Electric vehicle charging identification method based on multi-space and multi-parameter fusion
By extracting and combining the current signals of the electric vehicle charging network time domain, time-frequency domain and frequency domain features, combined with neural network recognition, the problems of low accuracy and high missed rate of electric vehicle charging recognition in the prior art are solved. , achieving more efficient banned charging monitoring of electric vehicles.
Patent Information
- Application Number
- CN202411133327.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-19
AI Technical Summary
The existing electric vehicle charging identification method based on electric signals has low accuracy and high missed rate, especially in multi-space and multi-parameter environments, it is difficult to effectively identify the prohibited charging behavior of electric vehicles.
By obtaining the current signal of the power network to be monitored, the time-domain, time-frequency domain and frequency domain characteristics are extracted, and the charging recognition feature vector is combined, and the neural network is used to charge and identify electric vehicles to improve the recognition accuracy.
It improves the accuracy of the identification of illegal charging of electric vehicles, reduces the rate of missed reports, and ensures effective monitoring of illegal charging of electric vehicles.
Smart Images

Figure CN118656709B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of circuit detection technology, and in particular to a multi-space and multi-parameter fusion method for electric vehicle charging identification. Background Art
[0002] In recent years, as the economy develops towards green, ecological and shared directions, the electric bicycle industry has developed rapidly due to its green, intelligent and high-end characteristics. However, there are certain safety hazards in privately bringing electric vehicles indoors or between corridors to charge, and corresponding technical means are needed to reduce the behavior of charging electric vehicles at home.
[0003] Based on the above situation, various types of electric vehicle charging identification technologies based on graphic recognition and non-invasive load identification have emerged. However, electric vehicle home entry identification equipment based on image recognition can only be arranged in specific locations such as elevators and building entrances, and there are large identification blind spots. Although the electric vehicle detection device based on non-invasive load identification technology can solve the identification blind spot problem of electric vehicle home entry identification equipment based on image recognition, it has a large number of false alarms and missed alarms due to the wide variety of user electrical equipment and the intervention of "electric vehicle-like" equipment from time to time. This brings great trouble to managers in investigating illegal home charging of electric vehicles, and it is urgent to develop more robust non-invasive electric vehicle charging identification technology. Summary of the invention
[0004] The main purpose of this application is to provide a multi-space, multi-parameter fusion electric vehicle charging identification method, aiming to solve the technical problems that the existing electric vehicle charging identification method based on electrical signals has low accuracy in identifying prohibited charging of electric vehicles and has a high false alarm rate.
[0005] To achieve the above objectives, the present application proposes a multi-space, multi-parameter fusion electric vehicle charging identification method, the multi-space, multi-parameter fusion electric vehicle charging identification method comprising:
[0006] Acquire the current signal of the power network to be monitored;
[0007] Extracting time distribution characteristics of the current signal to determine the time domain characteristics of the current signal;
[0008] Performing wavelet transform on the current signal, and obtaining time-frequency domain characteristics of the current signal based on the wavelet transform result;
[0009] Performing a fast Fourier transform on the current signal to obtain a frequency domain feature of the current signal;
[0010] Perform feature combination based on the time domain feature, the time-frequency domain feature and the frequency domain feature to obtain a charging identification feature vector;
[0011] The electric vehicle charging identification is performed based on the charging identification feature vector to obtain the electric vehicle charging identification result.
[0012] In one embodiment, the time domain feature includes a first time domain feature and a second time domain feature; the step of extracting the time distribution feature of the current signal to determine the time domain feature of the current signal includes:
[0013] determining a time length of a discrete current signal based on the current signal;
[0014] Determine the zero zone proportion of the current signal based on the maximum value and the minimum value of the discrete current signal and the time length of the discrete current signal; the zero zone proportion is the first time domain feature of the current signal;
[0015] The kurtosis of the current signal is determined according to the value of the discrete current signal and the time length of the discrete current signal; the kurtosis is a second time domain feature of the current signal.
