Lightning stroke electromagnetic protection method and device based on prefabricated cabin transformer substation

Abstract

The invention discloses a lightning stroke electromagnetic protection method and device based on a prefabricated cabin transformer substation, which is applied to the technical field of power grid safety and protection, and comprises the following steps: constructing a simulation model of a target prefabricated cabin transformer substation; performing direct lightning simulation processing on the simulation model to obtain a lightning transient current value; carrying out discrete processing on the lightning stroke transient current value and the transmission line parameters to obtain electromagnetic field distribution data; performing space electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters; constructing a lightning stroke electromagnetic optimization model according to the to-be-optimized parameters, the lightning stroke electromagnetic optimization model being configured to process the lightning stroke electromagnetic optimization model according to a reinforcement learning algorithm, and obtaining optimal protection data output by the lightning stroke electromagnetic optimization model based on an improved whale algorithm; and executing a lightning electromagnetic protection scheme generated by the optimal protection data. According to the method provided by the embodiment of the invention, accurate lightning electromagnetic protection can be carried out on the prefabricated cabin transformer substation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid safety and protection, and particularly relates to a lightning electromagnetic protection method and device based on prefabricated cabin substations. BACKGROUND

[0002] With the development of power systems, prefabricated cabin substations are increasingly widely used in power grids.

[0003] In the prior art, compared with the cement building structure of traditional substations, urban prefabricated cabins adopt modular metal cabin bodies, and traditional lightning protection methods mainly rely on empirical formulas and fixed parameter settings, which are difficult to accurately analyze the electromagnetic field distribution characteristics of the closed cabin bodies, and the protection effect is limited, which seriously threatens the safe operation of prefabricated cabin substations.

[0004] Therefore, how to accurately protect prefabricated cabin substations from lightning electromagnetic protection has become a technical problem to be solved by those skilled in the art. SUMMARY

[0005] The present application provides a lightning electromagnetic protection method and device based on prefabricated cabin substations to solve the technical problem that traditional lightning protection methods are difficult to accurately analyze the electromagnetic field distribution characteristics of the closed cabin bodies, and to accurately protect prefabricated cabin substations from lightning electromagnetic protection.

[0006] To solve the above technical problems, the present application provides a lightning electromagnetic protection method based on prefabricated cabin substations, the method comprising:

[0007] Constructing a simulation model of a target prefabricated cabin substation;

[0008] Performing a direct lightning simulation process on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation;

[0009] Discretely processing the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation obtained by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data;

[0010] Performing spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters;

[0011] Constructing a lightning electromagnetic optimization model with the to-be-optimized parameters, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale optimization algorithm;

[0012] Executing a lightning electromagnetic protection scheme generated by the optimal protection data.

[0013] As one of the preferred solutions, the lightning simulation process is performed on the simulation model to obtain the lightning transient current value of the target prefabricated cabin substation, including:

[0014] The lightning simulation process is performed on the simulation model to obtain three-dimensional transient electromagnetic field data;

[0015] The three-dimensional transient electromagnetic field data is processed using a current feature extraction method to obtain the lightning transient current value of the target prefabricated cabin substation.

[0016] As one of the preferred solutions, the lightning transient current value and the transmission line parameters obtained from the target prefabricated cabin substation are discretely processed using a time-domain transmission line matrix method to obtain electromagnetic field distribution data, including:

[0017] The lightning transient current value is sequentially processed by time interpolation and voltage conversion to obtain an incident voltage pulse sequence;

[0018] The transmission line parameters are processed by spatial discrete mapping to obtain a node scattering matrix;

[0019] The incident voltage pulse sequence and the node scattering matrix are processed using a time-domain transmission line matrix method to obtain time-domain node voltage and current data;

[0020] The time-domain node voltage and current data are processed by electromagnetic field reconstruction to obtain the electromagnetic field distribution data.

[0021] As one of the preferred solutions, the electromagnetic field distribution data is processed by spatial electromagnetic field time-frequency domain response to obtain the to-be-optimized parameters, including:

[0022] The electromagnetic field distribution data is processed by time-frequency domain conversion to obtain frequency domain electromagnetic field response feature data;

[0023] The frequency domain electromagnetic field response feature data is processed by spatial feature clustering to obtain a feature response matrix;

[0024] The feature response matrix is processed by device coupling effect analysis to obtain device port induction parameters;

[0025] The device port induction parameters are processed by multi-parameter sensitivity analysis to obtain the to-be-optimized parameters.

[0026] As one of the preferred solutions, the to-be-optimized parameters are used to construct a lightning electromagnetic optimization model, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale algorithm, including:

[0027] The parameterized state space construction method is used to process the to-be-optimized parameters to construct the lightning electromagnetic optimization model.

