56 results about "Global simulation" patented technology

The invention discloses a logistics transfer field digital twin distributed data storage and calculation platform, which comprises a distributed data storage module, a distributed data storage module, a distributed data storage module, a distributed data storage module and a distributed data storage module, real-time preprocessing and short-time caching are carried out, and long-term persistence is realized; the real-time calculation module is used for constructing a parallel calculation framework to process batch and streaming data; designing a global state updating model; the co-simulation module is used for constructing a high-precision digital twinborn model of a physical transfer field; and the cloud generates a scheduling decision and a correction amount according to a global simulation result, the scheduling decision and the correction amount are fed back to the edge node through secure communication, and the edge immediately responds and adjusts local data processing and equipment regulation and control parameters, so that closed-loop consistency of a real scene and a digital twin model is realized. According to the invention, a logistics sorting digital twin system scheduling architecture based on distributed data storage, edge-cloud collaboration, real-time calculation and collaborative simulation support is constructed.

The invention relates to the technical field of simulation, in particular to a simulation task resource allocation method and device, equipment and a medium, and the method comprises the steps: carrying out the global grid division of a current simulation task, obtaining a plurality of grid units, and extracting the key information of each grid unit, outputting a load index corresponding to each grid unit based on the target load prediction model, generating global load distribution data according to the load indexes of all the grid units, dividing the global simulation area into a plurality of sub-areas, and obtaining load prediction data of each sub-area; and according to the load prediction data of each sub-region, distributing the sub-tasks of each sub-region to a target computing unit. Therefore, the problems of insufficient fine-grained task division and high dynamic scheduling overhead in the prior art are solved, the overall calculation efficiency and the resource utilization rate are improved, and the system complexity and the synchronization delay are reduced on the premise of ensuring the simulation precision.

The invention relates to a multi-physics field coupling simulation method and equipment for industrial digital twinning. The method comprises the following steps: automatically dividing a plurality of heterogeneous physical sub-domains based on actual physical field data of industrial equipment, and defining a solving region and a boundary condition for each sub-domain; and then, a variable-driven region division mechanism is utilized to construct a parallel computing map of multiple physical domains, and efficient synchronization of inter-region coupling state variables and real-time interaction of boundary data are realized. In the parallel simulation process, calculation tasks and resources are dynamically and optimally distributed through a self-adaptive scheduling algorithm, bottleneck areas are effectively recognized and eliminated, and the overall simulation efficiency and stability are improved. According to the invention, co-evolution of a plurality of physical processes such as structure, heat, flow, magnetism, electricity and the like can be realized, and unified, flexible and extensible simulation support is provided for digital twinning, state monitoring, performance prediction, control optimization and other applications of a complex industrial system.

The invention discloses a training method of a generative physical distillation neural network and a flood prediction method. The generative physical distillation neural network comprises a space-time neural network and a shallow water equation solver. The method comprises the following steps: firstly, inputting a training set of a generative physical distillation neural network into a space-time neural network to obtain a global prediction result at each moment; and then multi-path parallel reasoning is performed on each moment through a shallow water equation solver to obtain a plurality of corresponding global simulation results, so that a comprehensive loss function is constructed, a trained generative physical distillation neural network is obtained, and a flood prediction result is obtained based on the obtained generative physical distillation neural network. Through a space-time neural network with a macroscopic time step length and a physical solver with a microscopic time step length, and in combination with multi-path parallel reasoning, real-time, accurate and physically consistent water depth prediction and flow field reconstruction under a zero sample are realized, and real-time, accurate and physical law-conforming prediction of a flood space-time dynamic state is obtained.

