Harmonic source identification method and device, computer equipment, readable storage medium and program product

By decomposing and evaluating the harmonic factors in the harmonic current data, accurately identifying and positioning the harmonic sources in the distribution network, the problem of inaccurate harmonic source identification in the existing technology is solved, and the efficiency of harmonic governance is improved. accuracy.

CN119089241APending Publication Date: 2024-12-06SHENZHEN POWER SUPPLY BUREAU

Patent Information

Application Number
CN202411109286.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art is difficult to accurately identify and locate harmonic sources in the distribution network, resulting in difficulties in harmonic governance and division of responsibilities.

Method used

By obtaining the harmonic current data of common points, decompose the harmonic factors, calculate the weight and evaluation value of each harmonic factor, determine the target harmonic source, and accurately identify the harmonic source using pre-trained decomposition model and information entropy calculation.

Benefits of technology

It realizes accurate identification and positioning of harmonic sources, in-depth analysis and diagnosis of harmonic problems, and improves the efficiency and accuracy of harmonic governance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089241A_ABST
    Figure CN119089241A_ABST
Patent Text Reader

Abstract

The invention relates to a harmonic source identification method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring common point harmonic current data; decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set; calculating the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor according to the weight; and determining a target harmonic source according to the evaluation value. By adopting the method, the harmonic source can be accurately identified.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a harmonic source identification method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] With the development of power electronics technology and the widespread use of nonlinear devices, the number of harmonic sources in distribution networks has gradually increased. The devices that generate harmonics in the system are harmonic sources, which are nonlinear electrical devices. The large-scale access of these devices has caused harmonic pollution, and it is necessary to control them. Considering the randomness and uncertainty of harmonic source access, the effective identification of the types of harmonic sources in the distribution network is an important reference for harmonic responsibility division and harmonic control. Therefore, it is of great significance to correctly identify the harmonic sources connected to the distribution network.

[0003] Currently, harmonic sources can be identified by a detection and positioning method that focuses on the harmonic status of the entire network and a detection and positioning method that focuses on the point of common coupling (PCC) point, but both methods are difficult to ensure the accuracy of harmonic source positioning. Summary of the invention

[0004] Based on this, it is necessary to provide a harmonic identification method, device, computer equipment, computer-readable storage medium and computer program product that can accurately identify harmonic sources in response to the above technical problems.

[0005] In a first aspect, the present application provides a harmonic source identification method, the method comprising:

[0006] Obtain common point harmonic current data;

[0007] Decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set;

[0008] Calculating the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor according to the weight;

[0009] A target harmonic source is determined according to the evaluation value.

[0010] In one embodiment, decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set includes:

[0011] Extracting features of each harmonic current to obtain harmonic components;

[0012] Each of the harmonic components is input into a decomposition model, and each of the harmonic currents is decomposed by the decomposition model to obtain the harmonic factor data set.

[0013] In one embodiment, the decomposition model is pre-trained; the training process of the decomposition model includes:

[0014] Acquire harmonic samples; the detection samples carry labels;

[0015] Inputting the harmonic samples into the initial model for training to obtain prediction factors;

[0016] A target loss function is obtained based on the prediction factors and the labels, and the parameters of the initial model are adjusted according to the target loss function until the training is completed to obtain the decomposition model.

[0017] In one embodiment, the calculating the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor according to the weight, includes:

[0018] Calculating the amount of information of each harmonic factor in each harmonic current to obtain information entropy;

[0019] Calculating the weight of each harmonic factor according to the information entropy;

[0020] An evaluation value of the harmonic factor is obtained according to the weight and the harmonic factor.

[0021] In one embodiment, calculating the weight of each harmonic factor according to the information entropy includes:

[0022] Calculating the information entropy difference of each harmonic factor according to the information entropy;

[0023] The proportion of the information entropy difference corresponding to each of the harmonic currents is calculated to obtain the weight of the harmonic factor.