[0016] In one embodiment, the time-frequency domain feature includes a first time-frequency domain feature and a second time-frequency domain feature; the step of performing a wavelet transform on the current signal and obtaining the time-frequency domain feature of the current signal based on the wavelet transform result includes:
[0017] Performing a two-layer wavelet transform on the current signal using the db4 wavelet function as a wavelet basis to obtain a second-layer wavelet detail coefficient and a second-layer approximation coefficient of the current signal;
[0018] Performing effective value calculation based on the second layer wavelet detail coefficients to obtain a first time-frequency domain feature of the current signal;
[0019] Obtaining a derivative sequence of the second-layer approximation coefficients;
[0020] A second time-frequency domain feature of the current signal is determined based on a relative position difference between a maximum value of the second-layer approximation coefficient and a maximum value of the derivative sequence in the same period.
[0021] In one embodiment, the step of performing a fast Fourier transform on the current signal to obtain a frequency domain feature of the current signal includes:
[0022] Performing a fast Fourier transform on the current signal to obtain a first harmonic component of the current signal at a first frequency and a second harmonic component of the current signal at a second frequency;
[0023] A frequency domain characteristic of the current signal is determined based on a ratio of the first harmonic component to the second harmonic component.
[0024] In one embodiment, the step of performing electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result includes:
[0025] Inputting the charging identification feature vector into a preset neural network for charging identification to obtain an identification output result;
[0026] An electric vehicle charging identification result is determined based on the identification output result.
[0027] In addition, to achieve the above purpose, the present application also proposes a multi-space, multi-parameter fusion electric vehicle charging identification device, the multi-space, multi-parameter fusion electric vehicle charging identification device comprising:
[0028] A data acquisition module, used to acquire the current signal of the power network to be monitored;
[0029] A feature recognition module, used to extract time distribution features of the current signal and determine the time domain features of the current signal;
[0030] The feature recognition module is further used to perform wavelet transform on the current signal and obtain the time-frequency domain features of the current signal based on the wavelet transform result;
[0031] The feature recognition module is further used to perform fast Fourier transform on the current signal to obtain the frequency domain feature of the current signal;
[0032] A feature combination module, used to perform feature combination based on the time domain feature, the time-frequency domain feature and the frequency domain feature to obtain a charging identification feature vector;
[0033] The charging identification module is used to perform electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result.
[0034] In addition, to achieve the above-mentioned objectives, the present application also proposes a multi-space, multi-parameter fusion electric vehicle charging identification device, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the multi-space, multi-parameter fusion electric vehicle charging identification method as described above.
[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the multi-space and multi-parameter fusion electric vehicle charging identification method as described above are implemented.
[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the multi-space and multi-parameter fusion electric vehicle charging identification method as described above.
[0037] One or more technical solutions proposed in this application have at least the following technical effects:
[0038] The present application obtains the current signal of the power network to be monitored; determines the time domain characteristics of the current signal; performs wavelet transform on the current signal, and obtains the time-frequency domain characteristics of the current signal based on the wavelet transform result; performs fast Fourier transform on the current signal to obtain the frequency domain characteristics of the current signal; performs feature combination based on the time domain characteristics, time-frequency domain characteristics and frequency domain characteristics to obtain the charging identification feature vector; performs electric vehicle charging identification based on the charging identification feature vector to obtain the electric vehicle charging identification result. Because the time domain characteristics, time-frequency domain characteristics and frequency domain characteristics are combined, multi-space and multi-parameter electric vehicle charging identification is achieved, and the accuracy of electric vehicle prohibited charging identification is improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0041] Figure 1 A flow chart of the first embodiment of the multi-space and multi-parameter fusion electric vehicle charging identification method of the present application;
[0042] Figure 2 A flow chart of the second embodiment of the multi-space and multi-parameter fusion electric vehicle charging identification method of the present application;
[0043] Figure 3 A flow chart of the third embodiment of the multi-space and multi-parameter fusion electric vehicle charging identification method of the present application;
[0044] Figure 4 This is a schematic diagram of the module structure of the multi-space and multi-parameter fusion electric vehicle charging identification device according to an embodiment of the present application;
[0045] Figure 5This is a schematic diagram of the device structure of the hardware operating environment involved in the multi-space and multi-parameter fusion electric vehicle charging identification method in the embodiment of the present application.
[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0049] The main solutions of the embodiments of the present application are: obtaining the current signal of the power network to be monitored; determining the time domain characteristics of the current signal; performing wavelet transform on the current signal, and obtaining the time-frequency domain characteristics of the current signal based on the wavelet transform result; performing fast Fourier transform on the current signal to obtain the frequency domain characteristics of the current signal; performing feature combination based on the time domain characteristics, time-frequency domain characteristics and frequency domain characteristics to obtain a charging identification feature vector; performing electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result.