The invention belongs to the technical field of semiconductor detectors, and particularly relates to a whole process simulation method and system for response of a semiconductor nuclear radiation detector. According to the method, through cooperative operation of a detector working parameter setting module, a carrier transport simulation module and a detection system electronics response module, whole-process response prediction of the semiconductor detector from radiation interaction to electronics output can be realized under different carrier transport characteristics and device structure conditions; according to the method, the carrier drift process is simulated in a small-step iteration mode, accurate reconstruction of a carrier drift track can be synchronously achieved, CSA signals and main amplifier forming signals can be continuously generated in real time, simulation output of an energy spectrum is finally completed, and therefore core performance indexes of a detector are comprehensively reflected. The method is wide in applicable semiconductor material range and device structure, the main amplifier module type can be flexibly configured, the overall simulation process is simple, convenient and efficient, and the method has good universality and engineering application value.

The invention discloses a microchannel condenser flow distribution global simulation method and system, and relates to the field of microchannel condenser flow distribution calculation. The method comprises the following steps: firstly, constructing a heat transfer and resistance model and forming a single-channel model by combining the size and structure of a parallel channel of the condenser and working medium flow heat exchange characteristics, and constructing a shunting and converging numerical model according to an inlet and outlet area structure of the condenser; secondly, numerical simulation is conducted on the division and convergence numerical model, and stable initial field distribution is obtained; then, determining the mass flow rate of each channel based on the shunting initial field, calculating the back pressure of the channel by taking the mass flow rate as the inlet boundary condition of a confluence model, calculating the inlet pressure of the channel through a single-channel model, and updating the outlet boundary of the shunting model; and finally, iterating the process until the channel mass flow error is smaller than a limit value, obtaining the distribution of the sub-confluence three-dimensional physical field and the one-dimensional flow heat exchange parameters and the heat exchange amount of the parallel channels, and checking whether the heat exchange amount meets the design requirements or not. The method gives consideration to calculation efficiency and precision, can provide support for structure optimization of the micro-channel condenser, and is suitable for micro-channel condenser design in the fields of refrigeration equipment, air conditioning systems and the like.

The invention relates to the technical field of nanometer motion tables, in particular to a nanometer motion table design method, device and equipment and a storage medium. In the method, a structure sample library is composed of structure samples of a nanometer motion table, and a simulation result covers characteristics such as microscale stress and displacement; the trained parameter prediction model can accurately support the micro-scale performance prediction and optimization of the nano motion platform; a simulation result set of the structure sample library comprises multi-physics field data, a training data set is constructed based on a global simulation result, a proxy model can learn global distribution and coupling relations of physics fields, and optimization hidden dangers caused by single-point simplification are avoided; a proxy model is constructed and trained into a parameter prediction model, traditional finite element analysis is replaced for rapid prediction, and the calculation cost and time consumption in the optimization process are remarkably reduced; the multi-objective optimization algorithm and the parameter prediction model are combined, the optimization scheme is automatically generated, multi-objective optimization can be carried out at the same time, multiple performance indexes can be considered, and the comprehensiveness of the design scheme is improved.

The invention discloses a hydrological digital twinborn model construction method and system based on an artificial intelligence technology, and relates to the technical field of hydrological monitoring and intelligent early warning, and the method comprises the steps: constructing a hydrological element measuring point monitoring model fusing multi-source sensor data, and introducing a graph convolution network to capture the complex correlation between environmental factors and hydrological elements; constructing a mapping model by using an improved long-short term memory neural network, and designing a multi-target dynamic monitoring loss function to balance data precision and space consistency; a measuring point prediction value and a global simulation value are fused through domain self-adaptive adversarial training, a basic hydrological digital twinborn model is generated, and an interaction model is constructed in combination with an extreme working condition parameter migration strategy; and constructing an inference mechanism based on the hydrological disaster knowledge graph, and outputting an entity engineering disposal scheme. The problems that a traditional hydrological model is weak in generalization ability, insufficient in data fusion, poor in extreme working condition adaptability and the like are solved, and high-precision real-time sensing and intelligent decision making in the hydrological process are achieved.

