Method and device for checking harmonic resistance of power equipment and computer device

Abstract

The application relates to a power equipment harmonic resistance capability checking method and device and a computer device. The method comprises the following steps: obtaining equipment parameters, equipment checking parameter values and real-time operation parameters of power equipment, the real-time operation parameters comprising current values and voltage values, performing harmonic analysis on harmonic components in the current values or the voltage values to obtain maximum harmonic current resistance values or maximum harmonic voltage resistance values of the power equipment, calling a trained harmonic resistance capability prediction model corresponding to the power equipment to perform equipment checking parameter prediction according to the maximum harmonic current resistance values and the equipment parameters or the maximum harmonic voltage resistance values and the equipment parameters, obtaining equipment checking parameter prediction values, and obtaining a power equipment harmonic resistance capability checking result according to the equipment checking parameter values and the equipment checking parameter prediction values. The method can improve the accuracy of power equipment harmonic resistance capability checking.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grids, in particular to a power equipment harmonic tolerance capability checking method and device, computer equipment, storage medium and computer program product. BACKGROUND

[0002] In recent years, with the access of high proportion of power electronic equipment and high proportion of new energy, the main grid structure and system operation characteristics have changed profoundly, and the system harmonic and resonance problems have become increasingly prominent. The risk of equipment failure or shutdown caused by system harmonics and resonance has gradually increased. Therefore, it is an important work to carry out power main equipment harmonic tolerance capability checking and to clarify the harmonic limit value and the equipment operation safety boundary.

[0003] However, for main equipment such as transformers (converter transformers), tap changers and AC filters, the harmonic checking calculation workload is large and complex, professional simulation models need to be built, and operation and maintenance personnel need to have high professional knowledge. At present, the harmonic tolerance capability checking of power electronic equipment only relies on manual calculation, lacks professional auxiliary calculation tools, so it is easy to make mistakes, and the correctness of the checking result cannot be guaranteed.

[0004] Therefore, it is necessary to provide a scheme capable of improving the accuracy of the power equipment harmonic tolerance capability checking result. SUMMARY

[0005] Therefore, it is necessary to provide a scheme capable of improving the accuracy of the power equipment harmonic tolerance capability checking result.

[0006] In a first aspect, the present application provides a power equipment harmonic tolerance capability checking method. The method comprises:

[0007] obtaining device parameters, device checking parameter values and real-time operation parameters of the power equipment, the real-time operation parameters comprising current values and voltage values;

[0008] performing harmonic analysis on harmonic components in the current values or voltage values to obtain maximum harmonic current tolerance values or maximum harmonic voltage tolerance values of the power equipment;

[0009] calling a trained harmonic tolerance capability prediction model corresponding to the power equipment to perform device checking parameter prediction according to the maximum harmonic current tolerance values and the device parameters, or the maximum harmonic voltage tolerance values and the device parameters, and obtain device checking parameter prediction values;

[0010] obtaining a power equipment harmonic tolerance capability checking result according to the device checking parameter values and the device checking parameter prediction values.

[0011] The harmonic tolerance capability prediction model is trained based on historical equipment parameters and historical real-time operation parameters of the power equipment.

[0012] In one of the embodiments, the harmonic analysis on the harmonic components in the current value or the voltage value obtains the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment, including:

[0013] The original signal includes an original current signal or an original voltage signal.

[0014] The Hilbert transform is performed on the target intrinsic mode function component to obtain the instantaneous characteristic quantity, including a harmonic current spectrum and a current amplitude, or a harmonic voltage spectrum and a voltage amplitude.

[0015] The maximum harmonic current tolerance value or the maximum harmonic current tolerance value of the power equipment is obtained based on the fundamental amplitude in the harmonic current spectrum or the harmonic voltage spectrum, and the harmonic current amplitude or the harmonic voltage amplitude is superimposed multiple times.

[0016] In one of the embodiments, the original signal is superimposed with the noise signal multiple times, and the target signal obtained after each superposition is subjected to the empirical mode decomposition until the target intrinsic mode function component is obtained, including:

[0017] The original current signal or the original voltage signal is superimposed with the Gaussian white noise signal multiple times based on the zero mean principle of the Gaussian white noise spectrum, and the target signal obtained after each superposition is subjected to the empirical mode decomposition to obtain the corresponding intrinsic mode function component.

[0018] The target intrinsic mode function component is selected from the intrinsic mode function components.

[0019] In one of the embodiments, the target intrinsic mode function component is selected from the intrinsic mode function components, including:

[0020] The error of the sum of the original signal and the intrinsic mode function component obtained after each round of empirical mode decomposition is obtained.

[0021] If the error is less than or equal to a preset error threshold, the intrinsic mode function component obtained after the current round of empirical mode decomposition is determined as the target intrinsic mode function component.

[0022] In one of the embodiments, the maximum harmonic current tolerance value or the maximum harmonic current tolerance value of the power equipment is obtained based on the harmonic current spectrum or the harmonic voltage spectrum, and the harmonic current amplitude or the harmonic voltage amplitude is superimposed multiple times, including:

[0023] Calculate the device checking parameter reference value of the power equipment after calculating the amplitude of each superimposed harmonic current or the amplitude of each superimposed harmonic voltage.

[0024] When the device checking parameter reference value exceeds the preset maximum allowable value of the device checking parameter, the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment is obtained.

[0025] In one of the embodiments, the harmonic tolerance capability prediction model is obtained based on the following manner:

[0026] Obtain historical equipment parameters, historical real-time operation parameters and historical device checking parameter reference values;

[0027] Based on the historical equipment parameters, the historical real-time operation parameters and the historical device checking parameter reference values, a training sample set is constructed;

[0028] An initial harmonic tolerance capability prediction model is constructed, the initial harmonic tolerance capability prediction model comprising an input layer, a hidden layer and an output layer, the number of nodes of the hidden layer being determined by using a trial method;

[0029] Based on the training sample set, the initial harmonic tolerance capability prediction model is trained by using a Traincap training algorithm to obtain a trained harmonic tolerance capability prediction model.

