Direct current signal feature extraction method, system and device and storage medium

Abstract

The invention discloses a direct current signal feature extraction method, system and device and a storage medium. The direct current signal feature extraction method comprises the following steps: step 1, for different direct current charging piles, sequentially acquiring waveform data of voltage and current signals corresponding to the different direct current charging piles during charging; respectively establishing a multi-channel signal matrix and a multi-component signal matrix according to the signals under the different direct current charging piles; 2, solving an autocorrelation matrix for the multi-channel signal matrix, and then carrying out eigenvalue decomposition on the autocorrelation matrix; step 3, based on the linear combination of the feature vectors obtained in the step 2, solving an optimal weight coefficient by using a swarm intelligence optimization algorithm; and step 4, iterating continuously and repeatedly to obtain a feature vector and a signal component until the whole signal decomposition is completed, and obtaining each component of the direct current signal. According to the method, the global optimal solution can be quickly and accurately obtained, and the problem that time-frequency domain dynamic characteristics are unclear for electric energy metering factors is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power signal feature extraction, and relates to a direct current signal feature extraction method, system, device and storage medium based on a swarm intelligence optimization algorithm. Background Art

[0002] As the proportion of new energy sources such as photovoltaics and wind power continues to increase, a large number of nonlinear dynamic loads are connected to the power grid, which has caused serious power quality problems. Studies have shown that a high proportion of current and voltage harmonics will not only have an adverse effect on the safe operation of equipment, but also cause errors in power metering equipment.

[0003] The traditional multi-channel multi-component decomposition method is a technology used in signal processing, which aims to decompose complex signals into several independent components, each of which represents a specific frequency or time-frequency characteristic of the signal. This method has a wide range of applications in power system analysis, audio processing, vibration analysis and other fields. It collects signals through multiple sensors or data channels, and then uses mathematical transformations (such as Fourier transform, wavelet transform, etc.) to decompose the signals into multiple components for further analysis and processing. In practical applications, signals are often interfered by various noises. When processing signals containing a lot of noise, the traditional multi-channel multi-component decomposition method is easily affected by noise, resulting in inaccurate decomposed components, which affects the accuracy of subsequent analysis.

[0004] Therefore, how to effectively extract the dynamic characteristics that lead to electricity metering errors and accurately evaluate their specific impact on electricity metering has become a key issue that needs to be solved urgently. Summary of the invention

[0005] In order to solve the problem that the traditional multi-channel multi-component decomposition method cannot quickly and accurately obtain the global optimal solution in the presence of a large amount of noise, the present invention provides a DC signal feature extraction method, system, device and storage medium based on a swarm intelligence optimization algorithm, which improves the multi-channel multi-component decomposition method through the swarm intelligence optimization algorithm to quickly and accurately obtain the global optimal solution, and solves the problem that the dynamic characteristics of the time-frequency domain are unclear about the factors of electric energy metering.

[0006] To achieve the above-mentioned object of the invention, the present invention adopts the following technical solution.

[0007] In a first aspect, the present invention provides a DC signal feature extraction method, comprising: Step 1, for different DC charging piles, sequentially obtain the waveform data of voltage and current signals corresponding to charging using different DC charging piles; and for the signals under the above-mentioned different DC charging piles, respectively establish a multi-channel signal matrix and a multi-component signal matrix, and the multi-channel signal matrix is ​​associated with the multi-component signal matrix through an association matrix; Step 2, calculate the autocorrelation matrix of the multi-channel signal matrix, and introduce the multi-component signal matrix through the correlation matrix, and then perform eigenvalue decomposition on the autocorrelation matrix to obtain the linear combination of eigenvectors; Step 3, based on the linear combination of the feature vectors obtained in step 2, a swarm intelligence optimization algorithm is used to solve the optimal weight coefficient of each component; Step 4, continuously repeat the iteration to obtain the characteristic vector and signal component until the entire DC signal is decomposed and each signal component of the DC signal is obtained.

