379 results about "Initial sample" patented technology

The invention discloses a wind field rapid prediction method and system based on optimized Latin hypercube sampling and POD-BPNN, and the method comprises the steps: carrying out Latin hypercube sampling to generate an initial sample point set, introducing a sensitivity weight, and carrying out the iterative optimization of sample distribution through a greedy strategy; assembling the CFD numerical simulation flow field data of all sample points in the sample point set into a flow field snapshot matrix, and determining a dynamic multi-target truncation order and a corresponding POD mode and coefficient; building and training a BPNN model, packaging the trained BPNN model, the POD modal matrix, the mean field and the flow field reconstruction logic into an FMU module, obtaining the FMU module which can be called in a cross-platform manner, and achieving the real-time prediction of a wind field. The invention relates to the technical field of wind field prediction, significantly improves the precision and calculation efficiency of wind field prediction, and provides an efficient and accurate solution for the rapid prediction of a wind field.

The invention discloses a post-pumping air tank robustness collaborative design method considering hydraulic parameter time-varying characteristics, which comprises the following steps: defining a hydraulic parameter uncertainty fluctuation interval of a water delivery system in a full life cycle, and setting a body structure decision variable range of a post-pumping air tank; performing combined sampling in the water conservancy parameter uncertainty fluctuation interval and the body structure decision variable range by using a test design method to generate an initial sample set; performing steady-state and transient-state coupling simulation on the initial sample set, constructing a constant-flow operation condition of the water delivery system by using a hydraulic equation, updating a water pump working point and pipeline pressure distribution, performing transient simulation by using a characteristic line method to obtain a hydraulic response index, and training to obtain a water hammer response agent model; constructing a robustness optimization objective function based on failure probability constraint; and performing global optimization on the target function by using an intelligent optimization algorithm, calling the water hammer response agent model to perform random simulation, evaluating a failure probability, and outputting a target design scheme.

The invention provides a structure reliability analysis method based on an adaptive variable fidelity model, and the method comprises the steps: generating an initial sample point set which is uniformly distributed and has representativeness through an improved random sampling method KMODMC, enabling the initial sample point set to comprise a low-fidelity sample set and a high-fidelity sample set, training a BP neural network through employing the low-fidelity sample set, and carrying out the training of the BP neural network through employing the high-fidelity sample set; a low-fidelity BP neural network model is obtained; meanwhile, based on an error training Kriging model of a high-fidelity sample set and a low-fidelity model predicted value, an error correction Kriging model is constructed, the low-fidelity BP neural network model and the error correction Kriging model are combined to form a multi-fidelity mixed agent model, and adaptive iterative optimization is performed through a double-model alternate point adding sampling strategy. And finally obtaining a high-precision multi-fidelity hybrid agent model for structural reliability evaluation. According to the method, the problems of high cost of high-fidelity simulation calculation and insufficient precision of a low-fidelity model are solved, and the adaptive capacity and prediction precision of the model in a complex nonlinear problem are effectively improved.

The invention discloses a variant reconstruction AUV (Autonomous Underwater Vehicle) shape optimization method based on proxy-assisted multi-starting-point space reduction. The variant reconstruction AUV shape optimization method comprises the following steps: establishing a parameterized model of a variant reconstruction AUV; constructing a variant reconstruction AUV shape modeling-grid division-performance simulation automation framework, realizing input of design variables, and automatically performing variant reconstruction AUV shape modeling and watershed grid division; a variant reconstruction AUV shape hydrodynamic force simulation calculation framework is built, and assessment of variant reconstruction AUV hydrodynamic force performance is achieved; generating a plurality of groups of initial samples for a design space of design variables, calculating target function values corresponding to the samples by utilizing the simulation automation framework and the simulation calculation framework, and importing the samples and corresponding sailing resistance into a sample library; and performing optimization in the design space of the design variables by utilizing an agent-assisted multi-starting-point space reduction method to obtain an optimal solution of the variant reconstruction AUV shape design problem. According to the method, the reliability of an optimization result and the design efficiency can be improved, and the optimization time is shortened.

