296 results about "Kriging" patented technology

The invention discloses a multiple-working-condition hydraulic design method for a guide vane type centrifugal pump. The multiple-working-condition hydraulic design method for the guide vane type centrifugal pump mainly comprises the following steps that specific speed solution is conducted on the design working conditions of the guide vane type centrifugal pump, and the design working condition with the specific speed as an intermediate specific speed is selected and designed; multiple-scheme design is conducted on an impeller and guide vanes through an experiment design method, and the CFturbo style is adopted; mesh generation is conducted on a model, numerical simulation is conducted on a scheme through CFX, the lift and the efficiency value are read, and function fitting is conducted between the lift and a flow; function fitting is conducted between the lift and the flow of a design parameter point, the coefficient of a fitting function is used as a design goal, input main geometrical parameters are used as input values, an approximate response model is established through the Kriging model, rapid computation is conducted on the approximate response model through a multiple-target genetic algorithm, and then the optimal value is obtained. By the adoption of the multiple-working-condition hydraulic design method for the guide vane type centrifugal pump, the requirement for multiple-working-condition hydraulic design of the guide vane type centrifugal pump can be met; the multiple-working-condition hydraulic design method for the guide vane type centrifugal pump can also be used for multiple-working-condition hydraulic design of other guide vane type centrifugal pumps.

The invention discloses a method for reducing that scale of surface temperature space. At first, that method quantitatively analyzes the surface temperature and the surface parameters including the impervious surface coverage, vegetation coverage, soil coverage, NDVI, NDBI, MNDWI, DEM, and the correlation between building density and its spatial distribution difference, Then the regression model of low spatial resolution land surface temperature products and related land surface parameters is established by using machine learning stochastic forest algorithm, land surface temperature with highspatial resolution can be predicted by combining the land surface parameters with high spatial resolution, Then the area-to-point Kriging interpolation method of geostatistics is used to reduce the residuals of the random forest regression model to improve the spatial resolution of the residuals, Finally, the high spatial resolution stochastic forest regression model and the surface-to-point Kriging interpolation residuals are added to generate high resolution and high precision surface temperature products to make up for the lack of spatial resolution of the existing surface temperature products.

The invention discloses a fracture-cavity type carbonate oil reservoir three-dimensional physical model establishing method and relates to the technical field of three-dimensional modeling methods for computer mapping. The fracture-cavity type carbonate oil reservoir three-dimensional physical model establishing method mainly comprises the following steps of selecting a three-dimensional earthquake image corresponding to a target region according to three-dimensional earthquake test data and actual production situation, utilizing a Kriging interpolation method to reconstruct a three-dimensional numerical model through a three-dimensional earthquake cross section image, compiling an engraving program to manufacture a three-dimensional physical model and applying a similarity theory to arrange a well position according to the actual situation of an oil reservoir. By means of the fracture-cavity type carbonate oil reservoir three-dimensional physical model establishing method, the fully-three-dimensional large-sized physical model consistent to an actual underground structure and morphology of the oil reservoir and capable of representing fracture-cavity type carbonate oil reservoir complicated characteristics can be obtained.

The invention discloses a structural reliability analysis method based on an agent model under the condition of hybrid uncertainty. The structural reliability analysis method comprises the steps that random uncertainty is modeled by adopting random variables, and epistemic uncertainty is modeled by adopting interval variables; uniform samples generated by the random variables in an approximate value section and all the interval variables within upper bounds and lower bounds of respective intervals and a system response value are used as training sample points for establishing a Kriging agent model, and according to the obtained Kriging agent model, the maximum values and the minimum values of the reliability sensitivity, the failure probability and the system failure probability under any interval variable value are calculated by adopting a Monte Carlo simulation method. By the adoption of the structural reliability analysis method, the problems that a traditional agent model under the condition of the hybrid uncertainty has a certain precision locally, and the traditional reliability analysis calculated quantity is larger are solved, and the structural reliability analysis method better accords with engineering practice.

The invention provides a self-adaption reliability analysis method. The self-adaption reliability analysis method includes the steps that sampling is carried out in indeterminate probability space, aninitial DoE is selected, and a Kriging substitution model is built through the initial DoE; sampling is carried out with the important sampling method, and candidate samples are obtained; a sample point nearest to a performance function limit state surface in the candidate samples is screened, and a response value of the sample point is computed; whether the Kriging substitution model meets the convergence criterion or not is judged, if the Kriging substitution model does not meet the convergence criterion, the sample point and the response value are added into the DoE, and the Kriging substitution model is updated according to the result till the Kriging substitution model meets the convergence criterion; the reliability of the Kriging substitution model is evaluated, if the Kriging substitution model does not meet the accuracy requirement, the quantity of candidate samples is increased with the important sampling method, and iteration updating is carried out according to the resulttill the Kriging substitution model meets the accuracy requirement. According to the self-adaption reliability analysis method, the analysis efficiency and accuracy of the reliability of a structure system in practical engineering can be effectively increased.