[0008] Furthermore, the step 1 comprises: Step 11, based on fixed sampling technology, using a digital-to-analog converter to The voltage and current signals corresponding to the charging pile when charging are discretely sampled at the sampling frequency to obtain a discrete sequence of the voltage and current signals corresponding to the charging pile when charging; Step 12, establish a multi-channel signal matrix and a multi-component signal matrix, as shown below: (1) In the formula, use Indicates Channel signals, ;use Indicates signal components, ; Indicates the instantaneous amplitude; represents an imaginary unit; represents the instantaneous phase; Indicates instantaneous frequency; multi-component signal ; Step 13: After the original signal passes through the sensor, its phase and amplitude will change. , In the formula, Indicates the amplitude passing through the sensor; Indicates the phase passing through the sensor; Formula (1) can be written as , where A is the correlation matrix, as shown in formula (2): (2) In the formula, represents the signal amplitude of the Fth component in the eth sensor; The size of matrix A is , there is a rank , then the number of independent channels , if and only if When the number of independent channels , then there must be F independent channels.

[0009] Furthermore, the step 2 comprises: Step 21: multi-channel signal Find the autocorrelation matrix R and introduce the multi-component signal matrix through the correlation matrix , the result is shown in formula (3): (3) In the formula, the H in the upper right corner represents the Hermitian transpose; Step 22, for size The autocorrelation matrix R is decomposed by eigenvalue to obtain formula (4): (4) In the formula, are orthogonal eigenvectors; is the characteristic value; Step 23, according to formula (4), Channel signal The linear combination of for The linear combination of is the signal component The linear combination of is shown in the following formula (5): (5) when When , there are F linearly independent quantities, and the signal components are represented by the linear combination of eigenvectors, as shown in formula (6): (6) In the formula, is the weight coefficient.

[0010] Furthermore, the step 3 comprises: Step 31, in order to obtain the most suitable set of weight coefficients, an intelligent optimization algorithm is introduced to perform a global search: First, according to the formula Prey Matrix Perform initialization settings; among them, is a random number in the range ; Indicates the initial value; and are the minimum and maximum values ​​respectively; Assume prey matrix and the predator matrix Size is , represents the number of solutions, Represents dimension; see formula (7) and formula (8) for details: (7) (8) in, Indicates The first dimensions, ; represents the top predator vector, which is the prey matrix The optimal solution in b Second-rate The vectors form the predator matrix ; Step 32, when the signal system size is constant, the iteration is based on different speed ratios It is divided into 3 stages: when At the beginning of the iteration, it is mainly based on the abundance of food. To evaluate whether to update, if the location has good food abundance, then update ; (9) This formula is used to determine whether the algorithm is in the initial stage of iteration; where: Indicates the current iteration condition. Indicates the maximum number of iterations; is the tensor product; is the phasor containing the random numbers of Brownian motion; is the step length; fixed; for A vector of uniform random numbers in ; when When it is in the middle of the iteration, the best strategy for the prey is movement, while the predator adopts the Brownian strategy:

[0011] This formula is used to determine whether the algorithm is in the middle of an iteration; The first half of the population (10) The second half of the population (11) In the formula, To include A vector of random numbers for motion; represents an adaptive parameter that controls the predator's moving step size; when When , in the late iteration, the optimal strategy of the predator is the movement development strategy, which can search a specific area more efficiently; Step 33, remember the current successful foraging location, and calculate the fitness of all solutions of the current iteration The fitness of the solution in the previous iteration Compare, if the current fitness If it is smaller, the current solution replaces the solution of the previous iteration and updates ; Step 34: Add fish gathering device renew , Make the predator jump farther to avoid stagnation in the local optimum.

[0012] Furthermore, in step 32, the motion development strategy adopted in the later stage of iteration is as follows: (12) In the formula, Represents a vector of random numbers.

