Residential charging facility identification method and system, electronic equipment and storage medium

Abstract

The invention discloses a resident charging facility identification method and system, an electronic device and a storage medium, and the method can accurately represent the charging characteristics of different types of resident charging facilities during normal charging through extracting the time domain features and frequency domain features of the charging currents of the different types of resident charging facilities during normal charging as feature vectors. The method comprises the following steps: firstly, establishing a training data set of each type of residential charging facility, then adding a label according to the type of the residential charging facility to establish a training data set of each type of residential charging facility, then establishing a support vector machine model, training the support vector machine model by using the training data set to obtain a load identification model, and finally obtaining time domain characteristics and frequency domain characteristics of a to-be-identified residential charging facility. And the time domain characteristics and the frequency domain characteristics are input into the load identification model for real-time load identification, so that the type of the residential charging facility can be accurately identified.

Description

Technical Field

[0001] The present invention relates to the technical field of charging facility identification, and in particular, to a method and system for identifying charging facilities for residents, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rapid development of technologies such as electric vehicles, battery vehicles, and household energy storage, residential charging facilities have become an important part of the smart grid. How to analyze the charging load characteristics of residential charging facilities to accurately determine the type of residential charging facilities and realize intelligent identification of residential charging facilities has become an urgent problem to be solved in the smart grid. In addition, on the low-voltage distribution side of the substation, illegal charging of residential charging facilities occurs from time to time, posing a huge hidden danger to people's lives and property safety. Therefore, safe monitoring of the charging status of residential charging facilities has become another key issue that needs to be solved urgently. Summary of the invention

[0003] The present invention provides a method and system for identifying residential charging facilities, an electronic device, and a computer-readable storage medium. By extracting the time domain characteristics and frequency domain characteristics of the charging current of different types of residential charging facilities during normal charging as feature vectors, the charging characteristics of different types of residential charging facilities during normal charging can be accurately characterized, and the load type of the residential charging facility can be accurately identified.

[0004] According to one aspect of the present invention, a method for identifying residential charging facilities is provided, comprising the following contents:

[0005] Obtain the time domain characteristics and frequency domain characteristics of the charging current of different types of residential charging facilities during normal charging;

[0006] Based on the time domain features and frequency domain features, feature vectors of different types of residential charging facilities are constructed, and labels are added accordingly to construct a training data set corresponding to each type of residential charging facility;

[0007] Construct a support vector machine model, and use the training data set to train the support vector machine model to obtain a load identification model;

[0008] The time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified are obtained, and the time domain characteristics and frequency domain characteristics are input into the load identification model for load identification.

[0009] Furthermore, the time domain characteristics include the time when the charging current reaches the peak value, the time when the charging current reaches the valley value, the maximum charging current, the minimum charging current and the charging current change rate, and the frequency domain characteristics include the fundamental frequency, the harmonic frequency, the displacement time between the maximum fundamental amplitude and the maximum harmonic amplitude, and the energy spectrum density.

[0010] Furthermore, the following contents are also included:

[0011] The charging status of the residential charging facilities to be identified is identified based on their time domain characteristics and frequency domain characteristics.

[0012] Furthermore, the process of identifying the charging status of the residential charging facility to be identified according to the time domain characteristics and frequency domain characteristics thereof includes the following:

[0013] The time domain features and frequency domain features of the residential charging facilities to be identified when charging normally are respectively fused to obtain the time domain fusion features and frequency domain fusion features of the normal charging state;

[0014] Determine a time domain feature threshold range and a frequency domain feature threshold range according to the time domain fusion features and the frequency domain fusion features of a normal charging state;

[0015] The time domain features and frequency domain features for identifying the current charging state of residential charging facilities are respectively fused to obtain the time domain fusion features and frequency domain fusion features of the current charging state;

[0016] The time domain fusion features and frequency domain fusion features of the current charging status are compared with the time domain feature threshold range and the frequency domain feature threshold range respectively, and whether the current charging status of the residential charging facility to be identified is normal is determined based on the comparison results.