The invention discloses an approximation model uncertainty state salon car body structure steady design method in the technical field of automobile manufacturing, based on parameter uncertainty of vehicle body design variable, and taking vehicle body performance to respond a Kriging model. The salon car body structure steady design method aims at overcoming the defects that at present, a vehicle steady design method just considers parameter uncertainty to obtain steady solving which easily generates big forecast error, and even generates failure constraints, vehicle body parameter uncertainty can be reduced, and approximation model uncertainty affects vehicle body structural performance. The salon car body structure steady design method improves accuracy of design scheme target performance of a vehicle body structure and effectiveness of restraint performance.

The invention relates to a method for optimally designing the structure of a sliding shaft sleeve based on a Kriging model. By using an unbiased optimal estimation theory of the Kriging model, the optimal design scheme of the sliding shaft sleeve is predicted and solved. The method comprises the following steps of: determining the basic appearance of the sliding shaft sleeve; analyzing and defining a design variable and a definition domain, which influence the shape of the sliding shaft sleeve; sampling a design space by using a Latin hypercube experiment design method; calculating the stress response of the sliding shaft sleeve by using a finite element method; constructing the Kriging model, and performing accuracy estimation; and constructing a mathematical optimization model, solving the optimal design scheme of the sliding shaft sleeve, and validating by using the finite element method. By using the design variable correlation and variability characteristic of the Kriging model, the unbiased optimal estimation is performed, and guidance is provided for optimal design of the structure of the sliding shaft sleeve. Compared with the conventional method, the method provided by the invention has the characteristics of high calculation speed, optimal scheme design and high reliability.

The invention discloses a structure robustness optimization design method containing interval parameter uncertainty. The method comprises the following steps that a structure robustness optimization design model based on an internal is built; sample points are obtained by adopting a Latin hypercube sampling and co-simulating technique; a Kriging proxy model for predicting a target function and a constraint function is constructed; an interval robustness optimization design model is solved by adopting a double layer-nested genetic algorithm, left boundaries and right boundaries of the target function and the constraint function are calculated in the inner layer of the genetic algorithm, and in the outer layer of the genetic algorithm, total interval constraint violation degree vectors of all design vectors are calculated, and the feasibility of the total interval constraint violation degree vectors is judged; all the design vectors are subjected to advantage and disadvantage sorting according to a superior relationship criterion based on the interval constraint violation degree vectors; when a largest evolution algebra or convergence threshold value is achieved, the optimal solution of the robustness optimization design model is output, and the structure robustness optimization design containing interval parameter uncertainty is achieved.

The invention discloses an industrial mechanical arm precision calibrating method based on collaborative Kriging and belongs to the technical field of robots. A device used for the method is composed of an industrial mechanical arm, a laser tracker and a target ball. The target ball is fixed to the tail end of the industrial mechanical arm and serves as a tool center point. According to the method, actual coordinates of some points are measured through the laser tracker; then position errors of theoretical coordinates and the actual coordinates of the points are obtained; and by building a crossover variation function and adopting a collaborative Kriging interpolation method, the position errors of the points in the movement space of the industrial mechanical arm are estimated. The method is simple, it is not needed to build a kinetic model of the industrial mechanical arm, and the method has the beneficial effects that universality is good, the running precision of the industrial mechanical arm can be improved, and inner parameters of an industrial mechanical arm controller device are not needed to be modified.

The invention discloses a gear contact fatigue reliability analysis method. Firstly, the contact stress model of gear is established, the residual fatigue strength after a certain cycle is obtained onthe basis of a fatigue S-N curve, and then the function of gear contact fatigue failure is constructed. Then, according to the distribution characteristics of the random parameters, the Monte Carlo method is used to generate point set, the initial Kriging model is constructed by randomly selecting N points as the experimental design points, and then the sample points which are closest to the limit state surface or have the largest error are obtained by active learning strategy, and the sample points are added to the original experimental design points as the best sample points, and the Kriging model is updated until convergence. According to the convergent Kriging model, the approximate value of the function corresponding to all the sample points is obtained, and the failure probability is calculated by Monte Carlo method. Finally, an example is given to verify the feasibility of the proposed method. The gear contact fatigue reliability analysis method of the invention is more efficient and practical.

