Distributed power supply access transformer area power supply quality monitoring method, terminal and storage medium

Abstract

The present application relates to the technical field of distributed power generation, and particularly relates to a distributed power supply access substation power supply quality monitoring method, a terminal and a storage medium, the method of the present application first acquires a plurality of waveforms, the waveforms are acquired based on the output curve of the power supply in the substation, then, the plurality of waveforms are respectively subjected to Fourier transform to acquire a plurality of waveform sets, then, the plurality of waveforms and the plurality of waveform sets are respectively input to a transform model to acquire a plurality of time-frequency features, wherein the time-frequency features represent the time when the fundamental wave and / or the plurality of high-order harmonics appear; finally, a monitoring curve is drawn according to the plurality of time-frequency features, wherein the monitoring curve reflects the substation power supply quality. Through the transform model, a curve reflecting the harmonic frequency, the proportion of harmonics and fundamental wave, and each time after the decomposition of the substation waveform is constructed, the transform efficiency is high, the real-time performance is good, and it is easy to understand at a glance.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of distributed power generation technology, and particularly relates to a distributed power supply access substation power supply quality monitoring method, a terminal and a storage medium. BACKGROUND

[0002] Distributed power supply refers to configuring a small generator set (generally less than 30 MW) at a user site or near a power consumption site to meet the needs of a specific user, support the economic operation of an existing power distribution network, or meet both of these requirements. These small units include fuel cells, small gas turbines, small photovoltaic power generation, small wind-solar complementary power generation, or hybrid devices of gas turbines and fuel cells. With the joint action of factors such as technological development, public environmental policy and expansion of the power market, distributed power generation has become an important energy choice in the future.

[0003] Since microgrids using distributed power supply mostly use natural energy such as solar energy and wind energy, wind resources and solar energy resources have obvious volatility and instability, which causes the output power of each subsystem to fluctuate, thereby affecting the power generation quality of the microgrid. On the other hand, the microgrid is integrated into the main grid, which also brings these unstable factors into the main grid, thereby affecting the power quality of the main grid, such as voltage deviation, voltage fluctuation, high-order harmonic and the like of the main grid.

[0004] How to timely find problems existing in the power quality of the distributed power supply access substation becomes the key to timely correcting the power supply quality of the substation. However, in the prior art, the data of the power supply quality of the previous period is usually sorted and summarized, and the real-time performance is poor.

[0005] Therefore, it is necessary to develop and design a distributed power supply access substation power supply quality monitoring method. SUMMARY

[0006] The embodiment of the present application provides a distributed power supply access substation power supply quality monitoring method, a terminal and a storage medium, which are used to solve the problem of poor real-time performance of the monitoring of the power supply quality of the distributed power supply access substation in the prior art.

[0007] In a first aspect, the embodiment of the present application provides a distributed power supply access substation power supply quality monitoring method, comprising:

[0008] obtaining a plurality of waveforms, wherein the waveforms are obtained based on the output curve of the power supply in the substation;

[0009] performing Fourier transform on the plurality of waveforms respectively to obtain a plurality of waveform sets, wherein the waveform set includes a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms;

[0010] inputting the plurality of waveforms and the plurality of waveform sets into a transform model respectively to obtain a plurality of time-frequency features, wherein the time-frequency features represent time instants at which the fundamental wave and / or the plurality of higher-order harmonics occur;

[0011] drawing a monitoring curve according to the plurality of time-frequency features, wherein the monitoring curve reflects power supply quality of a transformer area.

[0012] In a possible implementation, the Fourier transforming the plurality of waveforms respectively to obtain the plurality of waveform sets comprises:

[0013] For each of the plurality of waveforms, the following steps are performed:

[0014] Fourier transforming the waveform to obtain a fundamental wave and a plurality of higher-order harmonics;

[0015] calculating a ratio of an amplitude of each of the plurality of higher-order harmonics to an amplitude of the fundamental wave respectively;

[0016] adding the fundamental wave and the higher-order harmonics whose ratio is greater than a threshold to a waveform set.