[0050] At present, the existing technology usually performs electric vehicle charging identification based on image recognition or non-invasive load identification. However, the electric vehicle home identification equipment based on image recognition can only be arranged in specific locations such as elevators and building entrances, and there are large identification blind spots. Although the electric vehicle detection method based on non-invasive load identification technology can solve the identification blind spot problem of electric vehicle home identification equipment based on image recognition, due to the wide variety of user electrical equipment and the access of "electric vehicle-like" equipment, there are a large number of false alarms and missed reports, which brings great trouble to the management personnel in investigating the illegal charging behavior of electric vehicles.
[0051] The present application provides a solution, which can analyze the charging characteristics of electric vehicles from more dimensions by extracting the multi-temporal and spatial features of the current signal in the monitored power network, and make the description of the charging characteristics of electric vehicles more comprehensive and accurate. Finally, the above features are input into a trained neural network to detect whether there is any prohibited charging behavior of electric vehicles in the monitored power network, which can ensure that the multi-space and multi-parameter fusion electric vehicle charging identification method proposed in the present invention has higher accuracy in identifying prohibited electric vehicle charging.
[0052] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a computer, server, etc., or an electronic device, virtual device, etc. that can realize the above functions. The following takes the multi-space, multi-parameter fusion electric vehicle charging identification device (hereinafter referred to as the identification device) as an example to illustrate this embodiment and the following embodiments.
[0053] Based on this, the embodiment of the present application provides a multi-space, multi-parameter fusion electric vehicle charging identification method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the multi-space and multi-parameter fusion electric vehicle charging identification method of the present application.
[0054] In this embodiment, the multi-space and multi-parameter fusion electric vehicle charging identification method includes steps S10 to S60:
[0055] Step S10, obtaining a current signal of the power network to be monitored;
[0056] Step S20, extracting time distribution features of the current signal to determine the time domain features of the current signal;
[0057] It can be understood that the above-mentioned monitored power network is also the user power network that needs to be used for electric vehicle charging identification. By monitoring and analyzing the current signal of the user power network, it is possible to determine whether there is an electric bicycle / electric bicycle battery being charged in the user power network.
[0058] It should be noted that the time domain characteristics of the current signal are the characteristics obtained by analyzing the current signal from the time dimension. By extracting the time distribution characteristics of the current signal, the time domain characteristics of the current signal can be determined. The time domain characteristics of the current signal can describe the nature of the current signal changing with time, such as the characteristics presented by the waveform, amplitude, frequency, peak and valley values of the current changing with time. These characteristics are simple, small in calculation, and high in real time, and are of great significance for circuit fault diagnosis, power system monitoring, signal recognition and processing, etc.
[0059] In a specific implementation, the identification device of the embodiment of the present application can obtain the current signal of the power network to be monitored, and extract the time distribution characteristics based on the current signal to determine the corresponding time domain characteristics.
[0060] Step S30, performing wavelet transform on the current signal, and obtaining time-frequency domain characteristics of the current signal based on the wavelet transform result;
[0061] Step S40, performing a fast Fourier transform on the current signal to obtain a frequency domain feature of the current signal;
[0062] Step S50, combining features based on the time domain features, the time-frequency domain features and the frequency domain features to obtain a charging identification feature vector;
[0063] Step S60, performing electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result.
[0064] It is understandable that the frequency domain characteristics of the current signal, that is, the characteristics obtained by analyzing the current signal from the frequency domain dimension, can include a variety of sinusoidal or harmonic components of different frequencies. By performing a fast Fourier transform on the current signal, the current signal can be converted from the time domain to the frequency domain, thereby determining the distribution characteristics of the current signal in the frequency domain. Determining the frequency characteristics of the current signal plays an important role in signal processing, fault detection, system optimization, etc.
[0065] It should be understood that by combining the time domain features, time-frequency domain features and frequency domain features, the obtained charging identification feature vector has multi-dimensional and multi-parameter fusion features, which can more comprehensively characterize the signal characteristics of the current signal, thereby improving the recognition accuracy of electric vehicle charging / electric vehicle battery charging.
