed electrical signal is decomposed into M independent electrical signals corresponding to the mixed electrical signal of the electrical parameter.

[0025] In a possible implementation, the determination module includes:

[0026] A first judgment unit is used to compare, for each power usage parameter, the M distance values ​​corresponding to the power usage parameter with the preset distance value corresponding to the power usage parameter, and if the distance value of the power usage parameter is less than the preset distance value corresponding to the power usage parameter, determine that the power usage parameter is in an abnormal state;

[0027] The second judgment unit is used to determine that the user has engaged in mining behavior if the number of power usage parameters in an abnormal state is greater than a preset number.

[0028] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of a method for identifying mining behavior in the first aspect or any possible implementation of the first aspect.

[0029] The present invention provides a method, device, electronic device and storage medium for identifying mining behavior. The method decomposes the mixed electrical signals of the user's various electricity usage parameters to obtain an independent electrical signal, and obtains the distance value between the independent electrical signal and the preset mining electrical signal through calculation and solution, thereby judging whether the user has engaged in mining behavior. The method has a wide range of applications, high compatibility and accurate identification, and is conducive to timely identification and processing of mining users, thereby ensuring the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative labor.

[0031] Figure 1is a flowchart of the implementation of the method for identifying mining behavior provided by an embodiment of the present invention;

[0032] Figure 2 It is a schematic diagram of hardware for identifying mining behavior provided by an embodiment of the present invention;

[0033] Figure 3 It is a specific workflow diagram provided by an embodiment of the present invention;

[0034] Figure 4 is a flow chart of identifying the decomposition of a mixed data signal into independent electrical signals provided by an embodiment of the present invention;

[0035] Figure 5 It is a schematic diagram of the structure of a mining behavior identification device provided by an embodiment of the present invention;

[0036] Figure 6 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] 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 invention. However, it should be clear to those skilled in the art that the present invention may 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 invention.

[0038] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0039] See also Figure 1 , which shows a flowchart of the implementation of the method for identifying mining behavior provided by an embodiment of the present invention. Figure 1 As shown, a method for identifying mining behavior may include:

[0040] S101, obtaining a mixed electrical signal of at least one electrical usage parameter of a user.

[0041] Optionally, a mixed electrical signal of at least one power usage parameter of the user may be collected in real time, and the collection frequency may be in seconds, so as to achieve real-time detection of the user's power usage data and improve judgment efficiency.

[0042] Specifically, the smart meter can be used to adopt a non-invasive detection method to obtain in real time the electrical signals of various electrical usage parameters at the user entrance, and the electrical signals of various electrical usage parameters at the user entrance are all mixed electrical signals.

[0043] Optionally, the power parameters may include one or more of current, voltage, active power, reactive power, frequency and power factor, etc., which are power parameters collected at the user entrance. For example, they may include the current signal of the user's total input current, the voltage signal of the total input voltage, the power signal of the total input active power, etc., which may be selected according to actual conditions.

[0044] S102 , for each mixed electrical signal of the electrical usage parameter, based on an improved fast independent component analysis method, decompose the mixed electrical signal of the electrical usage parameter to obtain M independent electrical signals corresponding to the electrical usage parameter.

[0045] Optionally, for each mixed electrical signal of power usage parameters, the mixed electrical signal of power usage parameters includes electrical signals of multiple electrical devices of the user. Based on the improved fast independent component analysis method, the mixed electrical signal of power usage parameters can be decomposed into M independent electrical signals, where M is the number of electrical devices of the user. For example, the user has a computer, a refrigerator, and a water heater, and the mixed electrical signal of current is a mixture of electrical signals of multiple electrical devices such as the electrical signal of the computer, the electrical signal of the refrigerator, and the electrical signal of the water heater.

[0046] Specifically, based on the improved fast independent component analysis method, the mixed electrical signals of various electrical parameters acquired at each moment can be decomposed into corresponding independent electrical signals.

[0047] The embodiment of the present invention optimizes the data preprocessing of the fast independent component analysis method and the process of determining the mixing matrix, thereby obtaining an improved fast independent component analysis method, and uses the improved fast independent component analysis method to decompose the mixed electrical signal of each electrical parameter into corresponding independent electrical signals.