[0017] In a possible implementation, the transform model comprises an input layer, a transform layer, an accumulation node and an output layer;

[0018] The input layer, the transform layer and the output layer each have a plurality of nodes, the nodes of the input layer and the nodes of the output layer each correspond to a node of the transform layer, the accumulation node accumulates outputs of the plurality of nodes of the transform layer to obtain an accumulation result, and the output layer outputs a transform parameter of the transform layer;

[0019] A transfer function of the node of the transform layer adjusts a waveform state of a target waveform, wherein the target waveform is a waveform corresponding to the transfer function, and the waveform state comprises an extension width of a wave, a wave peak position and a wave peak height.

[0020] In a possible implementation, the nodes of the input layer comprise a time node and a plurality of frequency value nodes, the transform layer comprises a center frequency layer and an attenuation layer, and the plurality of nodes of the center frequency layer correspond to the plurality of nodes of the attenuation layer.

[0021] The plurality of nodes of the center frequency layer and the attenuation layer each receive an output of the plurality of frequency value nodes;

[0022] The plurality of nodes of the center frequency layer generate sinusoidal waves with phase offsets according to a plurality of offset parameters and the output of the plurality of frequency value nodes, and take values from the sinusoidal waves with phase offsets according to an output of the time node;

[0023] The plurality of nodes of the attenuation layer generate an attenuated wave with a protrusion according to the plurality of offset parameters and the outputs of the plurality of frequency value nodes, and take values from the attenuated wave according to the outputs of the time nodes.

[0024] In a possible implementation, the transfer function of the plurality of nodes of the center frequency layer is:

[0025]

[0026] The transfer function of the plurality of nodes of the attenuation layer is:

[0027]

[0028] In the formula, w(t) is the transfer function of the node of the center frequency layer, f(t) is the transfer function of the node of the attenuation layer, a n is a sine wave amplitude, ω0 is a fundamental frequency, n is a frequency multiplication parameter, t is a time point, and b is an offset parameter.

[0029] In a possible implementation, the inputting the plurality of waveforms and the plurality of waveform sets into a transform model respectively to obtain a plurality of time-frequency features includes:

[0030] For each waveform and each waveform set, the following steps are performed:

[0031] The amplitude of the fundamental wave and the amplitudes of a plurality of high-order harmonics in the waveform set are extracted to obtain a plurality of waveform set amplitudes;

[0032] The amplitudes of the waveforms are collected according to a plurality of time points to obtain a plurality of amplitude samples, wherein the time points correspond to the amplitude samples;

[0033] A plurality of iteration samples are made according to the plurality of time points and the plurality of waveform set amplitudes;

[0034] The plurality of iteration samples are input into the transform model respectively, and the difference between the cumulative sum output of the transform model and the amplitude samples is output, the plurality of parameters of the transform model are adjusted until the difference between the cumulative sum output of the transform model and the amplitude samples is less than a threshold value;

[0035] The waveform set amplitudes and the plurality of parameters of the transform model are taken as time-frequency features.

[0036] In a possible implementation, the time-frequency features include the amplitude of the wave and the attenuated waveform of the wave, and the monitoring curve is drawn according to the plurality of time-frequency features, including:

[0037] For the fundamental wave and the plurality of high-order harmonics, a three-dimensional coordinate system is established, wherein the X axis corresponds to the time, the Y axis corresponds to the amplitude, and the Z axis corresponds to the frequency of the wave.

[0038] For each of the fundamental wave and the plurality of high-order harmonics, in the three-dimensional coordinate system, a position of the Z axis is determined according to a frequency value;

[0039] According to the decay waveform of the fundamental wave and the decay waveforms of the plurality of high-order harmonics, curves are drawn in the plane formed by the X axis and the Y axis, as monitoring curves.

