73 results about "Cholesky decomposition" patented technology

The invention provides a rock-fill dam concrete panel cracking reliability calculation method and system, and the method comprises the steps: determining test parameters based on obtained physical parameters of a rock-fill material used by a rock-fill dam; duncan E-B model parameters are determined based on the test parameters, factor sensitivity analysis is conducted on the Duncan E-B model parameters based on an orthogonal test method, and sensitivity parameters are determined; carrying out random field characterization on the sensitivity parameters by using a normal random field, and discretizing random field data by using a Cholesky decomposition method to obtain a sample set and a test set of a training agent model; based on a Kriging model constructed by the sample set, performing optimization iteration through MPSO and a learning function to obtain an optimal agent model, and evaluating the optimal agent model; inputting the test set into the optimal agent model to calculate to obtain a predicted value and an evaluation index, establishing a structural performance function, and calculating to obtain the panel cracking reliability by adopting an important sampling subset simulation method; according to the method, the accuracy of the cracking reliability is improved.

The invention provides a Cholesky decomposition heterogeneous parallel optimization method and system based on an SW architecture, and relates to the technical field of high-performance computing. The method comprises the following steps: performing sub-block division on a symmetric positive definite matrix based on a distributed parallel distribution scheme, and performing iteration to complete matrix decomposition; each sub-block is distributed to different processes through an MPI programming model, data exchange is carried out between the processes through asynchronous communication, and coarse-grained task-level parallel acceleration is carried out; performing two-stage parallel acceleration on four operations in Cholesky decomposition by utilizing the acceleration parallel characteristic of a master core and a slave core of the SW architecture; wherein for GEMM and SYRK operations, column vectors of a matrix are mapped to a slave core array, and columns are divided according to the number of slave cores; the calculation process is optimized through a double-buffering mechanism, vectorization operation and a loop expansion technology, and the parallel efficiency is improved; and for the TRSM operation, the TRSM operation is decomposed into a plurality of TRSV operations, the TRSV operations are allocated to the slave cores for parallel execution, and a circular reading and data broadcasting mode is adopted to reduce data dependence and realize efficient parallel calculation.

The invention discloses an electromagnetic field simulation optimization method and system based on deep learning. The method comprises the following steps: discretizing a calculation area, and dividing the calculation area into a limited number of units; constructing a finite element matrix for the electric field of each unit; the finite element matrix is subjected to block processing, and two sub-block matrixes describing the electric field gradient and the electric field rotation of the triangular surface area are decomposed into an upper triangular matrix and a lower triangular matrix through an incomplete-like Cholesky decomposition model; inversing the upper triangular matrix and the lower triangular matrix to obtain approximate inverse of the finite element matrix; substituting the approximate inverse of the finite element matrix into a conjugate gradient algorithm, and solving to obtain an electric field of each unit; and obtaining a corresponding magnetic field according to the electric field of each unit so as to obtain an electromagnetic simulation result. According to the method, through a technical path of block dimension reduction-graph structure learning-physical constraint enhancement, the bottleneck problem that preprocessing efficiency and adaptability in electromagnetic field simulation are difficult to consider at the same time is solved.

Disclosed in the present invention are a method and apparatus for synthesizing spatially cross-correlated multi-point ground motions fitting a response spectrum. The method comprises: using an influence matrix method to obtain ground motion acceleration time histories fitting a target reaction spectrum with high precision, and calculating a Fourier amplitude spectrum and a phase spectrum thereof; and considering a calculation relationship between a power spectral density function and the Fourier amplitude spectrum, taking the power spectral density function of the obtained time histories as an initial value, using a random vibration theory and Cholesky decomposition to obtain spatially cross-correlated multi-point ground motion time histories, further taking into account a phase spectrum of the ground motion time histories fitting the target reaction spectrum with high precision, and performing correction and iteration to obtain spatially cross-correlated multi-point ground motions fitting a response spectrum. The present invention overcomes the shortcomings in current multi-point ground motion time history synthesis techniques, such as the difficulty in ensuring good fitting to a target response spectrum and the non-stationarity of synthesized ground motions, helping to improve the reliability of dynamic response analysis results for large-scale engineering structures under the action of multi-point ground motions.