[0013] Furthermore, in step 34, add renew The formula used is: (13) In the formula, is a random vector containing a binary array. If the array is less than 0.2, it will set the array to 0, and if the array is greater than 0.2, it will set the array to 1; ; for Uniform random numbers in ; , represent the positions of two randomly different prey individuals; Indicates rounding down to the nearest integer.

[0014] Furthermore, the step 4 comprises: Step 41, the optimal set of coefficients of the minimum support interval obtained by optimization is substituted into equation (6) to obtain the first signal component ,use Replace the first eigenvector , using formula (14) to eliminate Orthogonal projection on subsequent components to remove their effect on the remaining signal The influence of ; (14); Step 42, repeat step 41 to obtain a set of coefficients with the optimal area of ​​the optimized minimum support interval , then the second signal component is obtained ,use Replace , and eliminate the orthogonal projection to obtain a new set of eigenvectors; continue to iterate in this way until all signal components are iterated out.

[0015] In a second aspect, the present invention provides a DC signal feature extraction system, comprising: Signal matrix construction unit: for different charging piles, obtain the waveform data of voltage and current signals corresponding to charging with different DC charging piles; and establish multi-channel signal matrices for DC signals under different DC charging piles and a multi-component signal matrix, wherein the multi-channel signal matrix is ​​associated with the multi-component signal matrix via an association matrix; Eigenvalue decomposition unit: calculate the autocorrelation matrix of the multi-channel signal matrix, and introduce the multi-component signal matrix through the correlation matrix, and then perform eigenvalue decomposition on the autocorrelation matrix to obtain the linear combination of eigenvectors; Optimal weight coefficient solving unit: based on the linear combination of eigenvectors obtained by the eigenvalue decomposition unit, the optimal weight coefficient is solved by using the swarm intelligence optimization algorithm; DC signal decomposition unit: Continuously repeat the iteration to obtain the characteristic vector and signal component until the entire DC signal decomposition is completed and the various signal components of the DC signal are obtained.

[0016] In a third aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the DC signal feature extraction method when executing the computer program.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the DC signal feature extraction method.

[0018] In summary, compared with the prior art, the present invention has the following beneficial effects: the present invention improves the multi-channel and multi-component decomposition method through a swarm intelligence optimization algorithm, can quickly and accurately obtain the global optimal solution of the multi-channel and multi-component decomposition method, solves the problem of unclear factors of electric energy metering due to the dynamic characteristics of the time-frequency domain, and provides a reference for domestic standard modification suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in 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 work. The above and other purposes, features and advantages of the present invention will be more clear as shown in the drawings. The same reference numerals in all the drawings indicate the same parts, and the drawings are not deliberately scaled according to the actual size. The focus is on illustrating the main purpose of the present invention.

[0020] Figure 1 This is a flow chart of a DC signal feature extraction method according to Embodiment 1 of the present invention; Figure 2 It is a graph of average iterative convergence curve in an application example of the present invention; Figure 3 It is a composition diagram of the DC signal feature extraction system of the present invention; Figure 4 A schematic diagram of a logical structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0023] Example 1 A DC signal feature extraction method based on swarm intelligence optimization algorithm, such as Figure 1 As shown, the steps are as follows: Step 1: for different DC charging piles, the voltage and current signal waveform data corresponding to charging with different DC charging piles are obtained in turn; and for the signals under the above different DC charging piles, a multi-channel signal matrix is ​​established respectively. and multi-component signal matrix , the multi-channel signal matrix Through the correlation matrix and the multi-component signal matrix association; Step 2: Multi-channel signal matrix Find the autocorrelation matrix R and introduce the multi-component signal matrix through the correlation matrix , then perform eigenvalue decomposition on the autocorrelation matrix R to obtain the linear combination of eigenvectors; Step 3: Based on the linear combination of the feature vectors obtained in step 2, the swarm intelligence optimization algorithm is used to solve the optimal weight coefficients of each component. ; Step 4: Repeat the iteration to get the feature vector and signal components until the entire DC signal is decomposed and the various signal components of the DC signal are obtained.

