24 results about "Neural Network Simulation" patented technology

The invention discloses a three-dimensional magnetotelluric deep learning inversion method, and relates to the technical field of three-dimensional magnetotelluric inversion in electromagnetic exploration, and the method comprises the steps: constructing a three-dimensional layered underground resistivity theoretical model, and forming a sample pair through the structure data of the underground resistivity theoretical model and the corresponding visual parameter data; the method comprises the following steps: constructing a three-dimensional neural network based on a Swin Transform module and jump connection; a forward modeling sub-network is trained for the multiple visual parameters, and the weight of the forward modeling sub-network is frozen to serve as a fixed forward modeling operator, so that rapid forward modeling is achieved; after each fixed forward operator is migrated and spliced to the inversion sub-network, each fixed forward operator is used as an additional loss constraint term, and physical driving of neural network simulation is realized; and end-to-end mapping from each apparent parameter to the underground resistivity is established by fitting the inversion sub-network, and quasi-physics and data dual-drive three-dimensional magnetotelluric deep learning inversion is realized. The three-dimensional magnetotelluric inversion method has high practical value and popularization value in the technical field of three-dimensional magnetotelluric inversion with crossing of deep learning and electromagnetic exploration.

Systems and methods are provided for analog hardware realization of neural networks. The method incudes obtaining a neural network topology and weights of a trained neural network. The method also includes transforming the neural network topology into an equivalent analog network of analog components. The method also includes computing a weight matrix for the equivalent analog network based on the weights of the trained neural network. Each element of the weight matrix represents a respective connection between analog components of the equivalent analog network. The method also includes generating a schematic model for implementing the equivalent analog network based on the weight matrix, including selecting component parameter values for the analog components.

The invention relates to the technical field of underground water monitoring, in particular to a high-precision underground water pollution plume migration prediction and source identification method, which comprises the steps of constructing a graph structure, simulating an underground water convection-dispersion process by using a space-time graph neural network, introducing a physical equation residual error constraint to train a prediction model, and converting source identification into an optimization problem. A multi-task strategy is adopted to synchronously identify a sparse source position and reconstruct a release history of the sparse source position, a model is finely adjusted and updated according to gradient descent cooperative solution, and uncertainty is quantified. According to the high-precision groundwater pollution plume migration prediction and source identification method, source position identification and release history reconstruction are synchronously realized through a multi-task strategy; organizing data by using a graph structure, constructing static and dynamic feature vectors, and comprehensively describing pollution migration space-time characteristics; a multi-stage curriculum learning, a splitting algorithm and a Bayesian optimization initialization strategy are adopted, gradient is calculated in combination with automatic differential, and a multi-source uncertainty decomposition framework is constructed to quantify uncertainty.

The invention discloses a nonlinear multi-agent system double-clock asynchronous hybrid neural adaptive control method, and relates to the technical field of nonlinear multi-agent system cooperative control. According to the method, a double-clock asynchronous framework is provided, time decoupling is carried out on updating of the leader observer and updating of the local observer, the limitation of synchronous updating of all assemblies is broken through, and the leader observer and the local assembly are made to operate independently; an event trigger pulse mechanism is designed, sampling is carried out only when a specific event occurs, the communication and calculation cost is remarkably reduced, the event trigger mechanism allows each agent to autonomously determine a trigger moment, and self-adaptive resource allocation between heterogeneous dynamic agents is achieved; and the numerical value of the nonlinear function is simulated and estimated by using the neural network, so that approximate state information can still be obtained under different conditions. And the weight of the neural network is only updated at the triggering moment, so that the resource consumption in the learning process is reduced.

The application discloses an automatic needle insertion method combining a blood flow optimization model with a neural network. The method first calculates the blood vessel position and blood flow velocity distribution of a needle insertion area according to blood flow information measured by automatic ultrasonic scanning by means of the Doppler ultrasonic principle, then establishes a blood flow relative velocity optimization model and a neural network with a selection function, and decides the optimal needle insertion point and needle insertion angle on the basis of physical measurement results, and finally simulates the needle insertion path by means of a neural network with a learning function according to the needle insertion method of a professional. The method can be used for needle insertion of subcutaneous blood vessels of limbs and other body parts, and overcomes the difficulty of manual needle insertion when the blood vessel is not visible to the naked eye, thereby providing technical assistance for self-rescue and first aid in an environment lacking professional personnel.