The invention relates to a rock-soil-building block collaborative slope reliability analysis method considering spatial variability. The method comprises the following steps: establishing a slope finite element model; aiming at the finite element model, constructing an autocorrelation random field which takes a soil mass parameter as a variable and has a discrete characteristic by using a Cholesky Decomposition midpoint method; coupling the self-correlation random field based on a Copula model to form a cross-correlation standard uniform random field, and performing equal probability conversion on the cross-correlation standard uniform random field to form a cross-correlation random field in logarithmic normal distribution; and inputting the generated random field into a finite element model, obtaining a safety coefficient by using a strength reduction method, and determining the slope reliability based on a Monte Carlo method. According to the method, the finite element analysis result is closer to the actual situation, and the accuracy of the reliability analysis result is remarkably improved.

The invention belongs to the technical field of power distribution network reconstruction, and particularly relates to a power distribution network multistage reconstruction method and device considering main-distribution linkage under source load uncertainty, and the method comprises the steps: constructing a photovoltaic output model and a load model, and forming a source load uncertainty model; constructing a source load scene, and performing optical load scene generation based on Latin hypercube sampling and Cholesky decomposition through correlation modeling; performing scene reduction; dividing time periods by adopting a fuzzy C-means clustering method; constructing a reconstruction level evaluation double-layer model with the goal of minimizing light abandoning and load loss cost; converting the reconstruction level evaluation double-layer model into a single-layer model through integrated correlation modeling, and setting constraint conditions; and solving the single-layer model to obtain a multi-stage dynamic reconstruction scheme of the power distribution network. According to the method, through multi-scene modeling, time period dynamic division and multi-level collaborative optimization, efficient and stable operation of the power distribution network is realized, and the light abandoning and load loss cost is remarkably reduced.

The invention relates to a rapid simulation method and system for a bridge fluctuating wind field, and the method comprises the steps: obtaining double-index frequencies of each wind speed simulation point under all sampling frequency points, and constructing a double-index frequency matrix; calling a double-index frequency matrix, and constructing a spectral density matrix of a wind speed simulation point under a single sampling frequency point; performing Cholesky decomposition on the spectral density matrix of the wind speed simulation point under the single sampling frequency point to obtain a Cholesky decomposition matrix with the dimension of n * n under the single sampling frequency point; and so on, obtaining a Cholesky decomposition matrix under the N sampling frequency points; all the Cholesky decomposition matrixes with the dimensions of n * n are assembled, and a Cholesky decomposition matrix with the dimensions of n * n * N is obtained; based on a harmonic synthesis method and the Cholesky decomposition matrix with the dimension of n * n * N, the wind speed time history with the wind speed simulation points in the bridge fluctuating wind place is obtained. The generation efficiency of the fluctuating wind field can be improved.

A sensor unit is coupled to a machine and configured to detect anomalous behavior of the machine. The sensor unit includes a low power microcontroller that learns to recognize a plurality of operations of the machine. The sensor unit generates mean vector and inverse of a Cholesky decomposition matrix for each operation. During a detection mode the sensor unit computes a Mahalanobis distance for each feature vector, mean vector and first matrix. The sensor unit detects anomalous behavior or classifies the operation of the machine based on the Mahalanobis distances.