[0024] In one embodiment, the obtaining of common point harmonic current data includes:

[0025] The circuit corresponding to the common node of the main distribution network is converted into an equivalent circuit, and the common point harmonic current data is obtained according to the equivalent circuit.

[0026] In a second aspect, the present application further provides a harmonic source identification device, the device comprising:

[0027] An acquisition module, used to acquire common point harmonic current data;

[0028] A decomposition module, used for decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set;

[0029] A calculation module, used to calculate the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculate the evaluation value of each harmonic factor according to the weight;

[0030] A screening module is used to determine a target harmonic source according to the evaluation value.

[0031] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0033] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0034] The above-mentioned harmonic source identification method, device, computer equipment, computer-readable storage medium and computer program product decompose each harmonic current in the common point harmonic current data into a structure composed of various harmonic factors, then calculate the weight of each harmonic factor, determine the evaluation value of each harmonic factor according to the weight of each harmonic factor, and determine the target harmonic source from multiple harmonic factors according to the evaluation value. In this way, by decomposing the harmonic current, harmonic problems can be analyzed and diagnosed more deeply. And, according to the evaluation value of each harmonic factor, the source of the harmonic problem can be accurately located. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 is a schematic flow chart of a harmonic source identification method in one embodiment;

[0037] Figure 2 is a schematic diagram of a Thevenin equivalent circuit in one embodiment;

[0038] Figure 3is a structural block diagram of a harmonic identification device in one embodiment;

[0039] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] PCC, or Point of Common Coupling, is the connection point between different parts or systems in a power system. In a power system, PCC usually refers to the connection point between the power grid and user equipment, distributed power sources or other power systems. PCC is a key node for power flow and exchange in a power system, and its power quality directly affects the stability and efficiency of the connected equipment and the entire power grid.

[0042] A PCC point may be connected to multiple harmonic sources, including different loads, distributed power sources, etc. These sources may generate harmonics simultaneously, making it complicated to determine the responsibility of each source for harmonic contribution. In order to accurately determine the harmonic sources in the distribution network, this application proposes a harmonic source identification method.

[0043] In one embodiment, Figure 1 As shown, a harmonic source identification method is provided. This embodiment takes the method applied to a terminal as an example for illustration. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0044] Step S102, obtaining common point harmonic current data.

[0045] Optionally, a power quality analyzer or a harmonic analyzer may be used to perform real-time measurement of harmonic current at the PCC point.

[0046] Optionally, a data acquisition system (DAS) can be used to collect the signal output by the current sensor. DAS can record current waveform data at a high sampling rate to provide raw data for subsequent harmonic analysis.

[0047] Optionally, since the actual distribution network structure may be very complex and contain a large number of nodes and branches, the circuit will be further simplified, and the common point harmonic current data will be obtained in the simplified circuit. Exemplarily, the circuit can be simplified by the Thevenin equivalent circuit, the Norton equivalent circuit, and the circuit decomposition method.

[0048] Step S104, decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set.

[0049] Since the PCC point is where different parts or different systems are connected, it can be the connection point between the power grid and the power generation equipment, load or distributed power source. That is to say, in the power system, the harmonic current at the PCC point is greatly affected by the harmonic sources present in the system. For example, transformers, reactors, commutation devices, and bidirectional thyristors. The harmonic currents generated by these harmonic sources will propagate in the power grid and accumulate at the PCC point. Since the PCC point is the collection point of multiple power sources and loads, the harmonic currents generated by different harmonic sources are superimposed here, which may cause the harmonic current level at the PCC point to increase significantly.

[0050] Therefore, in order to identify the harmonic source, in this embodiment, the harmonic source of each harmonic in the harmonic current data of the common point is decomposed into a form of multiple harmonic sources to obtain a harmonic factor data set. Among them, the harmonic factor is the root cause of the current, that is, the harmonic source.