This application provides a method for preparing a dry binder, achieving stable quality control through dynamic sensing and multi-level intelligent adjustment of the moisture content of the raw material powder: First, moisture content and environmental humidity data are collected in real time, and time series analysis is used to predict the trend of moisture content changes; then, support vector machine is used to classify seasonal and batch differences to determine the main influencing categories; for high humidity interference scenarios, neural network is used to simulate the dynamic impact of material residence time in the mixing equipment on moisture content and determine the risk level; based on the risk level, historical data is retrieved, and a random forest algorithm is used to generate a preliminary adjustment plan for process parameters; then, a digital simulation model is used to simulate and verify the entire process and iteratively optimize it to finally determine the optimal process parameters; during production, the moisture content prediction model is dynamically updated using real-time feedback data to achieve closed-loop correction and continuous optimization. This invention effectively reduces the quality risks caused by environmental fluctuations and batch differences.

This application belongs to the field of delay differential equation modeling, specifically disclosing a delay differential equation modeling method based on Bayesian optimization and neural networks. The method includes: generating multiple trajectory data of the system; searching for the optimal delay term using a Bayesian optimization algorithm, where the delay term to be solved is the optimization variable, and the error based on neural network simulation is the objective function, obtaining the optimal delay term through iterative optimization using a surrogate model; constructing a state matrix and a delay matrix from the trajectory data based on the optimal delay term, using the concatenated matrix as input to a neural network to construct a neural network for approximating a nonlinear function; integrating a linear multi-step method into the loss function of the neural network, training the neural network using the trajectory data to obtain a nonlinear function approximation model; and separating the numerical discretization error and the neural network approximation error based on this model to construct a total error bound. This application can achieve high-precision, high-efficiency delay differential equation modeling with quantization error guarantee.

The invention relates to the technical field of public safety management, in particular to a panoramic video fused public safety risk intelligent early warning method and system, and the method comprises the steps: obtaining panoramic video data of a target monitoring area in real time under a unified space-time framework; extracting spatial features and time sequence features from the acquired panoramic video data; fusing the spatial features and the time sequence features, and constructing a space-time diagram of the target monitoring area based on the fused spatial features and time sequence features; and simulating propagation and evolution of the risk in the space-time diagram by using a graph neural network, and carrying out risk decision making and early warning based on propagation and evolution characteristics.

The invention relates to the technical field of artificial intelligence decision analysis and behavior modeling, in particular to a figure decision mode analysis method and device based on a situation-reasoning one graph, and the method comprises the steps: constructing a decision mode situation-reasoning one graph, extracting and quantifying decision influence factors, and extracting and quantifying the decision influence factors. The method comprises the following steps of: firstly, converting mass unstructured open source data into a computable and deducible situation-reasoning graph by utilizing the structure of the situation-reasoning graph; then, according to a decision theory, quantifying intrinsic psychological cognition characteristics of a person, and taking the intrinsic psychological cognition characteristics as key constraint conditions of a reasoning network; and finally, constructing a decision-making mode neural network, and simulating a'perception stimulation-cognitive screening-logical reasoning 'decision-making process of a person under a specific situation. According to the method, deep fusion and accurate analysis from an external objective situation to internal subjective cognition are realized.

This invention relates to the field of large model algorithm technology, and in particular to a dynamic compression optimization method and system for large models based on sparse pruning. The method captures raw weight fluctuation data caused by resource fluctuations during inference, and obtains sparse weight baseline data through sparsification. It analyzes the computational complexity of model inference latency data to separate the inference latency caused by model size. Based on the latency and sparse baseline data, the model compression ratio is dynamically controlled within a preset performance range, and inference accuracy distribution data under different compression parameters are collected. The model performance status under each parameter is evaluated using neural network simulation methods, generating performance status simulation results. Combined with real-time resource fluctuation data acquired during compression, model quality optimization compensation parameters are determined based on the simulation results. Finally, the compression strategy is adaptively adjusted through the compensation parameters to achieve coordinated optimization of model computational complexity, inference accuracy, and latency when hardware resources change dynamically.

The invention discloses a carbonate rock acid fracturing effect main control parameter analysis method and system, relates to the technical field of acidification, and solves the problem that main control parameters are difficult to identify in existing carbonate rock acid fracturing effect assessment. Calculating the correlation of each parameter based on the parameter data, and filtering out the parameters with extremely high correlation; executing a random forest algorithm and a recursive elimination algorithm based on the parameters to obtain a first weight and a second weight of the parameters; performing weighted average on the first weight and the second weight to obtain a comprehensive weight of the parameter; selecting parameters according to the comprehensive weight to construct a plurality of schemes, inputting the schemes into a BP neural network to simulate the yield to obtain the correlation between the actual yield and the predicted yield, and selecting the parameters contained in the scheme with the highest correlation as main control parameters of the acid fracturing effect; and analyzing carbonate rock acid fracturing effect master control parameters based on a random forest, recursive elimination and a BP neural network algorithm.