[0028] The lightning electromagnetic optimization model is subjected to global search processing to obtain a candidate optimization parameter matrix.

[0029] The improved whale optimization algorithm is used to perform parameter optimization processing on the candidate optimization parameter matrix to obtain the optimal protection data.

[0030] As one of the preferred solutions, after the lightning electromagnetic optimization model is constructed by using the to-be-optimized parameters, the lightning electromagnetic protection method based on the prefabricated cabin substation further comprises the following steps of:

[0031] The sensitivity of the to-be-optimized parameters is analyzed, and the convergence of the lightning electromagnetic optimization model is calculated.

[0032] The lightning electromagnetic optimization model is optimized based on the convergence of the lightning electromagnetic optimization model.

[0033] As one of the preferred solutions, after the lightning electromagnetic protection scheme generated by the optimal protection data is executed, the lightning electromagnetic protection method based on the prefabricated cabin substation further comprises the following steps of:

[0034] The simulation model of the target prefabricated cabin substation is optimized based on the lightning electromagnetic protection scheme, and the target prefabricated cabin substation is constructed according to the optimized simulation model.

[0035] Another embodiment of the present application provides a lightning electromagnetic protection device based on a prefabricated cabin substation, which comprises:

[0036] A construction module is configured to construct a simulation model of a target prefabricated cabin substation.

[0037] A simulation module is configured to perform lightning simulation processing on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation.

[0038] A discretization module is configured to perform discretization processing on the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation obtained by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data.

[0039] A response module is configured to perform spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters.

[0040] The processing module is configured to construct a lightning electromagnetic optimization model based on the to-be-optimized parameter, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale optimization algorithm.

[0041] The execution module is configured to execute a lightning electromagnetic protection scheme generated by the optimal protection data.

[0042] Another embodiment of the present application provides a lightning electromagnetic protection device based on a prefabricated cabin substation, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the lightning electromagnetic protection method based on the prefabricated cabin substation as described above when executing the computer program.

[0043] Still another embodiment of the present application provides a computer readable storage medium storing a computer program, wherein the device where the computer readable storage medium is located implements the lightning electromagnetic protection method based on the prefabricated cabin substation as described above when executing the computer program.

[0044] Compared with the prior art, the beneficial effects of the embodiments of the present application are at least one of the following:

[0045] The present application constructs a simulation model of a target prefabricated cabin substation, performs a direct lightning simulation process on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation, performs discrete processing on the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation obtained by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data, performs spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters, constructs a lightning electromagnetic optimization model based on the to-be-optimized parameters, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale optimization algorithm, and execute a lightning electromagnetic protection scheme generated by the optimal protection data.

[0046] Compared with the prior art, the present application performs lightning simulation on the constructed simulation model to obtain lightning current data, obtains electromagnetic field data in the target prefabricated cabin substation in combination with the parameters of the target prefabricated cabin substation, locates electromagnetic weak points from the electromagnetic field data, determines an optimization target, i.e., to-be-optimized parameters, constructs a lightning electromagnetic optimization model based on a reinforcement learning algorithm, generates optimal protection parameters, and thus executes a lightning electromagnetic protection scheme generated by the optimal protection data, thereby accurately performing lightning electromagnetic protection on the prefabricated cabin substation and solving the technical problem that the traditional lightning protection method is difficult to accurately analyze the electromagnetic field distribution characteristics of the closed cabin body. Attached Figure Description

[0047] Figure 1 This is a flowchart illustrating a lightning electromagnetic protection method based on a prefabricated substation in one embodiment of the present invention.

[0048] Figure 2 This is a schematic diagram of the structure of a lightning electromagnetic protection device based on a prefabricated substation in one embodiment of the present invention.

[0049] Figure 3 This is a schematic diagram of the structure of a lightning electromagnetic protection device based on a prefabricated substation in one embodiment of the present invention.

[0050] Figure label:

[0051] Among them, 11 is the construction module; 12 is the simulation module; 13 is the discrete module; 14 is the response module; 15 is the processing module; 16 is the execution module; 21 is the processor; and 22 is the memory. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0053] In the description of this invention, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0054] Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0055] In the description of this invention, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0056] With the development of power system, prefabricated cabin substations are increasingly widely used in power grids. In the prior art, compared with the cement building structure of the traditional substation, the urban prefabricated cabin adopts a modular metal cabin body, and the traditional lightning protection method mainly relies on empirical formula and fixed parameter setting, which is difficult to accurately analyze the electromagnetic field distribution characteristics of the closed cabin body, and the protection effect is limited, which seriously threatens the safe operation of the prefabricated cabin substation.

