Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

146 results about "Discrete particle" patented technology

Discrete element method. The discrete element method (DEM): is intended for modeling events in which large numbers of discrete particles contact each other; models each particle with a single-node element that has a rigid spherical shape, which may represent an individual grain, tablet, shot peen, or other simple body;

Integrated circuit wiring method and system, and device and medium

PCT designated stage expiredWO2025139865A1Artificial lifeComputer aided designPathPingLayout
Disclosed in the present application are an integrated circuit routing method and system, and a device and a medium. The method comprises: acquiring an integrated circuit layout model; performing routing area generation processing on the integrated circuit layout model on the basis of a particle swarm optimization algorithm, so as to obtain a routing area; performing routing processing on the routing area on the basis of an improved A* search algorithm, so as to obtain a routing path; on the basis of the routing path, removing a redundant segment, so as to obtain a post-processed path; and performing dictionary conversion processing on the post-processed path, so as to obtain a routing layout. In the embodiments of the present application, a discrete particle swarm optimization algorithm can be used to reduce a routing search space, and a detailed routing area is determined by means of an improved A* search algorithm, thereby further enhancing routing speed, and improving the routing efficiency of an integrated circuit. The embodiments of the present application can be widely applied to the field of integrated circuits.
Owner:SUN YAT SEN UNIV

Calculation method and device for multi-scale particle multiphase flow field and electronic equipment

The invention discloses a calculation method and device for a multiphase flow field of multi-scale particles and electronic equipment, and the method comprises the steps: determining large-scale analytic particles and small-scale non-analytic particles in a multiphase flow according to a preset computational domain grid size; acquiring flow field medium parameters of the analytic particles and physical parameters of discrete particles, and solving flow field information and physical information of multiphase flow by using an immersion boundary method; interface parameters of each medium composition in the non-analytic particle flow field and physical parameters of discrete particles are obtained, the particle volume fraction is solved through a statistical kernel method, and based on the particle volume fraction, physical information of multiphase flow is solved through a fluid volume method; and according to the physical information solved by the analytic particles and the non-analytic particles, calculating the physical parameters of the multi-scale particle multiphase flow field.
Owner:HEFEI GENERAL MACHINERY RES INST +2

Trusted task unloading method based on autonomous collaboration of vehicle side cloud

The invention discloses a trusted task unloading method based on autonomous collaboration of vehicle side cloud. The method can be applied to the dynamic heterogeneous Internet of Vehicles to solve the low-efficiency problems of task accumulation, resource preemption, poor cooperation and the like caused by false tasks and malicious nodes. Firstly, an unloading task and cooperative node trust evaluation model is provided, and false tasks and malicious nodes are accurately identified and filtered by analyzing data sensitivity, resource preemption, historical unloading success rate and cooperative feedback evaluation; then, a discrete particle swarm algorithm is utilized to iteratively obtain a vehicle edge cloud collaborative unloading decision, particle codes, a fitness function and a correction mechanism are redesigned, and random quantities, greedy and mapping functions are introduced to enhance the diversity of unloading decisions. Compared with a traditional task unloading method, the method shows better energy consumption and delay performance in a scene with compact and uniformly distributed tasks, and the unloading efficiency and safety are effectively improved.
Owner:CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Model copyright protection method and system based on multi-partition adaptive triggering

The invention discloses a model copyright protection method and system based on multi-partition self-adaptive triggering, and relates to the technical field of computer scientificity. Local pixel displacement is carried out by introducing a transformation field, so that a trigger is imperceptible in a sample; a discrete particle swarm optimization DPSO algorithm is adopted to adaptively optimize the position and the shape of a trigger of each sub-partition, the watermark embedding process is accurately controlled, in addition, due to the fact that a secret function of the partition is difficult to know by a pirate, the pirate is difficult to extract and tamper the watermark, and the anti-attack ability is high. Meanwhile, the design of the antagonistic samples can further ensure that the copyright of the model is still effectively protected when the watermarks face antagonistic attacks and other disturbance conditions. Generally speaking, the method has obvious advantages in the aspects of improving the watermark concealment, robustness and anti-attack ability, the watermark can be effectively prevented from being identified and removed, strong copyright protection is provided in a black box environment, and the intellectual property of the model is ensured to be fully guaranteed.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Simulation method and system for interaction of dust collection airflow and abrasive dust of rail grinding wagon