[0051] Exemplarily, assuming that the harmonic source is X, X is decomposed into the form of X=A+B, where X is the harmonic current of the common node, and A and B are the harmonic currents caused by other harmonic sources.

[0052] In this way, by decomposing the total harmonic current at the PCC point into the contributions of different harmonic sources, the responsibility of each harmonic source can be clarified, which helps to identify the main sources of harmonic pollution. In addition, since the harmonic currents A and B caused by the harmonic sources are dynamically changing, the decomposition method can be used to dynamically monitor the system harmonic situation and implement real-time control.

[0053] Step S106, calculating the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor according to the weight.

[0054] In step S104, the harmonic current is decomposed, that is, each harmonic current in the common point harmonic current data has its corresponding harmonic factor decomposition formula. In order to determine the evaluation value of each harmonic factor, that is, the contribution of each harmonic factor to the harmonic current, the weights corresponding to each harmonic factor corresponding to each harmonic current are calculated, and the evaluation value of the harmonic factor is calculated according to the weight.

[0055] For example, assume that the harmonic factor data set is

[0056]

[0057] Among them, A1 and B1 correspond to the harmonic factor decomposition formula of the first harmonic current, and A2 and B2 correspond to the harmonic factor decomposition formula of the other harmonic current. In this embodiment, the weights of A1, A2, B1 and B2 are calculated respectively, and the evaluation values ​​of harmonic factor A and harmonic factor B are calculated respectively according to the weights.

[0058] For example, the weights of A1 and A2 may be weighted to obtain the evaluation value of the harmonic factor A. Similarly, the evaluation value of the harmonic factor B may be calculated.

[0059] Alternatively, the contribution method can be used, that is, the ratio of the harmonic current generated by each harmonic source to the total harmonic current is calculated and used as the weight. For example, if A1 is the first harmonic current from source A and X1 is the total amount of the first harmonic current, the weight of A1 can be WA1=A1X1.

[0060] Optionally, a square sum method may be used to calculate the square sum of each harmonic source current, and then the square sum of each harmonic source is divided by the sum of the square sums of the total harmonic currents to serve as a weight.

[0061] Step S108, determining the target harmonic source according to the evaluation value.

[0062] Among them, target harmonic sources refer to those harmonic sources that are identified as having significant contributions to harmonic currents or having a greater impact on power quality.

[0063] Optionally, the target harmonic source may be determined by a preset method and an evaluation value. For example, the harmonic factor with the highest target score may be selected as the target harmonic source.

[0064] Furthermore, in other embodiments, a preset method is set according to actual use requirements or actual use scenarios, and a target harmonic source is determined according to the preset scheme and the evaluation value.

[0065] In the above embodiment, each harmonic current in the common point harmonic current data is decomposed into a structure composed of various harmonic factors, and then the weight of each harmonic factor is calculated, and the evaluation value of each harmonic factor is determined according to the weight of each harmonic factor, and the target harmonic source is determined from multiple harmonic factors according to the evaluation value. In this way, by decomposing the harmonic current, the harmonic problem can be analyzed and diagnosed more deeply. And, according to the evaluation value of each harmonic factor, the source of the harmonic problem can be accurately located.

[0066] Furthermore, in one of the embodiments, the above-mentioned decomposition of each harmonic current in the common point harmonic current data to obtain a harmonic factor data set includes: extracting features of each harmonic current to obtain harmonic components; inputting each harmonic component into a decomposition model, and decomposing each harmonic current through the decomposition model to obtain a harmonic factor data set.

[0067] In this embodiment, each harmonic current in the common point harmonic current data is decomposed, so the harmonic current is firstly feature extracted so as to accurately extract the harmonic components in the signal, thereby providing an accurate data base for decomposing the harmonics.

[0068] Optionally, since there is a certain amount of noise in the harmonic current, the noise is easily confused with the harmonic components, so the harmonic current is extracted and decomposed after the harmonic components are obtained.

