24 results about "Design matrix" patented technology

The invention provides a minimum cost flow phase unwrapping method and device based on phase gradient rate assistance. The method comprises the steps that an SAR data set and DEM data of a to-be-monitored area are acquired; based on this, a differential interferogram and a coherence map are generated; respectively calculating a shortest time baseline phase gradient rate and a full time baseline phase gradient rate based on the differential interferogram; constructing a Delaunay triangulation network based on the differential interferogram and the coherence graph, and determining a rotation-free constraint and a design matrix; on the basis of the coherence graph, the shortest time baseline phase gradient rate and the full time baseline phase gradient rate, performing weight determination on each triangular arc segment in the triangulation network to obtain a weight corresponding to each triangular arc segment; and based on the non-rotation constraint, designing a matrix and weights corresponding to the triangular arc segments to solve the integer ambiguity, and completing a phase unwrapping task based on the integer ambiguity. According to the embodiment, the absolute phase of the large-gradient deformation area is obtained, so that high-precision deformation monitoring of the earth surface is realized.

A method of estimating noise for individual gates of a quantum circuit uses averaged circuit eigenvalue sampling to determine an overall eigenvalue for the circuit. The circuit is sampled a sufficient number of times to fill a design matrix, wherein the design matrix allows for solving of a system of equations to determine eigenvalues for the individual gates using the averaged eigenvalue for the overall quantum circuit, the samples, and the sample results. Applying a logarithm to these relationships enables solving the system of equations using linear estimation or linear regression, in some embodiments.

The invention discloses a multi-dimensional student physical health monitoring method and system, and relates to the technical field of health monitoring, and the method comprises the steps: collecting data to construct a signal subset, carrying out time-frequency decomposition to construct a time-frequency graph matrix, carrying out autoregression modeling to extract an observation matrix and a design matrix, and constructing a frequency feature vector; according to the frequency characteristics of different frequency bands, calculating contribution factors and determining a dynamic health score, calculating a posterior probability of a health state based on a conditional probability of the health score, and calculating a frequency band offset to construct an abnormal frequency band set. According to the method, a health assessment model is constructed by using an observation matrix and a design matrix, so that signal values in each row are associated with lagging historical values, the time dependence of the signals can be captured, the dynamic characteristics of the health signals are reflected, and the mean value, variance, skewness and kurtosis are calculated based on PSD. And high-dimensional spectrum information is concentrated into a feature vector of a fixed dimension, so that the data complexity is reduced, and subsequent classification and health state analysis are facilitated.

Users interact with items, such as movies, music, and document templates, among others. Item recommendations based on these user interactions are determined and provided to a user. A binary matrix indicating what items users have interacted with is provided. A design matrix is determined from the binary matrix. In this format, the model can be processed in parallel by a computing device. Columns of the design matrix are processed by threads of one or more CPUs of a computing system, in which a least squares analysis is performed over each thread. The output of the processing is a trained model useable for outputting an item recommendation responsive to an input user interaction during inference.

The present invention discloses a shape space experimental design method for aerodynamic shape optimization, which includes the following steps: Step 1, given the calculation conditions for experimental design, including the number of sampling points in each experimental design matrix, the dimension of design variables, geometric constraint conditions, and the shape parameterization method; Step 2, construct a multi-objective optimization model with the sample point set as the design variable and the number of feasible solutions and the spatial uniformity evaluation index as the objective function; Step 3, use the non-dominated sorting genetic algorithm to iteratively solve the multi-objective optimization model to obtain the optimal experimental design scheme. The method of the present invention considers the uniformity of the distribution of the aerodynamic geometric shapes generated by the sample point set in the shape space and the feasibility of geometric constraints, making the initial sample point set more reasonable, obtaining more comprehensive spatial information, and having a higher quality of the initial surrogate model, thereby improving the efficiency of optimization design and analysis. The present invention is applied to the field of aerodynamic optimization technology for aircraft design.