The invention discloses a transformer substation secondary system modeling method and related equipment, and relates to the field of power system modeling.The method comprises the steps that firstly, feature information, hierarchical relations and connection relations of electrical elements are extracted from a transformer substation secondary system configuration file, and the system structure is comprehensively mastered; generating a historical information time sequence in combination with historical information of the transformer substation; then respectively mining a time influence factor and a space influence factor by using a long short-term memory network and a multiple regression model; and finally, establishing a global simulation model based on a digital twinning technology. According to the scheme, equipment operation data is deeply mined, and the data integration problem is solved; the space-time dimension is fully considered, and the equipment state is accurately simulated; information delay is reduced by means of a real-time data mechanism, and virtual-real synchronization is guaranteed; model lightweight and compatibility are achieved, and the multi-scene requirement is met. Therefore, active operation and maintenance decision is achieved, and the operation and maintenance efficiency and safety of the substation are remarkably improved.

The embodiment of the invention provides a wheel disc fracture failure prediction method and device, computer equipment and a medium, and relates to the technical field of digital twines.The method comprises the following steps that a uniaxial quasi-static tensile test is conducted on a tensile test sample, and an engineering stress-strain curve of a wheel disc is obtained; converting the engineering stress-strain curve into a true stress-strain curve; based on the true stress-strain curve, constructing a wheel disc failure prediction model under a deterministic condition; sensitivity analysis is conducted on the uncertainty quantitative parameters, sample data under different working conditions are obtained through finite element calculation based on the key parameters, a wheel disc maximum strain proxy model is constructed based on the sample data, the key parameters are input into the wheel disc maximum strain proxy model, and the confidence interval of the rotating speed of the wheel disc during fracture is obtained. According to the scheme, by constructing the wheel disc maximum strain proxy model, high-precision global simulation of the wheel disc breaking process is realized, and the problems of limited test points and insufficient simulation precision are solved.

The invention discloses a chip debugging bus centralized verification method, device and equipment and a storage medium, and relates to the technical field of chip debugging verification, and the chip debugging bus centralized verification method comprises the following steps: integrating paths of CSV files corresponding to all subsystem debugging buses; traversing the CSV files corresponding to all subsystems, extracting information in the CSV files by using scripts so as to automatically output standardized files, checking the reasonability of the content of the CSV files, and generating verification files when the content of the CSV files is reasonable; integrating all verification files generated based on the CSV file; and performing global simulation based on the integrated verification file, and automatically constructing associated excitation according to the dependency relationship of the extracted debugging bus signal so as to monitor coverage rate information of all debugging bus signal jumps, register configurations and signal paths in real time. On the basis of a centralized verification architecture, a pre-checking mechanism and a self-adaptive updating mechanism are added, so that the overall verification efficiency can be improved, and the verification cost can be reduced.

The invention relates to a BIM-based building complex node construction scheme dynamic simulation method and system, and relates to the technical field of constructional engineering informatization construction management, and the method comprises the steps: carrying out the construction region self-adaptive division of a node BIM model based on multi-dimensional feature clustering, and defining a heterogeneous substrate unit based on a self-adaptive division result; according to the heterogeneous substrate unit, the construction scheme parameters are dynamically divided based on the influence mode, and a bipartite construction parameter set is obtained; and according to the bipartite construction parameter set, performing two-stage dynamic simulation on the construction scheme in combination with the heterogeneous base unit and the node BIM model to obtain a node construction simulation result. The method solves the problems that in traditional complex node construction simulation, complex nodes are not effectively deconstructed, so that the overall simulation precision is insufficient, fixed-time quota is depended, the simulation process is not flexible, influences of different schemes are difficult to quickly evaluate, and scheme comparison, selection and optimization are difficult.