[0024] Specifically, the step 1 is as follows: Step 11, based on fixed sampling technology, using a digital-to-analog converter to The voltage and current signals corresponding to the charging pile when charging are discretely sampled at the sampling frequency to obtain a discrete sequence of the voltage and current signals corresponding to the charging pile when charging; Step 12: Create a multi-channel signal matrix and multi-component signal matrix , respectively as follows: (1) In the formula, use Indicates Channel signals, ;use Indicates signal components, ; Indicates the instantaneous amplitude; represents an imaginary unit; represents the instantaneous phase; Indicates instantaneous frequency; multi-component signal ; Step 13: After the original signal passes through the sensor, its phase and amplitude will change. , In the formula, Indicates the amplitude passing through the sensor; Indicates the phase passing through the sensor; Formula (1) can be written as , where A is the correlation matrix, as shown in formula (2): (2) In the formula, represents the signal amplitude of the Fth component in the eth sensor; The size of matrix A is , there is a rank , then the number of independent channels , if and only if When the number of independent channels , then there must be F independent channels.

[0025] Specifically, the step 2 is as follows: Step 21: multi-channel signal Find the autocorrelation matrix R and introduce the multi-component signal matrix through the correlation matrix , the result is shown in formula (3): (3) In the formula, the H in the upper right corner represents the Hermitian transpose; Step 22, for size The autocorrelation matrix R is decomposed by eigenvalue to obtain formula (4): (4) In the formula, are orthogonal eigenvectors; is the characteristic value; Step 23, according to formula (4), Channel signal The linear combination of for The linear combination of is the signal component The linear combination of is shown in the following formula (5): (5) when When , there are F linearly independent quantities, and the signal components are represented by the linear combination of eigenvectors, as shown in formula (6): (6) In the formula, is the weight coefficient.

[0026] Specifically, the step 3 is as follows: Step 31, in order to obtain the most suitable set of weight coefficients, an intelligent optimization algorithm is introduced to perform a global search: First, according to the formula Prey Matrix Perform initialization settings; among them, is a random number in the range ; Indicates the initial value; and are the minimum and maximum values ​​respectively; Assume prey matrix and the predator matrix Size is , represents the number of solutions, Represents dimension; see formula (7) and formula (8) for details: (7) (8) in, Indicates The first dimensions, ; represents the top predator vector, which is the prey matrix The optimal solution in b Second-rate The vectors form the predator matrix ; Step 32, when the signal system size is constant, the iteration is based on different speed ratios It is divided into 3 stages: when At the beginning of the iteration, it is mainly based on the abundance of food. To evaluate whether to update, if the location has good food abundance, then update ; (9) This formula is used to determine whether the algorithm is in the initial stage of iteration; where: Indicates the current iteration condition. Indicates the maximum number of iterations; is the tensor product; is the phasor containing the random numbers of Brownian motion; is the step length; fixed; for A vector of uniform random numbers in ; when When it is in the middle of the iteration, the best strategy for the prey is movement, while the predator adopts the Brownian strategy:

[0027] This formula is used to determine whether the algorithm is in the middle of an iteration; The first half of the population (10) The second half of the population (11) In the formula, To include A vector of random numbers for motion; represents an adaptive parameter that controls the predator's moving step size; when When , in the late iteration, the best strategy for the predator is the motion exploitation strategy, so as to search the specific area more effectively; the motion exploitation strategy is as follows: (12) In the formula, Represents a vector of random numbers.

[0028] Step 33, remember the current successful foraging location, and calculate the fitness of all solutions of the current iteration The fitness of the solution in the previous iteration Compare, if the current fitness If it is smaller, the current solution replaces the solution of the previous iteration and updates ; Step 34: Add fish gathering device (Fish Aggregating Devices) Update , Make the predator jump farther to avoid stagnation in the local optimum. Add renew The formula used is: (13) In the formula, is a random vector containing a binary array. If the array is less than 0.2, it will set the array to 0, and if the array is greater than 0.2, it will set the array to 1; ; for Uniform random numbers in ; , represent the positions of two randomly different prey individuals; Indicates rounding down to the nearest integer.