The invention provides a simulation method and system for interaction of dust collection airflow and abrasive dust of a steel rail grinding wagon, and the method comprises the steps: firstly, constructing an internal and external flow field model of a grinding dust collection device through a computational fluid dynamics method; secondly, establishing a discrete particle model capable of reflecting morphological characteristics of the abrasive dust by using a discrete element method, and defining deposition judgment criteria of the abrasive dust in the vehicle body and on wall surfaces such as a track plate; finally, on the basis of a discrete element and computational fluid dynamics coupling method, continuous phase and discrete phase information is interactively updated, and interaction of abrasive dust and dust collection airflow is simulated. According to the method and the system provided by the invention, the migration, agglomeration and deposition behaviors of the grinding dust under the action of the dust collection airflow are accurately captured for the first time; the dynamic real-time adjustment of the flow field characteristics under the influence of abrasive dust agglomeration and deposition is realized for the first time; macro-micro multi-scale simulation of interaction of dust collection airflow and abrasive dust under the real working condition of the grinding dust collection unit of the steel rail grinding wagon is realized for the first time.
Owner:BEIJING JIAOTONG UNIV

Design method of low-cost reconfigurable metasurface with brand-new topology

The invention discloses a low-cost reconfigurable metasurface design method with a brand new topology, which comprises a new topology representation method and a portable separation design architecture, and realizes reconfigurable intelligent metasurface design of different functions and structures without recollection of a data set and retraining of a model. By using a plurality of spline control points and pattern mapping, the method can quickly generate and finely adjust the continuous pattern, ensures smooth flow of excitation current in the pattern, and reduces a pattern solving space. Based on a microwave network theory, the reconfigurable metasurface is divided into an active device, a surface pattern layer, a dielectric layer and a metal ground layer by the architecture. Through a pre-increment learning network and theoretical calculation, the multi-position electromagnetic response of the reconfigurable metasurface unit can be quickly obtained without numerical simulation. And finally, through a continuous-discrete particle swarm optimization algorithm, obtaining the reconfigurable intelligent metasurface meeting the target function.
Owner:SOUTHEAST UNIV

Fluidized system digital twinborn construction and state evaluation method

The invention relates to the technical field of electronic digital data processing, and discloses a fluidization system digital twinning construction and state evaluation method, which comprises the following steps: carrying out CFD (Computational Fluid Dynamics) solution on various gas-solid fluidization working conditions, and establishing a numerical simulation database; according to the characteristics of the gas-solid fluidization system, determining a core reward function and physical constraints, training a reinforcement learning agent, and establishing a fluidization system digital twinborn model base; constructing a fluidized system environment according to the twin targets, and calculating multi-physical field distribution and discrete particle state evolution at subsequent moments; and using a multidisciplinary fusion degradation model to analyze the stress condition of the material at each position in a selected time period, calculating the fatigue condition and progressive loss rate of the material, performing system state evaluation, and outputting a result. The problem that in the prior art, simulation precision and efficiency of a fluidization system are difficult to consider at the same time is solved, and the purposes of efficient and accurate simulation, high operation reliability, comprehensive evaluation and analysis, convenient maintenance and high safety are achieved.
Owner:ZHEJIANG BAIMA LAKE LABORATORY CO LTD

Unmanned aerial vehicle cluster search and rescue task allocation method based on discrete particle swarm