The invention relates to a cloud service simulation method and device, computer equipment, a medium and a product. Comprising the steps of generating a to-be-simulated cloud service according to request type information carried by a cloud service simulation request; target overall simulation data of the to-be-simulated cloud service is output through a preset data evaluation model, and the preset data evaluation model is obtained based on overall simulation data iteration training of the full cloud service; and simulating the to-be-simulated cloud service according to the target overall simulation data. By adopting the method, the simulation efficiency and the simulation accuracy of cloud service simulation are both considered.

The invention relates to the technical field of engineering testing, and discloses a geotechnical engineering simulation testing system. The data acquisition module is used for acquiring multi-dimensional geological data of a test area; the model coupling module is used for dynamically coupling the geological three-dimensional model and the test area into a geological twinborn model; the simulation test module is used for applying test factors to the steady-state area and the sensitive area; the model prediction module is used for predicting a simulation state through a regional geological prediction model; the test analysis module is used for determining a simulation test grade and generating a simulation test report; according to the method, analysis resources of a simulation test can be focused on the sensitive area with higher risk according to the difference of mechanical properties and risk levels in the steady-state area and the sensitive area, so that the evaluation depth of the safety and reliability of the sensitive area in geotechnical engineering is improved, excessive resource consumption in the stable area is avoided, and the safety and reliability of the sensitive area in geotechnical engineering are improved. Therefore, the efficiency and the pertinence of the whole simulation test are obviously improved.

This invention belongs to the field of particulate materials technology and relates to a simulation method for the evolution of microscopic pore structure during the crushing process of porous and fragile particles. The method includes the following steps: sample preparation, high-resolution X-CT scanning, image processing to obtain the analysis volume, three-dimensional reconstruction to generate a three-dimensional rendering model, multi-scale simulation to establish the model, pore extraction, porosity analysis, pore connectivity analysis, connected porosity analysis, and pore structure parameter analysis. Based on X-CT technology and AVIZO software, using high-resolution tomographic data and combining the denoising, segmentation, and modeling functions of AVIZO software, the pore structure changes during particle crushing are accurately extracted. Through three-dimensional reconstruction and pore structure analysis of single particles at the microscale, and overall simulation of the crushing behavior of particle groups at the microscale, the evolution law of porosity and its key parameters is dynamically quantified, and a quantitative correlation model between the degree of crushing and porosity changes is established.

The invention relates to the technical field of agricultural hydraulic engineering, in particular to an intelligent decision-making method and control system for precise irrigation for agricultural hydraulic engineering, and the method comprises the steps: constructing a global simulation model to calculate theoretical operation variables, and carrying out the simulation evaluation and variable optimization processing through the collection of a historical operation sequence of a function module. The operation variables can be adjusted according to the actual performance, the problems of water resource waste, energy consumption increase and equipment service life shortening caused by insufficient data acquisition, uneven resource distribution and high-load equipment operation in the prior art are solved, and precise irrigation and efficient resource utilization are achieved.

The invention discloses a GPU (Graphics Processing Unit) parallel thread block adjustment and kernel function scheduling optimization method and system. The method comprises the following steps: acquiring GPU equipment attributes and kernel function execution attributes; determining a feasible thread block size solution space of each kernel function based on GPU equipment attributes and kernel function execution attributes, and selecting a thread block size which enables the load balance degree evaluation model value to be maximum as optimal execution configuration of the kernel function; on the basis of the determined optimal thread block size of each kernel function, dividing an execution grid of each kernel function into a plurality of kernel function slices, and establishing a concurrent execution relationship between the kernel functions; a CUDA graph is constructed in a mixed mode according to the established concurrent execution relation between the kernel functions and data dependence; and by taking an actual model of particle simulation software as a test object, respectively comparing GPU occupancy rates before and after thread block adaptive adjustment, multi-stream concurrent scheduling and hybrid CUDA graph scheduling optimization, kernel function execution time and overall simulation efficiency, and outputting an optimized particle simulation result.