The invention discloses a calculating method and system of a well-to-seismic integration average speed field. The method comprises the steps of: utilizing a well logging facies type of a target layer and a seismic facies type of the target layer to dividing a sedimentary facies of the target layer, encoding the sedimentary facies, and obtaining a sedimentary facies code; utilizing an earthquake to superpose speed fields, and by utilizing a Dix formula to calculate an earthquake average speed; utilizing well logging data to calculate a well logging average speed at each well drilling position of the target layer; and using the sedimentary facies code as a bound term, using the earthquake average speed as a secondary variable, using the well logging average speed as a main variable, utilizing a Co-Kriging estimating algorithm to carry out Co-Kriging interpolation, and obtaining a well-to-seismic integration average speed field. According to the invention, the high-precision well-to-seismic integration average speed field calculating method under the sedimentary facies constraint is utilized, and the consistence between a speed field transverse change trend and practical geological characteristics is ensured, so that the time-depth conversion precision of a structural map is improved.

The invention discloses a comprehensive analysis method for spatial and temporal distribution of environment variables, and the method comprises the steps: calculating a test variation function valueat each spatial and temporal lag distance, and carrying out the fitting of a theoretical variation function model; combining the spatial and temporal sampling point data, carrying out the spatial andtemporal Kriging interpolation, and estimating the geographic attribute value of an unmeasured spatial and temporal position; building a quantitative relation between environment variable values and aregional position, forming a trend of the spatial and temporal distribution of environment variable values, and obtaining a prediction result based on the spatial and temporal Kriging; proposing various types of spatial and temporal uncertainty estimation methods; and finally estimating the spatial and temporal distribution of environment variables visually. The method gives full consideration tothe spatial and temporal structural property and continuity of the environment variables, achieves the full simulation and analysis of the spatial and temporal distribution characteristics of the environment variables from many aspects: modeling, prediction, trend analysis, uncertainty analysis and the space and time, and provides a basis for the spatial and temporal decision making and auxiliaryanalysis for regional environment estimation and related departments.

The invention relates to an air quality index prediction method, in particular to an air quality index prediction method based on spatial and temporal distribution characteristics. The method adopts a time series prediction method to predict time orientation, i.e. an air quality index at certain time in the future; and then, a Kriging interpolation method is adopted, and the known latitude and longitude coordinates of a monitoring site are combined with a time series prediction result to carry out interpolate estimation on the air quality index of any place of a whole area. Therefore, the air quality index prediction method has the following advantages that the complexity of a model is lowered, whole calculation time is shortened, and meanwhile, the accuracy of the model is guaranteed; and in addition, the air quality indexes in multiple time periods in one day at each place within the area can be more accurately predicted.

The invention discloses a reliability design method of a force applying component of a high-speed press considering multiple types of uncertainties. The method includes the following steps: considering the random, interval and fuzzy uncertainties of high-speed press force components, choosing the minimum reliability value under the influence of three uncertainties as reliability index, establishing the stochastic model of high-speed press force components, and establishing the stochastic model of high-speed press force components; interval-Fuzzy mixed reliability design model; according to theconservation principle of entropy and '3 sigma criterion', a simplified stochastic-interval reliability design model; adopting Latin hypercube sampling and cooperative simulation technology, the Kriging model of function and objective function is constructed. The simplified reliability design model is decoupled from the reliability analysis to form a two-loop optimization solution. The inner loopuses adaptive step-size iterative method for reliability analysis, and the minimum value of reliability index is obtained. The outer loop uses genetic algorithm to optimize the design vector, and judges the feasibility of the design vector according to the reliability analysis results. When the maximum evolutionary algebra or convergence threshold is reached, the optimal solution is output.

The invention discloses a space-time continuous PM2.5 inversion method based on foundation and satellite observation. The method comprises the following steps: dividing a monitoring area into a plurality of sub-areas; Establishing a random forest regression model for each sub-region, and carrying out inversion under the optimal model to obtain a PM2.5 concentration estimation value of each sub-region; Calculating a spatial interpolation observed by each station in each sub-region by using a common Kriging interpolation algorithm; Based on the root-mean-square error of the PM2.5 concentration satellite estimation value and the spatial interpolation, calculating the PM2.5 concentration satellite estimation value and the spatial interpolation by using an inverse variance weighting method to obtain a final PM2.5 concentration inversion value; According to the method, multi-scale segmentation and a random forest regression model are comprehensively adopted, the ground observation result isinterpolated, and seamless high-precision calculation of the near-ground PM2.5 concentration is achieved.