[0017] Furthermore, the feature fusion of time domain features and frequency domain features is performed based on the following formula:

[0018]

[0019] Among them, P t represents the time domain fusion feature at time t, P f represents the frequency domain fusion feature when the frequency is f, a represents the number of time domain features, b represents the number of frequency domain features, x t,m represents the mth time domain feature at time t, x f,j represents the jth frequency domain feature at frequency f, ρ t,m represents the variance weight of the mth time domain feature at time t, ρ f,j represents the variance weight of the jth frequency domain feature when the frequency is f, β 1 represents the equal weight factor of the time domain features, β 2 Represents equal weight factors for frequency domain features.

[0020] Furthermore, the time domain feature threshold range is T t =u t ±Kσ t ,u t and σ tRespectively represent the mean and standard deviation of the time domain fusion features, and the frequency domain feature threshold range is T f =u f ±Kσ f ,u f and σ f They represent the mean and standard deviation of the frequency domain fusion features respectively, and K represents the factor coefficient.

[0021] Furthermore, the number of support vector machine models constructed is consistent with the number of types of residential charging facilities, and each support vector machine model is trained separately using the corresponding training data set to obtain a load identification model corresponding to each type of residential charging facility.

[0022] In addition, the present invention also provides a residential charging facility identification system, comprising:

[0023] A time-frequency domain feature acquisition module is used to obtain the time-domain and frequency-domain features of the charging current of different types of residential charging facilities during normal charging;

[0024] A training data set construction module is used to construct feature vectors of different types of residential charging facilities based on time domain features and frequency domain features, and to add labels accordingly to construct a training data set corresponding to each type of residential charging facility;

[0025] The model building and training module is used to build a support vector machine model and obtain a load identification model after training the support vector machine model using a training data set;

[0026] The real-time load identification module is used to obtain the time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified, and input their time domain characteristics and frequency domain characteristics into the load identification model for load identification.

[0027] In addition, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the above method by calling the computer program stored in the memory.

[0028] In addition, the present invention also provides a computer-readable storage medium for storing a computer program for identifying residential charging facilities, wherein the computer program executes the steps of the method described above when running on a computer.

[0029] The present invention has the following beneficial effects:

[0030] The method for identifying residential charging facilities of the present invention can accurately characterize the charging characteristics of different types of residential charging facilities during normal charging by extracting the time domain characteristics and frequency domain characteristics of the charging current of different types of residential charging facilities during normal charging as feature vectors, and then add labels according to the types of residential charging facilities to construct a training data set for each type of residential charging facility, and then construct a support vector machine model. After training the support vector machine model using the training data set, a load identification model is obtained, and finally the time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified are obtained, and the time domain characteristics and frequency domain characteristics are input into the load identification model for real-time load identification, so as to accurately identify the load type of the residential charging facilities.

[0031] In addition, the residential charging facility identification system of the present invention also has the above advantages.

[0032] In addition to the above-described purposes, features and advantages, the present invention has other purposes, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0034] Figure 1 It is a flowchart of a method for identifying charging facilities for residents according to a preferred embodiment of the present application.

[0035] Figure 2 It is another flowchart of the method for identifying charging facilities for residents according to the preferred embodiment of the present application.

[0036] Figure 3 yes Figure 2 Schematic diagram of the sub-process of step S5.

[0037] Figure 4 It is a schematic diagram of the module structure of a residential charging facility identification system according to another embodiment of the present application. DETAILED DESCRIPTION

[0038] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0039] Reference Figure 1 The preferred embodiment of the present application provides a method for identifying charging facilities for residents, comprising the following contents:

[0040] Step S1: Obtaining time domain characteristics and frequency domain characteristics of charging current of different types of residential charging facilities during normal charging;

[0041] Step S2: constructing feature vectors of different types of residential charging facilities based on time domain features and frequency domain features, and adding labels accordingly to construct a training data set corresponding to each type of residential charging facility;

[0042] Step S3: construct a support vector machine model, and use the training data set to train the support vector machine model to obtain a load identification model;

[0043] Step S4: Obtain the time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified, and input the time domain characteristics and frequency domain characteristics into the load identification model for load identification.

[0044] It can be understood that the residential charging facility identification method of the present embodiment can accurately characterize the charging characteristics of different residential charging facilities during normal charging by extracting the time domain characteristics and frequency domain characteristics of the charging current of different types of residential charging facilities during normal charging as feature vectors, and then add labels according to the types of residential charging facilities to construct a training data set for each type of residential charging facility, and then construct a support vector machine model. After training the support vector machine model using the training data set, a load identification model is obtained. Finally, the time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified are obtained, and their time domain characteristics and frequency domain characteristics are input into the load identification model for real-time load identification, so as to accurately identify the load type of the residential charging facilities.