The invention discloses a proxy model auxiliary evolution method based on two-stage adaptive switching and Voronoi niche. The method comprises the steps of generating an initial sample by adopting optimal Latin hypercube sampling, obtaining a real fitness value through simulation, constructing an initial training data set, and setting an initial iteration counter k and an evaluation budget threshold value; training a proxy model based on the current data set, and executing evolutionary algorithm optimization by using the proxy model to obtain a current optimal individual; judging two stages according to an iteration counter k and a distance threshold value; the development execution stage comprises the following steps: evaluating the real fitness and updating a data set; the exploration execution stage comprises the steps of multi-modal approximate detection, Voronoi niche division, multi-modal collaborative search, real fitness evaluation and data set updating; judging a termination condition and outputting a result; according to the method, three core technologies of an adaptive stage switching mechanism, multi-modal approximate detection and Voronoi niche division and multi-extremum collaborative filling are creatively integrated, so that the defects of insufficient global exploration, low local development precision and poor convergence efficiency of a traditional method in a high-dimensional multi-modal expensive optimization problem are effectively overcome; and the solving efficiency and reliability of a complex and expensive optimization problem are remarkably improved.

Active machine learning systems for anomalous event detection and classification. Initial samples from an industrial environment may be received and labeled. Initially, a training pool of audio samples may be labeled. These labeled samples may be used to train an audio event classifier to detect and categorize sounds. Environment states may be calculated using outputs from the classifier. A batch of audio samples may then selected from an unlabeled pool for annotation, guided by a reinforcement learning agent. These selected samples may be annotated and added to the labeled training pool. The classifier may be retrained with this updated pool. Rewards may be calculated for each of the annotated samples based on their annotations. The environment states may be updated using the retrained classifier, and the exploration-exploitation parameter of the reinforcement learning agent may be adjusted. The reinforcement learning agent may be retrained using the updated environment states and rewards.

The invention discloses a depth map super-resolution method based on blind degradation. The method comprises the following steps: forming an initial RGB-D sample pair by using a high-resolution RGB image and a corresponding high-resolution synthetic depth map; screening out a high-quality RGB-D sample pair from the initial RGB-D sample pair; inputting the high-quality RGB-D sample pair into a learnable degradation network, converting the high-quality RGB-D sample pair into a low-resolution training sample, and constructing an RGB-D training data set by using the low-resolution training sample and the high-resolution RGB image corresponding to the low-resolution training sample; using the RGB-D training data set to train the multi-modal super-resolution reconstruction network to obtain a depth map super-resolution model; inputting the low-resolution depth map and the corresponding high-resolution RGB image into a depth map super-resolution model to output a high-resolution depth map; the method solves the problems that an existing depth map super-resolution method mostly depends on a fixed degradation hypothesis, a real sensor and complex degradation distribution of compression transmission are ignored, and accordingly generalization ability is insufficient, edges are fuzzy and artifacts are increased in an actual scene.

The invention discloses a visual identification method and system fusing a large model and a visual model, a medium and a product, and relates to the technical field of visual identification. The method comprises the steps of obtaining a preset number of initial sample images of a target recognition category, inputting the initial sample images into a target multi-modal large model, generating fine-grained structured text description corresponding to each initial sample image, and constructing an enhanced data set; training by using the enhanced data set to obtain a target visual model; and in response to a received new input image, obtaining a first category probability distribution output by the target visual model and a second category probability distribution output by the target multi-modal large model based on semantic similarity matching in parallel, and determining a final recognition result according to the first category probability distribution and the second category probability distribution. By implementing the technical scheme, the recognition precision in a special visual recognition scene can be improved in an unstructured visual recognition scene with few samples.

The invention discloses an adaptive fidelity model scheduling method and system for circuit parameter optimization. The method comprises the following steps: selecting initial sample points to train a multi-precision agent model cluster; according to the parameter distribution characteristics of the to-be-evaluated individual, determining an adaptive target agent model from the multi-precision agent model cluster to perform performance evaluation on the to-be-evaluated individual; based on the evaluation error of the target agent model and the convergence state of the optimization process, judging whether a trigger threshold value of the high-precision circuit simulator is reached or not; if the triggering threshold value is reached, calling a high-precision circuit simulator to carry out performance verification on the to-be-evaluated individual, and obtaining generated verification data; and if the triggering threshold is not reached, obtaining an evaluation result output by the target agent model. According to the method, calling of a high-precision simulator is reduced from each individual to a key individual, conversion from whole-process high-precision to on-demand high-precision dynamic adaptation is achieved, and the large-scale circuit multi-target parameter optimization requirement under the advanced technology can be met.