[0030] In a second aspect, the present application further provides a power equipment harmonic tolerance capability checking device. The device comprises:

[0031] A data acquisition module is configured to acquire equipment parameters, device checking parameter values and real-time operation parameters of the power equipment, the real-time operation parameters comprising current values and voltage values;

[0032] A harmonic analysis module is configured to perform harmonic analysis on harmonic components in the current values or the voltage values to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment;

[0033] A device checking parameter prediction module is configured to call a trained harmonic tolerance capability prediction model corresponding to the power equipment to perform device checking parameter prediction according to the maximum harmonic current tolerance value and the equipment parameters or the maximum harmonic voltage tolerance value and the equipment parameters to obtain a device checking parameter prediction value;

[0034] A harmonic tolerance capability checking module is configured to obtain a harmonic tolerance capability checking result of the power equipment according to the device checking parameter value and the device checking parameter prediction value.

[0035] The harmonic tolerance capability prediction model is trained based on historical equipment parameters and historical real-time operation parameters of the power equipment.

[0036] In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0037] obtaining the device parameter, the device checking parameter value and the real-time running parameter of the power equipment, the real-time running parameter comprising a current value and a voltage value;

[0038] performing harmonic analysis on the harmonic component in the current value or the voltage value to obtain a maximum harmonic current tolerance value or a maximum harmonic voltage tolerance value of the power equipment;

[0039] calling a trained harmonic tolerance capability prediction model corresponding to the power equipment to perform device checking parameter prediction according to the maximum harmonic current tolerance value and the device parameter, or the maximum harmonic voltage tolerance value and the device parameter, and obtain a device checking parameter prediction value;

[0040] obtaining a harmonic tolerance capability checking result of the power equipment according to the device checking parameter value and the device checking parameter prediction value;

[0041] The harmonic tolerance capability prediction model is trained based on historical device parameters and historical real-time running parameters of the power equipment.

[0042] In a fourth aspect, the present application also provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0043] obtaining the device parameter, the device checking parameter value and the real-time running parameter of the power equipment, the real-time running parameter comprising a current value and a voltage value;

[0044] performing harmonic analysis on the harmonic component in the current value or the voltage value to obtain a maximum harmonic current tolerance value or a maximum harmonic voltage tolerance value of the power equipment;

[0045] calling a trained harmonic tolerance capability prediction model corresponding to the power equipment to perform device checking parameter prediction according to the maximum harmonic current tolerance value and the device parameter, or the maximum harmonic voltage tolerance value and the device parameter, and obtain a device checking parameter prediction value;

[0046] obtaining a harmonic tolerance capability checking result of the power equipment according to the device checking parameter value and the device checking parameter prediction value;

[0047] The harmonic tolerance capability prediction model is trained based on historical device parameters and historical real-time running parameters of the power equipment.

[0048] In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the following steps:

[0049] obtaining the device parameter, the device checking parameter value and the real-time running parameter of the power device, wherein the real-time running parameter comprises the current value and the voltage value;

[0050] performing harmonic analysis on the harmonic component in the current value or the voltage value to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power device;

[0051] calling the trained harmonic tolerance capability prediction model corresponding to the power device to perform device checking parameter prediction according to the maximum harmonic current tolerance value and the device parameter, or the maximum harmonic voltage tolerance value and the device parameter, and obtain the device checking parameter prediction value;

[0052] obtaining the harmonic tolerance capability checking result of the power device according to the device checking parameter value and the device checking parameter prediction value;

[0053] wherein the harmonic tolerance capability prediction model is trained based on the historical device parameter and the historical real-time running parameter of the power device.

[0054] The power device harmonic tolerance capability checking method, device, computer device, storage medium and computer program product described above obtain the device parameter, the device checking parameter value and the real-time running parameter of the power device, wherein the real-time running parameter comprises the current value and the voltage value, then perform harmonic analysis on the harmonic component in the current value or the voltage value to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power device, call the trained harmonic tolerance capability prediction model corresponding to the power device to perform device checking parameter prediction according to the maximum harmonic current tolerance value and the device parameter, or the maximum harmonic voltage tolerance value and the device parameter, and obtain the device checking parameter prediction value, and finally obtain the harmonic tolerance capability checking result of the power device according to the device checking parameter value and the device checking parameter prediction value. The above process uses the embedded program to perform harmonic analysis on the harmonic component in the current value or the voltage value, reduces the workload of harmonic checking calculation, greatly improves the work efficiency, and discards the manual harmonic tolerance capability checking method, calls the harmonic tolerance capability prediction model corresponding to the power device to perform device checking parameter prediction and obtain the device checking parameter prediction value to check the harmonic tolerance capability of the power device, which greatly improves the accuracy of the harmonic tolerance capability checking of the power device. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 It is an application environment diagram of the power device harmonic tolerance capability checking method in one embodiment;

[0056] Figure 2A flowchart of the power equipment harmonic tolerance checking method in one embodiment;

[0057] Figure 3 A flowchart of the harmonic analysis step in one embodiment;

[0058] Figure 4 A flowchart of the harmonic analysis step in another embodiment;

[0059] Figure 5 A detailed flowchart of the power equipment harmonic tolerance checking method in another embodiment;

[0060] Figure 6 A structural block diagram of the power equipment harmonic tolerance checking device in one embodiment;

[0061] Figure 7 A structural block diagram of the power equipment harmonic tolerance checking device in another embodiment;