The invention provides a method and system equipment for intelligently analyzing carbon emission based on abnormal carbon factors in a smart park in combination with energy storage, and a storage medium, and relates to the field of digital energy storage analysis. The method comprises the following steps: firstly, capturing an abnormal carbon factor in real time by combining a multi-time scale weighted threshold value and a fanotify technology through an intelligent electric meter comprising an intelligent sensing module and a carbon monitoring module; constructing four types of energy storage matrixes of hydropower, photovoltaic, wind power and non-green power, and predicting carbon factor response lag characteristics by using an NBP method; and finally, global simulation deduction is carried out through an MCTS algorithm, and an optimal energy-saving strategy is selected according to a comprehensive evaluation function. The system correspondingly comprises an intelligent electric meter deployment layer, an abnormal carbon factor sensing system and other modules. According to the invention, accurate real-time monitoring of abnormal carbon factors is realized, power grid cleanliness changes are dynamically adapted, a global optimal strategy is output, the park carbon management efficiency is improved, and the method is suitable for various smart park low-carbon management scenes.

This application relates to a BIM-based dynamic simulation method and system for construction schemes of complex building nodes, belonging to the field of information-based construction management technology for building engineering. The method includes: adaptively dividing the construction area of ​​the node BIM model based on multi-dimensional feature clustering, and defining heterogeneous base units based on the adaptive division results; dynamically dividing the construction scheme parameters based on the influence patterns according to the heterogeneous base units to obtain a bipartite construction parameter set; and performing a two-stage dynamic simulation of the construction scheme based on the bipartite construction parameter set, combining the heterogeneous base units and the node BIM model to obtain the node construction simulation results. This invention solves the problems in traditional complex node construction simulation, such as insufficient overall simulation accuracy due to the lack of effective deconstruction of complex nodes, reliance on fixed time quotas and inflexible simulation processes, difficulty in quickly assessing the impact of different schemes, and difficulties in scheme comparison and optimization.

The invention discloses a white oil refining intelligent joint control method and system based on the industrial internet, and particularly relates to the technical field of industrial automation and intelligent manufacturing, and the method comprises the steps: S1, collecting white oil refining process data through a multi-source sensor, S2, carrying out the real-time analysis based on an edge calculation node, and S3, carrying out the real-time analysis based on an edge calculation node; the method comprises the steps of S1, executing interlocking logic including dynamic threshold adjustment and long short-term memory network prediction and optimization control, S3, uploading data and an analysis result to a cloud platform, carrying out global simulation optimization based on a digital twin model and issuing a strategy, and S4, generating evidence information from key data, and writing the evidence information into a block chain to support full-process tracing. According to the method, intelligent control jump from passive response to active prediction is realized through cloud, edge and end cooperation, and the stability, economical efficiency and quality traceability of the white oil refining process are remarkably improved in combination with global optimization and credible traceability.

A method for low-latency generation and input of sensor data for control units or control unit networks includes: computing, by a simulator system or device, environmental data sets at a simulation frequency using an environment model of a virtual environment scene, wherein each environmental data set is associated with a respective point in time in an overall simulation time at which point in time the respective environment data set is available for further processing; and executing, by the simulator system or device or by at least one additional system or device, at least one sensor simulation model, wherein the at least one sensor simulation model generates sensor data sets at a sampling frequency, based on the environmental data sets, for further processing by at least one control unit, wherein each sensor data set is associated with a respective start time and respective time of completion in the overall simulation time.

The invention discloses a large wind turbine state evaluation system and method based on visual three-dimensional reconstruction, the system is composed of a path planning module, a three-dimensional reconstruction module, a visual evaluation module, a numerical simulation module and a comprehensive evaluation module, and the three-dimensional reconstruction and state evaluation are carried out on a wind turbine in a running state by obtaining visual information through an unmanned aerial vehicle. According to the method, an unmanned aerial vehicle obtains a panoramic image of a wind turbine according to a planned path, geometric parameters are extracted through three-dimensional reconstruction, then a visual evaluation module completes comprehensive visual monitoring and evaluation according to the geometric parameters, and a numerical simulation module synchronously carries out overall simulation of structural performance and aerodynamic performance. And finally, unified integration is performed through the comprehensive evaluation module, and a dynamic performance degradation model is established for the wind turbine through data updating, so that the full life cycle state evaluation of the wind turbine is realized.