[0057] Therefore, how to accurately perform lightning electromagnetic protection on the prefabricated cabin substation has become a technical problem to be solved by those skilled in the art.

[0058] To this end, an embodiment of the present application provides a lightning electromagnetic protection method based on a prefabricated cabin substation, and specifically, please refer to Figure 1 , Figure 1 Fig. 1 shows a flowchart of the lightning electromagnetic protection method based on the prefabricated cabin substation in one embodiment of the present application, and the method comprises the following steps:

[0059] S1: constructing a simulation model of a target prefabricated cabin substation;

[0060] S2: performing a direct lightning simulation process on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation;

[0061] S3: performing discrete processing on the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation obtained by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data;

[0062] S4: performing spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters;

[0063] S5: constructing a lightning electromagnetic optimization model based on the to-be-optimized parameters, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale optimization algorithm;

[0064] S6: executing a lightning electromagnetic protection scheme generated by the optimal protection data.

[0065] The simulation model of the target prefabricated cabin substation is constructed, specifically comprising:

[0066] Based on the SolidWorks three-dimensional modeling platform, a high-precision parameterized model containing the prefabricated cabin main structure, the ground net system and the soil environment is established, and is imported into the CST Studio Suite electromagnetic simulation environment.

[0067] The simulation model topological architecture comprises: a 110 kV GIS cabin, a transformer cabin (containing a radiator cabin), a double-layer cabin (the upper layer is a secondary equipment cabin and the lower layer is a 10 kV power distribution cabin), and the overall structural size is 36 m x 41 m. The grounding system adopts a composite ground net design, the horizontal grounding body is selected from 40 mm x 4 mm galvanized flat steel, the vertical grounding pole is selected from 40 mm x 40 mm x 4 mm galvanized angle steel, the length is 2.5 m, is uniformly arranged along the perimeter of the ground net at an interval of 5 m, and the ground net coverage range is 35 m x 40 m (grid density 5 m x 5 m).

[0068] The simulation model of the target prefabricated cabin substation comprises: a prefabricated cabin model, a site model, a ground net model and a soil model; wherein the prefabricated cabin model is used to simulate the flow of lightning current on its surface under the action of lightning to identify risk points; the site model can simulate the influence of the surrounding environment on the lightning current path and electromagnetic field distribution, including the electromagnetic shielding effect of the terrain and infrastructure; the ground net model helps to analyze the potential distribution and current dispersion of the grounding system, and ensures the reliability of the grounding system; the soil model considers the soil characteristics, simulates the current dispersion path and attenuation law of the lightning current in the soil, and reveals the ground potential rise problem; the multi-scale three-dimensional simulation model of the prefabricated cabin substation provides key data support for optimizing the grounding system design and reducing the lightning overvoltage risk.

[0069] Compared with the traditional reinforced structure of the civil substation, the three-dimensional model comprising the prefabricated cabin, the site, the ground net and the soil and other key parts can accurately reflect the actual geometric structure and layout of the substation, consider the mutual influence of the cabin body, the equipment and the ground net, provide an accurate geometric basis for electromagnetic field distribution calculation and subsequent simulation analysis, and ensure the authenticity of the simulation results.

[0070] In step S2, the simulation model is subjected to direct lightning simulation processing to obtain the lightning transient current value of the target prefabricated cabin substation, specifically including: the simulation model is subjected to direct lightning simulation processing to obtain three-dimensional transient electromagnetic field data; the three-dimensional transient electromagnetic field data is processed by using a current feature extraction method to obtain the lightning transient current value of the target prefabricated cabin substation.

[0071] The core target of this step is to quantify the key transient current generated when the direct lightning invades the prefabricated cabin substation, and the current is a core parameter for evaluating the degree of electromagnetic threat to the equipment and directly affects the design of the subsequent protection scheme.

[0072] Specifically, the lightning scenario is modeled, a typical direct lightning action point is set in the simulation software, and a current waveform conforming to the actual lightning characteristics is injected, in this embodiment, the excitation source is injected into the specified position of the cabin top through a discrete port, the path is set to conform to the IEC62305-1 standard, and a double exponential function waveform is used to represent the lightning transient characteristics.

[0073] The electromagnetic wave propagation process in space is simulated by an electromagnetic numerical algorithm. The electromagnetic numerical algorithm calculates electromagnetic field components of each point in the entire substation three-dimensional space at each time step, thereby obtaining a time series of three-dimensional electromagnetic field matrix data, i.e., electromagnetic field components of each coordinate point at time t. The electromagnetic numerical algorithm is preferably a FDTD time domain finite difference method or a FEM finite element method.

