8 results about "Stochastic partial differential equation" patented technology

The invention relates to a temperature field prediction and parameter inversion method based on a physical constraint generative adversarial network. The method comprises the following steps: acquiring sensor data and sampling random latent variables; constructing a generative adversarial model comprising a generator, a discriminator, an auxiliary parameter generator and an auxiliary variational encoder based on sensor data and a physical constraint partial differential equation; by minimizing reverse KL divergence and introducing physical consistency constraints, boundary condition constraints and information entropy regularization items, parameters of a generative adversarial model are jointly optimized; after offline training is completed, new space-time coordinates and random latent variables are input, a temperature field prediction result is obtained through a trained generator, and PDE parameter estimation of a corresponding position is obtained through an auxiliary parameter generator. Compared with the prior art, the method can perform unified modeling and prediction on the space-time dynamic system dominated by the random partial differential equation, and has generalization ability under uncertainty quantization, physical parameter estimation and sparse observation data.

The invention relates to the field of medical artificial intelligence, and discloses a CRRT data omnibearing acquisition and optimization processing system based on artificial intelligence, and the system comprises an acquisition calibration module which is used for acquiring CRRT equipment parameters, physiological signals and laboratory inspection data, forming multi-source data, and carrying out the time alignment and space calibration of the multi-source data, and obtaining calibration data; the modeling estimation module is used for constructing a space-time dynamic model for substance transportation and biochemical reaction in the CRRT treatment process based on a random partial differential equation, estimating a state variable in combination with calibration data, and generating high-dimensional state data; and the fusion reasoning module is used for carrying out dimensionality reduction and adversarial denoising processing on the high-dimensional state data. Through multi-source acquisition and space-time calibration of CRRT equipment parameters, physiological signals and laboratory data, a treatment data basis is constructed, space-time dynamics modeling of substance transportation and biochemical reaction is performed based on a random partial differential equation, and dynamic description of a treatment process is realized.

This invention relates to the field of medical artificial intelligence and discloses a comprehensive data acquisition and optimization system for CRRT based on artificial intelligence. The system includes: an acquisition and calibration module for acquiring CRRT equipment parameters, physiological signals, and laboratory test data to form multi-source data, and performing time alignment and spatial calibration to obtain calibration data; a modeling and estimation module for constructing a spatiotemporal dynamic model of material transport and biochemical reactions during the CRRT treatment process based on stochastic partial differential equations, and estimating state variables using calibration data to generate high-dimensional state data; and a fusion and inference module for performing dimensionality reduction and adversarial denoising on the high-dimensional state data. Through multi-source acquisition and spatiotemporal calibration of CRRT equipment parameters, physiological signals, and laboratory data, a foundation for treatment data is constructed. Based on stochastic partial differential equations, spatiotemporal dynamic modeling of material transport and biochemical reactions is performed, enabling dynamic characterization of the treatment process.

The present application belongs to the technical field of flight simulator database management, and relates to a data synchronization method for a flight simulator configuration database, aiming to solve the problems of low synchronization efficiency and difficult guarantee of data consistency. The present application generates / calibrates synchronization parameters through graph neural operators, optimizes the optimal synchronization sequence containing execution timing through manifold, generates a semantic consistency mapping table through a parameterized quantum model in combination with type constraint Hamiltonian and semantic matching baseline; then, based on the resource allocation benchmark in the synchronization parameters, the subsystem state is modeled as a stochastic partial differential equation, and the dynamic priority strategy is obtained by solving the HJB equation; after executing the synchronization task according to the optimal synchronization sequence and the mapping table, the consistency is verified by the directional slice distance, and if it exceeds the standard, rollback is triggered. The present application constructs a closed-loop system of parameter generation, sequence planning, field mapping, dynamic control and consistency verification, improves the synchronization adaptability and accuracy, and guarantees the data consistency.

