Harmonic characteristic determination method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a harmonic characteristic determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the historical operation data of to-be-tested equipment when a pre-established initial model does not meet a preset condition; performing data acquisition on the to-be-detected equipment according to a pre-established acquisition system and the historical operation data to obtain detection data of the to-be-detected equipment; determining harmonic characteristics based on the detection data and a predetermined windowing function; determining a training data set of the initial model according to the harmonic characteristics, and optimizing the initial model based on the training data set to obtain a target model; wherein the target model is used for identifying the harmonic source of the transformer substation according to the harmonic characteristics. According to the method, the accuracy and representativeness of harmonic feature extraction can be improved, the obtained harmonic features can comprehensively describe the influence of harmonic waves on equipment, and the efficiency and accuracy of subsequent model training are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of substation harmonic source analysis, and in particular to a harmonic feature determination method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of power electronics technology and new energy equipment, harmonic pollution will affect many devices in the power system and bring harm to the equipment. For example, it will shorten the service life of the equipment, increase the power loss of the equipment, affect the quality of electric energy, and in serious cases, cause a series of power accidents such as the collapse of the power system. As the problem of harmonic pollution of the power grid becomes increasingly serious, it puts a higher test on the ability of the power system to operate safely and reliably. In order to reduce the harmonic pollution phenomenon of the power system and improve the quality of electric energy, how to accurately and quickly identify the harmonic source is the key to solving the harmonic problem.

[0003] Nowadays, most neural network models are used to learn the harmonic characteristics of the power grid to identify the harmonic source. This method requires a large amount of training data, extracts training features based on the training data, and uses the training features to train and optimize the neural network model. The current feature determination method for training neural network models is mostly to organize the historical data of the equipment to be tested to obtain training features. For example, high-order statistics such as cumulants and skewness are used to describe the statistical characteristics of the signal. This method has a large amount of calculation and high requirements for data, resulting in the extracted features being inaccurate, which affects the subsequent model training process and cannot guarantee the accuracy of the model and the efficiency of processing features. Summary of the invention

[0004] The embodiments of the present invention provide a harmonic feature determination method, device, electronic device and storage medium, which can capture subtle harmonic changes in the signal of the device under test and improve the accuracy and representativeness of feature extraction. The obtained harmonic features can comprehensively describe the impact of harmonics on the device and improve the efficiency and accuracy of subsequent model training.

[0005] In a first aspect, an embodiment of the present invention provides a method for determining harmonic characteristics, comprising:

[0006] When the pre-established initial model does not meet the preset conditions, the historical operation data of the device under test is obtained;

[0007] Collecting data on the device under test according to a pre-established collection system and the historical operation data to obtain detection data of the device under test;

[0008] Determining harmonic characteristics based on the detection data and a predetermined windowing function;

[0009] A training data set of the initial model is determined according to the harmonic characteristics, and the initial model is optimized based on the training data set to obtain a target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics.

[0010] In a second aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements a harmonic characteristic determination method as described in any one of the embodiments of the present invention.

[0011] In a third aspect, an embodiment of the present invention provides a harmonic feature determination device, the device comprising:

[0012] A data acquisition module, used to acquire historical operation data of the device under test when the pre-established initial model does not meet the preset conditions;

[0013] A data detection module, used to collect data from the device under test according to a pre-established collection system and the historical operation data, to obtain detection data of the device under test;

[0014] A feature determination module, used for determining harmonic features based on the detection data and a predetermined windowing function;

[0015] A model training module is used to determine the training data set of the initial model according to the harmonic characteristics, and optimize the initial model based on the training data set to obtain a target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics.

[0016] In a fourth aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a harmonic characteristic determination method as described in any one of the embodiments of the present invention is implemented.

[0017] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a harmonic characteristic determination method as described in any one of the embodiments of the present invention.