The invention provides a universal satellite remote sensing atmospheric roof radiation simulation method, which belongs to the technical field of remote sensing image data processing, and comprises the following steps: (1) calculating latitude and longitude and observation geometric information of a transit area; (2) constructing global environment parameter background field data; (3) respectively performing radiation simulation on the ocean area and the land area in the transit area; (4) respectively calculating the atmospheric top radiance of the ocean area and the atmospheric top radiance of the land area; and (5) splicing the atmospheric top radiance data of the ocean area and the atmospheric top radiance data of the land area to obtain the atmospheric top radiance data of the whole image. According to the universal satellite remote sensing atmosphere top radiation data simulation method, the reliability of a physical model and the modeling capacity of a neural network are combined, the problem that existing satellite remote sensing atmosphere top radiation simulation is low in reliability is solved, and compared with full-data neural network simulation, consumed time is shorter.

The application discloses a boundary level grid physical constraint variational assimilation method embedded in a deep neural network, comprising: establishing a momentum equation containing a boundary level grid turbulent friction term, wherein the boundary layer turbulent friction term is simulated through a deep neural network; and constructing a weak constraint term of a variational assimilation framework cost function with the momentum equation; training the deep neural network with a dataset constructed from historical numerical weather prediction model simulation results; linearizing the trained deep neural network to obtain a corresponding tangent linear operator and an adjoint operator, and embedding the tangent linear operator and the adjoint operator into the variational assimilation framework cost function; obtaining multi-source remote sensing observation data and a numerical weather prediction model background field, and solving an analysis field by taking minimization of the cost function as an objective, to complete data assimilation. The application can improve the data assimilation and numerical prediction level of disastrous weather such as typhoon, especially the observation assimilation level related to the boundary layer.

This invention proposes a general method for simulating atmospheric top radiation from satellite remote sensing, belonging to the field of remote sensing image data processing technology. The method includes: (1) calculating the latitude, longitude, and observation geometry of the transit area; (2) constructing global environmental parameter background field data; (3) performing radiation simulations for the ocean and land regions within the transit area; (4) calculating the atmospheric top radiance of the ocean and land regions respectively; and (5) stitching together the atmospheric top radiance data of the ocean and land regions to obtain the atmospheric top radiance data for the entire image. This general method for simulating atmospheric top radiation from satellite remote sensing combines the reliability of physical models with the modeling capabilities of neural networks. It addresses the low reliability of existing satellite remote sensing atmospheric top radiation simulations while also being less time-consuming compared to full-data neural network simulations.

The present application relates to the technical field of artificial intelligence decision analysis and behavior modeling, in particular to a kind of situation-reasoning one figure-based character decision mode analysis method and equipment, including the construction decision mode situation-reasoning one figure, the extraction and quantization of decision influencing factors and the extraction and quantization steps of decision influencing factors, in the execution above-mentioned steps, first, the structure of situation-reasoning one figure is used, and massive unstructured open source data is converted into computable, situation-reasoning one figure that can be deduced;Then, according to the decision theory, the internal psychological cognitive characteristics of the character are quantified, and they are used as the key constraint condition of reasoning network;Finally, the decision mode neural network is constructed, and the decision process of "perception stimulation-cognitive screening-logical reasoning" of the character under a certain situation is simulated.The present application realizes the deep integration and accurate analysis from external objective situation to internal subjective cognition.

This application relates to the field of product carbon footprint calculation, and discloses a method and system for constructing a product carbon footprint model based on intelligent agents. This method automatically collects and standardizes product information from multiple data sources using a large language model, generates product production process flows and identifies emission sources through a lifecycle model inference module, simulates activity data using deep neural networks, and matches emission factors in a background database using semantic similarity. Finally, a carbon footprint calculation model is constructed based on the ISO 14067 standard. This method overcomes the problems of difficult data acquisition and time-consuming processes in traditional carbon footprint calculation methods, achieving intelligent construction of product carbon footprint models and improving the efficiency and accuracy of carbon footprint calculation.

This invention discloses an on-orbit intelligent processing method for spaceborne images based on brain-like computing, belonging to the field of on-orbit intelligent processing of spaceborne images. This invention utilizes a spiking neural network to simulate the structure of the human brain: including a feature extraction layer, a pulse coding layer, an STDP learning layer, a lateral inhibition layer, and a decision output layer; and improves model accuracy through on-orbit updates and federated learning. This invention reduces computational energy consumption and improves efficiency. Simultaneously, this invention leverages the synaptic plasticity of neurons to construct a SNN with excellent spatial and temporal resolution.