[0040] In a second aspect, an embodiment of the present application provides a distributed power supply access substation power supply quality monitoring device, comprising:

[0041] A waveform acquisition module is configured to acquire a plurality of waveforms, wherein the waveforms are acquired based on an output curve of a power supply in a substation;

[0042] A Fourier transform module is configured to perform Fourier transform on the plurality of waveforms respectively to acquire a plurality of waveform sets, wherein the waveform sets comprise a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms;

[0043] A time-frequency feature extraction module is configured to input the plurality of waveforms and the plurality of waveform sets into a transform model respectively to acquire a plurality of time-frequency features, wherein the time-frequency features represent time instants at which the fundamental wave and / or the plurality of high-order harmonics appear;

[0044] and,

[0045] A monitoring curve drawing module is configured to draw monitoring curves according to the plurality of time-frequency features, wherein the monitoring curves reflect substation power supply quality.

[0046] In a third aspect, an embodiment of the present application provides a terminal, comprising a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements steps of the method according to the first aspect or any possible implementation manner of the first aspect when executing the computer program.

[0047] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program implements steps of the method according to the first aspect or any possible implementation manner of the first aspect when executed by a processor.

[0048] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0049] The embodiment of the application discloses a distributed power supply access substation power supply quality monitoring method, which comprises the following steps: acquiring a plurality of waveforms, wherein the waveforms are acquired based on output curves of power supplies in a substation; performing Fourier transform on the plurality of waveforms respectively to acquire a plurality of waveform sets, wherein the waveform sets comprise a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms; inputting the plurality of waveforms and the plurality of waveform sets into a transformation model respectively to acquire a plurality of time-frequency features, wherein the time-frequency features represent time points at which the fundamental wave and / or the plurality of high-order harmonics appear; and drawing a monitoring curve according to the plurality of time-frequency features, wherein the monitoring curve reflects substation power supply quality. The embodiment of the application constructs a curve reflecting a substation waveform after decomposition, harmonic frequency, harmonic-to-fundamental wave ratio and specific time points through a transformation model, and has high transformation efficiency, good real-time performance and clearness. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0051] Figure 1 It is a flow chart of the distributed power supply access substation power supply quality monitoring method provided by the embodiment of the present application.

[0052] Figure 2 It is a substation principle diagram of the distributed power supply access substation power supply quality monitoring method provided by the embodiment of the present application.

[0053] Figure 3 It is a schematic diagram of different waveforms using Fourier transform provided by the embodiment of the present application.

[0054] Figure 4 It is a basic structure diagram of the transformation model provided by the embodiment of the present application.

[0055] Figure 5 It is a functional block diagram of the distributed power supply access substation power supply quality monitoring device provided by the embodiment of the present application.

[0056] Figure 6 It is a terminal functional block diagram provided by the embodiment of the present application. DETAILED DESCRIPTION

[0057] In the following description, specific details such as particular system structures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0058] To make the objectives, technical solutions, and advantages of the present invention clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

[0059] The embodiments of the present invention will be described in detail below. This example is implemented based on the technical solution of the present invention, and provides detailed implementation methods and specific operation processes. However, the protection scope of the present invention is not limited to the following embodiments.

[0060] Figure 1 A flowchart of a method for monitoring the power supply quality of a distributed power source access area provided in an embodiment of the present invention.

[0061] like Figure 1 As shown, a flowchart illustrating the implementation of the distributed power supply access area power quality monitoring method provided by an embodiment of the present invention is presented below:

[0062] In step 101, multiple waveforms are acquired, wherein the waveforms are acquired based on the output curve of the power supply in the transformer area.

[0063] For example, such as Figure 2 As shown, Figure 2 The diagram shows a schematic of a distribution area connected to a distributed power source according to an embodiment of the present invention. In the diagram, the main power source 201 supplies power to the electrical load 203 of the distribution area. Multiple distributed power sources 202 are also distributed in the distribution area, and the distributed power sources 202 and the main power source 201 supply power to the electrical load 203 of the distribution area.