The invention provides an efficient and high-precision prediction method for the minimum failure probability of an aviation structure system based on an exponential penalty learning mechanism, and relates to the technical field of structural reliability analysis. Respectively generating an initial sample and a candidate sample according to the probability density function of the random variable of the performance function to be analyzed; real performance function responses corresponding to the initial samples are calculated to form an initial training sample set, and an initial Kriging agent model is constructed; selecting an optimal sample point from the candidate sample set through the proposed EPAL function; merging the optimal sample and the real response thereof into the initial training sample set, and iteratively updating the Kriging model until an error-based stopping criterion is met; judging whether the failure probability variation coefficient meets the requirement or not; and finally, calculating the failure probability of the structure based on a trained Kriging model and a Monte Carlo method.

The invention discloses a time-space multi-scale feature fusion deep learning landslide susceptibility evaluation method based on number object dual drive, and the method comprises the steps: constructing a time sequence branch + Swindow-Transformer (upper branch) + CNN (lower branch) time-space fusion DL-LSA model, combining an AFF multi-scale space fusion module and a TSF time-space fusion module, and carrying out the deep learning of landslide susceptibility. A complete technical scheme of high-quality sample screening, deep spatial-temporal feature extraction, multi-scale adaptive fusion and dynamic probability prediction is formed, and normal form upgrading of geological disaster risk management from single-drive vector object double-drive and from static evaluation to dynamic early warning is promoted. Comprising the following steps: 1, acquiring influence factors (X); 2, constructing an initial sample set (X-Y pairs); 3, preprocessing the influence factor (X); and 4, influence factor coding (generating a standardized feature X '). And 5, providing physical constraints (optimizing a sample set X '-Y) based on the P-LSA model. And 6, constructing a space-time fusion DL-LSA model. And 7, designing a feature fusion module. And 8, outputting a landslide susceptibility evaluation result.

The invention discloses a data label calibration method based on a graph neural network and confidence reasoning, and the method comprises the steps: S1, collecting sample data to form an initial sample set, and constructing a label structure chart; s2, structural feature coding is executed on each node in the label structure chart through an improved Grapher network, and a node embedding vector is generated; s3, constructing a double-domain confidence scoring network, jointly evaluating a node embedding vector, and outputting a label confidence score; s4, establishing a confidence-density combined screening strategy, and generating a to-be-calibrated node set; s5, based on the to-be-calibrated node set, generating a calibration label set by adopting a similarity voting mechanism; s6, performing label consistency comparison and updating processing on the calibration label set and the initial sample set, and outputting a label calibration graph; and S7, constructing an end-to-end training process, and jointly optimizing the improved Grapher network and the double-domain confidence scoring network. According to the method, the label correction precision, the structure perception capability and the calibration robustness are improved.

The invention discloses a sparse magnetic field data reconstruction method, system and device and a storage medium, and relates to the technical field of magnetic field imaging and neural network image processing, and the method comprises the steps: obtaining initial sampling sparse magnetic field data of a target detection region through a data collection part; inputting the initial sampling sparse magnetic field data into a sampling strategy part, generating a sampling probability distribution diagram, and obtaining active sampling sparse magnetic field data according to the sampling probability distribution diagram; inputting the active sampling sparse magnetic field data and the initial sampling sparse magnetic field data into a space superposition part to obtain final sampling sparse magnetic field data; and inputting the final sampling sparse magnetic field data into a sparse data reconstruction module, and outputting high-resolution reconstruction magnetic field data. The method provided by the invention achieves better effects in the aspects of improving the sampling efficiency, optimizing the reconstruction quality, reducing redundant data and enhancing the reconstruction stability.