[0018] In an embodiment of the present invention, when the pre-established initial model does not meet the preset conditions, the historical operation data of the device to be tested is obtained; data is collected from the device to be tested according to the pre-established acquisition system and the historical operation data to obtain the detection data of the device to be tested; harmonic characteristics are determined based on the detection data and a predetermined windowing function; a training data set of the pre-established initial model is determined according to the harmonic characteristics, and the initial model is optimized based on the training data set to obtain a target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics. That is, in an embodiment of the present invention, the actual operation conditions can be effectively simulated according to the acquisition system, so as to obtain accurate detection data. The subtle harmonic changes in the signal of the device to be tested are captured by the windowing function and the detection data, and the accuracy and representativeness of the harmonic feature extraction are improved. The obtained harmonic features can comprehensively describe the impact of harmonics on the equipment, and improve the efficiency and accuracy of subsequent model training. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A first flow chart of a harmonic characteristic determination method provided by an embodiment of the present invention;

[0021] Figure 2 A second flow chart of a harmonic characteristic determination method provided by an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of a collection system provided by an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of the structure of a harmonic characteristic determination device provided by an embodiment of the present invention;

[0024] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0026] Figure 1The first flow chart of a harmonic feature determination method provided in an embodiment of the present invention, the method of the embodiment of the present invention can capture subtle harmonic changes in the signal of the device under test, improve the accuracy and representativeness of feature extraction, and the obtained harmonic features can comprehensively describe the impact of harmonics on the device, and improve the efficiency and accuracy of subsequent model training. The method can be executed by a harmonic feature determination device provided in an embodiment of the present invention, and the device can be implemented in software and / or hardware. The following embodiments will be described by taking the device integrated in an electronic device as an example, and the electronic device can be a computer device or a server.

[0027] refer to Figure 1 , the method may specifically include the following steps:

[0028] Step 101: When the pre-established initial model does not meet the preset conditions, the historical operation data of the device under test is obtained.

[0029] Among them, the initial model is a pre-established model that has not been trained. The initial model in this solution can be a recursive neural network model. The preset conditions include that the value of the predetermined loss function reaches convergence or the number of iterations reaches a preset number of times. The device under test is a device in a substation, such as a transformer, a mutual inductor, a switchgear, and a lightning protection device. The historical operation data includes the working parameters of the device under test under normal operating conditions in the historical period. The historical operation data includes electrical parameters (such as voltage, current, power, frequency, etc.), thermal parameters (such as operating temperature, ambient temperature, etc.), mechanical parameters (such as operating time, degree of wear, etc.), environmental parameters (conditions of the environment in which the device under test is located, such as temperature, humidity, altitude, etc.) and various data recorded by the device under test during operation (such as load changes, number of operations, and fault records, etc.).

[0030] Specifically, when the pre-established initial model does not meet the preset conditions, it indicates that data collection is required for the device under test, so that experiments can be conducted on the device under test based on historical operation data to obtain harmonic features for training the initial model. Furthermore, the server can obtain the historical operation data of the device under test through a preset data interface, or directly receive the historical operation data of the device under test uploaded by the user.

[0031] Step 102: Data collection is performed on the device to be tested according to a pre-established collection system and historical operation data to obtain test data of the device to be tested.

[0032] The acquisition system includes a power supply, a first protection resistor, a second protection resistor, a recorder and an acquisition module; wherein the first protection resistor is connected between the power supply and the recorder, the second protection resistor is connected between the power supply and the acquisition module, and the device under test is connected between the second protection resistor and the acquisition module. The power supply consists of a voltage regulator and a test transformer, and can output 0 to 50kV AC high voltage. This power supply can simulate the high voltage environment in the power system to test the performance of the equipment under high voltage. A 1MΩ protection resistor is connected to the high voltage output end, and the function of the protection resistor is to limit the overcurrent during short circuit and protect the acquisition system from damage by excessive current. The acquisition module is used to measure and record electrical parameters in the experiment, such as voltage, current, etc. The acquisition system is used to simulate and test the performance of the device under test under high voltage environment. The detection data is the data recorded by the acquisition system during the experiment on the device under test.

[0033] Specifically, when a high-voltage test is required for the device under test, the test voltage and other related parameters, such as frequency, test voltage, and sampling time, are determined according to the actual operating conditions of the acquisition system and the historical operating data of the device under test. The device under test is connected to the output end of the high-voltage power supply, and the sampling frequency and sampling time of the acquisition module are set. The high-voltage power supply is started according to the set experimental parameters, and it is gradually adjusted to the experimental voltage. From the beginning of the experiment, the data collected by the acquisition module, such as the voltage and current of the device under test, are monitored in real time to obtain the detection data of the device under test.

[0034] Step 103: Determine harmonic features based on the detection data and a predetermined windowing function.

[0035] Among them, the windowing function is a window function based on the Blackman window and used for signal processing. When processing power system harmonic analysis, choosing a suitable windowing function is crucial to improving detection accuracy and resolving signals with similar frequencies. Harmonic features are features used to train the initial model, and harmonic features include the harmonic content rate in the signal wave.