The invention relates to atmospheric chemical reaction calculation substitution and acceleration in an atmospheric chemical model, in particular to an atmospheric chemical reaction calculation substitution model and a construction method thereof, the model has a high-precision reappearance chemical reaction process, and in 19-day off-line prediction of 279 predictive variables of a case, the proportion of the predictive variable decision coefficient exceeding 0.99 is 96%; the model can realize continuous stable prediction for at least 10 days; compared with an original GEOS-Chem chemical integrator, the ChemKNet has the advantages that the time consumed by calculation on a single CPU can be saved by about 79%, only about 1% of the original calculation time is needed on a single GPU, and the calculation efficiency of large-scale simulation is greatly improved; the model supports coupling and continuous prediction; the model is provided with a full-chema chemical mechanism covering GEOS-Chem, and is provided with global simulation and a full-chema chemical mechanism covering GEOS-Chem.

The embodiment of the present invention relates to the field of simulation technology, and discloses a shooting simulation training method based on a motion vehicle, comprising: issuing a training task, generating a training task scenario based on the training task, and associating the training task scenario with the training terminal of the corresponding trainee; calling corresponding vibration data based on the training task scenario, and sending the vibration data to the vibration platform through network equipment and a vibration control cabinet in sequence for training; receiving the user's simulated weapon operation information based on the motion vehicle, and performing shooting simulation training based on the simulated weapon operation information to obtain simulation parameter information. The shooting simulation training method based on the motion vehicle in the embodiment of the present invention realizes motion state simulation in multiple scenarios by placing the motion vehicle on a vibration platform. By adopting a real vibration platform, the overall simulation training can be more in line with the actual situation, can more realistically reflect the actual state, and improve the training simulation effect.

The application provides an agricultural manure soil crop interaction optimization regulation method and system, divides a farmland unit for a farmland area, constructs a farmland unit intelligence and constructs a farmland unit social network containing a physical proximity network, a feature similarity network and a causal correlation network, the farmland unit intelligence agent carries out social learning based on the farmland unit social network, acquires individual performance data of manure regulation strategy, generates a candidate manure regulation strategy set, carries out strategy radiation simulation on the candidate manure regulation strategy set through the causal correlation network and the infectious disease model, acquires strategy radiation degree data, the global farmland unit intelligence agent carries out global simulation simulation based on the candidate manure regulation strategy set, acquires strategy global influence index, optimizes the candidate manure regulation strategy set according to the individual performance data, the strategy radiation degree data and the strategy global influence index, generates an agricultural manure regulation strategy, so as to improve the overall utilization rate of manure and the stability of farmland ecology.

The present invention discloses a digital twin distributed data storage and computing platform for a logistics transfer yard, including: a distributed data storage module, which is used to design a data partitioning strategy, a redundancy backup and fault tolerance mechanism; perform real-time preprocessing and short-term caching, and achieve long-term persistence; a real-time computing module, which constructs a parallel computing architecture to process batch and streaming data; designs a global state update model; a collaborative simulation module, which constructs a high-precision digital twin model of the physical transfer yard; the cloud generates scheduling decisions and correction amounts according to the global simulation results, and feeds them back to the edge nodes through secure communication, and the edge immediately responds to adjust the local data processing and device control parameters, so as to achieve the closed-loop consistency between the real scenario and the digital twin model. The present invention constructs a scheduling architecture for a logistics sorting digital twin system supported by distributed data storage, edge-cloud collaboration, real-time computing and collaborative simulation.