[0048] Specifically, the minimum noise separation method is used to remove noise and whiten the moderate electrical signal of the power parameters, and the steepest descent method is used to determine the initial mixing matrix of the fast independent component analysis method, and then the mixing matrix of the fast independent component analysis method is determined.

[0049] Exemplarily, the power parameters include current and voltage, and the current mixed electric signal can be decomposed into M independent current electric signals corresponding to the current by using the improved fast independent component analysis method; the voltage mixed electric signal can be decomposed into M independent voltage electric signals by using the improved fast independent component analysis method. The M independent electric signals correspond to the user's M power devices.

[0050] S103, for each power usage parameter, respectively calculate the distance value between each independent electrical signal corresponding to the power usage parameter and the preset mining electrical signal corresponding to the power usage parameter, and obtain M distance values ​​corresponding to the power usage parameter.

[0051] Optionally, each power parameter corresponds to a preset mining electrical signal. For example, if the power parameter is current, the current corresponds to the current preset mining electrical signal. The distance value between each independent electrical signal corresponding to the current and the current preset mining electrical signal is calculated respectively, and M distance values ​​corresponding to the current can be obtained. If the power parameter is voltage, M distance values ​​corresponding to the voltage can be obtained, and the same is true for other power parameters.

[0052] For each preset mining electric signal corresponding to an electric parameter, the preset mining electric signal corresponding to the electric parameter is an independent electric signal corresponding to the electric parameter when the user is in the mining state. The electric signals of each electric parameter of the user in the mining state are collected as the preset mining electric signal corresponding to each electric parameter. The electric signal obtained in the above manner is universal and can be applied to the scenario of determining whether other users have mining behavior.

[0053] Optionally, for each power usage parameter, a system clustering method can be used to calculate the distance value between each independent electrical signal corresponding to the power usage parameter and the preset mining electrical signal corresponding to the power usage parameter, with the preset mining electrical signal corresponding to the power usage parameter as the clustering center, to obtain M distance values ​​corresponding to the power usage parameter.

[0054] For example, the power parameters include voltage. The preset independent mining electrical signal corresponding to the voltage is used as the clustering center. The distance value between each independent voltage electrical signal and the preset independent mining electrical signal corresponding to the voltage is calculated through the system clustering method.

[0055] Optionally, you can use the formula Calculate the distance between each of the N independent electrical signals at each moment and the corresponding preset independent electrical signals for mining. i is the state distance value at the i-th moment, Zalone ij is the independent electrical signal of the jth electrical parameter at the ith moment, Zm ij is the preset mining independent electrical signal of the j-th power usage parameter at the i-th moment.

[0056] S104, judging whether the user has any mining behavior according to the M distance values ​​corresponding to each power usage parameter.

[0057] Optionally, the distance value of each power parameter can be compared with the preset distance value corresponding to the power parameter. If the distance value of the power parameter is less than the preset distance value corresponding to the power parameter, it can be determined that the user has engaged in mining. Alternatively, by counting the number of independent electrical signals whose distance values ​​are less than the preset distance value, it can be determined whether the user has engaged in mining. The specific setting can be made according to the actual situation.

[0058] You can use one electricity usage parameter condition to make a single judgment, or you can use multiple electricity usage parameters to make a comprehensive judgment. Using one electricity usage parameter condition to make a single judgment can improve the accuracy of mining behavior identification, and using multiple electricity usage parameters to make a comprehensive judgment can improve the reliability of mining behavior identification. The specific choice can be made according to actual conditions.

[0059] The embodiment of the present invention can accurately and reliably decompose the electrical signal of the power consumption parameter into independent electrical signals through the improved fast independent component analysis method, and further determine whether the user has mining behavior by calculating multiple distance values, so as to realize the reliable identification of non-entry "mining" behavior, and ensure the timeliness and continuity of the identification of "mining" behavior. The present invention has a wide range of applications, high reliability and high accuracy, and is conducive to maintaining the stable operation of the power grid.