[0066] The embodiment of the present application obtains the current signal of the power network to be monitored; determines the time domain characteristics of the current signal; performs wavelet transform on the current signal, and obtains the time-frequency domain characteristics of the current signal based on the wavelet transform result; performs fast Fourier transform on the current signal to obtain the frequency domain characteristics of the current signal; performs feature combination based on the time domain characteristics, time-frequency domain characteristics and frequency domain characteristics to obtain the charging identification feature vector; performs electric vehicle charging identification based on the charging identification feature vector to obtain the electric vehicle charging identification result. Because the time domain characteristics, time-frequency domain characteristics and frequency domain characteristics are combined, multi-space and multi-parameter electric vehicle charging identification is achieved, and the accuracy of electric vehicle prohibited charging identification is improved.
[0067] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 In an embodiment of the present application, the time domain feature includes a first time domain feature and a second time domain feature; the step of extracting the time distribution feature of the current signal to determine the time domain feature of the current signal includes:
[0068] Step S21, determining the time length of the discrete current signal based on the current signal;
[0069] It should be noted that the current signal is obtained by sampling the power network to be monitored. The sampling of the current signal may correspond to a sampling period. During the sampling period, a discrete current signal may be sampled and obtained, and the duration of the period is equivalent to the time length of the discrete current signal.
[0070] Step S22, determining a zero area ratio of the current signal based on a maximum value and a minimum value of the discrete current signal and a time length of the discrete current signal; the zero area ratio is a first time domain feature of the current signal;
[0071] It should be noted that for the waveform of the current signal, there are cases where the current value is lower than the preset current value in some time periods, and the zero zone ratio is the proportion of the above time period in the complete sampling cycle. The above preset current value can be one tenth of the maximum current value or other values, and the embodiments of the present application are not limited to this.
[0072] It should be explained that for the discrete current signal obtained by sampling, different current values may correspond to different moments. Among them, according to the current value of the discrete current signal, the maximum value and the minimum value thereof can be determined. Based on the maximum value and the minimum value of the discrete current signal and the time length of the discrete current signal, the zero zone proportion of the current signal is determined.
[0073] Specifically, calculate the proportion of zero area The formula can be shown as follows:
[0074] ;
[0075] in, Represents the current signal, represents the maximum value of the discrete current signal, Represents the minimum value of the discrete current signal, Represents the time length of a discrete current signal.
[0076] It is understandable that during the charging process of an electric vehicle / electric vehicle battery, the current signal will present a specific change pattern. By monitoring the zero zone proportion as the first time domain feature, it can be determined whether there is an electric vehicle / electric vehicle battery being charged in the circuit.
[0077] Step S23, determining the kurtosis of the current signal according to the value of the discrete current signal and the time length of the discrete current signal; the kurtosis is a second time domain feature of the current signal.
[0078] It should be noted that the kurtosis of the current signal is a parameter that can be used to represent the amplitude of the high-frequency harmonics in the current signal. In the embodiment of the present application, the kurtosis is defined based on the normalized fourth-order central moment and can be used to reflect the steepness of the current signal waveform. The kurtosis is particularly sensitive to changes in high-frequency harmonics caused by the electric vehicle charging current signal / electric vehicle battery charging current signal. The larger the amplitude of the high-frequency harmonics, the higher the kurtosis value and the steeper the current waveform. Specifically, for the kurtosis The calculation method can be as follows:
[0079] ;
[0080] in, That is the The amplitude of a discrete current signal.
[0081] In an embodiment of the present application, the time-frequency domain feature includes a first time-frequency domain feature and a second time-frequency domain feature; the step of performing a wavelet transform on the current signal and obtaining the time-frequency domain feature of the current signal based on the wavelet transform result includes:
[0082] Step S31, using the db4 wavelet function as a wavelet basis to perform a two-layer wavelet transform on the current signal to obtain a second-layer wavelet detail coefficient and a second-layer approximation coefficient of the current signal;
[0083] It should be noted that the db4 wavelet function is a commonly used wavelet function with 8 non-zero filter coefficients. By using the db4 wavelet function as a wavelet basis to perform a two-layer wavelet transform on the current signal, a multi-scale time-frequency analysis of the current signal can be achieved, and then the current signal can be decomposed into a combination of different frequency components, which correspond to different time scales. In the wavelet transform, the current signal can be decomposed into two parts, low frequency and high frequency. Among them, the coefficients of the low frequency part are also the wavelet approximation coefficients, and the coefficients of the high frequency part are also the wavelet detail coefficients.