[0062] Figure 8 An internal structural diagram of the computer device in one embodiment. DETAILED DESCRIPTION

[0063] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0064] The power equipment harmonic tolerance checking method provided by the embodiments of the present application can be applied to, for example, Figure 1The application environment is shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. Specifically, the operation and maintenance personnel can upload the device parameters, device checking parameter values and real-time running parameters of the power equipment to be checked to the server 102 through the terminal 102, and send the tolerance checking message to the server 104. The server 104 responds to the tolerance checking message, obtains the device parameters, device checking parameter values and real-time running parameters of the power equipment, and the real-time running parameters include current value and voltage value. Then, the harmonic components in the current value or voltage value are analyzed to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment. The trained harmonic tolerance prediction model corresponding to the power equipment is called to predict the device checking parameters according to the maximum harmonic current tolerance value and the device parameters, or the maximum harmonic voltage tolerance value and the device parameters, to obtain the device checking parameter prediction value. Finally, according to the device checking parameter value and the device checking parameter prediction value, the harmonic tolerance checking result of the power equipment is obtained, wherein the harmonic tolerance prediction model is trained based on the historical device parameters and historical real-time running parameters of the power equipment. Among them, the terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart TV, a smart air conditioner, a smart vehicle-mounted device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be realized by an independent server or a server cluster composed of multiple servers.

[0065] In one embodiment, as shown in Figure 2 , a power equipment harmonic tolerance checking method is provided. Taking the server 104 in Figure 1 as an example, the method includes the following steps:

[0066] Step S100, obtaining the device parameters, device checking parameter values and real-time running parameters of the power equipment, and the real-time running parameters including current value and voltage value.

[0067] The power equipment can be a main equipment of a power system, and can be various power equipment such as primary main equipment of a power transformation, specifically transformer (main transformer, converter transformer, coupling transformer), on-load tap changer, bridge arm reactor, circuit breaker, mutual inductor, filter group, and converter valve. The equipment parameters include parameters in a factory test report, key parameters in a technical specification book, and the like. Specifically, taking the transformer as an example, the parameters in the factory test report include rated current, winding resistance, and temperature rise test result of the transformer in the factory test report, wherein the temperature rise test result includes oil surface temperature rise, winding average temperature rise, winding hot spot temperature rise, total loss applied in the temperature rise test process, test current applied in the second stage (1h stage) of the temperature rise test, and load loss. The key parameters in the technical specification book include limit values of the oil surface temperature rise, winding average temperature rise, and winding hot spot temperature rise of the transformer. The real-time running parameter refers to a current value or a voltage value flowing through the power equipment or acting on the power equipment collected at a current time. The equipment checking parameter refers to a device parameter required for checking the harmonic resistance capability of each kind of power equipment, in other words, the calculation of the harmonic resistance capability needs to rely on the equipment checking parameter, and then, conversely, if the resistance capability of the calculated power equipment is to be checked whether it is accurate, the value of the equipment checking parameter can be inversely deduced according to the calculated harmonic resistance capability for verification. The value of the equipment checking parameter is different for each kind of power equipment. For example, for the transformer, the equipment checking parameter can be temperature rise, and for the on-load tap changer, the equipment checking parameter can be current change rate. In the embodiment, the value of the equipment checking parameter is a known quantity given according to experience.

[0068] The equipment checking parameter of the power equipment specifically includes: checking the oil surface temperature rise, winding average temperature rise, and winding hot spot temperature rise of the transformer by applying a harmonic current component on the basis of a fundamental current; checking the maximum total current change rate of the tap changer by applying a harmonic current component on the basis of a fundamental current; checking the thermal equivalent current and turn-to-turn breakdown voltage of the bridge arm reactor by applying a harmonic current and harmonic voltage component on the basis of a fundamental current and fundamental voltage; checking the breaking short-circuit current of the alternating current circuit breaker by applying a harmonic current component on the basis of a fundamental current; checking the short-time total harmonic voltage and current of the alternating current mutual inductor compared with a standard value by applying a harmonic current and harmonic voltage on the basis of a fundamental current and fundamental voltage; checking the simulation result of the alternating current filter to be less than the tolerance level of the harmonic specified in the technical agreement by applying a harmonic current component on the basis of a fundamental current; and checking the margin between the test current and rated current of the converter valve by applying a harmonic current component on the basis of a fundamental current.

[0069] In step S200, a harmonic analysis is performed on the harmonic component in the current value or voltage value to obtain a maximum harmonic current tolerance value or a maximum harmonic voltage tolerance value of the power equipment.

[0070] The maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value refers to a maximum Nth harmonic current tolerance value or a maximum Nth harmonic voltage tolerance value, and the value of N can be determined based on the actual situation of the device parameters and real-time operation parameters. After obtaining the current value and the voltage value of the power device, harmonic analysis can be performed on the harmonic components of the current value, or harmonic analysis can be performed on the harmonic components in the voltage value, to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power device. In specific implementation, the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value can be a maximum fifth harmonic current tolerance value or a maximum fifth harmonic voltage tolerance value. It can be understood that in other embodiments, the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value can also be a maximum fourth harmonic current tolerance value or a maximum fourth harmonic voltage tolerance value, which is determined according to the actual situation.

[0071] In step S300, the trained harmonic tolerance capability prediction model corresponding to the power device is called to perform device checking parameter prediction according to the maximum harmonic current tolerance value and the device parameters or the maximum harmonic voltage tolerance value and the device parameters, to obtain a device checking parameter prediction value.