[0060] In some embodiments of the present invention, the above-mentioned S102 of “for each mixed electrical signal of the electrical parameter, based on the improved fast independent component analysis method, decomposing the mixed electrical signal of the electrical parameter to obtain M independent electrical signals corresponding to the electrical parameter” may include:

[0061] For each mixed electrical signal of an electrical parameter, the mixed electrical signal of the electrical parameter is decentralized to obtain a first mixed electrical signal with a mean of zero; the first mixed electrical signal is whitened and denoised using a minimum noise separation method to obtain a second mixed electrical signal; the initial value of the mixing matrix is ​​determined using the steepest descent method, and based on the initial value, the mixing matrix is ​​iteratively obtained using the Newton method; based on the mixing matrix, the second mixed electrical signal is decomposed into M independent electrical signals corresponding to the mixed electrical signal of the electrical parameter.

[0062] In some embodiments of the present invention, the mixed electrical signal of at least one electrical parameter includes at least one of a mixed electrical signal of current, a mixed electrical signal of voltage, a mixed electrical signal of active power, a mixed electrical signal of reactive power, a mixed electrical signal of frequency, and a mixed electrical signal of power factor.

[0063] Specifically, the working process of the improved fast independent component analysis method is as follows:

[0064] First, the mixed electrical signals of power parameters such as current, voltage, active power, reactive power, frequency and power factor are decentralized, and the electrical signals of each power parameter are converted into mixed signals with a mean of zero. ij is a variable, specifically including: current I=Z i1 , voltage V = Z i2 , Active power P = Z i3 , reactive power Q = Z i4 、Frequency U=Z i5 、Power factor θ=Z i6 .

[0065] There are the following formulas (1) and (2):

[0066]

[0067]

[0068] Among them, formula (1) represents the decentralized signal set, and formula (2) represents decentralization.

[0069] Second, each mixed electrical signal is de-noised and whitened by the minimum noise fraction rotation (MNF) method. The covariance matrix of electrical signals such as current, voltage, active power, reactive power, frequency, and power factor is decomposed into an orthogonal eigenvector matrix and eigenvalue matrix, as shown in formula (3), where D is the eigenvector matrix of the covariance matrix decomposition, and λ is the eigenvalue matrix.

[0070]

[0071]

[0072]

[0073]

[0074] J(Z)≈[E{G(Z)}-E{G(v)}] 2 (7)

[0075] Where Y is the matrix after whitening and denoising, p is the matrix after decorrelation of the whitened matrix, R is the eigenvector of the covariance matrix of the matrix Y, and formula (7) is the load model, where J(Z) is the variable negative entropy, v is a Gauss random variable with an expected value of zero and a variance equal to the unit variance, E[●] is the mean calculation, and G(●) is a nonlinear function.

[0076] Third, the traditional fast independent component analysis method is very sensitive to the iterative initial value of the mixing matrix w, and the initial value of the mixing matrix w is generally randomly generated, and the final value is obtained after iteration. However, different initial values ​​will cause the algorithm to have different iterative efficiencies, and sometimes even fail to converge. To address this problem, this patent proposes the steepest descent method to improve the initial value of the mixing matrix, as follows:

[0077] (a): Randomly generate the initial iteration matrix w and orthogonalize it.

[0078] (b): Calculate E[Zg(w T Z)] at w, where g(●) is the derivative of G(●).

[0079]

[0080] w'=w-uE[xg(w T x)] (9)

[0081] If |w k+1 -w k |<ε, then w0=w', the iteration ends, and the initial value w0 of the mixing matrix w is obtained.

[0082] Substitute the improved iteration initial value w0 into the iterative formulas of equations (10) and (11), and normalize the mixing matrix w, as shown in equation (12), to obtain the final result of the mixing matrix.

[0083]

[0084]

[0085]

[0086] Z alone =w*Z (13)

[0087] Formula (10) is used to iterate the collected mixed electrical signal to obtain a mixed matrix w that meets the conditions, and the mixed signal is decomposed by formula (13) to obtain multiple independent electrical signals Z alone .