[0045] It can be understood that in step S1, when different types of residential charging facilities are charging normally, sensors are used to collect the charging start time, charging end time and charging current of different residential charging facilities. Among them, according to the sampling data frequency of every 15 minutes, the sampling points within 60 minutes are combined into one data. Then, according to the charging start time and charging end time, based on the time window length of 60 minutes, the starting point of charging is selected as the starting point of the time window, and the charging process is divided into multiple continuous charging segments. The It curve is established to analyze the time domain characteristics of the charging current, and then the wavelet transform is used to extract the frequency domain characteristics of each window. Among them, the It curve can be expressed as: I(t i )=I 0 sin(2πft i +ψ), where I(t i ) is the charging current time domain signal at the i-th sampling moment, I 0 represents the current peak value, f represents the frequency of the charging current, and ψ represents the phase difference of the charging current. In addition, the wavelet transform can be expressed as: Where W(t,f) represents the frequency domain signal of the charging current after wavelet transformation, j represents the imaginary unit, T represents the sampling period, ψ() represents the wavelet function, * represents the conjugate, and t′ represents the time variable. The extracted time domain features include the time t when the charging current reaches the peak value peak , the time t when the charging current reaches the valley value down , Maximum charging current I max , minimum charging current I min and the charging current change rate v I , Δt represents the time interval; the frequency domain characteristics include the fundamental frequency f base , harmonic frequency f harm , displacement time between maximum fundamental amplitude and maximum harmonic amplitude Energy Spectral Density Among them, Max(f base ) and Max(f harm ) is the frequency corresponding to the maximum amplitude fundamental wave and the maximum amplitude harmonic, and Δφ is the phase difference between them. In addition, after extracting the time domain features and frequency domain features, the extracted features need to be normalized to map the data within [0,1] to eliminate the adverse effects caused by the difference in the dimension and order of magnitude of the original data. The specific normalization formula is: Among them, X represents the normalized data, x max Indicates the maximum value of sample data, x min Indicates the minimum value of sample data, and x indicates the data before normalization. In addition, residential charging facilities include battery vehicles, electric vehicles, and household energy storage. Of course, in other embodiments of the present invention, they may also include common household electrical appliances such as refrigerators, air conditioners, and televisions. No specific limitation is made here. The present invention uses battery vehicles, electric vehicles, and household energy storage as examples of residential charging facilities.

[0046] It can be understood that in step S2, the feature vector of each residential charging facility is constructed based on the time domain features and frequency domain features extracted in step S1, which can be expressed as

[0047] And add labels according to the feature vectors of residential charging facilities to construct a training data set corresponding to each type of residential charging facility, which can be expressed as Among them, y i =1, 2, 3, representing battery vehicles, electric vehicles and household energy storage respectively.

[0048] It can be understood that in step S3, the support vector machine model SVM is used as the basic model of the load identification model, and the optimal classification hyperplane equation of the support vector machine model can be expressed as: Among them, λ represents the input sample, that is, the feature vector in step S2, w represents the weight vector, and each component ω in the feature vector w i Corresponding to the i-th feature in the input sample, represents the bias, which represents the model's initial judgment of the load type even without feature input, and the superscript T represents transposition. Among them, the objective function of the SVM model can be expressed as: The constraints are: It can be understood that the SVM model is an existing mature classification model, and its objective function solution process belongs to the existing technology, which will not be repeated here. For example, as a solution method, when solving the objective function, the Lagrange operator α is introduced i , use the Lagrange multiplier method to solve the problem. When the Lagrange function reaches its extreme value, we can obtain a set of optimal solutions to the above problem {a i}, and a that is not equal to 0 I The value is recorded as but The corresponding samples are support vectors, S is the number of support vectors, and the solution weight vector W of the optimal hyperplane is calculated at the same time 0 , the Lagrange optimization method is used to transform the optimal hyperplane problem into its dual problem, and the final classification rule is: Among them, the classification threshold Introducing kernel function d represents the mapping dimension, and the nonlinear input pattern vector is mapped to a high-dimensional space, and converted into a linear separable problem through an inner product operation. After the support vector machine model is constructed, the support vector machine model is trained using a training data set to obtain a load identification model, wherein the training process of the support vector machine model belongs to the prior art and will not be described in detail here.