The invention discloses an iterative computation matrix inversion method and system based on Cholesky decomposition, and relates to the technical field of DSP system optimization, and the method comprises the steps: obtaining a target source matrix; based on Cholesky decomposition, performing first iteration processing on the target source matrix to generate an upper triangular matrix; performing second iteration processing on the upper triangular matrix to generate an inverse matrix of the upper triangular matrix; performing conjugate transpose processing on the inverse matrix of the upper triangular matrix to generate a lower triangular matrix; wherein the lower triangular matrix is stored in the form of array storage; converting the storage mode of the inverse matrix of the upper triangular matrix into a sequential storage mode; and performing matrix multiplication processing on the inverse matrix of the upper triangular matrix and the lower triangular matrix to generate an inverse matrix of the target source matrix. According to the method, accumulative summation is replaced by iteration, complex multiplication and addition optimization calculation is adopted, multi-parallelism operation and parallelization processing zero padding operation are supported, a general matrix multiplication module can be adapted, and calculation time and area overhead are reduced.

The invention relates to the technical field of data center optimization, and particularly discloses a data center two-stage stochastic optimization method and system considering wind and light uncertainty, and the method comprises the steps: carrying out the modeling of a data center energy supply system, generating a wind and light output sample based on Monte Carlo simulation, enabling the generated random sample to meet wind power and photovoltaic output complementation through Corisky decomposition; introducing a first-order autoregression model, generating random scenes in combination with multivariate normal distribution, and obtaining a wind and light output curve in each scene; a two-stage stochastic optimization model containing computing power scheduling and multi-energy coordination is constructed by taking the minimum expected operation cost of a system as a target, the model is solved, and an optimal time sequence operation strategy of a computing power task is decided. According to the two-stage random optimization, the adjustment cost caused by prediction errors is covered with low risk premium, and effective support is provided for reliable operation of the data center under new energy output fluctuation and computing power load time sequence mismatch.

An energy storage coordination optimal control method based on photovoltaic power generation and an electric vehicle comprises the following steps: 1) using a Cholesky decomposition method to consider a scene generation process of correlation between a load demand and solar energy production, and establishing a model of solar power generation and load demand uncertainty; 2) establishing a system coordination optimization model by taking cost minimization as an objective function based on the model of solar power generation and load demand uncertainty and the optimal operation of energy storage equipment integrating photovoltaic and electric vehicles in the system; and 3) applying a random dual dynamic programming algorithm SDDP to solve the system coordination optimization model, and solving the optimal coordination control of the photovoltaic energy storage and the electric vehicle energy storage under the condition of considering the uncertainty of the photovoltaic power generation and the load demand.

An electronic device includes a communication circuit including 2N reception antennas, and a communication processor including a covariance matrix generation circuit that generates a covariance matrix for the 2N reception antennas based on a measurement of a received signal, and a whitening filter matrix generation circuit that calculates a whitening filter for N reception antennas based on Cholesky decomposition. The covariance matrix includes a first sub-matrix, a second sub-matrix, a third sub-matrix, and a fourth sub-matrix, and the whitening filter matrix generation circuit calculates a whitening filter matrix for the 2N reception antennas based on characteristics of a first whitening filter matrix and the Cholesky decomposition for the first sub-matrix corresponding to a diagonal sub-matrix of the covariance matrix.

The invention discloses a covariance matrix prediction method based on a neural network, and relates to the crossing field of financial engineering and deep learning. The method comprises the following steps: firstly, collecting five-minute-level high-frequency data of a Chinese stock market, screening and filling, then calculating a realized covariance (RCOV) matrix, and then preprocessing through square root transformation and Cholesky decomposition; thirdly, constructing a 3D input tensor and a label, and dividing and standardizing a time sequence data set; then, a CM-ConvBiLSTM model containing a coding layer (ConvBiLSTM + CNN) and a generation layer is built, and training is carried out through Huber loss and an Adam optimizer; and finally, carrying out inverse preprocessing to obtain a positive definite prediction RCOV matrix which is used for constructing investment portfolios such as global minimum variance and monthly rebalance. According to the method, the problems of high-dimensional adaptation, positive qualitative guarantee and the like are solved, the investment portfolio optimization precision and stability are improved, and the method adapts to Chinese stock market characteristics.