[0084] Specifically, by performing two-layer wavelet decomposition on the current signal, the high-frequency component of the current signal at the second layer of decomposition can be obtained, that is, the second-layer wavelet detail coefficient, which can be used to represent the rapidly changing part of the current signal; at the same time, the low-frequency component of the current signal at the second layer of decomposition can also be obtained, that is, the second-layer wavelet approximation coefficient, which can be used to represent the relatively stable or slowly changing part of the current signal.
[0085] It can be understood that based on the second-layer wavelet detail coefficients, the transient characteristics, noise level and high-frequency interference of the current signal can be analyzed; based on the second-layer wavelet approximation coefficients, the basic behavior of the current signal can be analyzed. Through the second-layer wavelet detail coefficients and the second-layer wavelet approximation coefficients, the high-frequency and low-frequency characteristics of the current signal can be determined, thereby realizing the analysis of whether there is an electric vehicle / electric vehicle battery being charged in the circuit.
[0086] Step S32, performing effective value calculation based on the second layer wavelet detail coefficient to obtain a first time-frequency domain feature of the current signal;
[0087] It should be noted that in the power network to be monitored, especially in the process of charging electric vehicles / electric vehicles, high-frequency noise or transient phenomena may appear as fluctuations in the second-layer wavelet detail coefficients. By calculating the effective value of the second-layer wavelet detail coefficients and using the effective value as the first time-frequency domain feature of the current signal, the phenomenon in the charging process can be better monitored, thereby realizing the identification of electric vehicles / electric vehicle battery charging.
[0088] Specifically, the effective value of the second layer wavelet detail coefficient is The calculation can be as follows:
[0089] ;
[0090] in, represents the second layer wavelet detail coefficient, is the total number of coefficients.
[0091] Step S33, obtaining a derivative sequence of the second layer approximation coefficients;
[0092] Step S34: determining a second time-frequency domain feature of the current signal based on a relative position difference between a maximum value of the second layer approximation coefficient and a maximum value of the derivative sequence in the same period.
[0093] It should be noted that the reciprocal sequence of the second-level approximation coefficients provides direct information about the change of the current signal over time, which can help identify the high-frequency components in the signal and the change trend of the signal. The derivative sequence of The way can be as follows:
[0094] .
[0095] In the embodiment of the present application, the position of the maximum value in each period of the second-layer approximation coefficient can be first found. At the same time, the derivative sequence corresponding to the second-level approximate coefficients can be determined, and the position of the maximum value of the derivative sequence in the corresponding period of the second-level approximate coefficient sequence (that is, the same period as the second-level approximate coefficients) can be determined. By determining the position of the maximum value of the sequence of the second-level approximate coefficients within the period The position of the maximum value of the derivative sequence within the period The relative position difference between , the relative position can be used as the second time-frequency feature of the current signal. Specifically, the relative position The calculation method can be as follows:
[0096] .
[0097] It should be noted that the maximum value in the sequence of the second-level approximate coefficients can reflect the significant features or main components appearing in the current signal; the position of the maximum value in the reciprocal sequence of the second-level approximate coefficients can reflect the time point at which the rate of change of the current signal is the largest; by determining the relative position difference , it is possible to identify the different charging stages during the charging process, thereby improving the accuracy of charging identification.
[0098] In an embodiment of the present application, the step of performing a fast Fourier transform on the current signal to obtain a frequency domain feature of the current signal includes:
[0099] Step S41, performing a fast Fourier transform on the current signal to obtain a first harmonic component of the current signal at a first frequency and a second harmonic component of the current signal at a second frequency spectrum;
[0100] Step S42: determining a frequency domain feature of the current signal based on a ratio of the first harmonic component to the second harmonic component.
[0101] It should be noted that the first harmonic component may be the fundamental frequency component in the current signal, and the second harmonic component may be the third harmonic in the current signal. For example, when the fundamental frequency component in the current signal is 50 Hz, the corresponding third harmonic is 150 Hz.
[0102] In the embodiment of the present application, the value of the fundamental frequency component is not limited and can be determined according to the situation in actual application.