[0049] Optionally, the number of support vector machine models constructed is consistent with the number of types of residential charging facilities, and each support vector machine model is trained separately using the corresponding training data set to obtain a load identification model corresponding to each type of residential charging facility. Specifically, assuming that it is necessary to identify three types of charging facilities, namely, battery vehicles, electric vehicles, and household energy storage, three support vector machine models are constructed, that is, 3 hyperplanes and 3 kernel functions are constructed. It is assumed that the first hyperplane sets battery vehicles as positive samples and the rest as negative samples, the second hyperplane sets electric vehicles as positive samples and the rest as negative samples, and the third hyperplane sets household energy storage as positive samples and the rest as negative samples. After the samples are input, classification can be achieved by judging them in sequence. Subsequently, the three load identification models are used for classification and identification, which is conducive to further improving the accuracy of load identification. For example, suppose They are the training data set for electric vehicles, the training data set for household energy storage, and the training data set for battery vehicles. Input the SVM1 model as an input sample and get y 1 =1, then the SVM1 model is the load identification model of the electric vehicle; As the input sample, input the SVM2 model and get y 2 =1, then the SVM2 model is the load identification model for household energy storage; As the input sample, we input the SVM3 model and get y 3 =1, then the SVM3 model is the load identification model of the battery vehicle.

[0050] It can be understood that in step S4, when the residential charging facility to be identified is charging, the time domain characteristics and frequency domain characteristics of the residential charging facility to be identified are extracted and input as feature vectors into the trained load identification model, so that real-time load identification can be performed.

[0051] Alternatively, if Figure 2 As shown, the residential charging facility identification method also includes the following contents:

[0052] Step S5: Identify the charging status of the residential charging facility to be identified based on its time domain characteristics and frequency domain characteristics.

[0053] It can be understood that the residential charging facility identification method of the present invention can also identify the charging status according to the time domain characteristics and frequency domain characteristics of the residential charging facility to be identified, thereby realizing real-time monitoring of the charging status and ensuring charging safety.

[0054] Specifically, Figure 3 As shown, the process of identifying the charging status of the residential charging facility to be identified based on the time domain characteristics and frequency domain characteristics includes the following:

[0055] Step S51: performing feature fusion on the time domain features and frequency domain features of the residential charging facility to be identified when the charging is normally performed, to obtain the time domain fusion features and frequency domain fusion features of the normal charging state;

[0056] Step S52: determining a time domain feature threshold range and a frequency domain feature threshold range according to the time domain fusion feature and the frequency domain fusion feature of the normal charging state;

[0057] Step S53: performing feature fusion on the time domain features and frequency domain features of the current charging state of the residential charging facility to be identified, respectively, to obtain the time domain fusion features and frequency domain fusion features of the current charging state;

[0058] Step S54: Compare the time domain fusion features and frequency domain fusion features of the current charging status with the time domain feature threshold range and the frequency domain feature threshold range respectively, and determine whether the current charging status of the residential charging facility to be identified is normal based on the comparison results.

[0059] Specifically, in steps S1 to S4, the time domain features and frequency domain features of different types of residential charging facilities have been extracted, and the load identification of the residential charging facilities to be identified has been completed, that is, the load type of the residential charging facilities to be identified has been determined. Therefore, the time domain features and frequency domain features of the residential charging facilities to be identified during normal charging are firstly fused based on the following formula:

[0060]

[0061] Among them, P t represents the time domain fusion feature at time t, P f represents the frequency domain fusion feature when the frequency is f, a represents the number of time domain features, b represents the number of frequency domain features, x t,m represents the mth time domain feature at time t, x f,j represents the jth frequency domain feature at frequency f, ρ t,m represents the variance weight of the mth time domain feature at time t, ρ f,j represents the variance weight of the jth frequency domain feature when the frequency is f, β 1 represents the equal weight factor of the time domain features, β 2 represents the equal weight factor of frequency domain features. In addition, In the formula represents the mth time domain feature of the extracted charging facility at time t, represents the mean of the mth time domain feature of the extracted charging facility, and N represents the number of sampling moments.