This application discloses an accelerated Cholesky decomposition calculation method based on a dataflow architecture. The method includes: a data preparation step, a 2×2 matrix block calculation step, and a 1×1 matrix block calculation step. The dataflow architecture divides the processing unit (PE) array into multiple PE groups. The irregular matrix to be calculated is divided into multiple regular matrix blocks according to a predetermined partitioning rule. If the N of the N×N matrix to be calculated is greater than a predetermined threshold, a 2×2 block-based Cholesky splitting algorithm is used to iteratively calculate the matrix blocks in each PE group. Data transfer between PE groups is achieved through the data dependency relationship between different PE groups on the Cholesky decomposition calculation, and the size of the matrix to be calculated is dynamically adjusted and reduced. If the N of the N×N matrix to be calculated is less than or equal to a predetermined threshold, a 1×1 block-based Cholesky splitting algorithm is used to iteratively calculate until the calculation is completed and the calculation result is output, thus completing the accelerated Cholesky decomposition calculation based on the dataflow architecture.

The invention discloses a cascade hydropower scene generation method and device, equipment, a medium and a product. The method comprises the steps of performing standardization and quantile transformation on actually measured data of a plurality of cycles before a plurality of hydropower station prediction periods of a target drainage basin; performing iterative random sampling through multivariate normal condition distribution and Cholesky decomposition by adopting a preset TVP-VAR model according to the converted measured data to generate a flow scene of each period in a prediction period; wherein the preset TVP-VAR model is formed by splicing a lag coefficient matrix and a disturbance covariance matrix of each period according to a time sequence; and quantile inverse transformation and inverse standardization are carried out on the flow scene of each period of the prediction period to obtain cascade hydropower flow scenes of the plurality of hydropower station prediction periods of the target drainage basin. The calculation efficiency under the high-dimensional condition and the model compatibility under the small sample condition can be considered, the consistency of the distribution of the generated scene and the real flow distribution of the hydropower station is improved, and the scene generation precision is improved.

The invention discloses a power grid new energy station power generation method and system considering spatial correlation. The method comprises the following steps: calculating correlation coefficients of any two different new energy stations based on a power change sequence; calculating the distance between stations by using the correlation coefficient, and carrying out clustering based on the distance to form a plurality of station groups; and for each station group, constructing a correlation coefficient matrix, and generating a new new energy station power change sequence through Cholesky decomposition. According to the invention, through the improved correlation analysis method, correlation characteristics between new energy units are accurately quantified; an optimized clustering algorithm is utilized to classify highly-correlated units into one group, so that the spatial dimension of a sample is remarkably reduced; a random generation method based on an advanced statistical model is adopted to generate a new energy power sequence with real randomness and correlation, so that the randomness of new energy power output is kept, and a correlation structure between units is ensured.

The invention provides a terminal initialization method and device, electronic equipment and a storage medium. The terminal initialization method comprises the following steps: acquiring initialization parameters, inertial constraints and visual constraints of a terminal; constructing an information matrix according to the initialization parameters, inertial constraints and visual constraints; performing Schel compensation elimination on the information matrix, and eliminating the feature points from the information matrix to obtain an eliminated information matrix; performing Cholesky decomposition on the eliminated information matrix to obtain an upper triangular matrix and a lower triangular matrix; performing inversion on the image frame state quantity corresponding to the nearest preset moment in the upper triangular matrix to obtain a square root of a covariance, and further determining the covariance; and determining the initialization state of the terminal according to the covariance and the initialization parameter. According to the method disclosed by the invention, the covariance can be quickly solved, and the state quantity fluctuation amplitude is reduced.

The invention relates to the technical field of power distribution network optimization, in particular to a power distribution network operation optimization method considering multiple uncertainties. According to the method, a robust optimization framework considering multiple uncertainties and relevance of a distributed power supply, a novel flexible load and distributed energy storage is constructed, so that the limitation that modeling is dispersed and resource coupling is ignored in a traditional method can be effectively overcome, random characteristics and association relationships of wind and light loads are accurately described by utilizing probability distribution and Cholesky decomposition, and the robustness of the distributed power supply, the novel flexible load and the distributed energy storage is improved. And the flexibility of the system is enhanced through energy storage dynamic balance and flexible load regulation and control, efficient solving is realized by adopting mixed integer linear programming and a column-constraint generation algorithm, and finally, on the premise of ensuring the voltage safety of the power distribution network, the power flow stability and the equipment capacity limitation, the new energy consumption capability is remarkably improved, and the system operation economy is optimized. And a scheduling scheme with high robustness and high implementability is generated.