[0036] Specifically, in the harmonic analysis of the power system, signals with similar frequencies but different amplitudes are often encountered. The use of windowing functions can help distinguish these signals, thereby accurately identifying each harmonic component. After obtaining the detection data of the device under test, the collected voltage or current signal is multiplied by a predetermined windowing function, and then the windowed signal is subjected to a fast Fourier transform to obtain a spectrum distribution. Based on the spectrum distribution results, the frequency and amplitude of each harmonic are identified and quantified. Furthermore, the harmonic characteristics are determined based on the frequency and amplitude of each harmonic.

[0037] Step 104: determine a training data set for the initial model according to the harmonic characteristics, and optimize the initial model based on the training data set to obtain a target model.

[0038] Among them, the target model is used to identify the harmonic source of the substation according to the harmonic characteristics. The initial model is a pre-established model that has not been trained. The initial model in this scheme can be a recursive neural network model. Specifically, after obtaining the harmonic features, the harmonic features are sorted and formed into a training data set for training the initial model, and the model parameters of the initial model are continuously adjusted based on the training data set to obtain the target model. In this scheme, optionally, the initial model is optimized based on the training data set to obtain the target model, including: selecting a harmonic feature from the training data set as the current feature, inputting the current feature into the initial model, and obtaining the current recognition result output by the initial model; adjusting the model parameters of the initial model based on the current recognition result and a pre-set loss function; selecting the next harmonic feature from the training data set as the current feature, and repeating the above operations until the initial model meets the preset conditions to obtain the target model.

[0039] Among them, the preset conditions include that the value of the predetermined loss function reaches convergence or the number of iterations reaches a preset number. The target model is a trained model that can accurately identify the harmonic source. When the initial model does not meet the preset conditions, a harmonic feature is selected from the training data set as the current feature, and the current feature is input into the initial model. After the initial model receives the current feature, it processes the current feature and outputs the current recognition result corresponding to the current feature. The current recognition result and the target recognition result of the current feature directly determined according to the detection data are input into the loss function to obtain the loss function value. After obtaining the loss function value, it is determined whether the loss function value meets the preset conditions. If the preset conditions are met, the initial model is determined to be the target model. If the loss function value does not meet the preset conditions, the next harmonic feature is selected from the training data set as the current feature, and the step of inputting the current feature into the initial model is repeated to obtain the current recognition result output by the initial model, and the model parameters of the initial model are adjusted until the initial model meets the preset conditions to obtain the target model.

[0040] Exemplarily, after obtaining the detection data, a harmonic classification and recognition model (initial model) is established as follows:

[0041] s t =Ux t +Wh t-1

[0042] h t =f(Ux t +Wh t-1 )

[0043] o t =g(Vh t )

[0044] Among them, the initial model includes input layer, hidden layer and output layer. t is the output vector after considering the combination of the input layer and the hidden layer, x t is an n-dimensional vector (harmonic feature), and the input of the recurrent network is a whole sequence, that is, x = [x1,...,x t-1 ,x t ,x t+1 ,...x T ];h t represents the hidden state at time t; o t represents the output at time t; U represents the weight from the input layer to the hidden layer; W represents the weight from the hidden layer to the hidden layer; V represents the weight from the hidden layer to the output layer. g and f are pre-set functions. In this scheme, the 3rd, 5th, 7th, 9th, 11th, 13th and 15th harmonic content rates and total harmonic distortion can be selected as feature vectors, i.e., harmonic features. Harmonic feature extraction and analysis are performed on each set of data obtained from the test to obtain the corresponding feature vector sample data. By training the samples, the corresponding harmonic source identification model is obtained.

[0045] In the above steps, by selecting the fixed subharmonic content rate and the total harmonic distortion as the feature vector, the harmonic components in the signal can be captured more comprehensively, thereby improving the accuracy of harmonic detection and obtaining a more accurate and efficient target model.