[0069] Furthermore, in some embodiments, the harmonic current is converted from a time domain signal to a frequency domain, and then the harmonic components are extracted.

[0070] For example, the harmonic current can be converted from the time domain signal to the frequency domain by using a fast Fourier transform, and then feature extraction can be performed. Specifically, the feature extraction of the harmonic current can be performed by using formula (2), and the spectrum of the signal can be extracted while extracting the signal feature.

[0071]

[0072] Where X(k) represents the amplitude and phase of the kth frequency in the frequency domain, x(n) represents the value of the nth sampling point in the time domain, N represents the total number of sampling points, W is the fast Fourier transform operator and

[0073] Optionally, after obtaining the harmonic components, the harmonic components are input into a decomposition model, and each harmonic current is decomposed by the decomposition model to obtain a harmonic factor data set.

[0074] Furthermore, the decomposition model decomposes the harmonic components into three types of harmonic factor data sets, namely, harmonic circuit at PCC point, ferromagnetic saturation type, electronic switch type and arc type. Specifically, it can be shown in formula (3).

[0075]

[0076] in, is the harmonic current at the PCC point,

[0077]

[0078] In the formula, Indicates the harmonic current generated on the system side, Indicates the harmonic current generated on the user side. In the method described in the present invention, only the harmonic source identification on the load side is considered, so it can be considered as a non-zero constant.

[0079] As shown above, the harmonic current measured in the PCC distribution network is greatly affected by typical harmonic sources. Therefore, when analyzing the harmonic current at the PCC point, it is necessary to pay attention to the harmonic emission levels of these typical harmonic sources, including three types of harmonic sources: ferromagnetic saturation type, electronic switch type, and arc type.

[0080] Among them, ferromagnetic saturation harmonic sources refer to various iron core devices, such as transformers, reactors, etc. Transformers are common devices in distribution networks. Because they will show saturation characteristics during actual operation, transformers are a typical harmonic source in distribution networks. Their model is shown in formula (5).

[0081]

[0082] In the formula, is the hth harmonic current amplitude of the transformer, h is the harmonic order, R is the transformer equivalent resistance, X is the transformer equivalent reactance, f is the grid frequency, N1 is the number of primary winding turns, is the main magnetic flux of the transformer.

[0083] Among them, electronic switch harmonic sources mainly include various commutation devices, bidirectional thyristor controllable switch devices, PWM inverters and other power electronic devices. As a common device containing power electronic devices, the harmonics of the three-phase fully controlled rectifier can be calculated by formula (6).

[0084]

[0085] In the formula, I d is the average value of the load current, and π is 3.14. Where k is a constant, which mainly indicates that the harmonic characteristics of the rectifier are 5th, 7th, 11th, 13th... harmonics.

[0086] Among them, the arc-type harmonic source has an arc ignition and violent fluctuation, which causes irregular current fluctuations and generates harmonics. Its nonlinear characteristics are shown in formula (7).

[0087]

[0088] Where U is the arc voltage, is the arc current of the hth time, R1 and R2 are arc resistances, U hg is the hth arcing voltage, i1 and i2 are the arcing current and arc extinction current.

[0089] In addition, other non-typical harmonic sources can be expressed by formula (8).

[0090]

[0091] Equation 8 is a general expression for other non-typical harmonic sources, expressing the harmonic current as a function of harmonic voltage and nonlinearity. U1 to Un represent the harmonic voltages of the non-typical harmonic sources from 1 to n, and C is a constant related to the non-linearity. It is also the size and characteristics of the remaining harmonic content after decomposing the main harmonic sources.

[0092] Therefore, formula (3) can be rewritten as

[0093]

[0094] In summary, the decomposition model decomposes the harmonic current and obtains the decomposition formula as shown in formula (6).

[0095] Exemplarily, in one embodiment, after the distribution network is connected to the harmonic source, the harmonic current at the PCC point naturally changes to a certain extent, and the amount of change can be described by the following formula.