[0072] The harmonic tolerance capability prediction model is trained based on the historical device parameters and the historical real-time operation parameters of the power device. The harmonic tolerance capability prediction model is used to perform device checking parameter prediction in reverse according to the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value, to obtain a device checking parameter prediction value. Specifically, a BP (Back Propagation Neural Network) neural network including an input layer, a hidden layer and an output layer can be trained based on the historical device parameters and the historical real-time operation parameters of the power device. In specific implementation, after obtaining the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value through the above steps, the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value and the device parameters can be input into the harmonic tolerance capability prediction model, so that the harmonic tolerance capability prediction model reversely calculates the device checking parameter prediction value corresponding to the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value according to the known maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value.

[0073] For example, taking a transformer as an example, the predicted device checking parameter is temperature rise data, and the input layer and the output layer of the harmonic tolerance capability prediction model are determined according to the actually measured experimental data, and the influence factors affecting the temperature rise of the transformer are the fifth harmonic current value, the total loss, the eddy current loss and the stray loss under the fundamental frequency, the rated current, the winding resistance and the total loss P NThe output layer outputs the oil surface temperature rise, winding average temperature rise and winding hot spot temperature rise. In the case of normalization, other variables are fixed, and under the condition of a single factor, the 5th harmonic current value, total loss, eddy current loss and stray loss under the fundamental frequency, rated current, winding resistance, and total loss applied in the temperature rise test process are respectively explored. The output layer outputs the oil surface temperature rise, winding average temperature rise and winding hot spot temperature rise. The corresponding relationship between each influencing factor and temperature is obtained through the test. Since the transformer is placed indoors, the effects of solar energy, wind speed, etc. can be ignored, and only the ambient temperature is considered. Therefore, the three-layer BP neural network can be simplified into a single hidden layer neural network with seven inputs and three outputs. The seven inputs of the input layer are the 5th harmonic current value, total loss, eddy current loss and stray loss under the fundamental frequency, rated current, winding resistance, and total loss applied in the temperature rise test process N The output of the output layer is the predicted transformer oil surface temperature rise, winding average temperature rise and winding hot spot temperature rise.

[0074] Step S400, according to the equipment checking parameter value and the equipment checking parameter prediction value, the harmonic resistance capacity checking result of the power equipment is obtained.

[0075] When the equipment checking prediction value predicted by the harmonic resistance capacity prediction model is obtained, the equipment checking prediction value and the known equipment checking parameter value can be compared. If they are the same or the error satisfies the preset error threshold, it is determined that the harmonic resistance capacity result of the power equipment is accurate. If the preset error threshold is not satisfied, it is determined that the harmonic resistance capacity of the power equipment is not accurate. Further, the most 5th closest maximum harmonic current resistance value or maximum harmonic voltage resistance value, and the corresponding equipment checking parameter value and equipment checking prediction value can be pushed to the operation and maintenance personnel for comparison, to further verify the correctness of the final checking result.

[0076] In the power equipment harmonic tolerance checking method, the equipment parameters, the equipment checking parameter values and the real-time operation parameters of the power equipment are obtained, the real-time operation parameters include current values and voltage values, then the harmonic components in the current values or the voltage values are subjected to harmonic analysis to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment, the trained harmonic tolerance prediction model corresponding to the power equipment is called to perform equipment checking parameter prediction according to the maximum harmonic current tolerance value and the equipment parameters or the maximum harmonic voltage tolerance value and the equipment parameters to obtain the equipment checking parameter prediction value, and finally, the power equipment harmonic tolerance checking result is obtained according to the equipment checking parameter values and the equipment checking parameter prediction value. In the above process, the harmonic components in the current values or the voltage values are subjected to harmonic analysis by using the embedded program, which greatly reduces the workload of harmonic checking calculation, greatly improves the work efficiency, and discards the manual harmonic tolerance checking method, calls the harmonic tolerance prediction model corresponding to the power equipment to perform equipment checking parameter prediction to check the harmonic tolerance of the power equipment, and greatly improves the checking accuracy.

[0077] In one of the embodiments, step S200 includes: performing harmonic analysis on the harmonic components in the current values or the voltage values by using the improved HHT (Hilbert-Huang Transform) algorithm to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment.

[0078] The HHT algorithm is an analysis and processing method for nonlinear and non-stationary signals. It mainly consists of two theoretical parts of EMD (Empirical Mode Decomposition) and Hilbert transform. The empirical mode decomposition can decompose any signal into a set of intrinsic mode functions; the intrinsic mode function can obtain the instantaneous frequency through Hilbert spectrum analysis. Therefore, the time-frequency diagram of the nonlinear and non-stationary signal can be finally obtained through the Hilbert-Huang transform. In this embodiment, the improved HHT algorithm can be used for harmonic analysis, and specifically, the improvement can be made on the empirical mode decomposition algorithm, that is, the criterion of IMF (Intrinsic Mode Function) is determined to avoid infinite times of EMD decomposition to obtain the frequency modulation wave with constant amplitude.

[0079] As shown in FIG. 2, Figure 3 In one of the embodiments, step S200 includes:

[0080] In step S220, the original signal is superimposed with the noise signal multiple times, and the target signal obtained after each superposition is subjected to empirical mode decomposition until the target intrinsic mode function component is obtained, and the original signal includes the original current signal or the original voltage signal.

[0081] Step S240, Hilbert transform is performed on the target intrinsic modal function component to obtain an instantaneous characteristic quantity, and the instantaneous characteristic quantity includes a harmonic current spectrum and a current amplitude or a harmonic voltage spectrum and a voltage amplitude.

[0082] Step S260, based on the fundamental wave amplitude in the harmonic current spectrum or the harmonic voltage spectrum, the harmonic current amplitude or the harmonic voltage amplitude is superimposed for multiple times to obtain a maximum harmonic current tolerance value or a maximum harmonic current tolerance value of the power equipment.