The invention belongs to the field of delay differential equation modeling, and particularly discloses a delay differential equation modeling method based on Bayesian optimization and a neural network, and the method comprises the steps: generating multiple pieces of trajectory data of a system; an optimal delay term is searched by adopting a Bayesian optimization algorithm, the Bayesian optimization takes a delay term to be solved as an optimization variable and an error based on neural network simulation as a target function, and the optimal delay term is obtained through iterative optimization of an agent model; constructing a state matrix and a delay matrix from the trajectory data based on the optimal delay term, taking the spliced matrix as neural network input, and constructing a neural network for approaching a nonlinear function; fusing a linear multi-step method into a loss function of the neural network, and training the neural network by using the trajectory data to obtain a nonlinear function approximation model; based on the model, a numerical discretization error and a neural network approximation error are separated, and a total error bound is constructed. According to the method, high-precision and high-efficiency delay differential equation modeling with quantization error guarantee can be realized.

The application belongs to the technical field of power system operation control and optimal scheduling, and provides a power transmission and distribution reactive power reserve planning method and system considering power distribution network power flow security domain, generates a power flow security domain sample set considering network reconstruction based on an improved radial iterative reconstruction method, uses a physical information graph neural network (PI-GNN) to simulate and solve the security domain in consideration of new energy uncertainty, defines an equivalent four-dimensional security domain cost model of the power distribution network on the basis of considering optimal carbon emission power flow, and deduces and forms a planning scheme of the power transmission and distribution system reactive power reserve considering the operation state under a typical scene. The implementability and economy of the planning scheme under multiple working conditions throughout the year are improved.

The invention discloses a flood risk dynamic assessment method and system based on digital twinning, and belongs to the technical field of water conservancy informatization. In order to solve the problems of poor timeliness, disjunction of evaluation and scheduling and the like in the prior art, the method comprises the following steps: constructing urban watershed digital twin bodies based on GIS and BIM, and establishing real-time mapping with physical sensing equipment; performing minute-level rolling prediction on the flood evolution process by using a time-space diagram neural network simulation model in which physical conservation constraint is introduced; generating a dynamic risk thermodynamic diagram in combination with the disaster-bearing body attributes and the population exposure degree model; and when the risk exceeds a threshold value, generating a control instruction set for the drainage pumping station and the traffic gate, and issuing and executing the control instruction set. According to the method, minute-level dynamic simulation of flood risks and closed-loop scheduling of physical facilities are realized, and the response speed and the active defense capability of urban flood control and disaster reduction are remarkably improved.

The application discloses a kind of based on quick identification's mine filling body spontaneous combustion tendency analysis method, comprising: obtaining mine filling body material field sample data, processing sample data extraction mineral proportion, obtain composition distribution information, adopt neural network simulation different mineral oxidation reaction path, determine interaction intensity value;Based on interaction intensity value, obtain sulfide and organic matter proportion subset, through logical screening rule calibration high-risk interaction combination, obtain risk classification label;Through historical spontaneous combustion data extraction flammable characteristic parameter sequence, from burning characteristic parameter sequence, obtain temperature and gas concentration correlation subsequence, and optimize subsequence, obtain dynamic change trend index;According to dynamic change trend index, judge spontaneous combustion trend type, obtain early warning level label, through early warning level label, obtain mine field environment parameter integration, determine final spontaneous combustion trend prediction result.The application improves the accuracy and real-time of spontaneous combustion risk prediction.

The invention relates to the technical field of exoskeleton control, and discloses an exoskeleton control system and method for patient displacement. The method comprises the following steps: querying historical displacement record information according to physiological feature categories and displacement activity modes of a patient, and carrying out space division to obtain monitoring position points; neural network simulation is conducted through the joint connection structure of the exoskeleton, a control reference unit is established, the input of the control reference unit is the joint use duration, and the output of the control reference unit is the control reference value of the monitoring position point; based on the variability of the use durations of the multiple joints, fusing the output average values of the multiple control reference units, constructing a control reference model, processing the use durations of the multiple joints, and generating a reference value of a monitoring position point; and when it is detected that the displacement action does not accord with the reference value of the monitoring position point, a delay check rule is implemented for data verification. According to the method, self-adaptive control and safety verification of the exoskeleton in the auxiliary displacement process are realized.

The application discloses a large-scale neuron network assimilation and simulation system based on fMRI signals, comprising a network structure generation module, a signal processing module, a data assimilation module and a neural network simulation module; the network structure generation module generates a brain model of a subject according to DTI brain structure connection and gray matter density signals measured from the subject, sets a network scale parameter, and outputs a storage address of the brain model; the signal processing module processes standardized BOLD signals of the fMRI signals under a specific task, realizes standardization processing of the fMRI signals, and outputs the processed BOLD signals; the data assimilation module runs a data assimilation algorithm for the storage address of the brain model and the processed BOLD signals, assimilates parameters in the brain model, stores the assimilated parameters, and inputs the assimilated parameters into the neural network simulation module, so that the output of the brain model is similar to the BOLD signals of the subject, and the assimilation and simulation of the brain model under the specific task are realized; and the neural network simulation module realizes reproduction and simulation of the large-scale neural network based on the assimilated parameters and GPU multi-card parallel computing.