[0096]

[0097] In the formula, It represents the steady-state harmonic current of the PCC point after the new harmonic source is connected to the distribution network. It indicates the steady-state harmonic current of the PCC point before the new harmonic source of the distribution network is connected.

[0098] Will After inputting into the decomposition model, the decomposition value of each harmonic current is obtained as shown in Formula 11.

[0099]

[0100] Since there are multiple harmonic currents in the common point harmonic current data, the harmonic factor data set shown in formula (12) can be obtained by decomposing the model.

[0101]

[0102] In this way, by decomposing the harmonic current through the decomposition model, the harmonic factor data set can be obtained quickly and accurately.

[0103] Among them, the above-mentioned decomposition model is pre-trained; the training process of the decomposition model includes: obtaining harmonic samples; detecting samples carrying labels; inputting harmonic samples into the initial model for training to obtain prediction factors; obtaining the target loss function based on the prediction factors and labels, and adjusting the parameters of the initial model according to the target loss function until the training is completed to obtain the decomposition model.

[0104] The harmonic sample refers to the data used to train the decomposition model, which may come from historical data of different time periods; the label refers to the true harmonic factor decomposition formula of the harmonic current in the harmonic sample.

[0105] The initial model refers to a model that has not been trained yet, which can be a BP (Back Propagation) neural network or a convolutional neural network (CNN).

[0106] BP network algorithm is the most commonly used one in neural network, and its structure mainly includes: input layer, hidden layer, and output layer. This algorithm takes the square of error as the objective function, and calculates the minimum value of the objective function through the forward propagation of the signal and the back propagation of the error. The output equation of the BP neural network can be expressed as formula (13).

[0107]

[0108] In the formula, net k is the hidden layer input; w ik is the connection weight between the input layer and the hidden layer; x i are the input quantities of input layer i; y(x) are the output quantities of output layer j; w jk is the weight of the hidden layer-output layer; f(net k ) is the output of the hidden layer; b kj is the bias from hidden layer to output layer.

[0109] The input and output layers of the neural network are defined as shown below.

[0110]

[0111] Optionally, the harmonic samples are input into the initial model for training to obtain prediction factors. The prediction factors refer to the factor decompositions predicted by the initial model during the training process. Therefore, the target loss function is calculated based on the prediction factors. The parameters of the initial model are adjusted by the target loss function until the training is completed to obtain the decomposition model.

[0112] In one of the embodiments, the above-mentioned calculation of the weights of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor based on the weight, includes: calculating the amount of information of each harmonic factor in each harmonic current to obtain information entropy; according to the information entropy, calculating the weight of each harmonic factor; according to the weight and the harmonic factor, obtaining the evaluation value of the harmonic factor.

[0113] In this embodiment, the weight of the harmonic factor corresponding to each harmonic current is calculated by information entropy, and then the evaluation value of the harmonic factor is obtained according to the weight corresponding to the harmonic factor.

[0114] Optionally, calculating the weight by information entropy is to use information entropy to quantify the amount of information or uncertainty contained in the harmonic current by each harmonic factor. Information entropy is an indicator to measure the information content of a random variable. The larger its value is, the higher the uncertainty of the random variable is, and the more information it contains. In other words, the more important the harmonic factor is to the harmonic current.

[0115] Optionally, the information entropy is obtained based on the probability distribution of harmonic factors. Exemplarily, in combination with formula (15), the probability distribution of harmonic factors is obtained:

[0116]

[0117] Wherein P represents the proportion of the i-th harmonic under the j-th harmonic source type to the harmonic current variation of the harmonic source of this type. In combination with the example in the above embodiment, it is the proportion of A1 in A1+B1.

[0118] Optionally, the harmonic factor data set needs to be standardized before calculating the probability distribution, and can be specifically standardized according to formula (16).

[0119]

[0120] Furthermore, the entropy value of each harmonic factor can be obtained according to formula (17), as shown in formula (17),

[0121]

[0122] in And need to meet e j ≥0.