[0083] In the embodiment, the noise signal can be a white noise signal. Specifically, taking the current signal as an example and taking the maximum harmonic current tolerance value as an example for illustration, the original signal can be:

[0084] Step A1: superimposing a group of white noise signals ω t to obtain a total signal.

[0085] Y(t)=y(t)+ω t (1)

[0086] Step A2, EMD decomposition is performed on Y(t) to obtain each order IMF component:

[0087]

[0088] In the formula, c j represents the j-th order IMF component, r n represents a residual component (remainder).

[0089] Step A3, different white noise ω t is added to the original signal, and steps A1 and A2 are repeated until the target intrinsic modal function component is obtained.

[0090]

[0091] In the formula, c ij represents the j-th order IMF component obtained in the i-th cycle, r n represents a residual component (remainder) obtained in the i-th cycle.

[0092] Step A4, Hilbert transform is performed on the target intrinsic modal function component to obtain a corresponding instantaneous characteristic quantity, and the instantaneous characteristic quantity includes a harmonic current spectrum and a current amplitude or a harmonic voltage spectrum and a voltage amplitude.

[0093] Step A5, based on the harmonic current spectrum and amplitude calculated in step A4, the N-th harmonic current amplitude is increased to obtain a maximum harmonic current tolerance value.

[0094] It can be understood that, by the same reason, if the original information is a voltage signal, the maximum harmonic voltage tolerance value can also be obtained by using the above method, which will not be described here. In this embodiment, by adding white noise signals multiple times in the signal decomposition process, the error can be reduced and the accuracy of the IMF component can be improved.

[0095] As shown in Figure 4 In one embodiment, step S220 includes: step S222, based on the zero mean principle of Gaussian white noise spectrum, adding Gaussian white noise signals to the original current signal or the original voltage signal multiple times, and performing empirical mode decomposition on the target signal obtained after each addition to obtain corresponding intrinsic mode function components, and screening target intrinsic mode function components from the intrinsic mode function components.

[0096] In this embodiment, the white noise signal added in the EMD decomposition process can be Gaussian white noise. Gaussian white noise is usually defined as a stationary random process with a mean of zero and a non-zero constant power spectral density, and the probability distribution of its noise value obeys Gaussian distribution. In this embodiment, using the zero mean principle of Gaussian white noise spectrum, the IMF component C n (t) can be represented as:

[0097]

[0098] In the formula, C in (t) represents the IMF component corresponding to the original signal obtained by the i-th cycle decomposition.

[0099] The frequency of the Gaussian white noise added in EMD obeys the following statistical law.

[0100]

[0101] In the formula, N is the number of the population; ε is the amplitude of the Gaussian white noise, and ε n is the error between the original signal and the signal obtained by adding the final IMF.

[0102] In specific implementation, a large amount of white noise is added in the signal decomposition process. Due to the existence of a large amount of noise, the new decomposition result is more complex than the EMD decomposition result. At this time, a sufficient number of test means can be called to offset the noise, and the mean value obtained by multiple tests is determined as the final result of signal decomposition. According to the above, after adding the Gaussian white noise signal multiple times, the empirical mode decomposition is performed on the target signal obtained after each addition to obtain a limited number of IMF components. Further, the final target IMF component can be screened according to whether the IMF component meets the error requirement. In this embodiment, by adding the Gaussian white noise signal multiple times in the signal decomposition process, the error can be further reduced and the accuracy of the IMF component can be improved.

[0103] In one embodiment, selecting the target intrinsic mode function component from the intrinsic mode function components includes: obtaining the error between the original current signal or the original voltage signal and the intrinsic mode function components obtained after each round of empirical mode decomposition; if the error is less than or equal to a preset error threshold, then the intrinsic mode function component obtained after this round of empirical mode decomposition is determined as the target intrinsic mode function component.

[0104] Following the above embodiments, since EMD decomposition is a multi-cycle process, to avoid infinitely repeated EMD decomposition, this embodiment can obtain the error ε by summing the original current signal or original voltage signal with the IMF components obtained after each round of EMD. n If the error ε n If the error is less than or equal to a preset error threshold, the IMF component obtained after this round of EMD is determined as the target IMF component. In this embodiment, the final target IMF component is selected by comparing the error between the original current signal or the original voltage signal and the sum of the IMF components obtained after each round of EMD. This avoids infinite repetition of EMD and ensures the quality of the selected IMF component.

[0105] like Figure 4 As shown, in one embodiment, step S260 includes: step S262, calculating the reference value of the equipment verification parameter of the power equipment after each superposition of harmonic current amplitude or harmonic voltage amplitude, and when the reference value of the equipment verification parameter exceeds the preset maximum allowable value of the equipment verification parameter, obtaining the maximum harmonic current withstand value or maximum harmonic current withstand value of the power equipment.

[0106] In the above embodiment, after obtaining the corresponding harmonic current spectrum and current amplitude, or the harmonic voltage spectrum and voltage amplitude through Hibert transformation, the device checking parameter reference value of the power equipment after each superposition of the harmonic current amplitude or the harmonic voltage amplitude can be compared with the preset maximum allowable value of the device checking parameter to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value. In this embodiment, the maximum harmonic current tolerance value is taken as an example for illustration. The fifth harmonic current amplitude can be added on the basis of the harmonic current spectrum and amplitude. After each addition of the fifth harmonic current value, the device checking parameter reference value of the power equipment is calculated. It is judged whether the device checking parameter reference value exceeds the maximum allowable value of the device checking parameter of the power equipment. If the device checking parameter reference value does not exceed the maximum allowable value of the device checking parameter, the fifth harmonic current value will be continuously added, and it is judged again whether the device checking parameter reference value exceeds the maximum allowable value of the device checking parameter. If the device checking parameter reference value exceeds the maximum allowable value of the device checking parameter, the fifth harmonic current value in the last five iteration processes is determined as the maximum fifth harmonic current tolerance value. In this embodiment, by comparing whether the device checking parameter reference value exceeds the maximum allowable value of the device checking parameter, the accurate maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment can be obtained.