The utility model provides a full-motion electric vertical take-off and landing aircraft simulator which comprises a counterweight seat, a multi-degree-of-freedom motion platform arranged on the counterweight seat, and a simulation cockpit arranged on the multi-degree-of-freedom motion platform, vR simulation equipment is arranged in the simulation cockpit, VR position indicators matched with the VR simulation equipment are arranged outside the simulation cockpit, and the two VR position indicators are arranged corresponding to the left side and the right side of the simulation cockpit; and at least four sound simulation devices are uniformly arranged in the simulation cockpit. According to the full-motion electric vertical take-off and landing aircraft simulator, a plurality of hardware function devices are integrated comprehensively through mechanical structure connection, ergonomic structure arrangement, mutual adjustment and configuration among devices, reasonable space application and other modes, and meanwhile, design modes such as operation stability of the whole simulator are considered; the utility model provides the all-moving electric vertical take-off and landing aircraft simulator which is superior to the previous solution.

The invention provides an agricultural manure soil crop interaction optimization regulation and control method and system, and the method comprises the steps: carrying out the farmland unit division of a farmland region, constructing farmland unit intelligence, and constructing a farmland unit social network which comprises a physical proximity network, a feature similarity network and a causal association network; the farmland unit intelligent agent performs social learning based on the farmland unit social network, obtains individual efficiency data of the manure regulation and control strategy, generates a candidate manure regulation and control strategy set, performs strategy radiation simulation on the candidate manure regulation and control strategy set through the causal association network and the infectious disease model, obtains strategy radiation intensity data, and sends the strategy radiation intensity data to the farmland unit intelligent agent; and the global farmland unit agent performs global simulation based on the candidate manure regulation strategy set to obtain a strategy global influence index, and optimizes the candidate manure regulation strategy set according to the individual efficiency data, the strategy radiation data and the strategy global influence index to generate an agricultural manure regulation strategy. Therefore, the overall utilization rate of manure and the stability of farmland ecology are improved.

The application discloses a method for identifying a leading particle in mud flow dynamic simulation and a method for querying a neighborhood particle. In view of the defect that the existing SPH model of mud flow cannot distinguish the leading particle, two schemes are provided under a single concept. The method for identifying the leading particle in mud flow dynamic simulation configures a 3D-CNN classification model in the SPH model to identify the leading particle and non-leading particle from the grid scale. The classification model is based on the frame data of the material model, defines a local aggregation space around the object particle, extracts a feature tensor, combines the object particle attribute, analyzes the particle attribute statistical index from the grid scale and the grid scale leading particle identification rule, generates a sample and trains the model. The method for querying the neighborhood particle in mud flow dynamic simulation is based on the leading particle identification technology, adopts tree storage for the leading particle, adopts hash storage for the opposite, obtains a global partition fusion hash table and optimizes the particle query. The application solves the problem of the leading particle of mud flow and global simulation, thereby reducing the operation complexity, optimizing the time and space cost, balancing the accuracy and efficiency of the numerical model.

This invention belongs to the field of energy demand forecasting technology, and discloses a method and system for forecasting regional energy system demand. The method includes: determining the primary energy demand of each industry in a target region; constructing a calculation model for carbon emissions and energy utilization costs in the target region based on the primary energy demand of each industry, carbon emission coefficients of various primary energy sources, and utilization cost coefficients of various energy sources; constructing an optimization function based on determined energy utilization constraints and carbon emission constraints; solving the optimization function to obtain the optimal solution; and obtaining energy consumption, carbon emissions, and energy cost data for all industries in the target region based on the optimal solution, the target region carbon emission calculation model, and the energy utilization cost calculation model. This invention constructs an optimization function based on energy utilization constraints and carbon emission constraints, with the optimization objectives of minimizing total energy costs and achieving carbon neutrality in the energy system, realizing the overall simulation of energy system demand and carbon emissions under multiple scenario conditions.