[0064] The purpose of this invention is to provide a method that can effectively and promptly address power quality issues in a distribution area. Therefore, in terms of data source acquisition, the waveforms of the output terminals of each power source in the distribution area are selected. The waveforms can be voltage waveforms and / or current waveforms of the power source output. For analyzing harmonics generated by distributed power grid connection, voltage waveforms should be used. If analyzing the power factor drop caused by the load and harmonic pollution generated by electricity consumption, current waveforms are obviously more appropriate. However, ultimately, the steps for waveform analysis are largely the same, all determining the power supply quality through waveform analysis.

[0065] In step 202, the plurality of waveforms are respectively subjected to Fourier transform to obtain a plurality of waveform sets, wherein the waveform set comprises a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms.

[0066] In some embodiments, step 202 comprises:

[0067] For each of the plurality of waveforms, the following steps are performed:

[0068] The waveform is subjected to Fourier transform to obtain a fundamental wave and a plurality of high-order harmonics;

[0069] The ratio of the amplitude of each of the plurality of high-order harmonics to the amplitude of the fundamental wave is calculated;

[0070] The fundamental wave and the high-order harmonic whose ratio is greater than a threshold value are added to the waveform set.

[0071] Exemplarily, a wave analysis method is a wavelet transform method, because the conventional wave transform method, Fourier transform method, has some shortcomings, mainly due to the fact that Fourier transform is mainly for periodic waveforms, and the periodic characteristics of power supply waveforms have various shortcomings, such as amplitude and frequency fluctuation during power supply and power consumption.

[0072] Figure 3 A schematic diagram of different waveforms using Fourier transform is shown.

[0073] As can be seen from the diagram, the left side is a time domain signal, and the right side is a frequency domain signal obtained by Fourier transform. From top to bottom, they are a signal with constant frequency, a signal with step-by-step accelerated frequency, and a signal with step-by-step decelerated frequency.

[0074] As can be seen from the frequency domain diagrams of the three different signals, the frequency signals contained in the three are the same, and each can be decomposed into four frequency waves. The uppermost diagram lacks some insignificant peak waves compared to the lower two diagrams, but the two lower diagrams are very similar.

[0075] The reason for the above problem is that Fourier transform only indicates the frequency and amplitude of each waveform after transformation, but lacks an indication of the time when the waveform appears.

[0076] Windowed Fourier transform and wavelet transform can solve the above problem. Wavelet transform has an inherent advantage as an improvement of windowed Fourier transform, but the disadvantage of wavelet transform is how to determine the parameters of the wavelet.

[0077] The embodiments of the present application provide a wavelet transform method based on the wave frequency obtained by Fourier transform, and then the parameters of the wavelet transform are solved by changing the model.

[0078] The wavelet transform adopts the last selected frequency waveform of the Fourier transform to accumulate iteration. When the Fourier transform selects the frequency, the ratio of the high-order harmonic to the fundamental wave is adopted. If the ratio is small, it indicates that the harmonic content is small, and these harmonics are discarded and no longer participate in the wavelet transform.

[0079] In step 203, the plurality of waveforms and the plurality of waveform sets are respectively input into a transform model to obtain a plurality of time-frequency features, wherein the time-frequency features represent the time when the fundamental wave and / or the plurality of high-order harmonics appear.

[0080] In some embodiments, the transform model includes an input layer, a transform layer, an accumulation node, and an output layer.

[0081] The input layer, the transform layer, and the output layer each have a plurality of nodes. The nodes of the input layer and the nodes of the output layer each correspond to the nodes of the transform layer. The accumulation node accumulates the outputs of the plurality of nodes of the transform layer to obtain an accumulation result. The output layer outputs the transform parameters of the transform layer.

[0082] The transfer function of the node of the transform layer adjusts the waveform state of the target waveform, wherein the target waveform is the waveform corresponding to the transfer function, and the waveform state includes the extension width of the wave, the wave peak position, and the wave peak height.

[0083] In some embodiments, the nodes of the input layer include a time node and a plurality of frequency value nodes. The transform layer includes a center frequency layer and an attenuation layer. The plurality of nodes of the center frequency layer correspond to the plurality of nodes of the attenuation layer.

[0084] The plurality of nodes of the center frequency layer and the attenuation layer each receive the output of the plurality of frequency value nodes.