[0046] The technical solution of this embodiment, when the pre-established initial model does not meet the preset conditions, obtains the historical operation data of the device to be tested; performs data acquisition on the device to be tested according to the pre-established acquisition system and the historical operation data to obtain the detection data of the device to be tested; determines the harmonic characteristics based on the detection data and a predetermined windowing function; determines the training data set of the pre-established initial model according to the harmonic characteristics, and optimizes the initial model based on the training data set to obtain the target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics. The technical solution of this embodiment can effectively simulate the actual operation conditions according to the acquisition system, so as to obtain accurate detection data. The subtle harmonic changes in the signal of the device to be tested are captured by the windowing function and the detection data, and the accuracy and representativeness of the harmonic feature extraction are improved. The obtained harmonic features can comprehensively describe the impact of harmonics on the equipment, and improve the efficiency and accuracy of subsequent model training.

[0047] Figure 2 The second flow chart of a method for determining harmonic characteristics provided by an embodiment of the present invention is a refinement of the above embodiment. The specific method can be as follows Figure 2 As shown, the method may include the following steps:

[0048] Step 201: When the pre-established initial model does not meet the preset conditions, the historical operation data of the device under test is obtained.

[0049] Step 202: Data collection is performed on the device to be tested according to a pre-established collection system and historical operation data to obtain test data of the device to be tested.

[0050] The detection data includes the current and voltage of the device under test. Figure 3 Schematic diagram of a collection system provided by an embodiment of the present invention. Figure 3 As shown, the acquisition system is connected to the server, and the acquisition system includes a power supply, a first protection resistor, a second protection resistor, a recorder and an acquisition module; wherein the first protection resistor is connected between the power supply and the recorder, the second protection resistor is connected between the power supply and the acquisition module, and the device to be tested is connected between the second protection resistor and the acquisition module. In this solution, optionally, data acquisition is performed on the device to be tested according to a pre-established acquisition system and historical operation data to obtain detection data of the device to be tested, including: determining experimental parameters of the device to be tested based on historical operation data; at the beginning of the experiment, adjusting the power supply voltage to the experimental voltage, and at the same time, performing data acquisition on the device to be tested according to the sampling frequency and sampling time to obtain detection data of the device to be tested.

[0051] Among them, the experimental parameters include the start time of the experiment, the experimental voltage, the sampling frequency and the sampling time. The experimental voltage is the highest voltage that needs to be adjusted during the experiment. The experimental voltage and other related parameters, such as frequency, experimental voltage and sampling time, can be determined according to the actual operating conditions of the acquisition system and the historical operating data of the device under test. After determining the start time of the experiment, at the start time of the experiment, the power supply voltage is adjusted to the experimental voltage at a certain speed. During the process of voltage rise, data is collected from the device under test according to the sampling frequency and sampling time. During the process of voltage rise, the acquisition module can record the detection data of the device under test in real time. The power supply of the acquisition system in this scheme can output 0-50kV AC high voltage, and the protection resistance is 1MΩ to prevent the impact of short-circuit overcurrent on the test system. The sampling frequency can be 20kHz and the sampling time is 2min.

[0052] In the above steps, the experimental voltage can be adjusted according to the historical operation data, so that the experiment is closer to the actual situation and the accuracy and reliability of the experiment are improved. The high-voltage output terminal is connected to the device under test through a protective resistor to prevent the impact of short-circuit overcurrent on the acquisition system, effectively protect the acquisition system, and avoid damage to the device under test due to short-circuit overcurrent.

[0053] Step 203: Determine the parameters of the windowing function based on the experimental parameters of the device to be tested, perform Blackman window calculation on the detection data based on the parameters of the windowing function and the windowing function, and obtain the windowing function value corresponding to the detection data.

[0054] Among them, the parameters of the windowing function include the total length and the effective length. The windowing function is a window function based on the Blackman window and used for signal processing. Specifically, the Blackman window has the largest attenuation of the first side lobe and the widest main lobe bandwidth, so the amplitude recognition accuracy is very high, and it can effectively detect signals with similar frequencies but different amplitudes. In this scheme, the fast Fourier transform of the windowing function is selected to carry out harmonic feature extraction, and the expression is as follows:

[0055]

[0056] Wherein, B(n) is the window function value, n=1, 2, ..., N-1, N is the total length of the window function, and M is the effective length of the window function.

[0057] Step 204: Determine a reference voltage and a reference current of the device under test based on the historical operation data; perform waveform analysis on the detection data to determine the harmonic voltage and harmonic current of the device under test.