Disclosed is a theoretical model constraint and data-driven fusion-based micro-seismic quantitative prediction method, comprising: 1, obtaining original micro-seismic data of a coal mine working face to form an initial sample data set; 2, performing data preprocessing, and dividing into a training set and a test set; 3, constructing a long short-term memory (LSTM) model; 4, sampling historical micro-seismic data for a micro-seismic event quantitative prediction sample; 5, constructing a multi-objective optimization model containing seven sub-objective functions: a micro-seismic time fractal dimension, a micro-seismic space fractal dimension, a micro-seismic energy fractal dimension, a micro-seismic prediction total energy, a micro-seismic reconstruction mining stress, a micro-seismic activity process and a micro-seismic energy-frequency power law b value; and 6, finding an optimal sampling sample to act as a prediction value. By means of the described steps, the present invention achieves theoretical model constraint and data-driven fusion-based micro-seismic event quantitative prediction. The prediction effect is good, and the prediction result can effectively guide on-site production activity process control and implement pressure relief measures and disaster early warning.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a task processing method and device based on meta-learning, equipment and a medium. And constructing a meta-training task set based on the category balance sample set, training the basic model to obtain model initialization parameters, obtaining a support set of the target task, adjusting the basic model by using the support set to obtain a target task model, and processing a query set of the target task by using the target task model to generate a target processing result. According to the method, the meta-training tasks are constructed on the class balance sample set and trained, so that the basic model obtains the initialization parameters with high generalization, and the initialization parameters can adapt to new tasks and complete query set identification after being quickly adjusted in combination with the support set of the target task, so that the problems of insufficient generalization and low adaptation efficiency under the condition of few samples are solved; and the identification accuracy and efficiency are improved.

The invention discloses a turbine blade anti-sinking cooling collaborative optimization method based on a proxy model and a genetic algorithm, and the method comprises the steps: firstly constructing an initial sample library through Latin hypercube sampling, building an initial neural network proxy model of a deposition rate, a heat exchange coefficient and a flow resistance coefficient, and then driving a multi-target genetic algorithm to carry out global optimization; in the anti-sinking cooling collaborative optimization process, a Pareto non-dominated solution generated in the middle and later periods of genetic algorithm iteration is selectively fed back to a training sample so as to enhance the prediction precision of an agent model in a key area, and a new round of iterative optimization is triggered. And continuously improving the quality of the solutions and the reliability of the model through the closed-loop iteration mechanism, and finally reordering based on comprehensive evaluation of all Pareto solution sets to determine an optimal anti-sinking cooling structure scheme. According to the invention, the efficient and high-precision automatic design of the anti-sinking cooling structure of the blade is realized.

The invention discloses a forward development and optimization design method for an engine liquid fuel atomization system, and relates to the field of optimization of a spray combustion system.The forward development and optimization design method comprises the steps that a numerical simulation method is adopted to conduct spray simulation, and high-precision transient three-dimensional spray characteristics are calculated; sampling by using a scrambling Holton sampling method, and constructing an initial sample library; constructing an agent model and training to obtain a low-precision agent model; performing multi-objective optimization by using an NSGA-II genetic algorithm based on the model to obtain a Pareto frontier solution; adopting K-means clustering to classify Pareto frontier solutions, select a finite solution set and calculate prediction and simulation errors, if requirements are met, outputting a high-precision proxy model, otherwise, screening potential optimal sample points based on an expected improvement function, and adding the potential optimal sample points into a sample library for retraining; and on the basis of the high-precision agent model, according to the optimization target, structure parameters and injection parameters are reversely deduced. By comprehensively adjusting the structure and working condition parameters, the mixing quality of fuel and air is remarkably improved, the combustion efficiency is improved, and emission is reduced.

This application discloses a method, device, medium, and product for optimizing the structure of a shaped charge shroud, relating to the field of structural design. The method includes: constructing an objective function with structural parameters as design variables and maximizing performance index values ​​as the objective; determining multiple initial sample points using a Latin hypercube sampling method based on the range of structural parameter values; constructing an initial sample library; constructing a surrogate model based on the initial sample library; determining candidate sample points and their corresponding performance index values ​​using a Bayesian optimization loop based on the surrogate model and the range of structural parameter values; updating the initial sample library and the surrogate model; continuing until a termination condition is met; and using the sample point corresponding to the maximum performance index value as the target structural parameter; and optimizing the design of the shaped charge shroud based on the target structural parameter. This application can reduce the computational cost of determining the structural parameters of a shaped charge shroud and improve the efficiency and intelligence of shaped charge shroud structure optimization.

The application discloses a kind of sparse magnetic field data reconstruction method, system, equipment and storage medium, is related to magnetic field imaging and neural network image processing technical field, including by data acquisition department obtaining the initial sampling sparse magnetic field data of target detection area;Initial sampling sparse magnetic field data is input into sampling strategy department, generates sampling probability distribution graph, according to sampling probability distribution graph, obtains active sampling sparse magnetic field data;Active sampling sparse magnetic field data and initial sampling sparse magnetic field data are input into spatial superposition department, obtain final sampling sparse magnetic field data;Final sampling sparse magnetic field data is input into sparse data reconstruction module, and high-resolution reconstructed magnetic field data is output.The method described in the application is more good in improving sampling efficiency, optimizing reconstruction quality, reducing redundant data, enhancing reconstruction stability.