[0103] In one implementation of the embodiment of the present application, the scheme of the embodiment of the present application is described by taking the fundamental frequency component of 50 Hz and the third harmonic of 150 Hz as an example. Specifically, the embodiment of the present application can perform a fast Fourier transform based on the current signal to determine the current signal The frequency domain signal , then we can determine The ratio of the harmonic component with a medium frequency of 150Hz to the harmonic component with a frequency of 50Hz , the specific calculation formula can be shown as follows:
[0104] ;
[0105] in, Represents frequency domain signal The amplitude of the harmonic component with a mid-frequency of 50Hz, Represents frequency domain signal The amplitude of the harmonic component with a mid-frequency of 150Hz, the ratio of the harmonic components It can be used as the frequency domain feature of the current signal.
[0106] In the embodiment of the present application, the time length of the discrete current signal is determined based on the current signal; the zero area ratio of the current signal is determined based on the maximum and minimum values of the discrete current signal and the time length of the discrete current signal; the zero area ratio is the first time domain characteristic of the current signal; the kurtosis of the current signal is determined according to the value of the discrete current signal and the time length of the discrete current signal; the kurtosis is the second time domain characteristic of the current signal; the db4 wavelet function is used as the wavelet basis to perform a two-layer wavelet transform on the current signal to obtain the second layer of wavelet detail coefficients and the second layer of approximate coefficients of the current signal; the effective value is calculated based on the second layer of wavelet detail coefficients to obtain the first time-frequency domain characteristic of the current signal; the derivative sequence of the second layer of approximate coefficients is determined; the second time-frequency domain characteristic of the current signal is determined based on the relative position difference between the maximum value of the second layer of approximate coefficients and the maximum value of the same period of the derivative sequence; the current signal is fast Fourier transformed to obtain the first harmonic component of the current signal at the first frequency and the second harmonic component of the current signal at the second frequency spectrum; the frequency domain characteristic of the current signal is determined based on the ratio of the first harmonic component to the second harmonic component. Since the first time domain characteristic, the second time domain characteristic, the first time-frequency domain characteristic, the second time-frequency domain characteristic and the frequency domain characteristic of the current signal are determined and then these characteristics are combined to realize the judgment of the charging current in the circuit, it is possible to more accurately determine whether there are electric vehicles / electric vehicle batteries being charged in the power network to be monitored.
[0107] Based on the first embodiment and / or the second embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those of the above-mentioned first embodiment and / or the second embodiment can refer to the above introduction, and will not be repeated later. Figure 3 In the embodiment of the present application, the step of performing electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result includes:
[0108] Step S61, inputting the charging identification feature vector into a preset neural network for charging identification to obtain an identification output result;
[0109] Step S62: determining an electric vehicle charging identification result based on the identification output result.
[0110] In the embodiment of the present application, the time domain features, time-frequency domain features and frequency domain features of the current signal can be combined to obtain a charging identification feature vector. Specifically, the charging identification feature vector I of the electric vehicle can be obtained as follows:
[0111] ;
[0112] in, is the first time domain feature, is the first time-frequency domain feature, is the second time-frequency domain feature, is the frequency domain feature, is the second time domain feature.
[0113] It can be understood that the above-mentioned preset neural network is a pre-trained neural network, through which the input charging identification feature vector can be detected and identified, and the corresponding identification output result can be output. In one implementation of the embodiment of the present application, the preset neural network used can be a BP neural network. When the identification output result of the BP neural network is "1", it can be judged that there are illegal electric vehicle / electric vehicle battery charging behaviors in the power network to be monitored; if the identification output result of the BP neural network is "0", it can be judged that the power network to be monitored is normal and there is no illegal electric vehicle / electric vehicle battery charging behavior.
[0114] This application obtains an electric vehicle charging identification feature vector by analyzing the time domain, frequency domain and time-frequency domain characteristics of the current signal of the power network to be monitored, and inputs the electric vehicle charging identification feature vector into the trained BP neural network to determine whether there is illegal electric vehicle charging behavior in the power network to be monitored. Compared with the traditional electric vehicle charging identification method based on electrical signals, this application integrates the derivative transformation, wavelet transformation and fast Fourier transformation of the current signal, effectively avoiding the limitations based on a single spatial feature, so that this solution can have a higher accuracy rate in identifying illegal electric vehicle charging behavior, a lower false negative rate, and more practical application value.
