12results about How to "Reduce modeling costs" patented technology

A method, apparatus, device, and storage medium for determining the output force of a hydraulic muscle include: acquiring geometric characteristic parameters, material characteristic parameters, and friction characteristic parameters of a target hydraulic muscle; acquiring the current operating parameters of the target hydraulic muscle; determining the elastic equivalent force based on the geometric characteristic parameters, material characteristic parameters, and current operating parameters; determining the frictional force and basic output force based on the geometric characteristic parameters, material characteristic parameters, frictional characteristic parameters, and current operating parameters; and determining the final output force of the target hydraulic muscle based on the basic output force, the elastic equivalent force, and the frictional force. This application establishes a simulation model through physical mechanism derivation. The modeling process only requires conventionally obtainable core parameters, eliminating the need for repeated complex experiments and resulting in low modeling costs. Furthermore, the simulation model comprehensively simulates the rubber elasticity and frictional hysteresis effect of the hydraulic muscle, improving simulation accuracy and achieving low-cost and high-accuracy modeling of the hydraulic muscle's output force.

The application discloses a kind of remote sensing time series data analysis method and system considering the spatio-temporal correlation of geographical object, belong to data analysis technical field.The method includes: obtaining multi-source multi-temporal remote sensing image and auxiliary data and pre-processing, generate consistent time series data stack;In three-dimensional space-time domain, image is divided into voxel and is adjacent tracking, identify geographical process object with evolution behavior and record its attribute;Determine the spatio-temporal topological relationship between geographical process object, generate unified spatio-temporal relationship table by composite reasoning;With geographical process object as node, spatio-temporal relationship as edge constructs geographical process object spatio-temporal graph model, extracts and standardizes the attribute characteristics of node and edge;Importance index of each node is calculated by using graph convolution network and topological dynamic mechanism joint modeling.The application realizes closed-loop analysis from data processing, relationship modeling, importance evaluation to decision support, improves the interpretability and decision effectiveness of remote sensing time series change detection.

This invention discloses a method for predicting the dynamic evolution of pollution plumes based on a physical perception spatiotemporal large model, comprising the following steps: acquiring multi-source heterogeneous monitoring data and constructing a static spatial topology matrix; constructing a PF-STGNN model, which adopts an encoder-decoder architecture; the encoder captures the long-term dependencies of pollution plume evolution through a context-aware temporal self-attention mechanism, and couples dynamic graph convolution with the static spatial topology matrix through a dynamic flow field interactive spatial solution module, outputting a feature matrix containing historical diffusion memories; the decoder ensures temporal unidirectionality through a causal masking temporal self-attention module, injects historical evolution laws into future predictions through a cross-spatiotemporal evolutionary context cross-attention module, and performs spatial morphology verification again through a dynamic flow field interactive spatial solution module; finally, a concentration prediction matrix for future periods is output through a parallel generator. The advantages of this invention are: it can be applied to groundwater pollution monitoring and environmental risk early warning systems.

The embodiment of the invention provides a molecular-level oil refining whole-process model construction method and device and computer equipment. The method comprises the steps that an SOL molecular library is constructed according to input SOL molecular data; constructing a reaction rule base according to the reaction rules; constructing a single device model according to the SOL molecular library, the reaction rule library and the reaction parameter library, and storing the single device model in a whole-process model construction system; and according to the constructed single device model in the construction system or the single device model obtained by importing the drawing and the logistics connection line between the single device models, a whole-process model is constructed and obtained. According to the method, the single device model can be constructed and stored as a system resource, and in the construction process of the whole-process model, the existing single device model can be reused, so that the manual operation of a user is reduced, and the modeling cost of the whole-process model is effectively reduced. And a single device model can be obtained by supporting a drawing import mode, so that the requirements of various whole-process model construction scenes are met.

The invention discloses a cognitive state recognition system based on single-channel electroencephalogram signal task perception and multi-scale modeling. The cognitive state recognition system comprises a task perception time domain feature extraction module, a frequency domain independent feature extraction module, a task perception frequency domain feature fusion module, a self-adaptive feature fusion module and a result output module. The task sensing time domain feature extraction module captures multi-time scale features from local to global by adopting a multi-scale convolutional neural network in combination with a Transform architecture; the frequency domain independent feature extraction module generates time-frequency representation through continuous wavelet transform, and designs an independent encoder for different frequency bands to extract specific features of the frequency bands; the task perception frequency domain feature fusion module adaptively identifies a task related frequency band through a significant frequency band attention mechanism and guides cross-frequency band feature fusion; the adaptive feature fusion module integrates time domain and frequency domain features by using an attention mechanism; and the result output module is used for completing cognitive state classification and providing an interpretable analysis result. According to the method, task related features can be efficiently and accurately extracted from the single-channel EEG signals, high-precision cognitive state recognition is achieved, and the method is suitable for various application scenes such as emotion recognition and workload evaluation.

This application relates to the field of medical image processing technology, and discloses a method, system, device, and medium for predicting tumor status, including: acquiring a set of CT images of the lungs of a target object during the current respiratory cycle; constructing a three-dimensional tumor model of the lung tumor based on the CT image set; the lung tumor has a real volume and real centroid coordinates; performing finite element analysis to obtain a finite element tumor model, calculating the simulated volume and simulated centroid coordinates of the lung tumor; comparing and obtaining the volume retention ratio and centroid offset; predicting the motion state of the lung tumor in the next respiratory cycle to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle; if the motion state prediction quality of the lung tumor meets the preset motion state prediction quality based on the volume retention ratio and centroid offset, then the initial motion state parameters are used as the target motion state parameters to predict the motion state of the lung tumor, thereby improving the accuracy and correctness of radiotherapy.