[0088] In some embodiments of the present invention, the above-mentioned S104 of “determining whether the user has mining behavior according to the M distance values ​​corresponding to each power usage parameter” may include:

[0089] For each power usage parameter, the M distance values ​​corresponding to the power usage parameter are compared with the preset distance value corresponding to the power usage parameter. If the distance value of the power usage parameter is less than the preset distance value corresponding to the power usage parameter, it is determined that the power usage parameter is in an abnormal state.

[0090] If the number of power usage parameters in an abnormal state is greater than a preset number, it is determined that the user has engaged in mining behavior;

[0091] If the number of power usage parameters in an abnormal state is not greater than a preset number, it is determined that the user does not engage in mining behavior.

[0092] Optionally, the preset distance value corresponding to each power consumption parameter may be 0.1.

[0093] Exemplarily, the electricity usage parameters include voltage, current, active power, reactive power, frequency and power factor. The preset number may be four. If more than four of the above six electricity usage parameters are in an abnormal state, it is determined that the user has engaged in mining behavior.

[0094] Specifically, the electrical signal of the electrical parameter includes the current I m , voltage V m , Active power P m , reactive power Q m , frequency U m 、Power factorθ m . With current I m Take this as an example to illustrate:

[0095] The current Im is decomposed into five independent electrical signals (I m1 , I m2 , I m3 , I m4 , I m5 ), the preset independent mining electric signal corresponding to the current is I m0 . Using the system clustering method, I m0 is the cluster center, and I is calculated respectively. m1 with I m0 The distance value, calculation I m2 with I m0 The distance value, calculation I m3 with I m0 The distance value, calculation I m4 with I m0 The distance value, calculation I m5 with I m0 The preset distance value corresponding to the current is S I .

[0096] The five distance values ​​obtained are respectively compared with the preset distance value S corresponding to the current. I Compare and if any of the five distance values ​​is smaller than the preset distance value S I If the user's current is in an abnormal state, it is determined that the user's current is in an abnormal state.

[0097] In the same way, the voltage V m , Active power P m , reactive power Q m , frequency U m 、Power factorθ m status.

[0098] When the number of power usage parameters in an abnormal state is greater than a preset number, it is determined that the user has engaged in mining behavior.

[0099] In some embodiments of the present invention, after "determining whether the user has mining behavior according to the M distance values ​​corresponding to each power usage parameter" in S103, the method further includes:

[0100] If the user is determined to be engaged in mining, an alarm signal will be sent to the power supply company.

[0101] See also Figure 2 , which shows a schematic diagram of a mining behavior identification hardware provided by an embodiment of the present invention. Figure 2 As shown in the figure, the hardware includes an electricity signal acquisition module, a mining behavior recognition module, a power module, and an alarm module. The specific working process is as follows:

[0102] (1) The power consumption signal acquisition module uses a three-phase smart meter (Linyang DTZY71-GPRS) to collect user power consumption parameters (voltage, current, active power, reactive power, frequency, power factor, etc.) and stores the collected data in a register.

[0103] (2) The load identification module includes a microprocessor (Intel Q8200), a communication module and a local server.

[0104] (3) The communication module consists of a WIFI module (Fn-Link 6221A-SRC C06086) and a WIFI router (MIAX6000).

[0105] (4) The microprocessor (Intel Q8200) reads the power usage information from the register of the three-phase smart meter (Linyang DTZY71-GPRS) through SPI communication.

[0106] (5) The microprocessor decomposes the user's electricity consumption data through an improved fast independent component analysis algorithm, wherein the improved fast independent component analysis algorithm includes using the minimum noise separation method (MNF) to denoise and whiten the mixed signal, and using the steepest descent method to iteratively optimize the initial value w of the mixing matrix, and finally decomposing the mixed data signal into independent electrical signals.

[0107] (6) Using the system clustering method, with the preset "mining" signal as the cluster center, the Euclidean distance between the independent electrical signals decomposed under each power consumption parameter and the cluster center is calculated as the distance value of each power consumption parameter. Among them, the preset "mining" signal is the preset mining electrical signal, which is the electrical signal of the power consumption parameter in the mining state.