The invention relates to the technical field of wireless communication, in particular to a low-complexity signal detection method of an MIMO-OTFS system, which comprises the following steps: setting a grouping symbol number according to a channel condition, and calculating a maximum iteration number; in each iteration: calculating a filtered received signal through the channel matrix and the received signal; constructing a matrix psi, processing a structure matrix psi S of the matrix psi by adopting an RCM algorithm to obtain a permutation matrix, and calculating a reordering matrix according to the permutation matrix; performing Cholesky decomposition on the reordering matrix to obtain a banded matrix; calculating the SINR of each symbol which is not detected at present; all symbols which are not detected at present are arranged in a descending order according to the SINR size, the first S symbols in the sorting result are taken to be detected one by one and output, and the channel matrix and the received signal are updated; judging whether the maximum iteration number is reached or not, and if not, continuing the next iteration; according to the method, the time complexity is reduced while the bit error rate performance is ensured through an iterative strategy of reliability symbol detection and interference elimination.

A computer implemented method for predicting observations. The method includes providing an input for predicting an observation, and training data comprising pairs of an input and an observation, wherein the input characterizes a technical system, and the observation characterizes the technical system or an environment of the technical system; determining, for the inputs, a covariance matrix of the inputs; determining a pivoted Cholesky decomposition of the covariance matrix; and determining a prediction for an observation depending on the pivoted Cholesky decomposition of the covariance matrix; wherein determining the pivoted Cholesky decomposition includes determining a covariance matrix of selected inputs and a covariance matrix of remaining inputs representing the covariance matrix of the inputs, determining a pivot ndex depending on a measure for a difference between the covariance matrix of the remaining inputs and a Nystrom approximation of the covariance matrix of the remaining inputs.

The invention discloses an effective resistance calculation method based on block Cholesky decomposition, and relates to the field of circuit simulation and graph computation.The effective resistance calculation method comprises the steps that firstly, a simulation sparse matrix is sequenced and blocked through a nested segmentation method, and a single-layer diagonal edging matrix is constructed; gradually converting the matrix structure into a multi-layer block mode through iterative optimization, reversely integrating coupling edges, and finally outputting a replacement vector and block position information; secondly, constructing a parallel processing framework based on block information, implementing parallel Cholesky decomposition on a plurality of initial matrixes with consistent structures, filling diagonal blocks of a lower triangular matrix through decomposed numerical values, and solving coupling edge numerical values; and block sorting and parallel triangular back substitution are carried out on the right end item of the linear equation set, an intermediate vector is generated, a norm and a vector product of the intermediate vector are calculated, and finally efficient solving of the effective resistance is realized. According to the method, through matrix block optimization and parallel computing strategies, the time complexity of large-scale circuit simulation is remarkably reduced while the computing precision is kept.

The invention provides a method for simultaneously reconstructing temperature and radiation characteristic parameters of particulate matters in a complex combustion system. The method comprises the following steps: measuring combustion flames of the particulate matters to be detected by using a spectrograph to obtain detection spectral radiation intensity; based on a wavelength-temperature double-variable emissivity model, calculating flame theoretical spectral radiation intensity; initial parameters are set, and a residual function about unknown parameters is constructed; transforming the residual function into a quadratic model by using Taylor expansion; solving and updating the iteration step length by combining a Cholesky decomposition method and a Cauchy point method; updating unknown parameters by utilizing an iteration step length, calculating a residual sum of squares and performing convergence judgment; and when the convergence condition is met, unknown parameters required by the radiation characteristic parameter model and the real temperature of the particulate matter are updated. According to the method, high-precision particle temperature and radiation characteristic parameters are given based on flame spectrum radiation intensity, and the method has the advantages of high precision and rapid convergence in a gas-liquid-solid multi-phase coupled complex combustion environment.