[0062] In the formula is the jth element of the extracted frequency domain feature of the charging facility, is the mean value of the jth element of the extracted time domain feature, and N represents the number of sampling frequencies. Other time domain and frequency domain features are calculated in the same way. In addition,

[0063] Then, after calculating the time domain fusion feature values ​​and frequency domain fusion feature sequence values ​​of a series of moments in the normal charging state, the calculation results are statistically analyzed to determine the time domain feature threshold range as T t =u t ±Kσ t ,u t and σ t Respectively represent the mean and standard deviation of the time domain fusion features, and the frequency domain feature threshold range is T f =u f ±Kσ f ,u f and σf They represent the mean and standard deviation of the frequency domain fusion features respectively, and K represents the factor coefficient. For example, K can be 1, 2, or 3.

[0064] Then, the time domain features and frequency domain features for identifying the current charging state of residential charging facilities are fused respectively. The feature fusion formula is the same as above and will not be repeated here. The time domain fusion feature P of the current charging state is obtained. t And frequency domain fusion feature P f .

[0065] Finally, the time domain fusion feature P of the current charging state is t And frequency domain fusion feature P f Respectively with the time domain feature threshold range T t and frequency domain feature threshold range T f For comparison, if P t Not T t And P f Not T f , then the current charging state is determined to be an abnormal state, otherwise the current charging state is determined to be a normal state.

[0066] It can be understood that the present invention obtains the time domain feature threshold range and the frequency domain feature threshold range by fusing the time domain features and the frequency domain features respectively, and performing statistical analysis on the time domain fusion features and the frequency domain fusion features respectively, and adopts a dual threshold strategy to determine whether the current charging status is normal, which can accurately identify the charging status of residential charging facilities and realize real-time and safe monitoring of the charging status.

[0067] In addition, if Figure 4 As shown, another embodiment of the present invention further provides a residential charging facility identification system, preferably using the residential charging facility identification method as described above, including:

[0068] A time-frequency domain feature acquisition module is used to obtain the time-domain and frequency-domain features of the charging current of different types of residential charging facilities during normal charging;

[0069] A training data set construction module is used to construct feature vectors of different types of residential charging facilities based on time domain features and frequency domain features, and to add labels accordingly to construct a training data set corresponding to each type of residential charging facility;

[0070] The model building and training module is used to build a support vector machine model and obtain a load identification model after training the support vector machine model using a training data set;

[0071] The real-time load identification module is used to obtain the time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified, and input their time domain characteristics and frequency domain characteristics into the load identification model for load identification.

[0072] It can be understood that the residential charging facility identification system of the present embodiment can accurately characterize the charging characteristics of different types of residential charging facilities during normal charging by extracting the time domain characteristics and frequency domain characteristics of the charging current of different types of residential charging facilities during normal charging as feature vectors, and then add labels according to the types of residential charging facilities to construct a training data set for each type of residential charging facility, and then construct a support vector machine model. After training the support vector machine model using the training data set, a load identification model is obtained. Finally, the time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified are obtained, and their time domain characteristics and frequency domain characteristics are input into the load identification model for real-time load identification, so as to accurately identify the load type of the residential charging facilities.

[0073] In addition, the residential charging facility identification system further includes a charging status identification module, which is used to identify the charging status of the residential charging facility to be identified based on the time domain characteristics and frequency domain characteristics of the residential charging facility to be identified.

[0074] It can be understood that each module of the system embodiment corresponds to each step of the above method embodiment, so the specific working principle of each module will not be repeated here, and the corresponding reference is made to each step of the above method embodiment.

[0075] In addition, another embodiment of the present invention further provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the above method by calling the computer program stored in the memory.

[0076] In addition, another embodiment of the present invention further provides a computer-readable storage medium for storing a computer program for identifying residential charging facilities, wherein the computer program executes the steps of the method described above when running on a computer.

[0077] The general form of computer readable storage media includes: floppy disk, flexible disk, hard disk, magnetic tape, any other magnetic medium, CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with a pattern of holes, random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), flash erasable programmable read-only memory (FLASH-EPROM), any other memory chip or cartridge, or any other medium that can be read by a computer. The instructions can further be transmitted or received by a transmission medium. The term transmission medium can include any tangible or intangible medium that can be used to store, encode or carry instructions for execution by a machine, and includes digital or analog communication signals or other intangible media that facilitate the communication of the above instructions. Transmission media include coaxial cables, copper wires and optical fibers, which include the wires of a bus used to transmit a computer data signal.