The invention discloses a gear drive reliability assessment method based on a Kriging model and is applied to the field of reliability assessment. According to the gear drive reliability assessment method, the Kriging model is established firstly according to an initial sample, then whether variable coefficients meet the requirements or not is judged according to the established Kriging model, new variable coefficients are recalculated in a sample point adding mode. The stress calculation quantity based on a finite element method in a traditional method is greatly decreased. The gear drive reliability assessment method adopts a Monte Carlo method to calculate the structural reliability, and meanwhile combines with a learning function to obtain a high-precision agent model with fewer sample points, and accordingly testing times are decreased.

The invention provides a WSN multidimensional vector fingerprint positioning method based on Kriging. The method comprises the following steps: step 1, carrying out Gauss filtering processing on a to-be-processed RSSI (received signal strength) value with a known position; step 2, carrying out optimal, unbiased and linear estimation on the RSSI value within an unknown position point in a positioning area of a processed sample with the known position by adopting an adaptive Kriging interpolation algorithm; step 3, repeating step 1 and step 2 on all beacon nodes, and carrying out a union set operation on all acquired single-dimensional fingerprint vectors to successfully construct a multidimensional fingerprint vector of the positioning area; step 4, acquiring grids corresponding previous mum vectors with similarity from high to low by adopting a vector similarity matching algorithm, that is a node positioning range; and step 5, classifying the acquired previous mum grids by adopting a K-Means clustering algorithm, extracting a cluster head of a cluster (a geometric center of the cluster) containing the most grids to serve as actual positioning result of the node, and outputting the actual positioning result of the node.

The invention discloses a forest soil nutrient spatial prediction method based on artificial neural network Kriging interpolation, which comprises the following steps of: obtaining environmental factor grid data; calculating to obtain a forest soil nutrient spatial distribution diagram based on a multi-layer perceptron neural network; carrying out residual calculation between a measured nutrient value and a predicted value; carrying out analysis and verification on the prediction residual of the neural network; carrying out semi-variance calculation of the residual simulating a model determined by a semi-variance function to obtain model types and parameters; carrying out ordinary Kriging interpolation on the parameters of semi-variance model parameters to obtain the spatial distribution of the neural network prediction residual; adding a forest soil nutrient grid and a prediction residual grid based on a multi-layer perceptron neural network to obtain the forest soil nutrient spatialdistribution diagram based on the artificial neural network Kriging interpolation. The prediction precision of the method is obviously improved compared with a method by using only a multi-layer perceptron neural network model or ordinary Kriging interpolation.

The invention provides a Kriging Kriging-based side slope system failure probability calculation method side slope system failure probability calculation method based on Kriging Kriging. An intensityreduction method SRM is proposed to evaluate the stability coefficient; an initial sampling point strategy and an active learning function are adopted; an active learning Kriging AK proxy model of anoriginal extreme state function LSF is constructed; the Monte Carlo simulation MCS and the AK agent model are combined to evaluate the failure probability of the slope system. According to the method,tThe influence of random variables and related parameters thereof on the slope stability can be quantified, the number of initial sample points is greatly reduced, the calculation efficiency is effectively improved, the sliding surface of any shape in the soil slope can be automatically recognized, and reliability analysis is more convenient when the layered slope with a complex geometrical shapeis subjected to reliability analysis.

The invention discloses a method and system for detecting a microseism event. The method includes the steps that the optimal time-window length L obtained after a microseism detection sequence of a marked microseism wave is trained with the first-order liner regression function and the kriging interpolation method is obtained; a to-be-detected microseism data sequence in time order is obtained; afirst time window and a second time window following the first time window are established, wherein the lengths of the two time windows are both L; data filling is conducted on the left side and the right side of the microseism data sequence; a first piece of data, aligned with the center of the first time window, of the microseism data sequence is slid by two time windows till the center of the first time window is aligned with a final piece of data of the microseism data sequence; every time sliding of the step size of one piece of data is conducted, the data in the two time windows is subjected to chi-square testing to determine whether a microseism wave is generated at each piece of data in the microseism data sequence. By means of the method and system, the influences of noise on detection precision can be effectively avoided, and detection accuracy can be improved.