The invention discloses a fading image color restoration method, system and device and a medium, and relates to the technical field of fading image restoration, and the method comprises the steps: obtaining a to-be-restored fading image, and selecting a reference image; inputting the fading image and the reference image into an image color rendition model, using zero filling operation to increase the channel dimension of an input image pair, and adopting a reversible residual network formed by a plurality of cascaded reversible residual blocks and extrusion layers connected between each pair of reversible residual layers, performing depth feature extraction on the input image after the channel dimension is increased to obtain a faded image feature and a reference image feature, performing whitening processing on the extracted faded image feature by using Cholesky decomposition, and coloring the whitened image feature to obtain a color restoration feature so as to restore the color of the faded image; according to the method, the color of the decolored mural image is accurately repaired, and meanwhile, the content structure and texture details in the original image are better reserved.

The present invention proposes a Cholesky decomposition heterogeneous parallel optimization method and system based on the Shenwei architecture, which relates to the field of high-performance computing technology. The method comprises: dividing a symmetric positive definite matrix into sub-blocks based on a distributed parallel allocation scheme and iteratively completing the matrix decomposition; allocating each sub-block to a different process through the MPI programming model, exchanging data between processes through asynchronous communication, and performing coarse-grained task-level parallel acceleration; utilizing the master-slave core acceleration parallel characteristics of the Shenwei architecture to perform two-level parallel acceleration on the four operations in the Cholesky decomposition; wherein, for GEMM and SYRK operations, the column vectors of the matrix are mapped to the slave core array, and the columns are divided according to the number of slave cores; the calculation process is optimized through a double buffering mechanism, vectorized operations and loop unrolling technology to improve parallel efficiency; for the TRSM operation, it is decomposed into multiple TRSV operations, which are allocated to the slave cores for parallel execution, and the data dependency is reduced by loop reading and data broadcasting to achieve efficient parallel computing.

This application relates to a rapid simulation method and system for a bridge fluctuating wind field. The method involves obtaining the dual-index frequency of each wind speed simulation point at all sampling frequencies and constructing a dual-index frequency matrix. The dual-index frequency matrix is ​​then used to construct a spectral density matrix for the wind speed simulation point at a single sampling frequency. The spectral density matrix of the wind speed simulation point at a single sampling frequency is subjected to Cholesky decomposition to obtain an n×n-dimensional Cholesky decomposition matrix for the single sampling frequency. This process is repeated to obtain Cholesky decomposition matrices for N sampling frequencies. All n×n-dimensional Cholesky decomposition matrices are assembled to obtain an n×n×N-dimensional Cholesky decomposition matrix. Using the harmonic synthesis method and the n×n×N-dimensional Cholesky decomposition matrix, the wind speed time series for all wind speed simulation points in the bridge fluctuating wind field are obtained. This application can improve the efficiency of fluctuating wind field generation.

The invention discloses a power grid prediction state estimation method and system based on square root unscented particle filtering, and the method comprises the steps: obtaining the historical operation data of a power grid, generating an initial particle set, and obtaining a state variable estimation value of the power grid and the weight of the state variable estimation value through employing a square root unscented particle filtering method based on a prediction state estimation model; in iteration, calculating a weighted covariance matrix by using a state variable estimation value of the power grid and a corresponding normalized weight, performing Cholesky decomposition on the weighted covariance matrix to obtain a square root of the weighted covariance matrix, and taking the square root as a square root estimation value of each particle after resampling; the number of effective particles is used as a normalized weight initial value of each particle after resampling; the state variable estimation value of the power grid and the weighted mean value of the weight of the state variable estimation value serve as the prediction state estimation result of the power system, and the accuracy and robustness of state estimation of the power system with new energy access are improved.