The application discloses a physical information multi-fidelity neural network three-dimensional cascade flow field reconstruction method based on Fourier characteristics, and relates to the field of aero-engine turbine machinery aerodynamic design. The method comprises the following steps: generating high / low fidelity data sets with boundary consistent and gradient perception sampling; constructing a multi-fidelity neural network containing Fourier characteristic embedding, multi-fidelity collaborative network and RANS equation residual constraint; adopting a two-stage training strategy, first optimizing data fitting loss to learn the flow field mapping relationship, and then jointly improving the conservation with physical loss; finally, realizing fast, high-precision and physically consistent reconstruction of three-dimensional cascade space coordinates to key physical quantities such as velocity, static pressure and temperature. The method significantly reduces the dependence on high-fidelity data, improves the prediction accuracy in high gradient areas, and is suitable for rapid iterative design of aero-engine cascades.

The invention belongs to the field of discrete event system control, intelligent manufacturing and reinforcement learning, and discloses a state feedback control strategy generation method and system of a time delay Petri network system in a non-deterministic environment, and the method comprises the steps: constructing a time delay Petri network model containing controllable / uncontrollable transition and minimum transmission delay constraint, defining a time extension state formed by the identification and the enable transition residual delay; a two-stage random judgment mechanism is introduced, two types of non-deterministic factors of control execution errors and uncontrollable event preemption are modeled, and the state transition probability is deduced; a control problem is formalized into a Markov decision process, and a reward function with time consumption as a negative reward and deadlock and an ultra-long path as strong punishment is designed; and adopting a table type Q learning algorithm based on dynamic learning rate scheduling, iteratively updating an action value function in interaction with a simulation environment, and exporting a state feedback control strategy. The method can be widely deployed in discrete event system control scenes such as flexible manufacturing, logistics scheduling and multi-robot cooperation.

The invention discloses a method and system for establishing a complementary metal oxide semiconductor tube model at extremely low temperature, and the method comprises the steps: obtaining an electrical characteristic curve of a CMOS tube at least at two extremely low temperature points, or carrying out the curve fitting of a known CMOS tube of a model; on the basis of the obtained CMOS tube electrical characteristic curves of the at least two low-temperature points, predicting the CMOS tube electrical characteristic curve under the target temperature Ttarget; modeling software is adopted to carry out curve fitting parameter extraction on the CMOS tube under the Ttarget, important parameters are corrected, and an electrical characteristic curve of the CMOS tube under the Ttarget is reconstructed based on the extracted parameters and the corrected parameters; complete modeling of low-temperature electrical behaviors of the CMOS tube is further completed after parameter extraction and modeling of the CMOS tube under the Ttarget are completed through modeling software, and accurate matching of a device characteristic curve and a real physical state under the extremely low temperature is achieved.

The embodiment of the invention provides a fissure connectivity modeling method and device based on surrounding rock fissure JRC, and the method comprises the steps: building a fissure quantitative analysis model based on a fissure image obtained through borehole imaging, and describing the geometric morphology of a fissure through a sine curve; fitting the fracture quantitative analysis model, and extracting characteristic parameters representing the geometrical morphology of the fracture; calculating a roughness coefficient JRC of the fracture surface based on the characteristic parameters, and representing the fracture as a fracture plane equation in a three-dimensional space through coordinate transformation; establishing an extension length probability model of the crack based on the JRC and the crack plane equation; and for any two fractures from different drill holes, calculating a spatial intersection line according to respective plane equations, and then calculating a connectivity probability along the intersection line based on an extension length probability model to complete quantitative modeling of fracture connectivity. According to the method, the fracture connectivity probability criterion is established by combining the fracture roughness coefficient JRC with the geometric parameters, and quantitative evaluation of the fracture connectivity is achieved.

This invention discloses a blade structure stress prediction method driven by the fusion of multi-source data and a reduced-order model. Through a reduced-order surrogate model combining unidirectional fluid-structure interaction (FSI) simulation of the blade, it achieves rapid prediction of the blade structure stress field under different wind speeds, rotational speeds, and pitch angles. The method includes: constructing a unidirectional FSI simulation model of the wind turbine blade; extracting reduced-order modes and coefficients from high-fidelity blade stress field data to reduce the order of the full-order simulation results; constructing and training a surrogate model based on the reduced-order modes and coefficients, and obtaining the mapping relationship between different wind speeds and reduced-order mode coefficients by optimizing the model hyperparameters; the surrogate model rapidly predicts the modal coefficients of the blade stress field based on the real-time wind speed of the wind turbine, and reconstructs the blade stress field results with the reduced-order modes. This invention can rapidly predict the blade stress field under real-time wind speed conditions based on a small number of high-fidelity simulation samples, which is significant for the intelligent operation and maintenance of offshore wind turbines.

The application provides a correction method and system of an OPC model and a computer readable storage medium, and is applied in the field of semiconductor technology. In the application, two fixed safety intervals currently set by the industry, i.e. a first minimum interval of side-to-side in a mask rule constraint condition and a second minimum interval of angle-to-angle, can be determined through an initial OPC model; then a new parameter, i.e. a direct length, constructed by the application is used to establish the correlation between the interval between adjacent test patterns and the change of the direct length of side-to-side between adjacent test patterns, so that the two independent safety intervals of side-to-side and angle-to-angle in the mask rule constraint condition in the prior art are integrated, so that the safety interval of the OPC model can dynamically change with the actual geometric shape (direct length) of the test pattern, i.e. a new mask rule constraint condition more in line with the constraint rule between adjacent patterns in the actual photolithography process is proposed, the photolithography process window is expanded, and the convergence is improved.