[0058] Specifically, after obtaining the historical operation data of the device under test, statistical analysis is performed on the historical voltage and current data of the device under test, including calculation of the average value, maximum value, minimum value, and standard deviation, etc. Based on the above calculation results, the voltage and current levels of the device under normal operating conditions and the performance under extreme conditions are identified. Furthermore, the reference voltage and reference current of the device under test are determined by combining the rated voltage and rated current of the device under test with the typical values ​​in actual operation.

[0059] Furthermore, after obtaining the test data of the device under test, the test data can be analyzed by a digital bandpass filter. Use a digital bandpass filter to select a specific frequency band, so as to analyze the signal within a certain frequency range separately, such as a single harmonic frequency, to obtain harmonic voltage and harmonic current. Alternatively, a power analyzer can be used to directly measure harmonic voltage and harmonic current. Alternatively, professional virtual instruments and software tools can be used to build a customized harmonic analysis function to obtain harmonic voltage and harmonic current.

[0060] Step 205: Determine the voltage distortion rate and current distortion rate of the device under test according to the reference voltage, the reference current, the harmonic voltage and the harmonic current.

[0061] Among them, voltage distortion rate and current distortion rate are important indicators to measure the impact of harmonics in power systems. They reflect the degree of deviation of voltage and current waveforms from sine waves. Indicates the voltage distortion rate, using Indicates the current distortion rate. The voltage distortion rate and current distortion rate are:

[0062]

[0063] Among them, V h is the hth harmonic voltage; I h is the hth harmonic current; V1 and I1 are the reference voltage and reference current respectively.

[0064] Step 206: Determine harmonic characteristics based on the windowing function value, the voltage distortion rate, the current distortion rate and the detection data.

[0065] The harmonic features are used to train the initial model to obtain the target model. In an optional embodiment, the harmonic features are determined based on the windowing function value, the voltage distortion rate, the current distortion rate and the detection data, including: determining the harmonic apparent power of the device under test according to the voltage distortion rate and the current distortion rate; extracting features from the detection data according to the windowing function value and the harmonic apparent power to obtain the harmonic features.

[0066] Among them, harmonic apparent power is an important indicator to measure the impact of harmonics in the power grid, which includes the impact of harmonic current and harmonic voltage. In this solution, the hth harmonic apparent power of the device under test is calculated as follows:

[0067]

[0068] Among them, S h is the hth harmonic apparent power. S1 is the fundamental apparent power. After determining the harmonic apparent power, the bed function value and the harmonic apparent power are integrated to obtain a feature vector, that is, the harmonic feature is: Feature Vector = [B(n), S h ,THD V ,THD I ], Feature Vector is a harmonic feature. In an optional implementation, after obtaining the harmonic feature, the values ​​in the harmonic feature are standardized or normalized to ensure the consistency of the numerical range of different harmonic features, thereby improving the training efficiency and performance of the model.

[0069] In the above steps, by combining multiple related parameters into a feature vector, the characteristics of the signal can be better captured, thereby improving the performance of the target model.

[0070] Step 207: determine a training data set for the initial model according to the harmonic characteristics, and optimize the initial model based on the training data set to obtain a target model.

[0071] Among them, the target model is used to identify the harmonic source of the substation according to the harmonic characteristics.

[0072] In the technical scheme of the present embodiment, the historical operation data of the device under test is obtained. Data is collected from the device under test according to the pre-established acquisition system and the historical operation data to obtain the detection data of the device under test. The parameters of the windowing function are determined based on the experimental parameters of the device under test, and the parameters of the windowing function include the total length and the effective length. The Blackman window calculation is performed on the detection data based on the parameters of the windowing function and the windowing function to obtain the windowing function value corresponding to the detection data. The reference voltage and reference current of the device under test are determined based on the historical operation data; the waveform analysis is performed on the detection data to determine the harmonic voltage and harmonic current of the device under test; the voltage distortion rate and current distortion rate of the device under test are determined according to the reference voltage, the reference current, the harmonic voltage and the harmonic current; the harmonic characteristics are determined based on the windowing function value, the voltage distortion rate, the current distortion rate and the detection data. The training data set of the pre-established initial model is determined according to the harmonic characteristics, and the initial model is optimized based on the training data set to obtain the target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics. In the technical scheme of the present embodiment, the actual operation can be effectively simulated according to the acquisition system to obtain accurate detection data. By adding window functions and detecting data, we can capture subtle harmonic changes in the signal of the device under test, improve the accuracy and representativeness of harmonic feature extraction, and obtain harmonic features that can comprehensively describe the impact of harmonics on the device, thus improving the efficiency and accuracy of subsequent model training.