[0115] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the multi-space and multi-parameter fusion electric vehicle charging identification method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0116] This application also provides a multi-space, multi-parameter fusion electric vehicle charging identification device, please refer to Figure 4 The multi-space, multi-parameter fusion electric vehicle charging identification device includes:
[0117] The data acquisition module 10 is used to acquire the current signal of the power network to be monitored;
[0118] A feature recognition module 20 is used to extract time distribution features of the current signal and determine the time domain features of the current signal;
[0119] The feature recognition module 20 is further used to perform wavelet transform on the current signal and obtain the time-frequency domain features of the current signal based on the wavelet transform result;
[0120] The feature recognition module 20 is further used to perform fast Fourier transform on the current signal to obtain the frequency domain feature of the current signal;
[0121] A feature combination module 30, configured to perform feature combination based on the time domain feature, the time-frequency domain feature and the frequency domain feature to obtain a charging identification feature vector;
[0122] The charging identification module 40 is used to perform electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result.
[0123] The multi-space, multi-parameter fusion electric vehicle charging identification device provided in this application adopts the multi-space, multi-parameter fusion electric vehicle charging identification method in the above-mentioned embodiment, which can solve the technical problems that the existing electric vehicle charging identification method based on electrical signals has a low accuracy rate in identifying prohibited charging of electric vehicles and a high false alarm rate. Compared with the prior art, the beneficial effects of the multi-space, multi-parameter fusion electric vehicle charging identification device provided in this application are the same as the beneficial effects of the multi-space, multi-parameter fusion electric vehicle charging identification method provided in the above-mentioned embodiment, and the other technical features of the multi-space, multi-parameter fusion electric vehicle charging identification device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.
[0124] The present application provides an electric vehicle charging identification device with multi-space and multi-parameter fusion. The electric vehicle charging identification device with multi-space and multi-parameter fusion includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the electric vehicle charging identification method with multi-space and multi-parameter fusion in the above-mentioned embodiment one.
[0125] Reference below Figure 5, which shows a schematic diagram of the structure of an electric vehicle charging identification device suitable for realizing multi-space and multi-parameter fusion in the embodiment of the present application. The electric vehicle charging identification device with multi-space and multi-parameter fusion in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The multi-space, multi-parameter fusion electric vehicle charging identification device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0126] like Figure 5 As shown, the multi-space, multi-parameter fusion electric vehicle charging identification device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the multi-space, multi-parameter fusion electric vehicle charging identification device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the multi-space, multi-parameter fusion electric vehicle charging identification device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a multi-space, multi-parameter fusion electric vehicle charging identification device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.
[0127] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0128] The multi-space, multi-parameter fusion electric vehicle charging identification device provided by the present application adopts the multi-space, multi-parameter fusion electric vehicle charging identification method in the above-mentioned embodiment, which can solve the technical problems that the existing electric vehicle charging identification method based on electrical signals has a low accuracy rate in identifying prohibited charging of electric vehicles and a high false alarm rate. Compared with the prior art, the beneficial effects of the multi-space, multi-parameter fusion electric vehicle charging identification device provided by the present application are the same as the beneficial effects of the multi-space, multi-parameter fusion electric vehicle charging identification method provided by the above-mentioned embodiment, and the other technical features of the multi-space, multi-parameter fusion electric vehicle charging identification device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0129] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0130] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0131] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the multi-space, multi-parameter fusion electric vehicle charging identification method in the above-mentioned embodiment.
[0132] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.
[0133] The above-mentioned computer-readable storage medium may be included in the multi-space, multi-parameter fusion electric vehicle charging identification device; or it may exist independently without being assembled into the multi-space, multi-parameter fusion electric vehicle charging identification device.
[0134] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the multi-space, multi-parameter fusion electric vehicle charging identification device, the multi-space, multi-parameter fusion electric vehicle charging identification device:
[0135] Acquire the current signal of the power network to be monitored;
[0136] Extracting time distribution characteristics of the current signal to determine the time domain characteristics of the current signal;
[0137] Performing wavelet transform on the current signal, and obtaining time-frequency domain characteristics of the current signal based on the wavelet transform result;
[0138] Performing a fast Fourier transform on the current signal to obtain a frequency domain feature of the current signal;
[0139] Perform feature combination based on the time domain feature, the time-frequency domain feature and the frequency domain feature to obtain a charging identification feature vector;
[0140] The electric vehicle charging identification is performed based on the charging identification feature vector to obtain the electric vehicle charging identification result.