A kind of GNSS data processing method based on single observation filtering, comprising the following steps: first, design matrix, observation vector and covariance matrix are decomposed into multiple row vectors or scalar, then one observation is processed each time, after all the observations of current epoch are processed through multiple cycles, the state vector and covariance matrix of current epoch recursive update are obtained;GNSS parameters in state vector are divided into common parameters and non-common parameters, when processing each observation, update common parameters, then gradually increase new parameters in state vector, i.e. process observation by observation, to obtain extended state vector and covariance matrix;In the third step, when data processing is carried out using the above-mentioned extended state vector and covariance matrix, it includes single epoch processing and multi-epoch processing;The state estimation of current epoch is output as the result of GNSS positioning.The present application has high efficiency when processing high-dimensional observation data.

The invention provides a Beidou multi-frequency positioning method and device, electronic equipment and a storage medium. The method comprises the following steps: S1, collecting observation data and satellite ephemeris data of two target frequency points of a Beidou satellite; s2, based on the satellite ephemeris data, modeling the Beidou satellite clock correction by adopting a quadratic polynomial to obtain a clock correction modeling error, and taking the clock correction modeling error as a constraint term of an original design matrix to generate a design matrix with clock correction constraint; s3, constructing an observation vector based on the observation data, and substituting the design matrix with the clock error constraint and the observation vector into a TLS resolving model for resolving to obtain a positioning parameter initial value and a corresponding resolving residual error; s4, fitting a mapping relation between the residual error and the noise intensity based on the resolving residual error, generating a weight matrix, and performing weighted updating on the TLS resolving model by using the weight matrix to obtain an updated TLS resolving model; according to the embodiment of the invention, effective constraint on the design matrix error can be realized, and the clock error modeling precision is improved.

The application provides a semi-sphere adaptive grid division method for MHGM multi-path error modeling, comprising the following steps: obtaining a high-resolution multi-path error prior model as prior information by using non-difference residuals, and obtaining the spatial distribution characteristics of the multi-path error at a survey station; establishing a fixed grid division MHGM model on the survey station, extracting an AMR initial grid, obtaining the prior model value in the grid, setting to-be-estimated parameters at the corner points of the grid, and obtaining the relationship between the prior model value and the coordinates by using a bilinear interpolation method; setting the grid corner points as a to-be-estimated parameter matrix, the corresponding bilinear interpolation coefficient matrix as a design matrix, and the prior model value as an observation value matrix, so as to obtain the estimated value of the parameter matrix and the corresponding residual vector; traversing the residual vector, and considering that the grid can be divided when the absolute value is greater than the corresponding threshold value; stopping the division when the preset condition is met for any grid, or taking the grid as four congruent grids; and outputting the semi-sphere adaptive grid division result after the division is completed.

The invention discloses a power system load self-learning prediction method and device and a storage medium. The method relates to the field of artificial intelligence, and comprises the following steps: receiving influence factor data of a power system to be subjected to load prediction; a target load prediction model is obtained, and the target load prediction model is a model obtained by adjusting a design matrix in the initial load prediction model according to the influence factor data; and inputting the influence factor data into the target load prediction model, and predicting a load prediction result of the power system. According to the invention, the technical problem of low accuracy of power system load prediction in the prior art is solved.

The invention relates to the technical field of electrical variable measurement, in particular to a voltage effective value rapid calculation method and device, and the method comprises the following steps: obtaining a voltage sampling sequence in any continuous quarter period time window; converting the voltage sampling sequence signal into a linear model; constructing a design matrix and an observation vector according to the sampling time sequence and the voltage sampling sequence, and obtaining a regular equation according to the design matrix and the observation vector; fitting each coefficient of the linear model by solving a regular equation through a least square method; and calculating a voltage amplitude according to each coefficient obtained by fitting, and calculating a voltage effective value according to the voltage amplitude. According to the method and the device provided by the invention, the voltage effective value can be quickly calculated at any initial phase in an extremely short data window, and the precision is relatively high.