[0029] Specifically, the step 4 is as follows: Step 41: Optimize the area of ​​the minimum support interval Substituting the best set of coefficients into equation (6) yields the first signal component ,use Replace the first eigenvector , using formula (14) to eliminate Orthogonal projection on subsequent components to remove their effect on the remaining signal The influence of ; (14); Because different signal components have different time-frequency aggregation in the time-frequency plane, the time-frequency aggregation can be used to judge the signal components. The area of ​​the support interval of the signal in the time-frequency domain can quantitatively describe the time-frequency aggregation of the signal. Let the area of ​​the support interval of each component signal in the time-frequency domain be D, the result of the first iteration of the minimum support interval area is D1, the result of the second iteration is D2, and so on.

[0030] Step 42, repeat step 41 to obtain the area of ​​the optimized minimum support interval The optimal set of coefficients , then the second signal component is obtained ,use Replace , and eliminate the orthogonal projection to obtain a new set of eigenvectors; continue to iterate in this way until all signal components are iterated out.

[0031] Application Examples The DC signal feature extraction method described in Example 1 was used as follows: the population size was set to 50, the maximum number of iterations was set to 200, and the number of channels G was set to 15. To avoid contingency, the optimization algorithm was run 10 times, and the average convergence curve of the optimization algorithm for 20 iterations was taken as follows: Figure 2 shown.

[0032] Construct a DC simulation test signal containing ripple components and noise interference components, and its expression is:

[0033] In the above formula: represents the noise signal, let ; Indicates the DC signal amplitude; Indicates the amplitude of the ripple component; represents the frequency of the k-th ripple; Indicates the phase of the k-th ripple.

[0034] The specific parameters of the DC component and ripple component are shown in Table 1.

[0035] Table 1 Test condition parameters

[0036] The decomposition results of the method of the present invention under noise conditions can be obtained through simulation, as shown in Table 2: Table 2. Decomposition error table of each component parameter of DC signal

[0037] In order to further verify the influence of noise on the algorithm of the present invention, the present invention adopts the test conditions shown in Table 1, and conducts simulation experiments in the environment of 40-80dB respectively, and obtains the following results in Table 3: Table 3 Signal decomposition error under different noise conditions

[0038] Example 2 This embodiment is a DC signal feature extraction system. Figure 3 As shown, it includes: Signal matrix construction unit: for different charging piles, obtain the voltage and current signal waveform data corresponding to charging with different DC charging piles; and for the DC signals under different DC charging piles, respectively establish a multi-channel signal matrix and a multi-component signal matrix, wherein the multi-channel signal matrix is ​​associated with the multi-component signal matrix through an association matrix; Eigenvalue decomposition unit: calculate the autocorrelation matrix of the multi-channel signal matrix, and introduce the multi-component signal matrix through the correlation matrix, and then perform eigenvalue decomposition on the autocorrelation matrix to obtain the linear combination of eigenvectors; Optimal weight coefficient solving unit: based on the linear combination of eigenvectors obtained by the eigenvalue decomposition unit, the optimal weight coefficient is solved by using the swarm intelligence optimization algorithm; DC signal decomposition unit: Continuously repeat the iteration to obtain the characteristic vector and signal component until the entire DC signal decomposition is completed and the various signal components of the DC signal are obtained.

[0039] It should be noted that each unit in the above-mentioned DC signal feature extraction system can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned units can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above-mentioned units. For the specific definition of a DC signal feature extraction system, please refer to the definition of a DC signal feature extraction method (i.e., Example 1) above. The two have the same functions and effects, which will not be repeated here.

[0040] Example 3 This embodiment provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the electronic device executes the method according to Embodiment 1 of the present invention.

[0041] Example 4 This embodiment provides a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method according to Embodiment 1 of the present invention.