[0085] The plurality of nodes of the center frequency layer generate sinusoidal waves with phase shifts according to the plurality of offset parameters and the output of the plurality of frequency value nodes, and take values from the sinusoidal waves with phase shifts according to the output of the time node.

[0086] The plurality of nodes of the attenuation layer generate attenuation waves with protrusions according to the plurality of offset parameters and the output of the plurality of frequency value nodes, and take values from the attenuation waves according to the output of the time node.

[0087] In some embodiments, the transfer function of the plurality of nodes of the center frequency layer is:

[0088]

[0089] The transfer function of the plurality of nodes of the attenuation layer is:

[0090]

[0091] wherein w(t) is a transfer function of a node of a center frequency layer, f(t) is a transfer function of a node of a decay layer, a n is a sine wave amplitude, ω0 is a fundamental frequency, n is a frequency multiplication parameter, t is a time point, and b is a shift parameter.

[0092] In some embodiments, step 203 comprises:

[0093] For each waveform and each waveform set, the following steps are performed:

[0094] The fundamental amplitude and the amplitudes of a plurality of higher harmonics in the waveform set are extracted to obtain a plurality of waveform set amplitudes;

[0095] The amplitudes of the waveform are collected at a plurality of time points to obtain a plurality of amplitude samples, wherein the time points correspond to the amplitude samples;

[0096] A plurality of iteration samples are generated according to the plurality of time points and the plurality of waveform set amplitudes;

[0097] The plurality of iteration samples are respectively input into the transformation model, and the difference between the cumulative sum output of the transformation model and the amplitude samples is output, and the plurality of parameters of the transformation model are adjusted until the difference between the cumulative sum output of the transformation model and the amplitude samples is less than a threshold value;

[0098] The plurality of parameters of the transformation model and the waveform set amplitudes are used as time-frequency features.

[0099] As shown in Figure 4 , a basic structure diagram of a transformation model provided by an embodiment of the present application is shown. Figure 4

[0100] The input layer has a plurality of input nodes, and the t input node is used to input the time, and the remaining nodes are used to input the frequencies of the harmonics used to synthesize the target curve.

[0101] The transformation layer has a two-layer structure, the first layer is a center frequency layer, and the second layer is a decay layer. The center frequency layer and the decay layer both accept the input of the input layer. Except for the t input node, the other nodes of the input layer form a one-to-one correspondence with the input layer. The nodes of the center frequency layer and the nodes of the decay layer form a multiplication relationship. For any one node of the center frequency layer, its transfer function is:

[0102]

[0103] For any one node of the decay layer, its transfer function is: ​

[0104]

[0105] In the formula, w(t) is the transfer function of the node of the center frequency layer, f(t) is the transfer function of the node of the attenuation layer, a n is the sine wave amplitude, ω0 is the fundamental frequency, n is the frequency multiplication parameter, t is the time point, and b is the offset parameter.

[0106] Since the nodes of the attenuation layer and the center frequency layer form a multiplication relationship, for the node output of the attenuation layer, the final expression and the relationship of the input node form the following formula:

[0107]

[0108] For the accumulation node, the accumulation node is to accumulate a plurality of nodes of the attenuation layer, and output an accumulation sum. The difference between the amplitude of the waveform curve (the output curve of the power supply in the station area) at the time indicated by t and the accumulation sum is the basis for indicating the adjustment of the parameters a n , b of the center frequency layer and the attenuation layer.

[0109] For the output node, after the above adjustment is completed, the output parameters sine wave amplitude a n and offset parameter b are output.

[0110] For the sample establishment for adjusting the model, the embodiment of the present application uses the frequency obtained in the foregoing steps and different time points as input node samples, and the sampling values of the waveforms (the output curve of the power supply in the station area) corresponding to the different time points as comparison values of the accumulation sum output. The difference between the foregoing output accumulation sum and the value of the waveform at the corresponding time is used to correct the parameters of the transformation layer.