The invention relates to the technical field of unmanned aerial vehicles, in particular to an unmanned aerial vehicle cluster search and rescue task allocation method based on discrete particle swarms. The method comprises the following steps: determining a legal cluster and a legal task at the current moment t according to the life cycle of a task and the task execution capability of the cluster, and generating a plurality of task pairs; calculating task values of the task pairs according to a preset task value function, and generating a task value matrix; generating random particles based on a random particle model, and performing genetic variation on the random particles according to local optimal particles and / or global optimal particles to obtain optimized random particles; optimizing the optimizing random particles based on the task value matrix to determine local optimal particles; optimizing the plurality of local optimal particles, and determining a global optimal particle with the maximum sum of task values and the minimum variance between the task values; and after the number of cycles is preset, the global optimal particles are decoded to obtain a plurality of optimal task pairs, and a task allocation scheme is generated, so that high adaptability and high completion rate of task allocation are realized.
Owner:成都流体动力创新中心

System and method for optimizing scheduling of container trucks in port based on dynamic time matrix prediction

The invention discloses an in-port container truck scheduling optimization system and method based on dynamic time matrix prediction, and the method comprises the steps: building a dynamic time matrix which introduces a bridge crane rhythm and a lane impedance factor through collection of TOS and vehicle monitoring data, and carrying out the feedback correction of the matrix through a task result; self-adaptive adjustment of a container truck resource pool threshold value is realized based on a task density function, and multi-target scheduling optimization is carried out by adopting a tabu search and discrete particle swarm interaction algorithm; and when the storage yard is congested or rhythm deviates, task priorities and key road marks of operation roads are considered, task sequence rearrangement is triggered, and algorithm parameters are automatically updated according to execution results. According to the system, a real-time closed loop of prediction-scheduling-feedback is realized, and the port operation efficiency and the resource utilization rate are improved.
Owner:SHANGHAI MARITIME UNIVERSITY +1

Power distribution network multi-target cluster division method and system suitable for risk prevention and control, computer equipment and storage medium

The invention discloses a power distribution network multi-target cluster division method suitable for risk prevention and control, and the method comprises the steps: setting a target function of a multi-target cluster division model, the target function being a weighted sum of multiple targets, such as a comprehensive electrical distance, a comprehensive reserve degree, strong coupling in clusters, weak coupling between clusters, and the like, based on voltage sensitivity; establishing constraint conditions of a multi-target cluster division model, wherein the constraint conditions comprise constraint through the minimum number of nodes in the cluster and constraint through the number of adjustable resource nodes in the cluster; based on the target function and the constraint condition of the multi-target cluster division model, constructing the multi-target cluster division model; and solving the multi-target cluster division model based on a discrete particle swarm cluster division algorithm of K-means. According to the method, the problems that the voltage of part of nodes rises, the voltage at the tail end of a line exceeds the standard, direct regulation and control are difficult, the control efficiency is low, the calculated amount is large, and communication is delayed due to the fact that an existing centralized method cannot meet the requirement for massive distributed photovoltaic access can be solved.
Owner:STATE GRID LIAONING ECONOMIC TECHN INST +5

Power grid target net rack reconstruction optimization method, system and device and medium

The invention belongs to the technical field of large power grid recovery, and discloses a power grid target net rack reconstruction optimization method, system and device and a medium, and the method comprises the steps: obtaining power grid operation data; identifying a fault line based on the power grid operation data, and evaluating the probability of a recoverable line fault caused by a disaster in a preset time period; dividing a power failure area into a plurality of recovery partitions, sampling and simulating a recoverable state of a line in the recovery partitions, and calculating a node importance degree expected value based on the recoverable state; and in combination with a discrete particle swarm algorithm, generating optimal particles of each recovery partition to optimize the target net rack, and converting the optimal particles of each recovery partition into a corresponding target net rack scheme. According to the method, optimization adjustment calculation of a large amount of unreasonable net racks is avoided, the algorithm efficiency is improved, the method can be applied to online optimization, the target net racks are dynamically updated online according to disaster information and power grid power failure scenes, and decision support can be provided for dispatching operation personnel for power grids in different recovery stages.
Owner:ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY +1

Virtual synchronization micro-grid adaptive secondary frequency modulation control method matched with load fluctuation