[0073] An embodiment of the present invention also provides a computer program product.

[0074] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer program products, which can include one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor, which can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0075] Figure 4 Schematic diagram of the structure of a harmonic feature determination device provided in an embodiment of the present invention, which is suitable for executing a harmonic feature determination method provided in an embodiment of the present invention. Figure 4As shown, the device may specifically include:

[0076] The data acquisition module 401 is used to acquire historical operation data of the device under test when the pre-established initial model does not meet the preset conditions;

[0077] The data detection module 402 is used to collect data from the device under test according to a pre-established collection system and the historical operation data to obtain detection data of the device under test;

[0078] A feature determination module 403, configured to determine harmonic features based on the detection data and a predetermined windowing function;

[0079] The model training module 404 is used to determine the training data set of the initial model according to the harmonic characteristics, and optimize the initial model based on the training data set to obtain a target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics.

[0080] Optionally, the acquisition system includes a power supply, a first protection resistor, a second protection resistor, a recorder and an acquisition module; wherein the first protection resistor is connected between the power supply and the recorder, the second protection resistor is connected between the power supply and the acquisition module, the device under test is connected between the second protection resistor and the acquisition module, and the data detection module 402 is specifically used to: determine the experimental parameters of the device under test based on the historical operation data; wherein the experimental parameters include the start time of the experiment, the experimental voltage, the sampling frequency and the sampling time;

[0081] At the beginning of the experiment, the power supply voltage is adjusted to the experimental voltage, and data of the device under test is collected according to the sampling frequency and the sampling time to obtain detection data of the device under test; wherein the detection data includes the current and voltage of the device under test.

[0082] Optionally, the feature determination module 403 is specifically used to: determine the parameters of the windowing function based on the experimental parameters of the device under test, the parameters of the windowing function including the total length and the effective length;

[0083] Performing Blackman window calculation on the detection data based on the parameters of the windowing function and the windowing function to obtain a windowing function value corresponding to the detection data;

[0084] The harmonic feature is determined according to the windowing function value and the detection data.

[0085] Optionally, the feature determination module 403 is further used to: determine a reference voltage and a reference current of the device under test based on the historical operation data;

[0086] Performing waveform analysis on the detection data to determine the harmonic voltage and harmonic current of the device under test;

[0087] Determining a voltage distortion rate and a current distortion rate of the device under test according to the reference voltage, the reference current, the harmonic voltage, and the harmonic current;

[0088] The harmonic feature is determined based on the windowing function value, the voltage distortion rate, the current distortion rate and the detection data.

[0089] Optionally, the feature determination module 403 is further used to: determine the harmonic apparent power of the device under test according to the voltage distortion rate and the current distortion rate;

[0090] Feature extraction is performed on the detection data according to the windowing function value and the harmonic apparent power to obtain the harmonic feature.

[0091] Optionally, the model training module 404 is specifically used to: when the initial model does not meet the preset conditions, select a harmonic feature from the training data set as the current feature, input the current feature into the initial model, and obtain the current recognition result output by the initial model;

[0092] The model parameters of the initial model are adjusted based on the current recognition result and a preset loss function; the next harmonic feature is selected from the training data set as the current feature, and the above operation is repeated until the initial model meets the preset conditions to obtain the target model.

[0093] The harmonic feature determination device provided in the embodiment of the present invention can execute the harmonic feature determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. The contents not described in detail in this embodiment can refer to the description in any method embodiment of the present invention.

[0094] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, referring to Figure 5 , Figure 5 The electronic device 12 shown is only an example and should not limit the functions and scope of use of the embodiments of the present application. Figure 5 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0095] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0096] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0097] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0098] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0099] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via the bus 18. It should be understood that although Figure 5 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0100] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, a harmonic feature determination method provided in an embodiment of the present invention is implemented: when the pre-established initial model does not meet the preset conditions, the historical operation data of the device under test is obtained; data is collected for the device under test according to the pre-established acquisition system and the historical operation data to obtain the detection data of the device under test; the harmonic features are determined based on the detection data and a predetermined windowing function; a training data set of the initial model is determined according to the harmonic features, and the initial model is optimized based on the training data set to obtain a target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic features.