The invention provides a hole position correcting method of an automatic hole forming system. The method comprises the following steps: a three-dimensional model of a workpiece to be punched is built;theoretical positions of a reference hole and a hole to be formed are marked; an actual position of the reference hole is machined and measured; a hole position deviation of the reference hole is calculated; based on a Kriging model, response functions delta u (x), delta v (x) and delta w (x) of the hole position deviation and mean square error functions su2 (x), sv2 (x) and sw2 (x) are obtained;three components of the hole position deviation of the hole to be formed are calculated according to the theoretical position of the hole to be formed and the three response functions; correspondingmean square errors are calculated according to the theoretical position of the hole to be formed and the three mean square error functions; and an actual position of the hole to be formed is obtained.The mean square errors of the hole position deviation of any one hole to be formed calculated through the method are determined by the hole position deviation of reference holes at two ends and the hole position deviation of multiple adjacent holes, so that the calculating precision of the hole position deviation of the hole to be formed is improved.

The invention discloses a multi-objective optimization method for injection molding parameters. The method is a fuzzy decision Gkriging-NSGA-value strategy processing multi-objective optimization design method based on an improved Kriging agent model Gkriging, a non-dominated sorting genetic algorithm NSGA-II and a value set, and is used for solving the problem of fuzzy decision Gkriging-NSGA-value strategy processing multi-objective optimization design. Selecting injection mold sub-runner section size parameters and injection molding process parameters as decision variables to be optimized; respectively taking the maximum volume shrinkage rate, the flow channel total volume and the forming period of the product as evaluation indexes of the product quality, the production cost and the production efficiency, establishing a model, obtaining an optimal value of multiple targets of the quality, and realizing multi-target optimization of the comprehensive quality of the product through a multi-target decision-making method. According to the injection molding parameter multi-objective optimization method, high-quality injection molding products can be economically and rapidly obtained onthe basis of a one-mold two-piece mold.

Provided is a particle swarm optimization algorithm based lightweight car body structure implementation method. The method comprises: by carrying out high-precision finite element modeling and collision condition simulation analysis on a specified car body, carrying out sampling on a obtained 40% frontal offset collision simulation model in a optimization problem design domain, establishing a Kriging approximation model, and using a deterministic coefficient to carry out precision verification on the Kriging approximation model, so as to obtain a high-precision Kriging approximation model; and identifying a constraint domain with a lower violation degree by using a data mining technology, obtaining an optimization result by using a particle swarm optimization algorithm, rounding the optimization result to a project value, and verifying whether the project value meets a collision condition requirement through finite element simulation calculation, so as to obtain an optimized lightweight car body design structure of collision condition. The method disclosed by the present invention operates efficiently, and can provide a high-precision lightweight body design approximation model.

The invention discloses a variation function model optimization method in forest site index spatial-temporal estimation. The method comprises the following steps of (1) establishing a reliable site index variation function model optimization method by utilizing a computer, thereby ensuring effective combination of fixation and quantification of variation function selection; (2) establishing a unified site index variation function multi-scale nested model expression form and a computer automatic parameter optimal fitting method by utilizing the computer, and realizing an expansion algorithm of a multi-scale nested model function in mainstream statistic software, thereby ensuring effective prediction of a spatial interpolation algorithm; and (3) establishing a site index spatial-temporal variation function model expression form by utilizing the computer, and realizing a Kriging spatial-temporal interpolation algorithm, thereby improving the precision and reliability of the spatial-temporal estimation. The artificial subjective factors can be effectively reduced; the site index anisotropy and multi-scale dependence can be effectively described; the effective prediction of the spatial interpolation algorithm can be ensured; and the precision and reliability of the spatial-temporal estimation are improved.

The invention discloses a small wind turbine wing type aerodynamic robust optimization design method suitable for turbulent working conditions, belonging to the technical field of wind turbines. The invention adopts the non-embedded probability collocation point method in the design to realize the quantitative characterization of the turbulence intensity of the uncertain parameter. Through the improved Hick-Henne type function parameterization method, Latin hypercube test method and CFD numerical calculation method, the kriging agent model between design variables, uncertain parameters and themaximum lift-to-drag ratio of the airfoil is established. On this basis, a robust optimization mathematical model is established to maximize the mean value of the maximum lift-to-drag ratio and minimize the standard deviation of the wind turbine wing under uncertain turbulent conditions. The non-embedded probabilistic configuration point method, the kriging proxy model, and the NSGA-II optimization algorithm are used to optimize the wind turbine airfoil. The invention improves the maximum lift-drag ratio of the airfoil, reduces the fluctuation range, improves the wind energy capture efficiency, and enhances the aerodynamic robustness under the turbulent condition. At the same time, the computational workload of robust optimization design is reduced, and the optimization efficiency is improved, which provides an important reference for the optimization design of wind turbine wing under turbulent conditions.