The invention discloses a method and a device for preprocessing industrial generated data containing high-dimensional noise, and relates to the field of data preprocessing, and the method comprises the following steps: outputting a sampling time point set and a multi-dimensional observation data set by collecting multi-dimensional function type observation data in a set time interval; and representing the real function of each dimension observation value as a primary function linear combination, extracting effective features, and outputting a primary function set and an expansion coefficient. And constructing a design matrix, and establishing association between the multi-dimensional observation data and the effective features. A combined objective function is constructed by combining multivariable synchronous processing requirements and signal importance differences, and a penalty matrix is constructed through an inner product of a second derivative of a primary function. And selecting a smoothing parameter by minimizing a generalized cross validation criterion, solving a target function to obtain an estimation expansion coefficient, and constructing and outputting a smoothing function as input data of a statistical process control or fault diagnosis model. The method solves the problems that in the prior art, effective features are prone to being lost, multi-dimensional collaboration is not considered, and smooth parameter selection lacks self-adaption.

The invention discloses a test design method for determining test repetition times by giving a test efficacy value, which comprises the following steps of: 1, determining influence factors of response variables, constructing an initial test design scheme, and setting constraint conditions for a factor test efficacy threshold value; step 2, extracting non-repeated test schemes from the test design schemes; 3, setting different repetition times for each row of tests of the non-repeated test scheme, and constructing a test design matrix; and step 4, considering a target optimization problem, optimizing a target function, and determining the minimum number of repetitions of each row of tests conforming to the factor test efficacy threshold. By adopting the technical scheme provided by the invention, the optimal repeated test times meeting the test efficacy limitation can be determined, so that the uncertainty of the test repeated times is reduced.

The present invention discloses a key parameter design and optimization method for an inductively coupled plasma source, which relates to the technical field of inductively coupled plasma sources, including: establishing a Plackett-Burman orthogonal matrix according to the design target of the inductively coupled plasma source. Calculating a response value coefficient matrix through a finite element analysis model, establishing a first-order linear regression equation, screening significant variables, and calculating and establishing a Box-Behnken design matrix based on the coefficients of the main effect variables. Calculating a response value coefficient matrix through a finite element analysis model, and establishing a high-order polynomial regression equation. Determining the importance and interaction of each significant variable through variance analysis and a three-dimensional response surface. Obtaining the optimal solution for the inductively coupled plasma source by solving the maximum value of the fitting equation. The solution of the present invention provides a solution to the difficult problem of multi-objective and multi-variable plasma source design that cannot be solved by traditional design methods.

The invention discloses a nacelle molded line optimization method and system based on CST parameterization and an intelligent algorithm and a storage medium, and the method comprises the steps: carrying out the parameterization modeling of an external molded line of a nacelle through employing a shape-like function method (CST), and taking a weight factor of a Bernstein polynomial as a design variable; setting a value range of a weight factor, and generating a test design matrix through a Latin hypercube sampling method; performing flow field simulation on the nacelle molded line corresponding to each group of weight factors based on ANSYS FLUENT, and calculating a resistance coefficient; constructing a back propagation neural network model, and performing training by taking the weight factor as input and the resistance coefficient as output; predicting an extended database by using the trained neural network, and optimizing by using a genetic algorithm to obtain an optimal weight factor combination; and generating a nacelle external molded line according to the optimal weight factor. According to the invention, through the weight factor based on the linear fitting polynomial, the optimization space is ensured under the condition that the optimization dimension is less, so that the nacelle scheme design efficiency is greatly improved.

The invention discloses a key parameter design and optimization method of an inductively coupled plasma source, and relates to the technical field of inductively coupled plasma sources, and the method comprises the steps: building a Plackett-Burman orthogonal matrix according to the design target of the inductively coupled plasma source; a response value coefficient matrix is calculated through a finite element analysis model, a first-order linear regression equation is established, significant variables are screened, and a Box-Behnken design matrix is calculated and established according to coefficients of main effect variables. A response value coefficient matrix is calculated through a finite element analysis model, and a high-order polynomial return equation is established; and determining the importance degree and interaction of each significant variable through variance analysis and a three-dimensional response surface. And the optimal scheme of the inductively coupled plasma source is obtained by solving the maximum value of the fitting equation. According to the scheme, a solution is provided for the problem of multi-target and multivariable plasma source design which cannot be solved by a traditional design method.

