9 results about "Volumetric model" patented technology

This invention belongs to the field of petroleum exploration and discloses a quantitative characterization method for structural fracture parameters based on the coupling of the minimum energy consumption and minimum action principle. To overcome the shortcomings of existing technologies in achieving quantitative prediction of structural fractures from qualitative description, this invention first calculates the energy consumption of fracture rupture through rock mechanics experiments; then, it couples the minimum energy consumption principle and the minimum action principle to establish a rock fracture criterion; based on this, it derives and establishes quantitative characterization models for fracture aperture, volumetric density, and linear density; subsequently, it constructs a heterogeneous mechanical parameter volumetric model and performs elastoplastic geostress field simulation; finally, it achieves batch prediction of structural fracture parameters through programming, and verifies the reliability of the prediction results using core, imaging logging, and production dynamic data. This invention, starting from the physical essence of energy distribution and path selection, provides a unified theoretical framework for rock fracture and significantly improves the prediction accuracy of fracture "sweet spots."

This invention discloses an uncertainty-based method for three-dimensional reconstruction and intelligent sampling of underground space, comprising the following steps: Step 1: Constructing a multi-source heterogeneous data acquisition system and performing data preprocessing and spatiotemporal registration; Step 2: Extracting multimodal heterogeneous features and unifying spatial mapping based on deep learning; Step 3: Constructing a high-fidelity three-dimensional reconstruction volumetric model of underground space based on adaptive octree subdivision; Step 4: Constructing a high-fidelity intelligent sampling database containing a Bayesian dynamic update layer; Step 5: Performing uncertainty assessment-driven sampling-assisted decision-making to update the database. This invention solves the problems of insufficient depth of multi-source data fusion, low fidelity due to rigid three-dimensional modeling mesh, and lack of an uncertainty-based active sampling feedback mechanism in the prior art, achieving accurate characterization of complex strata and pollution distribution and intelligent feedback of sampling decisions.

This application discloses a machine learning-based method, device, and medium for predicting frequent gout attacks, relating to the field of machine learning technology. The method includes: extracting radiomics features from regions of interest corresponding to DECT images; performing feature selection on the radiomics features to obtain a feature subset; training a pre-defined multi-model group based on the feature subset through multi-model cross-validation until each model converges, thereby determining the radiomics model and the DECT volume model; constructing a clinical prediction model for gout patients based on factor regression analysis according to factors influencing gout attacks; and determining the probability of gout attacks in gout patients through multi-model nomograph validation based on the radiomics model, the DECT volume model, and the clinical prediction model. This application solves the technical problem in existing technologies where gout prediction cannot effectively identify and predict frequent gout attacks using CT images.

A method for three-dimensional (3D) registration of three-dimensional virtual models, performed by a computing device, according to one embodiment of the present disclosure, comprises the steps of: generating a 3D interior digital model of an indoor space using a plurality of datasets collected in the indoor space; generating a 3D exterior digital model of an outdoor space using a plurality of image sets collected in the outdoor space; generating outline-based 3D volumetric models for the 3D interior digital model and the 3D exterior digital model; and performing registration between the 3D interior digital model and the 3D exterior digital model on the basis of external shape matching between a 3D interior volumetric model and a 3D exterior volumetric model.

Disclosed is a method of simulating an ultrasound scan of tissue in real-time. The method comprises loading a three dimensional deformable soft tissue model of a tissue region for scanning, the deformable soft tissue model being a volumetric model and determining a three dimensional interaction between the deformable soft tissue model and at least one medical tool. The method also comprises modifying the deformable soft tissue model according to the three dimensional interaction and properties of the deformable soft tissue model, the properties including compressible and incompressible regions of the deformable soft tissue model and generating a simulated scan of the tissue in real-time according to a position of an ultrasound probe and the modified soft tissue model.

This invention belongs to the field of mining engineering technology, specifically relating to a dynamic design method and system for backfill strength based on a three-dimensional geological model. The system constructs and converts a three-dimensional geological model into a volumetric model, generating theoretical stress maps using numerical simulation. It then combines real-time monitoring data with dynamic coupling analysis and parameter inversion to correct the model. A dynamic decision-making module for backfill strength calculates the critical strength based on the corrected indicators and generates a mix design scheme. An execution module then issues instructions and performs closed-loop optimization. This application solves the problem that backfill strength design cannot respond in real-time to complex mining-induced stress fluctuations, realizing a shift from static to dynamic precision in strength design. While preventing backfill instability risks and enhancing safety, it significantly reduces support costs and resource waste.

A method for three-dimensional (3D) registration of 3D virtual models, performed by a computing device, according to one embodiment of the present disclosure, comprises the steps of: generating a 3D interior digital model of an indoor space using a plurality of datasets collected in the indoor space; generating a 3D exterior digital model of an outdoor space using a plurality of image sets collected in the outdoor space; generating outline-based 3D volumetric models for the 3D interior digital model and the 3D exterior digital model; and performing registration between the 3D interior digital model and the 3D exterior digital model on the basis of external shape matching between the 3D interior volumetric model and the 3D exterior volumetric model.

A system for enhancing a three-dimensional volumetric model according to one embodiment of the present invention is a system for enhancing a three-dimensional volumetric model connected to a user terminal via a network, the system comprising: a model information unit that stores a three-dimensional volumetric model and three-dimensional volumetric model data generated by modeling object images captured by a plurality of cameras using a volumetric technique; a model reconstruction unit that selects optimal data from the three-dimensional volumetric model data corresponding to the three-dimensional volumetric model and reconstructs the three-dimensional volumetric model on the basis of the selected optimal data; a model conversion unit that converts the reconstructed three-dimensional volumetric model into a mesh format; and a model enhancement unit that processes the converted three-dimensional volumetric model using a diffusion model.