[0107] In one of the embodiments, the harmonic tolerance capability prediction model is obtained based on the following manner: obtaining historical device parameters, historical real-time running parameters and historical device checking parameter reference values, constructing a training sample set based on the historical device parameters, the historical real-time running parameters and the historical device checking parameter reference values, constructing an initial harmonic tolerance capability prediction model, the initial harmonic tolerance capability prediction model including an input layer, a hidden layer and an output layer, the number of nodes of the hidden layer being determined by using a trial method, training the initial harmonic tolerance capability prediction model based on the training sample set by using a Traincap training algorithm to obtain a trained harmonic tolerance capability prediction model.

[0108] In specific implementation, after the training sample set is constructed based on the historical device parameters, the historical real-time running parameters and the historical device checking parameter reference values of the power equipment, the initial harmonic tolerance capability prediction model can be constructed. The initial harmonic tolerance capability prediction model can be a three-layer BP neural network including an input layer, a hidden layer and an output layer. The number of nodes of the hidden layer can be determined by using a trial method.

[0109]

[0110] In the formula, l is the number of hidden layer units, n is the number of input layer units, m is the number of output layer units, and a is a constant in the interval [1, 10]. For each hidden layer node number, 10 different training is performed. The node number at the time of the minimum average training error is taken as the optimal hidden layer node number to avoid the influence of the randomness of the initialized weight value.

[0111] In practical applications, the specific number of network input parameters and output parameters can be designed according to the different requirements of power equipment. For example, taking a transformer as an example, the initial harmonic withstand capability prediction model can be a single hidden layer neural network with seven inputs and three outputs.

[0112] After constructing the initial harmonic tolerance prediction model, the model can be trained using the Traincap training method based on actual training data and prediction results. Specifically, the model training process can be as follows:

[0113] (1) Set the initial values ​​for the iteration to p0 = r0, k = 0;

[0114] (2) Substitute into formulas (7) to (9) and iterate;

[0115]

[0116] X k+1 =X k +α k p k (8)

[0117] r k+1 =r k -α k Ap k (9)

[0118] Where A is the coefficient, r k To calculate the gradient value, β k X is the combination coefficient. K Let α represent the iteration point. k P represents the step size. K Conjugate direction. Equation (7) is used to calculate the step size, Equation (8) is used to update the iteration point, and Equation (9) is used to calculate the new gradient.

[0119] (3) Determine the error value of the equipment calibration parameters. If it is less than the set value, proceed to step (5). Alternatively, determine the maximum value of the number of training sessions. If the maximum value is reached, proceed to step (5); otherwise, proceed to step (4).

[0120] (4) Update the result value of the equipment verification parameters, substitute it into formulas (10) to (12), and then return to step 2;

[0121]

[0122] P k+1 =r k+1 +β k P k (11)

[0123] k = k + 1 (12)

[0124] In the formula, β k Equation (10) is used to calculate the combination coefficients, and equation (11) is used to calculate the conjugate direction.

[0125] (5) When the results of the equipment verification parameters reach the expected values, the iterative process of the harmonic tolerance prediction model ends.

[0126] In this embodiment, by training the harmonic tolerance prediction model as described above, the accuracy of the harmonic tolerance prediction model can be improved, and the efficiency of harmonic tolerance verification can be increased.

[0127] To provide a clearer explanation of the harmonic withstand capability verification method for power equipment provided in this application, the following is in conjunction with the appendix. Figure 5 The following specific embodiments will be described, which include the following steps:

[0128] Step S1: Obtain the equipment parameters, equipment verification parameter values, and real-time operating parameters of the power equipment. The real-time operating parameters include current and voltage values.

[0129] Step S2: Based on the zero-mean principle of Gaussian white noise spectrum, Gaussian white noise is superimposed multiple times on the original current signal or original voltage signal, and empirical mode decomposition is performed on the target signal obtained after each superposition to obtain the corresponding intrinsic mode function components. Specifically, the error between the original current signal or original voltage signal and the sum of the intrinsic mode function components obtained after each round of empirical mode decomposition is obtained. If the error is less than or equal to a preset error threshold, the intrinsic mode function component obtained after this round of empirical mode decomposition is determined as the target intrinsic mode function component.

[0130] Step S3: Perform Hilbert transform on the target intrinsic mode function components to obtain instantaneous characteristic quantities, including harmonic current spectrum and current amplitude, or harmonic voltage spectrum and voltage amplitude.

[0131] Step S4: Based on the fundamental amplitude in the harmonic current spectrum or harmonic voltage spectrum, superimpose the harmonic current amplitude or harmonic voltage amplitude multiple times to obtain the maximum harmonic current withstand value or maximum harmonic current withstand value of the power equipment.

[0132] Step S5: Call the trained harmonic withstand capability prediction model corresponding to the power equipment to predict the equipment verification parameters based on the maximum harmonic current withstand value and equipment parameters, or the maximum harmonic voltage withstand value and equipment parameters, and obtain the predicted values ​​of the equipment verification parameters.

[0133] Step S6: Based on the equipment verification parameter values ​​and the predicted values ​​of the equipment verification parameters, obtain the verification results of the harmonic tolerance capability of the power equipment.

[0134] Step S7: The push device checks the parameter value, the device check parameter prediction value, and the power device harmonic tolerance capability check result.

[0135] It should be understood that, although each step in the flowchart involved in each embodiment as described above is shown in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless explicitly stated herein, there is no strict order limitation for the execution of these steps, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps.