The present invention discloses a multi-dimensional student physical health monitoring method and system, which relates to the field of health monitoring technology, including collecting data to construct a signal subset, performing time-frequency decomposition to construct a time-frequency graph matrix, performing autoregressive modeling to extract an observation matrix and a design matrix, and constructing a frequency feature vector; calculating a contribution factor and determining a dynamic health score based on the frequency characteristics of different frequency bands, calculating the posterior probability of a health state based on the conditional probability of the health score, and calculating a frequency band offset to construct an abnormal frequency band set. The method of the present invention constructs a health assessment model by utilizing an observation matrix and a design matrix, so that each row of signal values ​​is associated with its lagged historical value, which can capture the time dependence of the signal and reflect the dynamic characteristics of the health signal. The mean, variance, skewness and kurtosis are calculated based on the PSD, and the high-dimensional spectrum information is condensed into a feature vector of fixed dimension, thereby reducing data complexity and facilitating subsequent classification and health status analysis.

The invention discloses a mining subsidence ground surface three-dimensional deformation estimation method, device and equipment, a medium and a product, relates to the field of ground surface three-dimensional deformation estimation, and particularly relates to a method comprising the following steps: determining observation quantity types according to sources and characteristics of different observation quantities in a subsidence monitoring mining area; the different observed quantities comprise the ascending orbit and the descending orbit calculated by InSAR, and the vertical direction, the coal seam trend and the coal seam tendency simulated by PIM; constructing an observed quantity matrix according to the observed quantity measurement error and the observed quantity type; based on the observed quantity matrix, combining with the design matrix, and according to the three-dimensional deformation quantity to be solved and the product error of the design matrix, constructing a real model; based on the real model, determining a variance matrix of observation measurement errors; constructing an observation equation according to the variance matrix; and on the basis of the observation matrix, updating a weight matrix of the observation quantity matrix by adopting an optimal estimation criterion of total least squares, and determining a three-dimensional deformation estimation result of the three-dimensional deformation quantity to be solved.

The application discloses a GNSS and leveling fusion ground deformation monitoring method and system with dynamic optimization weight, and relates to the technical field of geodesy and deformation monitoring.The method comprises the following steps: analyzing leveling and GNSS rate observation data; setting the elevation correction number and subsidence rate parameter of a monitoring point as unknown parameters, constructing adjustment observation equations coupled with observation time and subsidence rate parameters, forming a design matrix, an observation vector and an initial weight matrix; performing dynamic weight optimization, introducing a global weight factor for adaptive scanning, and on the basis of the optimal global weight ratio, calculating a weight reduction factor by using robust estimation according to the standardized residual error of GNSS observation values, and obtaining the optimal weight matrix; and finally solving the optimal estimation value of unknown parameters based on the optimal weight matrix.The application realizes two-stage dynamic optimization of the weight, objectively optimizes the weight by data driving, effectively suppresses the influence of gross errors, and significantly improves the precision and reliability of multi-source data fusion deformation monitoring.

The present application belongs to the field of color correction, and discloses a multi-classification color correction method based on spectral shape driving, which comprises the following steps: obtaining standard tristimulus values of a plurality of standard color panels, collecting spectral reflectance data of the standard color panels and performing smoothing and normalization processing; extracting a group of spectral shape features from the processed spectral reflectance data, and performing standardization processing on the feature vectors composed of the spectral shape features; dividing all the standard color panels into multiple categories, and determining the centroid of each category; constructing a design matrix and a target matrix for each category, designing a corresponding loss function, solving to obtain the calibration coefficient matrix and the regularization hyperparameter of each category, and packaging them into a calibration model for deployment to a color difference meter; predicting samples by using the calibration model of each category, and performing weighted fusion according to the similarity value to output corrected tristimulus values. While maintaining the measurement accuracy of the color difference meter, the color calibration stability of the high and low reflectivity regions is significantly improved.