[0111] This iteration process is similar to the guessing game of apples and pears. The game question is that apples are 5 yuan per jin, pears are 3 yuan per jin, and a total of 11 yuan is spent. If 2 jins of apples and 1 jin of pears are guessed, the total price is 13 yuan, which is 2 yuan different from the actual spending. Therefore, the number of apples purchased is reduced, and the number of pears purchased is increased. It is guessed that 1 jin of apples and 1 jin of pears are purchased, and the total price is 8 yuan, which is 3 yuan less than the actual spending. Again, it is guessed that 1 jin of apples and 2 jins of pears are purchased, and the total price is 13 yuan, which is not different from the actual spending, and the iteration ends. In the above process, the specific amount of increase or decrease is determined according to the deviation, and the step size (1 jin in the example) is increased or decreased in time according to the weight of the apples and pears, and the iteration process is completed.

[0112] In step 104, a monitoring curve is drawn according to the plurality of time-frequency features, wherein the monitoring curve reflects the power supply quality of the station area.

[0113] In some embodiments, the time-frequency feature comprises: an amplitude of a wave and an attenuation waveform of the wave, and step 104 comprises:

[0114] For the fundamental wave and the plurality of high-order harmonics, a three-dimensional coordinate system is established, wherein the X-axis corresponds to the time, the Y-axis corresponds to the amplitude, and the Z-axis corresponds to the frequency of the wave.

[0115] For each wave of the fundamental wave and the plurality of high-order harmonics, in the three-dimensional coordinate system, the position of the Z-axis is determined according to the frequency value.

[0116] According to the attenuation waveform of the fundamental wave and the attenuation waveforms of the plurality of high-order harmonics, curves are drawn in the plane formed by the X-axis and the Y-axis respectively as monitoring curves.

[0117] Exemplarily, on the premise of the wave amplitude and the aforementioned attenuation waveform, a three-dimensional graph reflecting the amplitudes, times and frequencies of the waveforms of various frequencies can be constructed, and through the three-dimensional graph, the amplitudes of the waveforms of different frequencies at the same time can be seen, and the frequencies of the harmonics contained in the time and the proportions of the harmonics and the fundamental wave can be seen at a glance.

[0118] The embodiment of the power supply quality monitoring method for the distributed power supply access to the transformer area provided by the present application firstly acquires a plurality of waveforms, wherein the waveforms are acquired based on the output curve of the power supply in the transformer area, then performs Fourier transform on the plurality of waveforms respectively to acquire a plurality of waveform sets, wherein the waveform set comprises a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms; then inputs the plurality of waveforms and the plurality of waveform sets into a transformation model respectively to acquire a plurality of time-frequency features, wherein the time-frequency feature represents the time when the fundamental wave and / or the plurality of high-order harmonics appear; finally, draws a monitoring curve according to the plurality of time-frequency features, wherein the monitoring curve reflects the power supply quality of the transformer area. Through the transformation model, a curve reflecting the harmonic frequency, the proportion of the harmonics and the fundamental wave and the specific time after the waveform decomposition of the transformer area is constructed, the transformation efficiency is high, the real-time performance is good, and everything can be seen at a glance.

[0119] It should be understood that the size of the serial number of each step in the above-mentioned embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0120] The following is the device embodiment of the present application. For details not described in detail, please refer to the corresponding method embodiments described above.

[0121] Figure 5 is the functional block diagram of the power supply quality monitoring device for the distributed power supply access to the transformer area provided by the embodiment of the present application, which is referred to Figure 5The distributed power supply access substation power supply quality monitoring device 5 comprises a waveform acquisition module 501, a Fourier transform module 502, a time-frequency feature extraction module 503 and a monitoring curve drawing module 504.

[0122] The waveform acquisition module 501 is configured to acquire a plurality of waveforms, wherein the waveforms are acquired based on output curves of power supplies in a substation.

[0123] The Fourier transform module 502 is configured to perform Fourier transform on the plurality of waveforms respectively to acquire a plurality of waveform sets, wherein the waveform set comprises a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms.