[0108] (7) The microprocessor sends the recognition results and power consumption information to the WIFI module (Fn-Link6221A-SRC C06086) through serial port communication.

[0109] (8) The WIFI module (Fn-Link 6221A-SRC C06086) sends data to the WIFI router (MI AX6000) wirelessly.

[0110] (9) The WIFI router (MI AX6000) uploads the data to the local server and stores it in the database on the local server.

[0111] (10) If mining activity is detected, the local server will trigger the alarm module with a high voltage and send an alarm signal to the power supply company.

[0112] See also Figure 3 , which shows a specific workflow diagram provided by an embodiment of the present invention. Figure 3 As shown, the working steps are as follows:

[0113] Step 1: The power signal acquisition module uses a three-phase smart meter (Linyang DTZY71-GPRS) to collect user power data (voltage, current, active power, reactive power, frequency, power factor, etc.) and stores the collected data in the register.

[0114] Step 2: The microprocessor (Intel Q8200) reads the power usage information of the three-phase smart meter (Linyang DTZY71-GPRS) register through SPI communication

[0115] Step 3: The microprocessor uses an improved fast independent component analysis algorithm to decompose the user's power consumption data. The improved fast independent component analysis algorithm includes using the minimum noise separation method (MNF) to denoise and whiten the mixed signal, and using the steepest descent method to iteratively optimize the initial value w of the mixing matrix, and finally decompose the mixed data signal into independent electrical signals. Figure 4 As shown, it shows a recognition flow chart of decomposing a mixed data signal into independent electrical signals provided by an embodiment of the present invention.

[0116] Step 4: Use the system clustering method to calculate the distance values ​​corresponding to each power usage parameter of the user, and determine whether each power usage parameter is in an abnormal state based on each distance value. When the number of power usage parameters in an abnormal state is greater than a preset number, it is determined that the user has mining behavior; otherwise, it is determined that the user does not have mining behavior.

[0117] Step 5: The microprocessor sends the recognition result and power consumption information to the WIFI module (Fn-Link6221A-SRC C06086) through serial communication.

[0118] Step 6: The WIFI module (Fn-Link 6221A-SRC C06086) sends the data to the WIFI router (MI AX6000) wirelessly.

[0119] Step 7: The WIFI router (MI AX6000) uploads the data to the local server and stores it in the database in the local server.

[0120] Step 8: If mining activity is detected, the local server will trigger the alarm module with a high voltage and send an alarm signal to the power supply company.

[0121] The embodiments of the present invention can identify "mining" behavior in real time and accurately.

[0122] Regarding real-time performance: the use of smart meters (Linyang DTZY71-GPRS) can collect user electricity consumption data (voltage, current, active power, reactive power, frequency, power factor, etc.) in real time, and the use of SPI, serial port, wireless and other communication methods can realize real-time analysis and storage of data. The system realizes non-home "mining" behavior identification, ensuring the timeliness and continuity of "mining" behavior identification.

[0123] Regarding accuracy: The fast independent component analysis method is simple to calculate, requires little memory, and has a fast convergence speed. The denoising process of the original data using the minimum noise separation method increases the accuracy of the algorithm recognition, making up for the disadvantage of the fast independent component analysis method being greatly disturbed by noise. The iteration of the initial value of the mixing matrix W using the steepest descent method solves the problem of the fast independent component analysis method being sensitive to the initial value. The algorithm can directly find the independent components of any non-Gaussian distribution by using a nonlinear function g. The calculation is simple and the implementation path is convenient. The system clustering method is widely used, fast, robust, and sensitive to isolated points. The combination of the two is applied to the identification of user mining behavior, which can find mining signals among many loads of electricity users, increase the accuracy and real-time nature of the "mining" behavior identification, and can realize non-entry identification of mining behavior, providing a way to achieve continuous and real-time rectification of "mining" behavior.