The invention provides a virtual synchronization micro-grid adaptive secondary frequency modulation control method matched with load fluctuation, and the method comprises the steps: building an inverter island operation model based on VSG control, and generating a transfer function; determining stable operation conditions of the system according to the transfer function; and according to stable operation conditions of the system, optimizing values of a droop coefficient K [omega], a virtual inertia J, a virtual damping D, a proportionality coefficient Kp and an integral coefficient Ki according to change of a switching load by utilizing a discrete particle swarm algorithm, and controlling operation of the VSG. The droop coefficient K omega, the virtual damping D, the virtual inertia J, the proportionality coefficient Kp and the integral coefficient Ki in the secondary frequency modulation controller can be automatically adjusted according to the size of the switching load, and the problem that the system frequency exceeds the safe operation range in the adjusting process due to the fact that the switching load of the system is too large is solved.
Owner:STATE GRID HUBEI ELECTRIC POWER RES INST +1

Flexible job shop scheduling and maintenance decision joint optimization method considering working conditions

A working condition-considered flexible job shop scheduling and maintenance decision joint optimization method in the field of intelligent manufacturing comprises the following steps of: in a first stage, constructing a production scheduling model according to workshop equipment production capacity, a product process route and order task requirements, and generating an initial production scheme based on a hybrid discrete particle swarm and a variable neighborhood search method; and in the second stage, on the basis of the maintenance decision model, analyzing equipment maintenance requirements under the production scheme, formulating a maintenance scheme, and when production tasks and maintenance activities on the same equipment conflict, dynamically optimizing the production scheme and updating the equipment state in real time on the basis of a variable neighborhood search method, and synchronously formulating a production scheme and a maintenance plan with excellent economical efficiency. On the basis of ensuring equipment fault-free operation and production process continuity, dynamic balance between system production efficiency and equipment maintenance requirements is realized, maintenance cost caused by equipment degradation is remarkably reduced, dissatisfaction of customers on delivery delay is reduced, and balanced utilization of multiple equipment in a workshop is promoted.
Owner:TENGZHOU SHANDONG DAHAN INTELLIGENT TECH CO LTD

Agricultural machinery intelligent scheduling method and system based on yield prediction

The invention discloses an agricultural machinery intelligent scheduling method and system based on yield prediction, and belongs to the technical field of intelligent agricultural machinery, and the method comprises the steps of data collection, data preprocessing, crop yield prediction, agricultural machinery intelligent scheduling and comprehensive agricultural machinery scheduling. According to the method, crop yield prediction is carried out by adopting the time convolution feature enhanced gated circulation network, so that the method has better long and short term time sequence dependence modeling capability, key features can be adaptively enhanced, the stability and accuracy of crop yield prediction are improved, and the reliability of subsequent agricultural machinery intelligent scheduling is improved; the discrete particle swarm optimization algorithm is adopted to perform agricultural machinery intelligent scheduling, so that the method has relatively strong global search capability, can adapt to different agricultural production environments and scheduling requirements, has significant advantages in large-scale agricultural production, and improves agricultural machinery scheduling efficiency; comprehensive agricultural machinery intelligent scheduling based on yield prediction is adopted, crop yield difference is fully considered, agricultural machinery operation is reasonably arranged, and resource waste is effectively avoided.
Owner:BEIJING BOCHUANG LIANDONG TECH CO LTD

Online optimization method for operation efficiency of multi-track slope type gravity energy storage system

ActiveCN118971390AMeet scheduling instructionsMaximize electrical energy efficiencyElectrical storage systemData processing applicationsDischarge efficiencyElectric machine
The invention discloses a multi-track slope type gravity energy storage system operation efficiency online optimization method, which comprises the following steps: calculating control variables for maximizing the overall charging efficiency and discharging efficiency of a gravity energy storage system by using a discrete particle swarm algorithm according to a power grid charging instruction and a discharging instruction; constraint conditions of the slope type gravity energy storage system under an energy storage working condition and an energy release working condition; and calculating a control variable by using a discrete particle swarm algorithm. According to the method, the problem that an existing control strategy cannot improve the electric energy efficiency through coordinated optimization of the number of slope rail mass blocks and the transformation ratio of a traction motor gearbox is effectively solved, so that the electric energy efficiency of the whole system is maximized while it is guaranteed that a power grid dispatching instruction is met, and online optimization of the system operation efficiency is achieved.
Owner:GUANGDONG UNIV OF TECH