[0136] Based on the same inventive concept, the embodiments of the present application also provide a power device harmonic tolerance capability checking device for implementing the above-mentioned power device harmonic tolerance capability checking method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more power device harmonic tolerance capability checking device embodiments provided below can refer to the limitations of the power device harmonic tolerance capability checking method described above, which will not be repeated here.

[0137] In one embodiment, as shown in Figure 6 a power device harmonic tolerance capability checking device is provided, comprising: a data acquisition module 610, a harmonic analysis module 620, a device check parameter prediction module 630, and a harmonic tolerance capability checking module 640, wherein:

[0138] The data acquisition module 610 is configured to acquire device parameters, device check parameter values, and real-time running parameters of the power device, wherein the real-time running parameters include current values and voltage values.

[0139] The harmonic analysis module 620 is configured to perform harmonic analysis on harmonic components in the current values or the voltage values to obtain maximum harmonic current tolerance values or maximum harmonic voltage tolerance values of the power device.

[0140] The device check parameter prediction module 630 is configured to call a trained harmonic tolerance capability prediction model corresponding to the power device to perform device check parameter prediction according to the maximum harmonic current tolerance values and the device parameters, or the maximum harmonic voltage tolerance values and the device parameters, and obtain a device check parameter prediction value.

[0141] The harmonic tolerance checking module 640 is configured to obtain the harmonic tolerance checking result of the power equipment according to the equipment checking parameter value and the equipment checking parameter prediction value.

[0142] The harmonic tolerance prediction model is trained based on historical equipment parameters and historical real-time operation parameters of the power equipment.

[0143] In the harmonic tolerance checking device for the power equipment, the equipment parameters, the equipment checking parameter value and the real-time operation parameters of the power equipment are obtained, the real-time operation parameters include the current value and the voltage value, then the harmonic analysis is performed on the harmonic components in the current value or the voltage value to obtain the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power equipment, the trained harmonic tolerance prediction model corresponding to the power equipment is called to perform the equipment checking parameter prediction according to the maximum harmonic current tolerance value and the equipment parameters or the maximum harmonic voltage tolerance value and the equipment parameters to obtain the equipment checking parameter prediction value, and finally the harmonic tolerance checking result of the power equipment is obtained according to the equipment checking parameter value and the equipment checking parameter prediction value. In the above process, the harmonic analysis is performed on the harmonic components in the current value or the voltage value by using the embedded program, which greatly reduces the workload of the harmonic checking calculation, greatly improves the work efficiency, and discards the manual harmonic tolerance checking method, calls the harmonic tolerance prediction model corresponding to the power equipment to perform the equipment checking parameter prediction to check the harmonic tolerance of the power equipment, and greatly improves the checking accuracy.

[0144] In one of the embodiments, the harmonic analysis module 620 is further configured to superimpose the noise signal on the original current signal or the original voltage signal for multiple times, and perform the empirical mode decomposition on the target signal obtained after each superimposition until the final intrinsic mode function component is obtained, perform the Hilbert transform on the target intrinsic mode function component to obtain the instantaneous characteristic quantity, the instantaneous characteristic quantity includes the harmonic current spectrum and the current amplitude, or the harmonic voltage spectrum and the voltage amplitude, superimpose the harmonic current amplitude or the harmonic voltage amplitude on the fundamental amplitude in the harmonic current spectrum or the harmonic voltage spectrum for multiple times to obtain the maximum harmonic current tolerance value or the maximum harmonic current tolerance value of the power equipment.

[0145] In one of the embodiments, the harmonic analysis module 620 is further configured to superimpose the Gaussian white noise signal on the original current signal or the original voltage signal for multiple times based on the zero mean principle of the Gaussian white noise spectrum, and perform the empirical mode decomposition on the target signal obtained after each superimposition to obtain the corresponding intrinsic mode function component, and filter out the target intrinsic mode function component from the intrinsic mode function component.

[0146] In one of the embodiments, the harmonic analysis module 620 is further configured to obtain the original current signal or the original voltage signal, an error added with each intrinsic mode function component obtained after the empirical mode decomposition, and determine the intrinsic mode function component obtained after the current empirical mode decomposition as the target intrinsic mode function component if the error is less than or equal to a preset error threshold.

[0147] In one of the embodiments, the harmonic analysis module 620 is further configured to calculate a device checking parameter reference value of the power equipment after each superimposed harmonic current amplitude or harmonic voltage amplitude, and obtain the maximum harmonic current tolerance value or the maximum harmonic current tolerance value of the power equipment when the device checking parameter reference value exceeds a preset maximum allowable value of the device checking parameter.

[0148] As shown in Figure 7 In one of the embodiments, the device further includes a model training module 650 configured to obtain historical equipment parameters, historical real-time operation parameters and historical device checking parameter reference values, construct a training sample set based on the historical equipment parameters, the historical real-time operation parameters and the historical device checking parameter reference values, construct an initial harmonic tolerance capacity prediction model, the initial harmonic tolerance capacity prediction model including an input layer, a hidden layer and an output layer, the number of nodes of the hidden layer being determined by a trial method, and train the initial harmonic tolerance capacity prediction model based on the training sample set by using a Traincap training algorithm to obtain a trained harmonic tolerance capacity prediction model.

[0149] The above-mentioned modules of the power equipment harmonic tolerance capacity checking device can be realized by software, hardware and combinations thereof in whole or in part. The above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned modules.

[0150] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 8As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store device parameters, real-time running parameters and device calibration parameter prediction values and other data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with the terminal outside through network connection. The computer program is executed by the processor to realize a power equipment harmonic tolerance capability calibration method.

[0151] Those skilled in the art can understand that, Figure 8 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0152] In one of the embodiments, a computer device is provided, including a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the steps in the above-mentioned power equipment harmonic tolerance capability calibration method.