The invention belongs to the technical field of flight simulator database management, relates to a data synchronization method of a flight simulator configuration database, and aims to solve the problems that the synchronization efficiency is low and the data consistency is difficult to guarantee. According to the method, synchronization parameters are generated / calibrated through a graph field neural operator, an optimal synchronization sequence containing an execution time sequence is generated through manifold optimization, and a semantic consistency mapping table is generated through a parameterized quantum model in combination with a type constraint Hamiltonian and a semantic matching baseline; modeling the state of the subsystem into a random partial differential equation based on a resource allocation benchmark in the synchronization parameters, and solving an HJB equation to obtain a dynamic priority strategy; and after the synchronization task is scheduled and executed according to the optimal synchronization sequence and the mapping table, verifying the consistency by using the direction slice distance, and triggering rollback if the consistency exceeds the standard. According to the method, a closed-loop system of parameter generation, sequence planning, field mapping, dynamic regulation and control and consistency verification is constructed, the synchronization adaptability and accuracy are improved, and the data consistency is guaranteed.

The invention relates to the technical field of electric energy storage, in particular to a prediction method, device and equipment for generating capacity increment, a storage medium and a product. The method comprises the steps of predicting a wind power generation increment of a wind power station after a future time period based on wind power generation parameter information, predicting a photovoltaic power generation increment of a photovoltaic power station based on photovoltaic power generation parameter information, and predicting a load increment of a virtual power station based on load parameter information, predicting charge and discharge increments of charge and discharge of the clustered resources based on the charge and discharge parameter information; and on the basis of a random partial differential equation, according to the wind power generation increment, the photovoltaic power generation increment, the load increment, the charging and discharging increment, the wind power generation parameter information, the photovoltaic power generation parameter information, the load parameter information and the charging and discharging parameter information, predicting the power generation increment of the virtual power plant to obtain the total power generation increment of the virtual power plant. According to the invention, the problems of poor real-time performance and poor accuracy of prediction of the power generation increment of the virtual power plant can be solved.

The invention relates to the field of seedling cultivation, and discloses a method for fusing water quality regulation and disease control in seedling cultivation, which comprises the following steps of: acquiring multi-field coupling space-time continuous data of a water quality field, a biological and physiological field, a medicament diffusion field and an environment auxiliary field in a seedling cultivation pond; performing fractional order multi-field data preprocessing on the multi-field coupling space-time continuous data to obtain a feature vector containing a long-time memory feature and a coupling feature; and constructing a fractional order LSTM-SPDE coupling prediction model formed by coupling the fractional order LSTM and a random partial differential equation based on the feature vector, and predicting water quality evolution data in a future preset duration by taking the real-time feature vector as input. Multi-field coupling space-time continuous data is acquired, information containing long-term memory features and multi-field coupling features is accurately extracted through fractional order multi-field data preprocessing, and the future water quality evolution trend and disease risk level are pre-judged in advance, so that dynamic cooperation, pre-judgment and long-term adaptation of water quality regulation and control and disease prevention and control are realized.

The application belongs to the technical field of scientific computing and artificial intelligence, and in particular to a random partial differential equation regular structure feature construction method and system. The integral operation of the regular structure feature is transferred from the physical space to the Fourier space. The Fourier diagonalization property of the Laplace operator is used to convert the integral of the partial differential equation coupled at each space point into the accurate solution of the scalar ordinary differential equation independent of each wave number. On the applicable periodic domain or the region processed by the periodization, the spectral accuracy is realized. Further, the serial recursive format is expanded into the causal convolution matrix form in the Fourier space. The integral factor power is pre-calculated and the three-dimensional causal convolution tensor is assembled. Through the parallel pipeline of batch fast Fourier transform, de-aliasing, tensor contraction causal convolution and batch inverse fast Fourier transform, the memory occupation is significantly reduced and the calculation efficiency is improved. The feature calculation efficiency and approximation accuracy of the machine learning system based on the regular structure feature construction are improved.