The invention relates to a random test design and robust optimization method and system for a complex equipment system. The method comprises the following steps: generating an initial test design matrix; according to the initial test design matrix, obtaining system response variable data; identifying key test factors according to system response variable data, and establishing an agent model; calculating an estimation result of a random error term according to the proxy model, and establishing a joint multi-parameter distribution model; coupling the agent model and the joint multi-parameter distribution model, and establishing a prediction model of system response variables; and analyzing a prediction result of the prediction model to obtain a robustness metric value, and if the robustness metric value does not reach a preset threshold value or does not meet a preset convergence criterion, optimizing the prediction model of the system response variable by newly adding data until a preset condition is met, obtaining the optimized prediction model, and outputting a final robust test design scheme. According to the invention, the robustness and reliability of the equipment system test can be obviously improved in a complex environment.

A GNSS data processing method based on single observation value filtering comprises the following steps that a design matrix, observation vectors and a covariance matrix are decomposed into a plurality of row vectors or scalar quantities, then one observation value is processed each time, and after all observation values of a current epoch are processed through multiple times of circulation, all observation values of the current epoch are processed; obtaining a recursively updated state vector and covariance matrix of the current epoch; dividing GNSS parameters in the state vector into common parameters and non-common parameters, updating the common parameters when processing each observation value, and then gradually adding new parameters into the state vector, that is, processing the observation values one by one to obtain an extended state vector and a covariance matrix; 3, when the expanded state vector and the covariance matrix are adopted for data processing, single epoch processing and multi-epoch processing are included; and outputting the state estimation of the current epoch as a GNSS positioning result. The method is high in efficiency when processing the high-dimensional observation data.

The invention discloses an asphalt pavement performance multivariable grey prediction method of a sparrow optimization regular term, which takes PCI sequences of a plurality of detection units as system behavior variables, constructs a novel discrete multivariable grey model NSMGM (1, 6, 1), weakens data randomness through grey accumulation generation and adjacent mean value generation, and improves the performance of an asphalt pavement. A model structure is perfected by introducing a linear correction term and a gray action quantity, and the problem of non-homology of parameters is solved; a regularization item is introduced, model deviation and variance are balanced through an Euclidean norm of a penalty parameter vector, and the ill-conditioned problem of a design matrix under a small sample is improved; a sparrow search algorithm is adopted to simulate a "explorer-follower-alerter" population behavior, regularization parameters are adaptively optimized in a preset search space, and subjective trial and error are avoided. The three components organically cooperate to form an integrated prediction framework of variable correlation capture, parameter stability estimation and global optimization, and a quantitative basis is provided for pavement maintenance planning and engineering decision.

The invention belongs to the field of color correction, and discloses a multi-classification color correction method based on spectral shape driving, and the method comprises the steps: obtaining the standard tristimulus values of a plurality of standard color palettes, collecting the spectral reflectivity data of the standard color palettes, and carrying out the smoothing and normalization processing; extracting a group of spectral shape features from the processed spectral reflectivity data, and carrying out standardization processing on a feature vector formed by the spectral shape features; dividing all the standard color plates into a plurality of categories, and determining the centroid of each category; constructing a design matrix and a target matrix for each category, designing a corresponding loss function, solving to obtain a calibration coefficient matrix and a regularization hyper-parameter of each category, and packaging the calibration coefficient matrix and the regularization hyper-parameter into a calibration model to be deployed to a colorimeter; and predicting the sample by using the calibration model of each category, performing weighted fusion according to the similarity value, and outputting a corrected tristimulus value. While the measurement precision of the colorimeter is maintained, the color calibration stability of high and low reflectivity areas is significantly improved.

The application discloses a kind of exploitation subsidence surface three-dimensional deformation estimation method, device, equipment, medium and product, is related to surface three-dimensional deformation estimation field, which comprises determining observation type according to the source and feature of different observation in subsidence monitoring mining area;Different observation includes the ascending track and descending track calculated by InSAR, and the vertical direction, coal seam strike and coal seam tendency simulated by PIM;According to observation error and observation type, construct observation matrix;Based on observation matrix, combine design matrix, according to the three-dimensional deformation variable to be solved and design matrix product error, construct real model;Based on real model, determine the variance matrix of observation error;According to variance matrix, construct observation equation;Based on observation matrix, the optimal estimation criterion of total least square is used to update weight matrix of the observation matrix, to determine the three-dimensional deformation estimation result of the three-dimensional deformation variable to be solved, and the north-south direction displacement is accurately estimated.