[0123] Furthermore, in one of the embodiments, the above-mentioned calculation of the weight of each harmonic factor based on information entropy includes: calculating the information entropy difference of each harmonic factor based on the information entropy; calculating the proportion of the information entropy difference in the information entropy difference corresponding to each harmonic current, to obtain the weight of the harmonic factor.

[0124] Exemplarily, the information entropy difference of each harmonic factor can be calculated according to formula (18).

[0125] d j =1-e j Formula (18)

[0126] Then the weight of each harmonic factor is calculated according to formula (19).

[0127]

[0128] Where n represents the number of harmonic factors in each harmonic current.

[0129] Furthermore, the evaluation value of the harmonic factor can be calculated according to formula (20).

[0130]

[0131] Among them, s represents the evaluation value of the harmonic factor, s i , i=1,2,3,4, respectively representing the evaluation values ​​of 4 types of harmonic sources.

[0132] In the above embodiment, according to the influence of the change of each harmonic factor on the common point harmonic current data, the entropy value of the harmonic factor is calculated, and then the weight is determined to accurately calculate the evaluation value.

[0133] In one of the embodiments, obtaining common point harmonic current data includes: converting a circuit corresponding to a common node of the main distribution network into an equivalent circuit, and obtaining the common point harmonic current data according to the equivalent circuit.

[0134] Optionally, in this embodiment, the circuit corresponding to the public node of the main distribution network is converted into a Thevenin equivalent circuit.

[0135] Exemplarily, the Thevenin equivalent circuit is determined. In the process of determining the Thevenin equivalent circuit, the Thevenin equivalent voltage source and the Thevenin equivalent impedance need to be calculated. Then, the equivalent model of the harmonic source is determined, and finally, the harmonic current is calculated. Exemplarily, combined with Figure 2 As shown, Figure 2 FIG. 4 is a schematic diagram of a Thevenin equivalent circuit in an embodiment.

[0136] Through the Thevenin equivalent circuit, a complex power grid can be simplified into an equivalent voltage source and an equivalent impedance. In the simplified Thevenin equivalent circuit, the calculation of harmonic current is more intuitive and simple.

[0137] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0138] Based on the same inventive concept, the embodiment of the present application also provides a harmonic source identification device for implementing the harmonic source identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more harmonic source identification device embodiments provided below can refer to the limitations of the harmonic source identification method above, and will not be repeated here.

[0139] In an exemplary embodiment, Figure 3 As shown, a harmonic source identification device is provided, including: an acquisition module 310, a decomposition module 320, a calculation module 330 and a screening module 340, wherein:

[0140] The acquisition module 310 is used to acquire common point harmonic current data.

[0141] The decomposition module 320 is used to decompose each harmonic current in the common point harmonic current data to obtain a harmonic factor data set.

[0142] The calculation module 330 is used to calculate the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculate the evaluation value of each harmonic factor according to the weight.

[0143] The screening module 340 is used to determine the target harmonic source according to the evaluation value.

[0144] In one embodiment, the above-mentioned decomposition module includes:

[0145] The extraction unit is used to extract the characteristics of each harmonic current to obtain the harmonic components.

[0146] The factor decomposition unit is used to input each harmonic component into the decomposition model, decompose each harmonic current through the decomposition model, and obtain a harmonic factor data set.

[0147] In one embodiment, the decomposition module further includes:

[0148] The sample acquisition unit is used to acquire harmonic samples and detect the sample carrying labels.

[0149] The training unit is used to input the harmonic samples into the initial model for training to obtain the prediction factors.

[0150] The adjustment unit is used to obtain a target loss function based on the prediction factors and the labels, and adjust the parameters of the initial model according to the target loss function until the training is completed to obtain a decomposition model.

[0151] In one embodiment, the computing device comprises:

[0152] The information entropy unit is used to calculate the information amount of each harmonic factor in each harmonic current to obtain the information entropy.