[0124] The time-frequency feature extraction module 503 is configured to input the plurality of waveforms and the plurality of waveform sets into a transform model respectively to acquire a plurality of time-frequency features, wherein the time-frequency feature represents a time when the fundamental wave and / or the plurality of high-order harmonics appear.

[0125] The monitoring curve drawing module 504 is configured to draw a monitoring curve according to the plurality of time-frequency features, wherein the monitoring curve reflects the substation power supply quality.

[0126] Figure 6 is a functional block diagram of a terminal provided by an embodiment of the present application. As shown in Figure 6 the terminal 6 of the embodiment comprises a processor 600 and a memory 601, and the memory 601 stores a computer program 602 which can run on the processor 600. The processor 600 implements the steps in the above various distributed power supply access substation power supply quality monitoring methods and embodiments when executing the computer program 602, for example, the steps 101 to 104 shown in Figure 1 .

[0127] For example, the computer program 602 can be divided into one or more modules / units, which are stored in the memory 601 and executed by the processor 600 to complete the present application.

[0128] The terminal 6 can be a desktop computer, a notebook computer, a palm computer and a cloud server, etc. The terminal 6 can include, but is not limited to, the processor 600 and the memory 601. Those skilled in the art can understand that Figure 6 the terminal 6 is only an example and does not constitute a limitation on the terminal 6, and can include more or fewer components than those shown, or combine certain components, or different components, for example, the terminal can also include an input / output device, a network access device, a bus, etc.

[0129] The processor 600 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0130] The memory 601 can be an internal storage unit of the terminal 6, for example, a hard disk or a memory of the terminal 6. The memory 601 can also be an external storage device of the terminal 6, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD), a flash card, etc. equipped on the terminal 6. Further, the memory 601 can also include both the internal storage unit and the external storage device of the terminal 6. The memory 601 is used to store the computer program and other programs and data required by the terminal. The memory 601 can also be used to temporarily store data that has been output or will be output.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit, and the integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0132] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can refer to the relevant description of other embodiments.

[0133] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0134] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / terminal and method can be implemented in other ways. For example, the apparatus / terminal embodiments described above are merely schematic. The division of the modules or units is merely a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between the units can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or in other forms.

[0135] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0136] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0137] The integrated module / unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method and device embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer-readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0138] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A distributed power supply access substation power supply quality monitoring method, characterized in that, The method comprises: acquiring a plurality of waveforms, wherein the waveforms are based on an output curve of a power supply in a transformer area; performing Fourier transform on the plurality of waveforms respectively to obtain a plurality of waveform sets, wherein the waveform set comprises a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms; inputting the plurality of waveforms and the plurality of waveform sets into a transform model respectively to obtain a plurality of time-frequency features, comprising: for each waveform and each waveform set, performing the following steps: extracting the amplitude of the fundamental wave and the amplitudes of the plurality of high-order harmonics in the waveform set to obtain a plurality of waveform set amplitudes; collecting the amplitudes of the waveforms according to a plurality of time points to obtain a plurality of amplitude samples, wherein the time points correspond to the amplitude samples; making a plurality of iteration samples according to the plurality of time points and the plurality of waveform set amplitudes; inputting the plurality of iteration samples into the transform model respectively, adjusting a plurality of parameters of the transform model until the difference between the cumulative sum output of the transform model and the amplitude samples is less than a threshold value, wherein the transform model comprises an input layer, a transform layer, a cumulative node, and an output layer; taking the waveform set amplitudes and the plurality of parameters of the transform model as time-frequency features, wherein the time-frequency features represent the time when the fundamental wave and / or the plurality of high-order harmonics appear; drawing a monitoring curve according to the plurality of time-frequency features, wherein the monitoring curve reflects the power supply quality of the transformer area; wherein the nodes of the input layer comprise time nodes and a plurality of frequency value nodes; the transform layer comprises a center frequency layer and an attenuation layer, and the plurality of nodes of the center frequency layer correspond to the plurality of nodes of the attenuation layer; the plurality of nodes of the center frequency layer and the attenuation layer respectively receive the output of the plurality of frequency value nodes; the plurality of nodes of the center frequency layer generate sinusoidal waves with phase shifts according to a plurality of offset parameters and the output of the plurality of frequency value nodes, and take values from the sinusoidal waves with phase shifts according to the output of the time nodes; the plurality of nodes of the attenuation layer generate attenuation waves with protrusions according to the plurality of offset parameters and the output of the plurality of frequency value nodes, and take values from the attenuation waves according to the output of the time nodes.