[0124] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0125] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0126] Figure 5The following is a schematic diagram showing the structure of a device for identifying mining behavior provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0127] like Figure 5 As shown, the mining behavior identification device 20 may include:

[0128] An acquisition module 201 is used to acquire a mixed electrical signal of at least one electrical usage parameter of a user;

[0129] A decomposition module 202 is used to decompose the mixed electrical signal of each electrical parameter based on an improved fast independent component analysis method to obtain M independent electrical signals corresponding to the electrical parameter;

[0130] The calculation module 203 is used to calculate, for each power usage parameter, the distance value between each independent electrical signal corresponding to the power usage parameter and the preset mining electrical signal corresponding to the power usage parameter, and obtain M distance values ​​corresponding to the power usage parameter;

[0131] The judgment module 204 is used to judge whether the user has mining behavior according to the M distance values ​​corresponding to each power usage parameter.

[0132] In some embodiments of the present invention, the decomposition module 202 is further configured to:

[0133] For each mixed electrical signal of an electrical parameter, the mixed electrical signal of the electrical parameter is decentralized to obtain a first mixed electrical signal with a mean of zero; the first mixed electrical signal is whitened and denoised using a minimum noise separation method to obtain a second mixed electrical signal; the initial value of the mixing matrix is ​​determined using the steepest descent method, and based on the initial value, the mixing matrix is ​​iteratively obtained using the Newton method; and based on the mixing matrix, the second mixed electrical signal is decomposed into M independent electrical signals corresponding to the mixed electrical signal of the electrical parameter.

[0134] In some embodiments of the present invention, the mixed electrical signal of at least one electrical parameter includes at least one of a mixed electrical signal of current, a mixed electrical signal of voltage, a mixed electrical signal of active power, a mixed electrical signal of reactive power, a mixed electrical signal of frequency, and a mixed electrical signal of power factor.

[0135] In some embodiments of the present invention, the determination module 204 may include:

[0136] A first judgment unit is used to compare, for each power usage parameter, the M distance values ​​corresponding to the power usage parameter with the preset distance value corresponding to the power usage parameter, and if the distance value of the power usage parameter is less than the preset distance value corresponding to the power usage parameter, determine that the power usage parameter is in an abnormal state;

[0137] The second judgment unit is used to determine that the user has engaged in mining behavior if the number of power usage parameters in an abnormal state is greater than a preset number.

[0138] In some embodiments of the present invention, the device 20 may further include:

[0139] The alarm module is used to determine whether the user has engaged in mining behavior based on the M distance values ​​corresponding to each power consumption parameter. If it is determined that the user has engaged in mining behavior, an alarm signal is sent to the power supply company.

[0140] Figure 6 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 6 As shown, the electronic device 30 of this embodiment includes: a processor 300, a memory 301, and a computer program 302 stored in the memory 301 and executable on the processor 300. When the processor 300 executes the computer program 302, the steps in the above-mentioned mining behavior identification method embodiments are implemented, such as Figure 1 Alternatively, when the processor 300 executes the computer program 302, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 5 Functionality of modules / units 201 to 204 is shown.

[0141] Exemplarily, the computer program 302 may be divided into one or more modules / units, one or more modules / units are stored in the memory 301, and are executed by the processor 300 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments that can implement specific functions, and the instruction segments are used to describe the execution process of the computer program 302 in the electronic device 30. For example, the computer program 302 may be divided into Figure 5 Modules / units 201 to 204 are shown.

[0142] The electronic device 30 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 30 may include, but is not limited to, a processor 300 and a memory 301. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 30 and does not constitute a limitation of the electronic device 30. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0143] The processor 300 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0144] The memory 301 may be an internal storage unit of the electronic device 30, such as a hard disk or memory of the electronic device 30. The memory 301 may also be an external storage device of the electronic device 30, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the electronic device 30. Further, the memory 301 may also include both an internal storage unit of the electronic device 30 and an external storage device. The memory 301 is used to store computer programs and other programs and data required by the electronic device. The memory 301 may also be used to temporarily store data that has been output or is to be output.