The invention discloses a sample data expansion method and device for whole genome selection, equipment and a medium, and the sample data expansion method for whole genome selection comprises the steps: obtaining real genotype data of a target crop in a historical crop breeding process and phenotype data corresponding to the real genotype data, generating an initial sample set according to the real genotype data and the phenotype data; based on linkage feature information of the real genotype data, performing segment segmentation on initial gene sample data in the initial sample set, and performing segment replacement on segmented gene segments based on auxiliary gene sample data to generate a mixed gene sample; and training a pre-constructed crop prediction model based on the mixed gene sample and the initial sample set. According to the technical scheme, the prediction efficiency of crop character prediction and the reliability of the prediction result are improved.

The application discloses a phase sequence identification method and device, a storage medium and electronic equipment. The method comprises the following steps: collecting voltage time sequence data samples of a total table and each single-phase table to construct initial sample data sets corresponding to each phase sequence and containing a plurality of voltage time sequence data samples; performing calculation and processing based on each initial sample data set to obtain initial clustering center data sets corresponding to each initial sample data set, so as to obtain an initial phase sequence identification model; cyclically updating the initial phase sequence identification model based on each to-be-identified sample, and obtaining a phase sequence identification model when a preset iteration condition is met; identifying a target to-be-identified sample based on the phase sequence identification model, determining a target clustering center corresponding to the target to-be-identified sample, and determining a phase sequence corresponding to the target clustering center as a target phase sequence corresponding to the target to-be-identified sample. The phase sequence identification method in the application does not require manual identification of the phase sequence on site, saves manual cost, and improves work efficiency.

The application provides a high-throughput high-entropy alloy component design method, comprising the following steps: S1) preparing an initial sample of pure metal or alloy; S2) preparing a master alloy ingot according to the high-entropy alloy component; S3) assembling the initial sample at the bottom of a mold shell, fixing the mold shell on a directional solidification furnace pulling device, and exposing a part of the initial sample from the liquid level of a cooling tank, and immersing the remaining part into the cooling liquid in the cooling tank; S4) assembling the master alloy ingot on the upper part of an induction dripping system of the directional solidification furnace, and turning on the heating power supply of the directional solidification furnace; S5) turning on the induction dripping system until the master alloy ingot is melted and dripped into the mold shell, and then cooling and solidifying after heat preservation. The high-throughput sample component prepared by the method provided in the application is uniform and linear, and the component screening precision is higher; the high-throughput sample with single-element or multi-element coupling change can be efficiently prepared, the performance data reliability is higher, and the industrial application potential of the alloy is greater.

The invention provides a sample positioning method suitable for an X-ray free electron laser monopulse experiment, and relates to the field of X-ray free electron laser experiments. The method comprises the following steps: step 1), acquiring an initial sample image of a sample to be detected; step 2), processing the initial sample image to obtain a target sample image; 3) identifying the contour of the target sample in the target sample image, and obtaining the pixel coordinates of the target sample; 4) performing visual proportion calibration on the target sample image to obtain a visual proportion coefficient; 5, based on the visual proportionality coefficient and the pixel coordinates of the target sample, the positioning coordinates of the target sample on the experimental platform are calculated in combination with datum point information.According to the method, accurate coordinate mapping and positioning can be achieved, the experimental performance is improved, and automation of the experimental process is promoted.

The application belongs to the field of shell structure design, and particularly discloses a shell stability prediction method and system based on combined proxy model sequence sampling, which comprises the following steps: obtaining initial samples and corresponding shell critical pressures, and putting them into a database; obtaining training samples from the database, and establishing a temporary combined proxy model based on the training samples; randomly obtaining candidate samples, calculating the prediction uncertainty and sparsity degree of the candidate samples based on the temporary combined proxy model and the sample distribution in the database, and then selecting part of the samples in the candidate samples to add to the database; repeating the sampling until a preset termination condition is reached, and ending the sampling process; and using the samples in the database and the corresponding shell critical pressures to establish a final combined proxy model, so as to realize shell structure stability prediction. The application uses the information provided by the model and data to guide sample selection, can reduce the number of samples required for establishing a shell structure proxy model, and improves the design efficiency.