[0074] The obtained electromagnetic field data is converted into a current parameter that can directly describe the degree of lightning strike on a conductor. Specifically, the current can be extracted at a specific conductor path according to the Ampere loop law. It should be noted that the conductor path for monitoring the current needs to be determined, such as a lightning rod grounding down conductor, a device shell grounding wire, and a cable shielding layer. Then, a virtual integral loop is constructed around the selected conductor, and the magnetic field value at each time step is numerically integrated along the loop. The integral value represents the instantaneous current passing through the target prefabricated cabin substation.

[0075] The final obtained transient current value essentially describes the spatiotemporal distribution of lightning energy in the internal conductive path of the substation. Its effect is equivalent to a "digital lightning physical examination report" for the substation, which enables subsequent electromagnetic field calculation and protection scheme optimization to be based on quantifiable lightning threats.

[0076] In step S3, the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation are discretely processed by using a time domain transmission line matrix method to obtain electromagnetic field distribution data. Specifically, time interpolation and voltage conversion processing are sequentially performed on the lightning transient current value to obtain an incident voltage pulse sequence. Spatial discrete mapping processing is performed on the transmission line parameters to obtain a node scattering matrix. The incident voltage pulse sequence and the node scattering matrix are processed by using the time domain transmission line matrix method to obtain time domain node voltage and current data. Electromagnetic field reconstruction processing is performed on the time domain node voltage and current data to obtain the electromagnetic field distribution data.

[0077] It should be noted that the core objective of step S3 is to combine the lightning transient current and the substation structure parameters to calculate the transient electromagnetic field distribution in the three-dimensional space through numerical simulation, thereby revealing the spatial characteristics of the electromagnetic threat caused by lightning and providing field-level basis for protection design.

[0078] Time interpolation and voltage conversion processing are sequentially performed on the lightning transient current value to obtain an incident voltage pulse sequence.

[0079] Specifically, considering that the sampling interval of the lightning transient current does not meet the TLM time step requirement, the lightning transient current is resampled by cubic spline interpolation, and the current after resampling is converted into a voltage pulse based on the characteristic impedance of the transmission line, and the voltage represents an excitation wave incident on the transmission line network. It should be noted that the characteristic impedance of the transmission line is determined by the conductor parameters of the transmission line.

[0080] The transmission line parameters are subjected to spatial discrete mapping processing to obtain a node scattering matrix. This step is mainly a numerical calculation network for mapping the physical structure of the substation into a time-domain transmission line matrix method. The node scattering matrix describes the scattering relationship of the reflection / transmission rules of electromagnetic waves between nodes.

[0081] The incident voltage pulse sequence and the node scattering matrix are processed by using the time-domain transmission line matrix method to obtain time-domain node voltage and current data.

[0082] Specifically, this step simulates the propagation and interaction of electromagnetic waves in the substation. The core of the time-domain transmission line matrix method is to abstract the transmission line network into a grid composed of discrete nodes and transmission line units. In each time step, the incident voltage pulse starts from the source node and propagates along the transmission line to the adjacent node.

[0083] At each node, the incident voltage pulse is calculated according to the scattering matrix of the node. Part of the energy is reflected back to the original transmission line, and the other part of the energy is transmitted to the transmission line in other directions. Through iterative calculation of the voltage and current changes of all nodes in each time step, the node voltage and current distribution data of the entire transmission line network in the time domain are finally obtained, i.e., the electrical parameter responses at different times and different positions.

[0084] The voltage and current distribution on the transmission line is directly related to the surrounding electromagnetic field. Through the basic relationships in electromagnetic field theory, such as Ampere's law and Faraday's law, the time-domain node voltage and current data can be converted into the electromagnetic field intensity in space.

[0085] Specifically, the voltage corresponds to the line integral of the electric field, and the current corresponds to the loop integral of the magnetic field. Through interpolation or numerical integration methods, the electrical parameters of the discrete nodes are "reconstructed" into continuous spatial electromagnetic field distribution, so as to obtain the time and space distribution characteristics of the electromagnetic field in the substation during the lightning transient process.

[0086] This step essentially converts the lightning transient current and the transmission line parameters into calculable time-domain transmission line matrix parameters through discretization of time and space, and then obtains the time and space distribution of the electromagnetic field in the substation through scattering matrix iterative calculation and electromagnetic field reconstruction.