Discrete particle swarm optimization-based influence maximization method on hypergraph

The invention relates to the technical field of big data mining, and particularly discloses a discrete particle swarm optimization-based influence maximization method on a hypergraph, which comprises the following steps of: S1, constructing a hypergraph model and a propagation rule: defining a hypergraph which is a node set and a hyperedge set, and satisfying hyperedges; a threshold model is adopted to describe the propagation process, a seed node set is activated at the beginning, other nodes and all hyperedges are not activated, the non-activated hyperedges are traversed, if the proportion of the activated nodes in the hyperedges is larger than or equal to a threshold value, all the nodes in the hyperedges are activated, and the process is repeated until no new hyperedges are activated; s2, initializing a particle swarm; s3, performing two-layer local influence evaluation; s4, particle speed and position updating; s5, local search optimization; and S6, iteration is terminated. By adopting the technical scheme of the invention, the global search capability, the convergence speed and the evaluation precision can be balanced, and efficient and accurate identification of high-influence nodes in the hypergraph is realized, so that the influence propagation effect and the algorithm expandability are improved.
Owner:DALIAN UNIV OF TECH

Directed acyclic graph modeling-based inter-vehicle path planning method for single-load automatic guided vehicle

Aiming at the construction of an automatic warehouse logistics system of a digital workshop production line, the invention provides a single-load automatic guided vehicle workshop path planning method based on directed acyclic graph modeling, and the method comprises the functions of task selection, task execution sequence planning and the like. The method comprises a fusion algorithm framework based on a binary discrete particle swarm optimization algorithm and a genetic algorithm component, and can solve and fully consider the diversity of task selection strategies in a short time according to information such as known task arrival time and transportation starting point, so that normal production is ensured; and the task execution sequence with the shortest total driving distance is the optimal (or close to the optimal) task execution sequence.
Owner:SHENYANG GOLDING NC & INTELLIGENCE TECH CO LTD

Multi-UAV collaborative task allocation method and system based on hybrid-discrete particle swarm algorithm

The present invention discloses a multi-UAV collaborative task allocation method and system based on hybrid-discrete particle swarm algorithm, establishes a model for multi-UAV collaborative task allocation, and takes the benefits obtained by the UAVs from executing tasks and the loss costs of executing tasks as the two most important factors to measure the quality of task allocation schemes. And further considers indicators such as the probability of successful execution of tasks, the probability of damage, the time to complete tasks, and the probability of resource loss as the optimization objective function of multi-objective task allocation, and realizes the simultaneous optimization of these indicators. Aiming at the characteristics of the problem of multi-UAV collaborative task allocation, the present invention discretizes the particle swarm algorithm, designs new coding rules, improves the accuracy of problem measurement, and also incorporates a hybrid mechanism to effectively improve the convergence speed and convergence accuracy of the algorithm.
Owner:NANJING UNIV OF SCI & TECH

VR virtual simulation system for simulating multi-scene dust diffusion process

A VR virtual simulation system for simulating a multi-scene dust diffusion process belongs to the technical field of dust visualization experiment devices, and comprises an integrated helmet, a handheld controller and multi-scene software which are in coupling connection; the multi-scene software achieves dust diffusion simulation based on the gas-solid two-phase flow physical principle, physical simulation calculation is conducted on dust diffusion behaviors by solving a control equation set describing gas-solid two-phase movement, and the control equation set comprises a drag force item, a gravity item and a turbulence coupling item. The calculation process considers momentum transfer, energy exchange and interaction force between the continuous fluid phase and the discrete particle phase; a VR virtual simulation experiment of a multi-scene dust diffusion process can be realized, and formation, diffusion and distribution characteristics and the like of dust in tunnel blasting, fully-mechanized excavation, lifting and typical transfer processes can be visually researched.
Owner:CHINA UNIV OF MINING & TECH +1