[0145] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[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] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0148] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0151] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned mining behavior identification method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0152] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A method for identifying mining behavior, characterized in that: include: Acquire a mixed electrical signal of at least one electrical usage parameter of a user; For each mixed electrical signal of the electrical parameter, based on the improved fast independent component analysis method, the mixed electrical signal of the electrical parameter is decomposed to obtain M independent electrical signals corresponding to the electrical parameter; For each power usage parameter, respectively calculate the distance value between each independent electrical signal corresponding to the power usage parameter and the preset mining electrical signal corresponding to the power usage parameter to obtain M distance values ​​corresponding to the power usage parameter; According to the M distance values ​​corresponding to the various power consumption parameters, determining whether the user has engaged in mining; For each mixed electrical signal of the electrical parameter, based on the improved fast independent component analysis method, the mixed electrical signal of the electrical parameter is decomposed to obtain M independent electrical signals corresponding to the electrical parameter, including: For each mixed electrical signal of an electrical parameter, the mixed electrical signal of the electrical parameter is decentralized to obtain a first mixed electrical signal with a mean of zero; the first mixed electrical signal is whitened and denoised using a minimum noise separation method to obtain a second mixed electrical signal; the initial value of the mixing matrix is ​​determined using a steepest descent method, and based on the initial value, a mixing matrix is ​​obtained by iteratively using a Newton method; based on the mixing matrix, the second mixed electrical signal is decomposed into M independent electrical signals corresponding to the mixed electrical signal of the electrical parameter; The determining, based on the M distance values ​​corresponding to the respective power usage parameters, whether the user has engaged in mining behavior includes: For each power usage parameter, the M distance values ​​corresponding to the power usage parameter are compared with the preset distance value corresponding to the power usage parameter. If the distance value of the power usage parameter is less than the preset distance value corresponding to the power usage parameter, it is determined that the power usage parameter is in an abnormal state. If the number of power usage parameters in an abnormal state is greater than a preset number, it is determined that the user has engaged in mining behavior.

2. The method for identifying mining behavior according to claim 1, characterized in that: The mixed electrical signal of at least one electrical parameter includes at least one of a mixed electrical signal of current, a mixed electrical signal of voltage, a mixed electrical signal of active power, a mixed electrical signal of reactive power, a mixed electrical signal of frequency and a mixed electrical signal of power factor.

3. The method for identifying mining behavior according to claim 1 or 2, characterized in that: After judging whether the user has mining behavior according to the M distance values ​​corresponding to each power usage parameter, the method further includes: If it is determined that the user has engaged in mining activities, an alarm signal is sent to the power supply company.

4. A mining behavior identification device, characterized in that: include: An acquisition module, used to acquire a mixed electrical signal of at least one electrical usage parameter of a user; A decomposition module, for decomposing the mixed electrical signal of each electrical parameter based on an improved fast independent component analysis method to obtain M independent electrical signals corresponding to the electrical parameter; A calculation module, for calculating, for each power usage parameter, a distance value between each independent electrical signal corresponding to the power usage parameter and a preset mining electrical signal corresponding to the power usage parameter, to obtain M distance values ​​corresponding to the power usage parameter; A judgment module, used for judging whether the user has mining behavior according to the M distance values ​​corresponding to each power consumption parameter; The decomposition module is also used for: For each mixed electrical signal of the electrical parameters, the mixed electrical signal of the electrical parameters is decentralized to obtain a first mixed electrical signal with a mean value of zero; Using a minimum noise separation method, whitening and removing noise from the first mixed electrical signal to obtain a second mixed electrical signal; Determine the initial value of the mixing matrix by using the steepest descent method, and obtain the mixing matrix by using the Newton method based on the initial value; Based on the mixing matrix, decomposing the second mixed electrical signal into M independent electrical signals corresponding to the mixed electrical signal of the electrical parameter; The judgment module includes: A first judgment unit is used to compare, for each power usage parameter, the M distance values ​​corresponding to the power usage parameter with the preset distance value corresponding to the power usage parameter, and if the distance value of the power usage parameter is less than the preset distance value corresponding to the power usage parameter, determine that the power usage parameter is in an abnormal state; The second judgment unit is used to determine that the user has engaged in mining behavior if the number of power usage parameters in an abnormal state is greater than a preset number.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for identifying mining behavior as described in any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying mining behavior as described in any one of claims 1 to 3 above are implemented.

Images