[0153] The weight calculation unit is used to calculate the weight of each harmonic factor according to the information entropy.

[0154] The evaluation value calculation unit is used to obtain the evaluation value of the harmonic factor according to the weight and the harmonic factor.

[0155] In one embodiment, the weight calculation unit includes:

[0156] The difference calculation subunit is used to calculate the information entropy difference of each harmonic factor according to the information entropy.

[0157] The weight calculation subunit is used to calculate the proportion of the information entropy difference corresponding to each harmonic current to obtain the weight of the harmonic factor.

[0158] In one embodiment, the acquisition module includes:

[0159] The equivalent conversion unit is used to convert the circuit corresponding to the common node of the main distribution network into an equivalent circuit, and obtain the common point harmonic current data according to the equivalent circuit.

[0160] Each module in the above harmonic source identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0161] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store harmonic current data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a harmonic source identification method is implemented.

[0162] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0163] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining common point harmonic current data; decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set; calculating the weights of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating an evaluation value of each harmonic factor based on the weight; and determining a target harmonic source based on the evaluation value.

[0164] In one embodiment, when the processor executes the computer program, the following steps are also implemented: extracting features from each harmonic current to obtain harmonic components; inputting each harmonic component into a decomposition model, and decomposing each harmonic current through the decomposition model to obtain a harmonic factor data set.

[0165] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining harmonic samples; detecting samples carrying labels; inputting the harmonic samples into the initial model for training to obtain prediction factors; obtaining a target loss function based on the prediction factors and labels, and adjusting the parameters of the initial model according to the target loss function until the training is completed to obtain a decomposition model.

[0166] In one embodiment, when the processor executes the computer program, the following steps are also implemented: calculating the amount of information of each harmonic factor in each harmonic current to obtain information entropy; calculating the weight of each harmonic factor based on the information entropy; and obtaining an evaluation value of the harmonic factor based on the weight and the harmonic factor.

[0167] In one embodiment, when the processor executes the computer program, the following steps are also implemented: according to the information entropy, the information entropy difference of each harmonic factor is calculated; the proportion of the information entropy difference in the information entropy difference corresponding to each harmonic current is calculated to obtain the weight of the harmonic factor.

[0168] In one embodiment, when the processor executes the computer program, the following steps are also implemented: converting the circuit corresponding to the common node of the main distribution network into an equivalent circuit, and obtaining the common point harmonic current data according to the equivalent circuit.

[0169] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining common point harmonic current data; decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set; calculating the weights of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor based on the weight; and determining the target harmonic source based on the evaluation value.

[0170] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: extracting features from each harmonic current to obtain harmonic components; inputting each harmonic component into a decomposition model, decomposing each harmonic current through the decomposition model, and obtaining a harmonic factor data set.

[0171] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining harmonic samples; detecting labels carried by the samples; inputting the harmonic samples into the initial model for training to obtain prediction factors; obtaining a target loss function based on the prediction factors and the labels, and adjusting the parameters of the initial model according to the target loss function until the training is completed to obtain a decomposition model.

[0172] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: calculating the amount of information of each harmonic factor in each harmonic current to obtain information entropy; calculating the weight of each harmonic factor based on the information entropy; and obtaining an evaluation value of the harmonic factor based on the weight and the harmonic factor.

[0173] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the information entropy, the information entropy difference of each harmonic factor is calculated; the proportion of the information entropy difference in the information entropy difference corresponding to each harmonic current is calculated to obtain the weight of the harmonic factor.

[0174] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: converting the circuit corresponding to the common node of the main distribution network into an equivalent circuit, and obtaining the common point harmonic current data according to the equivalent circuit.

[0175] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps: obtaining common point harmonic current data; decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set; calculating the weights of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating an evaluation value of each harmonic factor based on the weight; and determining a target harmonic source based on the evaluation value.