A Discrete Particle Trajectory Prediction Method for Pipeline Centrifugal Separators Based on Surrogate Models

The object of the present invention is to provide a method for predicting the discrete particle trajectories of a pipeline centrifugal separator based on a surrogate model, which comprises the following steps: planning the experimental matrix of the structural parameters and flow field distribution of the pipeline centrifugal separator; obtaining the corresponding matrix between each structural parameter and flow field characteristic parameter according to the simulation experimental data; conducting a sensitivity analysis of the input variables, selecting a modeling technique, and constructing a surrogate model for the key input parameters and response values; comparing the results of the surrogate model with the experimental data; constructing a force model for discrete particles in the swirling flow field; establishing a transient motion trajectory equation for discrete particles by using the Euler method, and coupling and solving the flow field calculation model and the particle force model to obtain a discrete particle motion prediction model. The present invention can predict the motion trajectories of discrete particles in the separator under conditions of different physical property parameters, different structural parameters, and different flow parameters, so as to provide guidance for the structural design and application of the pipeline centrifugal separator.
Owner:HARBIN ENG UNIV

Garbage retention area analysis method and system based on two-dimensional shallow water equation model

The invention belongs to the field of water pollutant treatment, particularly relates to a garbage retention area analysis method and system based on a two-dimensional shallow water equation model, and aims to solve the problem of inaccurate garbage retention area prediction. The method comprises the steps of performing grid division on a target water area, and constructing a hydrodynamic model of the target water area in a preset time period; according to the hydrodynamic model, simulating the motion trail of discrete garbage in the target water area through a discrete particle motion equation; based on the shoreline gradient and the river curvature of the target water area, determining the stranding probability of the discrete garbage under the motion trail; and in a preset time period, determining a garbage retention index of each grid based on the water flow speed, the discrete garbage retention time in each grid and the stranding probability, so as to screen a garbage retention area in the target water area. According to the method, the prediction deviation caused by simplifying the garbage into an ideal tracer in the prior art is overcome, and the prediction accuracy of the garbage transportation path and the final gathering position is remarkably improved.
Owner:HEBEI WATER CONSERVANCY RES INST

Power plant mushroom head type water intake structure water intake boundary layer and characteristic value estimation method thereof

ActiveCN119089825AScientific and efficient designImproving the safety of water intake for nuclear power plantsData processing applicationsHydrodynamic testingEnvironment waterEnvironmental engineering
The invention relates to a power plant mushroom head type water intake structure water intake boundary layer and a characteristic value estimation method thereof. The method comprises the following steps: establishing a three-dimensional flow field model of a water intake sea area including a mushroom head type water intake structure; verifying the flow field model based on a physical model experiment result; analyzing water intake inflow characteristics and a flow field of the mushroom head type water intake structure; analyzing a boundary layer of the mushroom head type water intake structure based on discrete particle tracing; key factors influencing a water taking boundary layer of the mushroom head type water taking structure are identified; and constructing a quick estimation formula for the feature values and key design parameters of the water intake boundary layer of the mushroom head type water intake structure. When the mushroom head type deep water taking structure is used for taking water, water taking boundary layer estimation is carried out on the influence range of the water taking environment water body, the influence characteristics of the mushroom head type deep water taking structure on the environment water body during water taking are determined, and multiple factors such as mushroom head water taking inflow characteristics and environment flow field changes are comprehensively considered; a basis is provided for the influence range of the mushroom head water taking structure on the water body.
Owner:CHINA INST OF WATER RESOURCES & HYDROPOWER RES

A method for optimizing the arrangement of sensors in a tensile membrane structure