[0042] refer to Figure 4 , a block diagram of an electronic device 400 that can be used as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0043] like Figure 4 As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0044] A plurality of components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, an output unit 407, a storage unit 408, and a communication unit 409. The input unit 406 may be any type of device capable of inputting information to the electronic device 400, and the input unit 406 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 407 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 408 may include, but is not limited to, a disk, an optical disk. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0045] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above. For example, in some embodiments, the aforementioned DC signal feature extraction method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. In some embodiments, the computing unit 401 may be configured to perform the aforementioned DC signal feature extraction method in any other appropriate manner (e.g., by means of firmware).

[0046] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0047] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0048] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0049] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0050] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0051] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0052] It is obvious that those skilled in the art can easily make various modifications to the above embodiments and apply the general principles described herein to other embodiments without creative work. Therefore, the present invention is not limited to the above embodiments, and improvements and modifications made by those skilled in the art based on the disclosure of the present invention should be within the scope of protection of the present invention.

Claims

1. A DC signal feature extraction method, characterized in that: include: Step 1, for different DC charging piles, sequentially obtain waveform data of voltage and current signals corresponding to charging using different DC charging piles; And for the signals under the above-mentioned different DC charging piles, a multi-channel signal matrix and a multi-component signal matrix are established respectively, and the multi-channel signal matrix is ​​associated with the multi-component signal matrix through an association matrix; Step 2, calculate the autocorrelation matrix of the multi-channel signal matrix, and introduce the multi-component signal matrix through the correlation matrix, and then perform eigenvalue decomposition on the autocorrelation matrix to obtain the linear combination of eigenvectors; Step 3, based on the linear combination of the feature vectors obtained in step 2, a swarm intelligence optimization algorithm is used to solve the optimal weight coefficient of each component; Step 4, continuously repeat the iteration to obtain the characteristic vector and signal component until the entire DC signal is decomposed and each signal component of the DC signal is obtained.

2. The DC signal feature extraction method according to claim 1, characterized in that: The step 1 comprises: Step 11, based on fixed sampling technology, using a digital-to-analog converter to The voltage and current signals corresponding to the charging pile when charging are discretely sampled at the sampling frequency to obtain a discrete sequence of the voltage and current signals corresponding to the charging pile when charging; Step 12: Create a multi-channel signal matrix and multi-component signal matrix , respectively as follows: (1) In the formula, use Indicates Channel signals, ;use Indicates signal components, ; Indicates the instantaneous amplitude; represents an imaginary unit; represents the instantaneous phase; Indicates instantaneous frequency; multi-component signal ; Step 13: After the original signal passes through the sensor, its phase and amplitude will change. ， In the formula, Indicates the amplitude passing through the sensor; Indicates the phase passing through the sensor; Formula (1) can be written as , where A is the correlation matrix, as shown in formula (2): (2) In the formula, represents the signal amplitude of the Fth component in the eth sensor; The size of matrix A is , there is a rank , then the number of independent channels , if and only if When the number of independent channels , then there must be F independent channels.

3. The DC signal feature extraction method according to claim 2, characterized in that: The step 2 comprises: Step 21: multi-channel signal Find the autocorrelation matrix R and introduce the multi-component signal matrix through the correlation matrix , the result is shown in formula (3): (3) In the formula, the H in the upper right corner represents the Hermitian transpose; Step 22, for size The autocorrelation matrix R is decomposed by eigenvalue to obtain formula (4): (4) In the formula, are orthogonal eigenvectors; is the characteristic value; Step 23, according to formula (4), Channel signal The linear combination of for The linear combination of is the signal component The linear combination of is shown in the following formula (5): (5) when When , there are F linearly independent quantities, and the signal components are represented by the linear combination of eigenvectors, as shown in formula (6): (6) In the formula, is the weight coefficient.