The invention discloses a soil texture detection device, and relates to the technical field of soil texture detection, the soil texture detection device comprises a base, a soil collection assembly and a detection assembly, the soil collection assembly comprises a spiral blade, an adjusting mechanism, a clearing mechanism and a screening mechanism; the detection assembly comprises a conveying channel, a temperature detector, a humidity detector, a pH value detection mechanism and a detection box. According to the invention, the arranged clearing mechanism passively rotates along with the rotation of the spiral blade, so that the clearing mechanism removes large impurities on the surface of soil and prevents the impurities from entering the collecting cylinder, and meanwhile, the arranged screening mechanism screens out fine impurities in the soil, so that the detection assembly is protected from being worn while the purity of an initial sample is ensured; and the conveying channel guides the screened soil to sequentially pass through the detection components, so that the temperature detector, the humidity detector and the pH value detection mechanism respectively detect the temperature, the humidity and the pH value of the soil, and meanwhile, different reagents are placed in the detection box so as to further detect the components of the soil.

The embodiment of the invention provides an adversarial verification evaluation method, system and device for a working condition coverage capability boundary of a fault detection and diagnosis model, and the method comprises the steps: dividing an obtained working condition search domain into at least two sub-domains, the working condition search domain is generated by combining a plurality of working condition parameters of the target equipment; according to the accuracy corresponding to each verification sample belonging to the target sub-domain in the (i-1) th round, the sample extraction number corresponding to the target sub-domain in the current ith round is determined, and the target sub-domain is each of the at least two sub-domains; performing extraction in the initial sample set according to the sample extraction number to obtain a corresponding target verification sample; inputting the target verification sample into a fault detection model for processing, and generating a fault detection result; and based on the fault detection result and a preset evaluation index, verifying and evaluating the working condition coverage capability of the fault detection model and generating a corresponding verification and evaluation result.

The present application relates to power industry safety domain boundary fitting technology, in particular to a kind of high-dimensional static security domain boundary fitting method of power system, considering system generator output constraint, node load value sampling is carried out, through power flow calculation, the sample in the security domain is filtered out, and initial sample set is formed.Boundary sample search algorithm is proposed, for each sample in initial sample set, find a sample in the security domain, a sample outside the security domain, and satisfy the distance between the two is less than the set distance threshold value.The data in the boundary sample set in the original power injection space is converted to new three-dimensional feature space by deep neural network model.Extract the boundary in feature space by the weighted tilt decision tree algorithm based on information gain ratio, and evaluate the boundary performance, select the optimal boundary.The method can realize the fitting of high-dimensional boundary of power system security domain, and reduce the error with actual boundary.

The application provides a data fragmentation recommendation method, device and server, comprising: obtaining at least one data table to be fragmented, randomly generating P kinds of non-repeating fragmentation schemes, and generating an initial sample library according to the P kinds of non-repeating fragmentation schemes; determining the initial sample library as a current sample library, and determining the fitness of each fragmentation scheme included in the current sample library according to a preset fitness function; selecting, crossing and mutating the samples in the current sample library, and updating the current sample library; continuing to determine the fitness of each fragmentation scheme included in the current sample library according to the preset fitness function until a preset termination condition is reached; and determining the fragmentation schemes corresponding to the first N fitnesses as recommended fragmentation schemes. The recommended fragmentation schemes can be quickly determined by using a genetic algorithm, which is efficient and has better use effect to a certain extent.

The application discloses a lightning impulse grounding grid frequency characteristic analysis method, system, device and medium, including: obtaining initial sample data; using the sample and a preset test frequency set to construct at least two different structure rational function interpolation models, and calculating the output residual thereof in the test frequency band; determining the target frequency point with the maximum modeling uncertainty according to the residual, calling the moment method to supplement high-precision response samples at the point; based on the updated sample set, constructing a diagonal or near-diagonal form rational interpolation model, and judging whether the prediction error of the model at the target frequency point is lower than a preset convergence threshold; if the convergence condition is not met, returning to the multiple model construction step, reiterating using the current sample set until the error meets the standard, and finally outputting the grounding grid frequency response characteristics covering the lightning impulse frequency band. The application realizes efficient analysis of the grounding grid frequency characteristics under lightning impulse, and effectively reduces the time used for analyzing the grounding grid frequency characteristics under lightning impulse.