ActiveCN116432480BElement modelAlgorithm
This invention is applicable to the field of tensile membrane structure acquisition response damage diagnosis, and provides a method for optimizing the arrangement of sensors in tensile membrane structures. The method includes: establishing a finite element model of the tensile membrane structure; determining the number of modes for optimal sensor arrangement using two methods based on Fisher's information matrix eigenvalue matrix theory: the rate of change of the Fisher information matrix trace and the difference of the information matrix's second norm; determining the number of sensors for optimal arrangement based on the mode-independent correlation criterion in MAC modal confidence matrix theory; optimizing the sensor positions using an improved discrete particle swarm optimization algorithm based on a stochastic strategy combined with the MAC off-diagonal root mean square fitness function; and evaluating the quality of the optimized sensor arrangement results using the MAC modal confidence criterion. This invention can quickly determine the optimal sensor layout scheme, ensuring the effectiveness of the measurement signals from each sensor.
Owner:CHINA UNIV OF MINING & TECH +2

Physical Design Method of Flow Layers Based on Discrete Particle Swarm under Continuous Microfluidic Biochips

The present invention relates to a physical design method of flow layers based on discrete particle swarm under a continuous microfluidic biochip, which comprises the following steps: Step S1: Construct a particle coding scheme based on sequence pairs according to the characteristics of the physical design problem of the continuous microfluidic biochip; Step S2: Search the solution space of the physical design of the flow layers of the continuous microfluidic biochip based on the particle update strategy; Step S3: Generate a design scheme that meets the preset requirements according to the particle coding scheme and the solution space obtained in Step S2. The present invention can effectively improve the efficiency of the physical design of flow layers.
Owner:FUZHOU UNIV

Reinforcement learning-based software function iteration priority decision method and system

The application relates to the technical field of software function decision, in particular to a software function iteration priority decision method and system based on reinforcement learning, which comprises the following steps: obtaining a software function set to be decided; obtaining a sub-function module set contained by a first software function to an Nth software function, and the sub-function module sets are respectively recorded as a first sub-function module set to an Nth sub-function module set; calculating the overall coincidence degrees of the first sub-function module set to the Nth sub-function module set, and the overall coincidence degrees are recorded as a first overall coincidence degree to an Nth overall coincidence degree; obtaining a basic software function; taking the basic software function as a starting point, adopting a discrete particle swarm optimization algorithm to obtain an optimal development sequence of the first software function to the Nth software function; and developing the software function according to the optimal development sequence of the first software function to the Nth software function. The optimal development sequence is solved by the discrete particle swarm optimization algorithm, and global optimization of the software function development sequence is realized.
Owner:DELING SMART SERVICE (BEIJING) TECHNOLOGY CO LTD

New energy control parameter adaptive identification method based on double-layer particle swarm optimization

The application provides a new energy control parameter self-adaptive identification method based on double-layer particle swarm optimization, and belongs to the technical field of power system simulation analysis. Typical control strategies of heterogeneous new energy units are comprehensively used to construct a strategy database and perform verification; test data are acquired for processing and feature extraction, so that high and low threshold values, current initial states and test feature data are obtained; a fitness function is constructed based on the strategy database, a discrete particle swarm algorithm is used in the global optimization layer to select an optimal strategy combination from the strategy database, and in the local optimization layer, parameters of the selected strategy are continuously optimized in combination with a momentum factor and a learning rate. The application uses actual unit test data characteristic values as inputs of the double-layer particle swarm algorithm, determines an optimal strategy-parameter pair through a total error index weighting, verifies the accuracy of the strategy-parameter pair, and effectively improves the efficiency and precision of modeling of heterogeneous new energy equipment.
Owner:福建中试所电力调整试验有限责任公司 +1