[0101] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a harmonic feature determination method as provided in all embodiments of the present invention: when a pre-established initial model does not meet a preset condition, obtaining historical operation data of the device under test; performing data acquisition on the device under test according to a pre-established acquisition system and the historical operation data to obtain detection data of the device under test; determining harmonic features based on the detection data and a predetermined windowing function; determining a training data set for the initial model according to the harmonic features, and optimizing the initial model based on the training data set to obtain a target model; wherein the target model is used to identify harmonic sources of a substation according to harmonic features. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but is not limited to, an electronic device, device or device of electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction-executing electronic device, apparatus, or device.

[0102] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction-executing electronic device, apparatus, or device.

[0103] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0104] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0105] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining harmonic characteristics, characterized in that: The method comprises: When the pre-established initial model does not meet the preset conditions, the historical operation data of the device under test is obtained; Collecting data on the device under test according to a pre-established collection system and the historical operation data to obtain detection data of the device under test; Determining harmonic characteristics based on the detection data and a predetermined windowing function; A training data set of the initial model is determined according to the harmonic characteristics, and the initial model is optimized based on the training data set to obtain a target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics.

2. The method according to claim 1, characterized in that: The acquisition system includes a power supply, a first protection resistor, a second protection resistor, a wave recorder and an acquisition module; The first protection resistor is connected between the power supply and the recorder, the second protection resistor is connected between the power supply and the acquisition module, the device under test is connected between the second protection resistor and the acquisition module, and data acquisition is performed on the device under test according to the pre-established acquisition system and the historical operation data, including: Determine the experimental parameters of the device under test based on the historical operation data; wherein the experimental parameters include the start time of the experiment, the experimental voltage, the sampling frequency and the sampling time; At the beginning of the experiment, the power supply voltage is adjusted to the experimental voltage, and data of the device under test is collected according to the sampling frequency and the sampling time to obtain detection data of the device under test; wherein the detection data includes the current and voltage of the device under test.

3. The method according to claim 1, characterized in that Determining harmonic characteristics based on the detection data and a predetermined windowing function includes: Determining parameters of the windowing function based on experimental parameters of the device under test, the parameters of the windowing function including a total length and an effective length; Performing Blackman window calculation on the detection data based on the parameters of the windowing function and the windowing function to obtain a windowing function value corresponding to the detection data; The harmonic feature is determined according to the windowing function value and the detection data.

4. The method according to claim 3, characterized in that Determining the harmonic feature according to the windowing function value and the detection data includes: Determine a reference voltage and a reference current of the device under test based on the historical operation data; Performing waveform analysis on the detection data to determine the harmonic voltage and harmonic current of the device under test; Determining a voltage distortion rate and a current distortion rate of the device under test according to the reference voltage, the reference current, the harmonic voltage, and the harmonic current; The harmonic feature is determined based on the windowing function value, the voltage distortion rate, the current distortion rate and the detection data.

5. The method according to claim 4, characterized in that Determining the harmonic feature based on the windowing function value, the voltage distortion rate, the current distortion rate and the detection data includes: Determining the harmonic apparent power of the device under test according to the voltage distortion rate and the current distortion rate; Feature extraction is performed on the detection data according to the windowing function value and the harmonic apparent power to obtain the harmonic feature.

6. The method according to claim 1, characterized in that Optimizing the initial model based on the training data set to obtain a target model includes: When the initial model does not meet the preset conditions, a harmonic feature is selected from the training data set as a current feature, and the current feature is input into the initial model to obtain a current recognition result output by the initial model; The model parameters of the initial model are adjusted based on the current recognition result and a preset loss function; the next harmonic feature is selected from the training data set as the current feature, and the above operation is repeated until the initial model meets the preset conditions to obtain the target model.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements a harmonic characteristic determination method according to any one of claims 1 to 6.

8. A harmonic characteristic determination device, characterized in that: include: A data acquisition module, used to obtain historical operation data of the device under test when the pre-established initial model does not meet the preset conditions; A data detection module, used to collect data from the device under test according to a pre-established collection system and the historical operation data, to obtain detection data of the device under test; A feature determination module, used to determine harmonic features based on the detection data and a predetermined windowing function; A model training module is used to determine the training data set of the initial model according to the harmonic characteristics, and optimize the initial model based on the training data set to obtain a target model; wherein the target model is used to identify the harmonic source of the substation according to the harmonic characteristics.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, a harmonic characteristic determination method as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a harmonic characteristic determination method as claimed in any one of claims 1 to 6 is implemented.

Images