4. The DC signal feature extraction method according to claim 3, characterized in that: The step 3 comprises: Step 31, in order to obtain the most suitable set of weight coefficients, an intelligent optimization algorithm is introduced to perform a global search: First, according to the formula Prey Matrix Perform initialization settings; among them, is a random number in the range ; Indicates the initial value; and are the minimum and maximum values ​​respectively; Assume prey matrix and the predator matrix Size is , represents the number of solutions, Represents dimension; see formula (7) and formula (8) for details: (7) (8) in, Indicates The first dimensions, ; represents the top predator vector, which is the prey matrix The optimal solution in b Second-rate The vectors form the predator matrix ; Step 32, when the signal system size is constant, iteration is performed according to different speed ratios. It is divided into 3 stages: when At the beginning of the iteration, it is mainly based on the abundance of food. To evaluate whether to update, if the location has good food abundance, then update ; (9) This formula is used to determine whether the algorithm is in the initial stage of iteration; where: Indicates the current iteration condition. Indicates the maximum number of iterations; is the tensor product; is the phasor containing the random numbers of Brownian motion; is the step length; fixed; for A vector of uniform random numbers in ; when When it is in the middle of the iteration, the best strategy for the prey is movement, while the predator adopts the Brownian strategy: This formula is used to determine whether the algorithm is in the middle of an iteration; The first half of the population (10) The second half of the population (11) In the formula, To include A vector of random numbers for motion; represents an adaptive parameter that controls the predator's moving step size; when When , in the late iteration, the best strategy for the predator is the movement development strategy, which can search a specific area more efficiently; Step 33, remember the current successful foraging location, and calculate the fitness of all solutions of the current iteration The fitness of the solution in the previous iteration Compare, if the current fitness If it is smaller, the current solution replaces the solution of the previous iteration and updates ; Step 34: Add fish gathering device renew , Make the predator jump farther to avoid stagnation in the local optimum.

5. The DC signal feature extraction method according to claim 4, characterized in that: In step 32, the motion development strategy adopted in the later stage of iteration is as follows: (12) In the formula, Represents a vector of random numbers.

6. The DC signal feature extraction method according to claim 4, characterized in that: In step 34, add renew The formula used is: (13) In the formula, is a random vector containing a binary array. If the array is less than 0.2, it will set the array to 0, and if the array is greater than 0.2, it will set the array to 1; ; for Uniform random numbers in ; , represent the positions of two randomly different prey individuals; Indicates rounding down to the nearest integer.

7. The DC signal feature extraction method according to claim 3, characterized in that: The step 4 comprises: Step 41, the optimal set of coefficients of the minimum support interval obtained by optimization is substituted into equation (6) to obtain the first signal component ,use Replace the first eigenvector , using formula (14) to eliminate Orthogonal projection on subsequent components to remove their effect on the remaining signal The influence of ; (14)； Step 42, repeat step 41 to obtain a set of coefficients with the optimal area of ​​the optimized minimum support interval , then the second signal component is obtained ,use Replace , and eliminate the orthogonal projection to obtain a new set of eigenvectors; continue to iterate in this way until all signal components are iterated out.

8. A DC signal feature extraction system, characterized in that: include: Signal matrix construction unit: for different charging piles, obtains waveform data of voltage and current signals corresponding to charging with different DC charging piles; And for the DC signals under different DC charging piles, a multi-channel signal matrix and a multi-component signal matrix are established respectively, and the multi-channel signal matrix is ​​associated with the multi-component signal matrix through an association matrix; Eigenvalue decomposition unit: calculate the autocorrelation matrix of the multi-channel signal matrix, and introduce the multi-component signal matrix through the correlation matrix, and then perform eigenvalue decomposition on the autocorrelation matrix to obtain the linear combination of eigenvectors; Optimal weight coefficient solving unit: based on the linear combination of eigenvectors obtained by the eigenvalue decomposition unit, the optimal weight coefficient is solved by using the swarm intelligence optimization algorithm; DC signal decomposition unit: Continuously repeat the iteration to obtain the characteristic vector and signal component until the entire DC signal decomposition is completed and the various signal components of the DC signal are obtained.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images