Remote sensing satellite image ship target association method and system

The invention provides a remote sensing satellite image ship target association method and system, and relates to the technical field of satellite remote sensing image processing, and the method comprises the steps: S1, constructing a ship multi-source satellite remote sensing image training sample set; s2, based on a deep convolutional neural network, learning coupling and correlation of multi-source satellite remote sensing images, mapping different types of ship target satellite remote sensing images to a common depth feature space, and learning in the depth feature space to obtain a metric function; s3, inputting a ship target multi-source satellite remote sensing image test set into the depth measurement learning network obtained by training, and carrying out feature similarity measurement calculation; s4, designing an association cost matrix ACM; and S5, through a binary discrete particle swarm optimization algorithm DPSO, acceleration association cost matrix ACM optimal scheme solving is carried out, and multi-source remote sensing image ship multi-target association is carried out. According to the method, fuzziness caused by single feature association can be reduced, and the accuracy of ship multi-target association is improved.
Owner:SHANGHAI SATELLITE ENG INST

Water intake boundary layer estimation method for deep water intake structure of power plant

The invention relates to a water intake boundary layer estimation method for a deep water intake structure of a power plant. The method comprises the following steps: establishing a three-dimensional water intake flow field model comprising a sea area environment and the deep water intake structure; verifying the flow field model based on a physical model experiment result; analyzing water intake inflow characteristics and a flow field of the deep water intake structure; analyzing a water taking boundary layer of the deep water taking structure based on discrete particle tracing; and determining a water taking boundary layer of the deep water taking structure. When the deep water taking structure is used for taking water, multiple factors such as water taking structure design characteristics, deep water taking inflow characteristics and environmental flow field changes are comprehensively considered, water taking boundary layer estimation is carried out on the influence range of a water taking environmental water body, and the influence characteristics of the deep water taking structure on the environmental water body during water taking are determined. According to the method, a scientific basis is provided for defining the influence range of water taking operation of the deep water taking structure on an environmental water body and improving nuclear power water taking safety.
Owner:CHINA INST OF WATER RESOURCES & HYDROPOWER RES

A numerical simulation method for particle migration in lead-bismuth fast reactor fuel assemblies

This invention discloses a numerical simulation method for particle migration in lead-bismuth fast reactor fuel assemblies. 1. A fluid domain mesh model is established, including the wire rod bundle and the assembly box wall, and user-defined memory is allocated to the wall surface elements to store deposition layer information. 2. Based on CFD solutions of the flow and temperature fields, a discrete particle model is used for Lagrangian tracking to construct a criterion for particle collision with the wall, deposition rebound, and wall-attached sliding. 3. The deposition quality is statistically analyzed using the user-defined memory, and the deposition layer thickness and thermal resistance are calculated, with feedback used to correct the wall heat transfer boundary and the wire rod bundle heat source. 4. A deposition layer peeling and release model is established, including shear-induced buoyancy and rolling desorption and particle impact-induced desorption, and attribute inheritance and re-injection at the next time step are achieved using a wall particle information stack and a release event queue. 5. The wall normal displacement is updated according to the deposition layer thickness through a dynamic mesh, forming geometric feedback to the flow field, achieving iterative prediction capabilities for deposition evolution and heat transfer effects.
Owner:XI AN JIAOTONG UNIV

Cross-scale discrete Boltzmann method suitable for calculating interference flow field of hypersonic shock wave boundary layer

The invention discloses a cross-scale discrete Boltzmann method suitable for calculation of an interference flow field of a hypersonic shock wave boundary layer, and the method comprises the steps: building an evolution equation of a cross-scale discrete Boltzmann model based on a Boltzmann-BGK equation, the discrete speed selection of the discrete particle speed space meets the kinetic moment constraint determined based on Chapman-Enskog multi-scale analysis; based on the kinetic moment constraint and the fluid macroscopic physical quantity, a discrete equilibrium state distribution function is solved by adopting a matrix inversion method; obtaining an initial discrete distribution function based on a local equilibrium state hypothesis; performing numerical solution on the evolution equation based on the initial discrete distribution function and the equilibrium state distribution function to obtain an evolved distribution function; and calculating a high-order non-conservation momentum between the evolved distribution function and a discrete equilibrium state distribution function corresponding to the evolved distribution function to obtain a physical quantity for quantifying the thermodynamic unbalance characteristic of the flow field.
Owner:BEIJING INST OF TECH