[0153] In one of the embodiments, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by the processor to realize the steps in the above-mentioned power equipment harmonic tolerance capability calibration method.

[0154] In one of the embodiments, a computer program product is provided, including a computer program, and the computer program is executed by the processor to realize the steps in the above-mentioned power equipment harmonic tolerance capability calibration method.

[0155] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0156] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0157] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0158] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method of checking harmonic withstand capability of a power equipment, characterized by, The method comprises: obtaining device parameters, device checking parameter values and real-time operation parameters of a power device, the real-time operation parameters comprising current values and voltage values, the device checking parameter values being device parameters required for checking harmonic tolerance of the power device; performing harmonic analysis on harmonic components in the current values or the voltage values to obtain maximum harmonic current tolerance values or maximum harmonic voltage tolerance values of the power device; calling a trained harmonic tolerance prediction model corresponding to the power device to perform device checking parameter prediction according to the maximum harmonic current tolerance values and the device parameters or the maximum harmonic voltage tolerance values and the device parameters, and obtain device checking parameter prediction values; obtaining a harmonic tolerance checking result of the power device according to the device checking parameter values and the device checking parameter prediction values; wherein the harmonic tolerance prediction model is trained based on historical device parameters and historical real-time operation parameters of the power device.

2. The method of claim 1, wherein, The harmonic analysis on the harmonic components in the current values or the voltage values to obtain the maximum harmonic current tolerance values or the maximum harmonic voltage tolerance values of the power device comprises: superimposing a noise signal on an original signal multiple times, and performing empirical mode decomposition on a target signal obtained after each superimposition until a target intrinsic mode function component is obtained, the original signal comprising an original current signal or an original voltage signal; performing Hilbert transform on the target intrinsic mode function component to obtain instantaneous characteristic quantities, the instantaneous characteristic quantities comprising harmonic current frequency spectrum and current amplitude or harmonic voltage frequency spectrum and voltage amplitude; superimposing harmonic current amplitude or harmonic voltage amplitude on a fundamental amplitude in the harmonic current frequency spectrum or the harmonic voltage frequency spectrum multiple times to obtain the maximum harmonic current tolerance values or the maximum harmonic voltage tolerance values of the power device.

3. The method of claim 2, wherein, The superimposing the noise signal on the original signal multiple times and performing the empirical mode decomposition on the target signal obtained after each superimposition until the target intrinsic mode function component is obtained comprises: superimposing a Gaussian white noise signal on an original current signal or an original voltage signal multiple times based on a zero mean principle of a Gaussian white noise spectrum, and performing empirical mode decomposition on a target signal obtained after each superimposition to obtain a corresponding intrinsic mode function component; screening a target intrinsic mode function component from the intrinsic mode function components.

4. The method of claim 3, wherein, The screening the target intrinsic mode function component from the intrinsic mode function components comprises: obtaining an error of a sum of the original signal and the intrinsic mode function component obtained after each round of empirical mode decomposition; if the error is less than or equal to a preset error threshold, determining the intrinsic mode function component obtained after the current round of empirical mode decomposition as the target intrinsic mode function component.

5. The method of claim 2, wherein, The superimposing the harmonic current amplitude or the harmonic voltage amplitude on the fundamental amplitude in the harmonic current frequency spectrum or the harmonic voltage frequency spectrum multiple times to obtain the maximum harmonic current tolerance values or the maximum harmonic voltage tolerance values of the power device comprises: calculating a device checking parameter reference value of the power device after each superimposition of the harmonic current amplitude or the harmonic voltage amplitude; When the device checking parameter reference value exceeds a preset maximum allowed value of the device checking parameter, the maximum harmonic current tolerance value or the maximum harmonic voltage tolerance value of the power device is obtained.

6. The method according to any one of claims 1 to 5, characterized in that, The harmonic tolerance capability prediction model is obtained based on the following manner: obtaining historical device parameters, historical real-time operation parameters and historical device checking parameter reference values; constructing a training sample set based on the historical device parameters, the historical real-time operation parameters and the historical device checking parameter reference values; constructing an initial harmonic tolerance capability prediction model, the initial harmonic tolerance capability prediction model comprising an input layer, a hidden layer and an output layer, the number of nodes of the hidden layer being determined by using a trial method; training the initial harmonic tolerance capability prediction model based on the training sample set by using a Traincap training algorithm to obtain a trained harmonic tolerance capability prediction model.

7. An electric power equipment harmonic withstand capability checking device, characterized by, The device comprises: a data acquisition module configured to acquire device parameters, device checking parameter values and real-time operation parameters of a power device, the real-time operation parameters comprising current values and voltage values, the device checking parameter values being device parameters required for checking harmonic tolerance capability of the power device; a harmonic analysis module configured to perform harmonic analysis on harmonic components in the current values or the voltage values to obtain maximum harmonic current tolerance values or maximum harmonic voltage tolerance values of the power device; a device checking parameter prediction module configured to call a trained harmonic tolerance capability prediction model corresponding to the power device to perform device checking parameter prediction according to the maximum harmonic current tolerance values and the device parameters or the maximum harmonic voltage tolerance values and the device parameters to obtain device checking parameter prediction values; a harmonic tolerance capability checking module configured to obtain a harmonic tolerance capability checking result of the power device according to the device checking parameter values and the device checking parameter prediction values. The harmonic tolerance capability prediction model is obtained based on historical device parameters and historical real-time operation parameters of the power device. 8.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-7. The processor implements the method of any one of claims 1 to 6 when executing the computer program.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the method of any one of claims 1 to 6 when executed by the processor.

10. A computer program product comprising a computer program, characterized in that, The computer program implements the method of any one of claims 1 to 6 when executed by the processor.

Images