[0176] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: extracting features from each harmonic current to obtain harmonic components; inputting each harmonic component into a decomposition model, decomposing each harmonic current through the decomposition model, and obtaining a harmonic factor data set.

[0177] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining harmonic samples; detecting labels carried by the samples; inputting the harmonic samples into the initial model for training to obtain prediction factors; obtaining a target loss function based on the prediction factors and the labels, and adjusting the parameters of the initial model according to the target loss function until the training is completed to obtain a decomposition model.

[0178] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: calculating the amount of information of each harmonic factor in each harmonic current to obtain information entropy; calculating the weight of each harmonic factor based on the information entropy; and obtaining an evaluation value of the harmonic factor based on the weight and the harmonic factor.

[0179] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on the information entropy, the information entropy difference of each harmonic factor is calculated; the proportion of the information entropy difference in the information entropy difference corresponding to each harmonic current is calculated to obtain the weight of the harmonic factor.

[0180] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: converting the circuit corresponding to the common node of the main distribution network into an equivalent circuit, and obtaining the common point harmonic current data according to the equivalent circuit.

[0181] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0182] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0183] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A harmonic source identification method, characterized in that: The method comprises: Obtain common point harmonic current data; Decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set; Calculating the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor according to the weight; A target harmonic source is determined according to the evaluation value.

2. The method according to claim 1, characterized in that The step of decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set includes: Extracting features of each harmonic current to obtain harmonic components; Each of the harmonic components is input into a decomposition model, and each of the harmonic currents is decomposed by the decomposition model to obtain the harmonic factor data set.

3. The method according to claim 2, characterized in that The decomposition model is pre-trained; the training process of the decomposition model includes: Acquire harmonic samples; the detection samples carry labels; Inputting the harmonic samples into the initial model for training to obtain prediction factors; A target loss function is obtained based on the prediction factors and the labels, and the parameters of the initial model are adjusted according to the target loss function until the training is completed to obtain the decomposition model.

4. The method according to claim 1, characterized in that: The step of calculating the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculating the evaluation value of each harmonic factor according to the weight, includes: Calculating the amount of information of each harmonic factor in each harmonic current to obtain information entropy; Calculating the weight of each harmonic factor according to the information entropy; An evaluation value of the harmonic factor is obtained according to the weight and the harmonic factor.

5. The method according to claim 4, characterized in that The step of calculating the weight of each harmonic factor according to the information entropy includes: Calculating the information entropy difference of each harmonic factor according to the information entropy; The proportion of the information entropy difference corresponding to each of the harmonic currents is calculated to obtain the weight of the harmonic factor.

6. The method according to claim 1, characterized in that The obtaining of common point harmonic current data includes: The circuit corresponding to the common node of the main distribution network is converted into an equivalent circuit, and the common point harmonic current data is obtained according to the equivalent circuit.

7. A harmonic source identification device, characterized in that: The device comprises: An acquisition module, used to acquire common point harmonic current data; A decomposition module, used for decomposing each harmonic current in the common point harmonic current data to obtain a harmonic factor data set; A calculation module, used to calculate the weight of each harmonic factor corresponding to each harmonic current in the harmonic factor data set, and calculate the evaluation value of each harmonic factor according to the weight; A screening module is used to determine a target harmonic source according to the evaluation value.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Method for identifying types of harmonic sources on basis of characteristic quantity analysis

    CN104375026A

  • Harmonic traceability method for determining system side as primary harmonic source

    CN106093570A

  • Harmonic pollution degree evaluation method, terminal equipment and storage medium

    CN112085414A

  • Electric energy metering method and system based on deep learning, equipment and storage medium

    CN115774147A

  • Method and system for identifying multiple harmonic sources of power distribution network

    CN116609612A

Cited By

  • Harmonic source ensemble learning positioning method based on dominant scale feature transfer matching

    CN119807725A

  • Harmonic source integrated learning positioning method based on dominant scale feature transmission matching

    CN119807725B