[0087] In step S4, the spatial electromagnetic field time-frequency domain response processing is performed on the electromagnetic field distribution data to obtain the to-be-optimized parameters, including: performing time-frequency domain conversion processing on the electromagnetic field distribution data to obtain frequency domain electromagnetic field response feature data; performing spatial feature clustering processing on the frequency domain electromagnetic field response feature data to obtain a feature response matrix; performing device coupling effect analysis processing on the feature response matrix to obtain device port induction parameters; and performing multi-parameter sensitivity analysis processing on the device port induction parameters to obtain the to-be-optimized parameters.

[0088] Specifically, the electromagnetic field generated by lightning appears as a rapidly changing pulse signal in the time domain, such as a nanosecond transient process, and contains rich frequency components. The time domain electromagnetic field data is decomposed into an amplitude-frequency relationship in the frequency domain through time-frequency conversion methods such as Fourier transform or short-time Fourier transform. The core of this step is to reveal the distribution characteristics of electromagnetic field energy at different frequencies: high-frequency components are usually related to spatial radiation and rapid changes of electromagnetic waves, and low-frequency components are related to long-distance transmission or static field effects.

[0089] The frequency domain characteristics of electromagnetic fields at different positions in the substation space may differ, such as stronger high-frequency components near the lightning strike point and higher low-frequency proportion in the remote area. Spatial grouping of frequency domain data is performed through clustering algorithms such as K-means and DBSCAN, and regions with similar electromagnetic field responses are divided into the same class.

[0090] Each cluster corresponds to a set of feature response parameters, and finally forms a feature response matrix whose element value is the electromagnetic field intensity or energy distribution of the region at a specific frequency, realizing dimension reduction and abstraction of complex spatial frequency characteristics.

[0091] The feature response parameters at least include dominant frequency, energy peak frequency, and frequency bandwidth.

[0092] Based on the feature response matrix, the induction parameters of the device port are calculated through an electromagnetic field coupling model combined with the physical position and structure of the device. The induction parameters of the device end are affected by multiple factors, such as electromagnetic field intensity, frequency, protection device parameters (such as arrester residual voltage and filter cutoff frequency), and device installation position.

[0093] Through a sensitivity analysis method, the influence degree of each factor on the induction parameters of the device is quantified, and parameters that significantly affect the induction of the device are screened out and defined as to-be-optimized parameters. Adjustment of these parameters can effectively reduce the induction interference of the device end and become input variables of the subsequent optimization model.

[0094] Preferably, the sensitivity analysis method adopts a local sensitivity analysis method.

[0095] The pre-step (time domain transmission line matrix discrete processing) obtains the space-time distribution "phenomenon" of electromagnetic field, and the time-frequency domain processing further reveals the "essence". Specifically, the frequency domain conversion decomposes the wide frequency electromagnetic pulse into different frequency components, facilitating the analysis of the interference mechanism of each frequency band; the characteristic clustering and coupling analysis directly associates the spatial electromagnetic field characteristics and the device response, and determines which frequency components in which region will affect which devices.

[0096] Meanwhile, the essence of the to-be-optimized parameter is a "key controllable variable affecting the lightning strike sensitivity of the device".

[0097] In this step, the frequency characteristics of the electromagnetic field are analyzed and decomposed through the time-frequency domain analysis, the key interference source and sensitive device are located through the clustering and coupling model, and finally the adjustable protection parameter is screened through the sensitivity analysis.

[0098] In step S5, a lightning electromagnetic optimization model is constructed based on the to-be-optimized parameter, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale algorithm. Specifically, the to-be-optimized parameter is processed based on a parameterized state space construction method to construct the lightning electromagnetic optimization model; the lightning electromagnetic optimization model is globally searched to obtain a candidate optimization parameter matrix; and the candidate optimization parameter matrix is optimized based on the improved whale algorithm to obtain the optimal protection data.

[0099] Specifically, the to-be-optimized parameter is defined as a state variable of the model, and a value range is set for each variable; meanwhile, an action space and a reward function are defined in combination with a reinforcement learning framework; the protection parameter at the physical level is converted into a "state-action-reward" three-tuple at the mathematical level to form an optimization model that can be solved by an algorithm, i.e., a lightning electromagnetic optimization model. The reinforcement learning defines the protection target through the reward function, so that the algorithm focuses on the optimization direction with actual physical meaning and avoids blind search.

[0100] The state represents the current protection parameter combination, the action represents the parameter adjustment mode, the reward represents the improvement degree of the lightning strike resistance of the device after adjustment, and the essence of the lightning electromagnetic optimization model is to find the parameter combination that maximizes the cumulative reward.

[0101] Since there may be multiple local optimal solutions in the lightning electromagnetic protection parameter space, such as a certain group of parameters reducing the interference of device A while increasing the interference of device B, it is necessary to first cover the main area of the parameter space through global search to avoid falling into local optimization.