2. The method for monitoring power quality of a distribution network with distributed power sources as claimed in claim 1, wherein, The Fourier transform on the plurality of waveforms to obtain a plurality of waveform sets comprises: for each waveform in the plurality of waveforms, performing the following steps: performing Fourier transform on the waveform to obtain a fundamental wave and a plurality of high-order harmonics; calculating the ratio of the amplitude of each high-order harmonic to the amplitude of the fundamental wave respectively; adding the fundamental wave and the high-order harmonics with a ratio greater than a threshold value to the waveform set.

3. The method for monitoring power quality of a distribution network with distributed power sources as claimed in claim 1, wherein, The input layer, the transform layer, and the output layer each have a plurality of nodes, the nodes of the input layer and the nodes of the output layer correspond to the nodes of the transform layer respectively, the cumulative node accumulates the outputs of the plurality of nodes of the transform layer to obtain a cumulative result, and the output layer outputs the transform parameters of the transform layer. The transfer function of the node of the transform layer adjusts a waveform state of a target waveform by a transform parameter, wherein the target waveform is a waveform corresponding to the transfer function, and the waveform state includes an extension width of a wave, a wave peak position, and a wave peak height.

4. The method for monitoring power quality of a distribution network with distributed power sources as claimed in claim 1, wherein, The transfer functions of the plurality of nodes of the center frequency layer are: The transfer functions of the plurality of nodes of the attenuation layer are: wherein is a transfer function of a node of a central frequency layer, is a transfer function of a node of a decay layer, is a sine wave amplitude, is a fundamental frequency, is a frequency multiplication parameter, is a time point, is an offset parameter.

5. The method of claim 1-4, wherein, The time-frequency features include an amplitude of a wave and an attenuation waveform of the wave, and the monitoring curve is drawn according to the plurality of time-frequency features. For the fundamental wave and the plurality of high-order harmonics, a three-dimensional coordinate system is established, wherein an X-axis corresponds to a time, a Y-axis corresponds to an amplitude, and a Z-axis corresponds to a frequency of a wave. For each of the fundamental wave and the plurality of high-order harmonics, a position of the Z-axis is determined in the three-dimensional coordinate system according to a frequency value. According to the attenuation waveform of the fundamental wave and the attenuation waveforms of the plurality of high-order harmonics, curves are drawn in a plane formed by the X-axis and the Y-axis as monitoring curves.

6. A distributed power supply access substation power supply quality monitoring device, characterized in that, The distributed power supply access substation power supply quality monitoring device for implementing the method according to any one of claims 1-5 comprises: a waveform acquisition module configured to acquire a plurality of waveforms, wherein the waveforms are obtained based on an output curve of a power supply in a substation; a Fourier transform module configured to perform Fourier transform on the plurality of waveforms respectively to obtain a plurality of waveform sets, wherein the waveform sets include a fundamental wave and a plurality of high-order harmonics, and the plurality of waveform sets correspond to the plurality of waveforms; a time-frequency feature extraction module configured to input the plurality of waveforms and the plurality of waveform sets into a transform model respectively to obtain a plurality of time-frequency features, wherein the time-frequency features represent a time at which the fundamental wave and / or the plurality of high-order harmonics appear; a monitoring curve drawing module configured to draw a monitoring curve according to the plurality of time-frequency features, wherein the monitoring curve reflects a power supply quality of the substation. The processor executes the computer program to implement the steps of the method according to any one of claims 1-5.

7. A terminal comprising a memory and a processor, said memory having stored therein a computer program executable on said processor, characterized in that, The computer program is executed by the processor to implement the steps of the method according to any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: ​

Images