[0078] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0079] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0083] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying residential charging facilities, characterized in that: Includes the following: Obtain the time domain characteristics and frequency domain characteristics of the charging current of different types of residential charging facilities during normal charging; Based on the time domain features and frequency domain features, feature vectors of different types of residential charging facilities are constructed, and labels are added accordingly to construct a training data set corresponding to each type of residential charging facility; Construct a support vector machine model, and use the training data set to train the support vector machine model to obtain a load identification model; The time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified are obtained, and the time domain characteristics and frequency domain characteristics are input into the load identification model for load identification.

2. The method for identifying residential charging facilities according to claim 1, characterized in that: The time domain characteristics include the time when the charging current reaches the peak value, the time when the charging current reaches the valley value, the maximum charging current, the minimum charging current and the charging current change rate; the frequency domain characteristics include the fundamental frequency, the harmonic frequency, the displacement time between the maximum fundamental amplitude and the maximum harmonic amplitude, and the energy spectrum density.

3. The method for identifying residential charging facilities according to claim 1, characterized in that: Also included are the following: The charging status of the residential charging facilities to be identified is identified based on their time domain characteristics and frequency domain characteristics.

4. The method for identifying residential charging facilities according to claim 3, characterized in that: The process of identifying the charging status of the residential charging facility to be identified based on the time domain characteristics and frequency domain characteristics thereof includes the following: The time domain features and frequency domain features of the residential charging facilities to be identified when charging normally are respectively fused to obtain the time domain fusion features and frequency domain fusion features of the normal charging state; Determine a time domain feature threshold range and a frequency domain feature threshold range according to the time domain fusion features and the frequency domain fusion features of a normal charging state; The time domain features and frequency domain features for identifying the current charging state of residential charging facilities are respectively fused to obtain the time domain fusion features and frequency domain fusion features of the current charging state; The time domain fusion features and frequency domain fusion features of the current charging status are compared with the time domain feature threshold range and the frequency domain feature threshold range respectively, and whether the current charging status of the residential charging facility to be identified is normal is determined based on the comparison results.

5. The method for identifying residential charging facilities according to claim 4, characterized in that: The feature fusion of time domain features and frequency domain features is performed based on the following formula: Among them, P t represents the time domain fusion feature at time t, P f represents the frequency domain fusion feature when the frequency is f, a represents the number of time domain features, b represents the number of frequency domain features, x t,m represents the mth time domain feature at time t, x f,j represents the jth frequency domain feature at frequency f, ρ t,m represents the variance weight of the mth time domain feature at time t, ρ f,j It represents the variance weight of the jth frequency domain feature when the frequency is f, β1 represents the equal weight factor of the time domain feature, and β2 represents the equal weight factor of the frequency domain feature.

6. The method for identifying residential charging facilities according to claim 5, characterized in that: The time domain feature threshold range is T t =u t ±Kσ t ,u t and σ t Respectively represent the mean and standard deviation of the time domain fusion features, and the frequency domain feature threshold range is T f =u f ±Kσ f ,u f and σ f They represent the mean and standard deviation of the frequency domain fusion features respectively, and K represents the factor coefficient.

7. The method for identifying residential charging facilities according to claim 1, characterized in that: The number of support vector machine models constructed is consistent with the number of types of residential charging facilities, and each support vector machine model is trained separately using the corresponding training data set to obtain the load identification model corresponding to each type of residential charging facility.

8. A residential charging facility identification system, characterized in that: include: A time-frequency domain feature acquisition module is used to obtain the time-domain and frequency-domain features of the charging current of different types of residential charging facilities during normal charging; A training data set construction module is used to construct feature vectors of different types of residential charging facilities based on time domain features and frequency domain features, and to add labels accordingly to construct a training data set corresponding to each type of residential charging facility; The model building and training module is used to build a support vector machine model and obtain a load identification model after training the support vector machine model using a training data set; The real-time load identification module is used to obtain the time domain characteristics and frequency domain characteristics of the residential charging facilities to be identified, and input their time domain characteristics and frequency domain characteristics into the load identification model for load identification.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the method according to any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium for storing a computer program for identifying residential charging facilities, characterized in that: When the computer program is run on a computer, the steps of the method according to any one of claims 1 to 7 are executed.

Images