[0102] The random sampling, Latin hypercube sampling and other methods are used to generate multiple groups of candidate parameter combinations in the parameter value range, each group of parameters corresponds to a protection scheme, and a candidate optimization parameter matrix is formed. Each row of the matrix represents a group of parameter combinations, and each column corresponds to a parameter to be optimized.

[0103] The improved whale algorithm is used for parameter optimization processing on the candidate optimization parameter matrix to obtain the optimal protection data.

[0104] The basic principle of the whale algorithm is to simulate the hunting behavior of a humpback whale, and the optimal solution is iteratively searched in the parameter space through operators such as “surrounding prey”, “spiral bubble net attack” and “random search”. The standard whale algorithm is easy to fall into local optimization in complex space, and the convergence speed is unstable.

[0105] Compared with the standard whale algorithm, the improved whale algorithm introduces an adaptive inertia weight, combines an elite reservation mechanism and incorporates a mutation operator. The search step can be dynamically adjusted according to the number of iterations, the global exploration ability is enhanced in the early stage, the local optimization is focused in the later stage, the historical optimal solution is recorded and the population evolution is guided, the loss of high-quality solutions is avoided, and random disturbance is added to the local search results to jump out of the local optimal trap.

[0106] Therefore, the candidate parameter matrix is taken as the initial population, and the improved whale algorithm is iteratively calculated. In each iteration, the advantages and disadvantages of each group of parameters are evaluated according to the reward function, and the inferior solutions are gradually eliminated and the high-quality solutions are evolved. Finally, the optimal parameter combination that minimizes the device induced interference is output, that is, the optimal protection data.

[0107] In this step, the physical problem is converted into a mathematical model by parameterizing the state space, candidate schemes are generated by global search, and the optimal solution that takes into account the protection effect, economy and feasibility is selected from a large number of parameter combinations by the efficient optimization ability of the improved whale algorithm.

[0108] The lightning electromagnetic protection scheme generated by the optimal protection data is executed.

[0109] After the lightning electromagnetic optimization model is constructed with the parameters to be optimized, the lightning electromagnetic protection method based on the prefabricated cabin substation further includes:

[0110] The sensitivity of the parameters to be optimized is analyzed, and the convergence of the lightning electromagnetic optimization model is calculated.

[0111] Based on the convergence of the lightning electromagnetic optimization model, the lightning electromagnetic optimization model is optimized.

[0112] The influence degree of the parameters to be optimized on the lightning electromagnetic protection effect is quantified, and the most sensitive parameter to the optimization target is identified to provide priority basis for subsequent model optimization.

[0113] The purpose of the convergence calculation is to verify whether the optimization algorithm such as the improved whale optimization algorithm is stably convergent to a global optimal solution, and to avoid optimization failure caused by algorithm precocity or oscillation.

[0114] After performing the lightning electromagnetic protection scheme generated by the optimal protection data, the lightning electromagnetic protection method based on the prefabricated cabin substation further comprises:

[0115] Based on the lightning electromagnetic protection scheme, the simulation model of the target prefabricated cabin substation is optimized, and the target prefabricated cabin substation is constructed according to the optimized simulation model.

[0116] In one embodiment, as Figure 2 shown, the embodiment of the present application provides a lightning electromagnetic protection device based on a prefabricated cabin substation, which comprises:

[0117] A construction module 11 is configured to construct a simulation model of a target prefabricated cabin substation;

[0118] A simulation module 12 is configured to perform a direct lightning simulation process on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation;

[0119] A discretization module 13 is configured to perform discretization processing on the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation obtained by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data;

[0120] A response module 14 is configured to perform spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters;

[0121] A processing module 15 is configured to construct a lightning electromagnetic optimization model with the to-be-optimized parameters, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale optimization algorithm;

[0122] An execution module 16 is configured to perform a lightning electromagnetic protection scheme generated by the optimal protection data.

[0123] Referring to Figure 3 , which is a structural schematic diagram of the lightning electromagnetic protection device based on a prefabricated cabin substation provided by the embodiment of the present application, the lightning electromagnetic protection device based on a prefabricated cabin substation 20 provided by the embodiment of the present application comprises a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21, and the processor 21 implements the steps in the above lightning electromagnetic protection method based on a prefabricated cabin substation embodiment when executing the computer program, for example Figure 1The processor 21 performs the steps S1-S6 described above; or, the processor 21 implements the functions of each module in the above-mentioned device embodiments when executing the computer program, for example, the constructing module 11.

[0124] For example, the computer program can be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the lightning electromagnetic protection equipment 20 based on prefabricated cabin substation. For example, the computer program can be divided into a constructing module 11, a simulation module 12, a discrete module 13, and the like, and the specific functions of each module are as follows:

[0125] The constructing module 11 is configured to construct a simulation model of a target prefabricated cabin substation.