The invention relates to the technical field of automatic driving, in particular to a self-adaptive trajectory tracking control method for an automatic driving vehicle, and the method comprises the following steps: building a vehicle dynamics trajectory tracking model; based on the vehicle dynamics trajectory tracking model, a high-order strong tracking volume Kalman filtering algorithm is adopted to estimate the lateral force of the tire, and in the high-order strong tracking volume Kalman filtering algorithm, singular value decomposition is adopted to replace Cholesky decomposition, and a fading factor is introduced to dynamically adjust the filtering covariance; according to the tire lateral force obtained through estimation and the tire lateral force obtained through calculation based on a linear tire model, a cornering stiffness correction factor is calculated; and correcting a tire cornering stiffness parameter in a model prediction controller in real time by using the obtained cornering stiffness correction factor, and constructing a self-adaptive model prediction controller. According to the invention, the path tracking performance of the autonomous vehicle under the uncertain working condition can be improved.

The invention provides a fan three-dimensional flow field reconstruction method based on multi-point observation. The fan three-dimensional flow field reconstruction method comprises the following steps: S1, multi-point observation data acquisition: acquiring a wind speed time sequence of N actual measurement points; s2, trend and turbulence separation and frequency domain transformation: obtaining a spatially distributed average wind speed field and a disturbance time sequence, and obtaining actually measured frequency domain disturbance distribution; s3, generating a standard background turbulent flow field: based on a Kaimal turbulent flow spectrum model, combining a coherence function, and generating a standard turbulent flow field conforming to statistical characteristics and frequency domain distribution of the standard turbulent flow field through random phase superposition and inverse Fourier transform; s4, observation constraint superposition and spatial coherence reconstruction: establishing a joint vector matrix; constructing a complex covariance matrix based on the coherence function; carrying out Cholesky decomposition, and extracting an actual measurement-simulation structure coupling relationship; standardization processing of actual measurement constraints; constructing simulation disturbance of a belt actual measurement structure; performing inverse Fourier transform to generate a time domain turbulence field; and S5, superimposing a trend field and outputting a final flow field.

The invention relates to the technical field of soil slope reliability analysis, in particular to a stability evaluation and reinforcement decision-making method for a slope containing a soft rock interlayer under a rainfall condition. Soft rock parameters are generated based on logarithmic normal distribution, sample uniformity is ensured through LHS, and negative correlation is introduced through Cholesky decomposition; mapping the data back to engineering actual distribution; calculating a slope stability coefficient K in combination with correction software, adding Gaussian noise to simulate an actual error, and standardizing input features and output labels; after the data set is divided into a training set and a test set, predicting a K value by adopting an SVR model, and optimizing hyper-parameters through grid search; and finally, constructing a DNN based on the standardized K value, judging reinforcement measures through a classification task, performing regression to output specific parameters, and finally generating a complete reinforcement scheme in stages. According to the method, the reliability of parameter generation and analysis is improved, the stability evaluation and decision-making precision is enhanced, and the data processing and model generalization ability is optimized.

The application discloses a kind of non-stationary wind field high-efficiency simulation method based on dynamic interpolation setting point strategy, including determining simulation point number and its space position;According to the time-varying fluctuation power spectrum model of typhoon, the evolution power spectrum density matrix is calculated;Determine the time range and frequency range of simulation, and it is evenly dispersed into P and Q nodes on time axis and frequency axis respectively;In these discrete nodes, the interpolation node coordinates are selected by dynamic interpolation setting point strategy;By Cholesky decomposition to the evolution power spectrum at interpolation node, the spectral decomposition matrix at the place is obtained, then combined with interpolation method, the spectral decomposition matrix at non-interpolation node is obtained;According to the formula of harmonic superposition method, generate fluctuating wind speed sample.The application is based on classical harmonic superposition method, constructs a kind of dynamic interpolation setting point strategy, can accurately, conveniently select the interpolation node of frequency dimension, effectively reduces the amount of calculation, significantly improves simulation efficiency.