12results about How to "Realize Quantitative Prediction" patented technology

The application discloses a kind of prediction methods of high-strength steel wire high temperature creep behavior of rust, belong to bridge cable safety assessment technical field.The method is first obtained by test the material intrinsic material parameters of rust high-strength steel wire test piece and un-rust high-strength steel wire test piece;Then three-dimensional scanning quantization corrosion morphology is used, the maximum pit depth of rust high-strength steel wire surface and the pit root radius of pit bottom are extracted, and then the stress concentration coefficient and the effective bearing area decay function after net section loss are calculated, and the corrosion damage index is introduced;On this basis, the creep strain rate prediction model considering local stress concentration, section loss and material damage is established.The prediction method of the application realizes the quantitative prediction from pit micro-morphology to macro creep behavior, and has great engineering application value for evaluating the safety and residual life of in-service bridge cable.

This application provides a temperature control method and system for vacuum wetting indium in an array field emitter, relating to the field of vacuum electronic device manufacturing technology. The method includes: obtaining the three-dimensional temperature field distribution of the surface of the field emitter using a deep convolutional neural network based on spectral radiation energy; calculating the transverse and longitudinal temperature gradients between the emitter pins based on this distribution data, and inputting this data into an evaluation model to dynamically assess the wetting uniformity; and generating multi-temperature zone heating power control commands based on the uniformity results using a proportional-integral-derivative controller, and adjusting the power output of each temperature zone to ensure the array temperature field meets the requirements for promoting uniform indium wetting. This application improves the control accuracy and reliability of indium wetting uniformity in complex three-dimensional field emitters under vacuum and high-temperature conditions.

This invention relates to the field of seismic resistance technology for spatial frame structures, and discloses a method for determining the energy dissipation mechanism of a steel-concrete composite column-composite beam spatial frame. The energy dissipation mechanism includes steel beams, steel-concrete composite columns, and reinforced concrete slabs. The steel beams are welded and fixed to the steel-concrete composite columns via reinforcing rings, and the steel beams are fixedly connected to the reinforced concrete slabs via studs. Tie bars are provided at the ends of the steel-concrete composite columns. The ratio of the flexural bearing capacity of the steel beams to that of the steel-concrete composite columns is within the range of 0.42 to 1.05. By introducing the ductile damage parameter of the steel, combined with the inter-story drift angle, cumulative energy dissipation, beam-column energy dissipation ratio curve, and finite element calculation results of stiffness damage of the spatial frame, the energy dissipation characteristics and energy dissipation mechanism type of the structure are determined. This invention aims to solve the technical problems in the prior art where the steel-concrete composite columns do not form sufficient compression-bending hinges for energy dissipation during seismic resistance, easily leading to collapse, and the technical problems of using beam energy dissipation mechanisms in seismic design while rarely considering column energy dissipation.

This invention discloses a method for printing two-dimensional structures of thermosetting materials with controllable surface roughness, comprising: controlling the rheological properties of the extrusion behavior of a selected thermosetting material; calculating and determining the relationship between the deposition morphology of the thermosetting material and printing parameters, and plotting an H-V phase diagram to determine the critical printing range for achieving uniform deposition; establishing a single-fiber deposition morphology evolution model and a multi-fiber fusion geometric evolution model to provide a correlation between the degree of fusion of adjacent deposited fibers and the surface micro-roughness, thereby obtaining a preset surface microstructure morphology; and, according to the required surface roughness, solidifying and locking the interface through thermal curing at different fusion stages to obtain a continuously adjustable and structurally stable two-dimensional film of thermosetting material. This invention can realize the printing of two-dimensional structures of any thermosetting material system on any spread substrate, and can continuously and programmably adjust the surface roughness.

The application discloses a drinking water taste score method and device, equipment and a storage medium, and relates to the field of water quality detection. Water quality index data and taste score data are acquired, the water quality data is formed into an initial water quality index matrix, the taste score data is formed into a taste score vector, and a taste regression model is established; principal components of water quality are extracted based on the taste regression model, and principal component indexes are screened from the initial water quality index matrix and the taste score vector according to a mapping relationship therebetween; the principal component indexes are screened with reference to a variable projection importance and a correlation coefficient reference standard, and key water quality factors are extracted; the key water quality factor set is taken as new independent variables, the water quality index matrix and the taste score vector are subjected to regression modeling again, a taste score prediction model is obtained, and taste score detection is performed.

The invention relates to the technical field of oil-gas exploration, in particular to a lithologic trap evaluation method, device and equipment, a medium and a computer program.The method comprises the steps that under the condition that a sedimentary facies type is a single-well sedimentary facies, a seismic facies plane distribution diagram corresponding to a target area is obtained; based on the first corresponding relation and the seismic facies plane distribution diagram, obtaining a reservoir porosity plane distribution diagram; based on the second corresponding relation and the seismic facies plane distribution diagram, a packing layer porosity plane distribution diagram is obtained; and determining an evaluation result of the lithologic trap based on the seismic facies plane distribution, the reservoir porosity plane distribution diagram and the packing layer porosity plane distribution diagram. According to the method, when the distribution of the reservoir and the packing layer is predicted, the wave impedance corresponding to the porosity is considered, quantitative prediction is achieved, the evaluation result of the lithologic trap is obtained based on the distribution conditions of the seismic facies, the reservoir and the packing layer, the accuracy of the evaluation result of the lithologic trap is improved, and then the exploration success rate of the lithologic trap is improved.