[0126] The simulation module 12 is configured to perform a lightning direct strike simulation process on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation.

[0127] The discrete module 13 is configured to perform a discrete process on the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation obtained by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data.

[0128] The response module 14 is configured to perform a spatial electromagnetic field time-frequency domain response process on the electromagnetic field distribution data to obtain a to-be-optimized parameter.

[0129] The processing module 15 is configured to construct a lightning electromagnetic optimization model with the to-be-optimized parameter, wherein the lightning electromagnetic optimization model is configured to be processed according to a reinforcement learning algorithm, and optimal protection data output by the lightning electromagnetic optimization model is obtained based on an improved whale optimization algorithm.

[0130] The execution module 16 is configured to execute a lightning electromagnetic protection scheme generated by the optimal protection data. The lightning electromagnetic protection equipment 20 based on the prefabricated cabin substation can include, but is not limited to, the processor 21, the memory 22. Those skilled in the art can understand that the schematic diagram is only an example of the lightning electromagnetic protection equipment 20 based on the prefabricated cabin substation, and does not constitute a limitation on the lightning electromagnetic protection equipment 20 based on the prefabricated cabin substation, and can include more or fewer components than the diagram, or combine certain components, or different components, for example, the lightning electromagnetic protection equipment 20 based on the prefabricated cabin substation can also include an input / output device, a network access device, a bus, and the like.

[0131] The processor 21 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor. The processor 21 is a control center of the lightning electromagnetic protection equipment 20 based on the prefabricated cabin substation, and is connected with various parts of the lightning electromagnetic protection equipment 20 based on the prefabricated cabin substation through various interfaces and lines.

[0132] The memory 22 can be used to store computer programs and / or modules. The processor 21 realizes various functions of the lightning electromagnetic protection equipment 20 based on the prefabricated cabin substation by running or executing the computer programs and / or modules stored in the memory 22, and calling data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program required for a function (such as a sound playing function, an image playing function, etc.), etc. The data storage area can store data created according to use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a nonvolatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory device.

[0133] If the modules integrated in the lightning electromagnetic protection equipment 20 based on prefabricated cabin substation are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can include any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0134] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned various method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0135] Correspondingly, the embodiment of the present application provides a computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located executes the steps in the lightning electromagnetic protection method based on prefabricated cabin substation of the above-mentioned embodiment, such as the steps S1-S6 in the method described in the above-mentioned embodiment. Figure 1

[0136] Compared with the prior art, the embodiment of the present application has at least one of the following advantages:

[0137] ​The application constructs a simulation model of a target prefabricated cabin substation, performs lightning direct stroke simulation processing on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation, performs discrete processing on the lightning transient current value and obtained transmission line parameters of the target prefabricated cabin substation by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data, performs spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters, constructs a lightning electromagnetic optimization model with the to-be-optimized parameters, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale optimization algorithm, and executes a lightning electromagnetic protection scheme generated by the optimal protection data.

[0138] Compared with the prior art, the simulation model constructed is subjected to lightning simulation to obtain lightning current data, the electromagnetic field data in the target prefabricated cabin substation is obtained in combination with the parameters of the target prefabricated cabin substation, the electromagnetic weak point is located from the electromagnetic field data, the optimization target, i.e., the to-be-optimized parameter, is determined, the lightning electromagnetic optimization model of the reinforcement learning algorithm is constructed again, the optimal protection parameter is generated, and thus the lightning electromagnetic protection scheme generated by the optimal protection data is executed, thereby realizing precise lightning electromagnetic protection of the prefabricated cabin substation and solving the technical problem that the traditional lightning protection method is difficult to precisely analyze the electromagnetic field distribution characteristics of the closed cabin body.

[0139] The above-described embodiments only express several embodiments of the application, which are described in detail and specifically, but should not be understood as a limitation on the patent scope of the application. It should be noted that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the application, and these all belong to the protection scope of the application. Therefore, the patent protection scope of the application should be subject to the appended claims.