[0141] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0142] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0143] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0144] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned multi-space, multi-parameter fusion electric vehicle charging identification method, which can solve the technical problems that the existing electric vehicle charging identification method based on electrical signals has a low accuracy rate for identifying prohibited charging of electric vehicles and a high false alarm rate. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the multi-space, multi-parameter fusion electric vehicle charging identification method provided in the above-mentioned embodiment, and will not be repeated here.
[0145] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the multi-space, multi-parameter fusion electric vehicle charging identification method as described above.
[0146] The computer program product provided by the present application can solve the technical problems that the existing electric vehicle charging identification method based on electrical signals has a low accuracy rate in identifying prohibited charging of electric vehicles and a high false alarm rate. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the multi-space and multi-parameter fusion electric vehicle charging identification method provided by the above embodiment, which will not be elaborated here.
[0147] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A multi-space and multi-parameter fusion electric vehicle charging identification method, characterized in that: The method comprises: Acquire the current signal of the power network to be monitored; Extracting time distribution characteristics of the current signal to determine the time domain characteristics of the current signal; Performing wavelet transform on the current signal, and obtaining time-frequency domain characteristics of the current signal based on the wavelet transform result; Performing a fast Fourier transform on the current signal to obtain a frequency domain feature of the current signal; Perform feature combination based on the time domain feature, the time-frequency domain feature and the frequency domain feature to obtain a charging identification feature vector; Performing electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result; The time domain feature includes a first time domain feature and a second time domain feature; The step of extracting the time distribution feature of the current signal to determine the time domain feature of the current signal includes: determining a time length of a discrete current signal based on the current signal; Determine the zero zone proportion of the current signal based on the maximum value and the minimum value of the discrete current signal and the time length of the discrete current signal; the zero zone proportion is the first time domain feature of the current signal; Determining the kurtosis of the current signal according to the value of the discrete current signal and the time length of the discrete current signal; the kurtosis is a second time domain feature of the current signal; The time-frequency domain features include a first time-frequency domain feature and a second time-frequency domain feature; Calculate the zero zone ratio The formula is as follows: ; in, Represents the current signal, represents the maximum value of the discrete current signal, Represents the minimum value of the discrete current signal, Represents the time length of a discrete current signal; Calculate Kurtosis The formula is as follows: ; in, For the The amplitude of a discrete current signal; The step of performing wavelet transform on the current signal and obtaining the time-frequency domain characteristics of the current signal based on the wavelet transform result comprises: Performing a two-layer wavelet transform on the current signal using the db4 wavelet function as a wavelet basis to obtain a second-layer wavelet detail coefficient and a second-layer approximation coefficient of the current signal; Performing effective value calculation based on the second layer wavelet detail coefficients to obtain a first time-frequency domain feature of the current signal; Obtaining a derivative sequence of the second-layer approximation coefficients; Determine a second time-frequency domain feature of the current signal based on a relative position difference between a maximum value of the second-layer approximation coefficient and a maximum value of the derivative sequence in the same period; The effective value of the second layer wavelet detail coefficient The calculation is as follows: ; in, represents the second layer wavelet detail coefficient, is the total number of coefficients; The second level approximation coefficient The derivative sequence of The calculation method of is as follows: ; The step of performing a fast Fourier transform on the current signal to obtain a frequency domain feature of the current signal comprises: Performing a fast Fourier transform on the current signal to obtain a first harmonic component of the current signal at a first frequency and a second harmonic component of the current signal at a second frequency; A frequency domain characteristic of the current signal is determined based on a ratio of the first harmonic component to the second harmonic component.
2. The multi-space and multi-parameter fusion electric vehicle charging identification method according to claim 1, characterized in that: The step of performing electric vehicle charging identification based on the charging identification feature vector to obtain an electric vehicle charging identification result comprises: Inputting the charging identification feature vector into a preset neural network for charging identification to obtain an identification output result; An electric vehicle charging identification result is determined based on the identification output result.
Citation Information
Patent Citations
Electric vehicle charging harmonic wave identification method based on wavelet transform
CN106908663A
Early warning method and system for charging potential safety hazards of electric bicycle
CN115980519A
Direct-current arc detection method and device of photovoltaic system
CN116150588A
Charging pile electricity consumption abnormity processing method, device and equipment and storage medium
CN118259103A
Systems and methods for harmonic-based battery charging
US20220085633A1