The invention discloses a collaborative monitoring and early warning method for sag, windage yaw and galloping of a conductor, and belongs to the technical field of online monitoring of power transmission lines. The method comprises the following steps: firstly, deploying a multi-modal sensing network, and synchronously acquiring wire strain, three-dimensional space point cloud and environment wind field data; performing time synchronization and space registration on the multi-source data, and constructing a standardized fusion data unit; then, reconstructing a lead center line based on the fused data, and extracting sag, wind deflection angle and galloping characteristic parameters; further, establishing a nonlinear coupling dynamic model, simulating a wire dynamic response under multi-physics field excitation, dynamically evaluating the risk in combination with a real-time working condition, and triggering graded early warning; and finally, verifying an early warning result through unmanned aerial vehicle inspection, optimizing model parameters by using feedback information, and forming a self-learning closed loop. According to the invention, collaborative perception and coupling analysis of three types of deformation are realized, and the accuracy and foresight of early warning are improved.

This application discloses a method and system for predicting fold-related fractures based on the principle of stress superposition, belonging to the field of geological analysis technology. The method includes: acquiring past 3D seismic data and past regional stress tensors of a region, and constructing a high-precision structural grid cell on the top surface of the target reservoir; based on the high-precision structural grid cell, determining the fracture type and fracture orientation according to the sliding window-least squares surface fitting joint method, the principle of stress superposition, and rock fracture criteria, thus obtaining a fracture prediction model; acquiring the current 3D seismic data and current regional stress tensor of the target region, and inputting them into the fracture prediction model to obtain the current fracture type and current fracture orientation. This application achieves accurate prediction of the type and orientation of fold-related fractures.

The application discloses a shale oil horizontal well microseismic fracture parameter interpretation prediction method, and steps are as follows: step (1), microseismic fracture parameter interpretation prediction data preparation, determining the principle of parameter screening, and collecting the data of the screened parameters; step (2), data preprocessing; step (3), fracture parameter influence factor screening; step (4), regression prediction model construction; step (5), regression prediction model verification and evaluation; and step (6), application of the regression prediction model. The application has the following beneficial effects: 1. two modeling methods are used to establish a shale oil fracturing fracture parameter prediction model, and quantitative prediction of microseismic fracture parameters is realized; 2. high accuracy; 3. as a basis for shale oil horizontal well design, the application can optimize construction scale and design parameters, and also can provide a diagnosis method for fracturing construction, timely adjustment of construction parameters and improvement of fracturing reconstruction effect.

The invention belongs to the field of oil and gas geology, and particularly relates to a method for establishing an identification chart of oil saturation in a reservoir. The method comprises the following steps: carrying out an oil-displacement-water experiment on a plurality of core samples in the same research area, and drawing a charging pressure-oil saturation curve graph according to corresponding oil saturation data of each sample under different charging pressures; introducing the porosity and permeability of each sample, drawing a porosity / permeability-oil saturation and filling pressure relation chart, and connecting data points with the same filling pressure to form a fitting curve; and according to the corresponding porosity and permeability of the fitted curve of the plate under different oil saturation, establishing a porosity / permeability-filling pressure identification oil saturation plate by taking the reservoir physical property and the filling pressure as x and y coordinate axes, thereby providing a theoretical basis for the relationship among the reservoir physical property, the filling pressure and the oil saturation, and providing a theoretical basis for the relationship among the reservoir physical property, the filling pressure and the oil saturation. And oil saturation prediction under different reservoir physical property and dynamic conditions is realized.

This invention provides a method for igneous rock facies classification and prediction based on multi-physics discriminant factors, relating to the field of oil and gas field exploration and development technology. The method includes: S1: Constructing a multi-dimensional facies classification model based on diagenesis, integrating lithology index and structural maturity index to quantitatively classify geological facies; S2: Performing principal component analysis on well logging curves to select sensitive well logging curves and construct a sensitive well logging dataset; S3: Constructing rock physical facies factors through Fisher discriminant analysis; S4: Projecting known facies samples onto the rock physical facies factor space, training a classification model using a support vector machine algorithm, and generating a facies identification map; S5: Substituting target well data into the model to complete single-well facies identification; S6: Establishing the correlation between rock physical facies factors and seismic elastic parameters, inverting the seismic data volume into a three-dimensional attribute volume of rock physical facies factors based on a Bayesian inversion framework, fusing them to generate a three-dimensional facies model, thus realizing facies prediction from well point to three-dimensional space.

This invention discloses a hybrid attention network method for 3D prediction of deep-sea rare earth elements, integrating spatial and depth data, and relating to the interdisciplinary fields of artificial intelligence and marine mineral resources. The method first acquires multi-source environmental and depth data, which are then integrated, cleaned, spatially aligned, interpolated, and standardized to construct a model input containing environmental feature image patches and standardized depth values. Spatial feature vectors are extracted using a convolutional neural network, and depth feature vectors are encoded using a multilayer perceptron. The two types of features are concatenated, and dynamic weights are generated and weighted using an attention network to obtain a weighted feature vector. This weighted feature vector is input into the prediction head module, and the model is trained using a loss function, optimizer, and early stopping mechanism. The trained model is applied to a 3D mesh of the target region, and after inference prediction and de-standardization, the predicted 3D rare earth element content is output. Simultaneously, the feature contribution is analyzed through an interpretable model.