Claims

1. A lightning electromagnetic protection method for a prefabricated cabin substation, characterized in that, The application relates to a lightning electromagnetic protection method for a prefabricated cabin substation. The method comprises the following steps: constructing a simulation model of a target prefabricated cabin substation; performing a direct lightning simulation process on the simulation model to obtain a lightning transient current value of the target prefabricated cabin substation; discretely processing the lightning transient current value and transmission line parameters of the target prefabricated cabin substation obtained by using a time-domain transmission line matrix method to obtain electromagnetic field distribution data; performing spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters; constructing a lightning electromagnetic optimization model by using the to-be-optimized parameters, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale algorithm; 2. The lightning electromagnetic protection method for a prefabricated cabin substation based power station as claimed in claim 1, wherein, executing a lightning electromagnetic protection scheme generated by the optimal protection data. The method comprises the following steps: performing a direct lightning simulation process on the simulation model to obtain three-dimensional transient electromagnetic field data; 3. The lightning electromagnetic protection method for a prefabricated cabin substation based power station as claimed in claim 1, wherein, processing the three-dimensional transient electromagnetic field data by using a current feature extraction method to obtain the lightning transient current value of the target prefabricated cabin substation. The method comprises the following steps: sequentially performing time interpolation and voltage conversion processing on the lightning transient current value to obtain an incident voltage pulse sequence; performing spatial discrete mapping processing on the transmission line parameters to obtain a node scattering matrix; processing the incident voltage pulse sequence and the node scattering matrix by using a time-domain transmission line matrix method to obtain time-domain node voltage and current data; 4. The lightning electromagnetic protection method for a prefabricated cabin substation based power station as claimed in claim 1, wherein, performing electromagnetic field reconstruction processing on the time-domain node voltage and current data to obtain the electromagnetic field distribution data. The method comprises the following steps: performing time-frequency domain conversion processing on the electromagnetic field distribution data to obtain frequency domain electromagnetic field response feature data; performing spatial feature clustering processing on the frequency domain electromagnetic field response feature data to obtain a feature response matrix; performing device coupling effect analysis processing on the feature response matrix to obtain device port induction parameters; 5. The lightning electromagnetic protection method for a prefabricated cabin substation based power station as claimed in claim 1, wherein, performing multi-parameter sensitivity analysis processing on the device port induction parameters to obtain the to-be-optimized parameters. The method comprises the following steps: processing the to-be-optimized parameters based on a parameterized state space construction method to construct the lightning electromagnetic optimization model; performing global search processing on the lightning electromagnetic optimization model to obtain a candidate optimization parameter matrix; performing parameter optimization processing on the candidate optimization parameter matrix based on the improved whale algorithm to obtain the optimal protection data.

6. The lightning electromagnetic protection method for a prefabricated cabin substation based power station as claimed in claim 1, wherein, After the lightning electromagnetic optimization model is constructed based on the to-be-optimized parameter, the lightning electromagnetic protection method based on the prefabricated cabin substation further comprises: Performing sensitivity analysis on the to-be-optimized parameter, and calculating the convergence of the lightning electromagnetic optimization model; Based on the convergence of the lightning electromagnetic optimization model, the lightning electromagnetic optimization model is optimized.

7. The lightning electromagnetic protection method for a prefabricated cabin substation based power station as claimed in claim 1, wherein, After the lightning electromagnetic protection scheme generated by the optimal protection data is executed, the lightning electromagnetic protection method based on the prefabricated cabin substation further comprises: Based on the lightning electromagnetic protection scheme, the simulation model of the target prefabricated cabin substation is optimized, and the target prefabricated cabin substation is constructed according to the optimized simulation model.

8. A lightning electromagnetic protection device for a prefabricated cabin substation, characterized by Comprise: The construction module is used for constructing the simulation model of the target prefabricated cabin substation; The simulation module is used for performing lightning simulation processing on the simulation model to obtain the lightning transient current value of the target prefabricated cabin substation; The discrete module is used for performing discrete processing on the lightning transient current value and the transmission line parameters of the target prefabricated cabin substation obtained by using the time domain transmission line matrix method to obtain electromagnetic field distribution data; The response module is used for performing spatial electromagnetic field time-frequency domain response processing on the electromagnetic field distribution data to obtain to-be-optimized parameters; The processing module is used for constructing a lightning electromagnetic optimization model based on the to-be-optimized parameters, wherein the lightning electromagnetic optimization model is configured to process the lightning electromagnetic optimization model according to a reinforcement learning algorithm, and obtain optimal protection data output by the lightning electromagnetic optimization model based on an improved whale optimization algorithm; The execution module is used for executing the lightning electromagnetic protection scheme generated by the optimal protection data.

9. Lightning electromagnetic protection equipment for a prefabricated cabin substation, characterised in that, The computer readable storage medium stores a computer program, wherein the device where the computer readable storage medium is located executes the computer program, and the lightning electromagnetic protection method based on the prefabricated cabin substation as claimed in any one of claims 1 to 7 is realized.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein the device where the computer readable storage medium is located executes the computer program, and the lightning electromagnetic protection method based on the prefabricated cabin substation as claimed in any one of claims 1 to 7 is realized.

Images