416 results about "Fluid modeling" patented technology

The invention discloses an integrated water quality monitoring and processing system for aquaculture, and the system comprises a data collection module which is used for obtaining dissolved oxygen, ammonia nitrogen, pH value, temperature and flow data from a plurality of spatial distributed sensing nodes; the data preprocessing module is used for completing noise removal, correction and time sequence synchronization; the water quality state estimation module is used for outputting real-time multi-point water quality states based on a distributed unscented Kalman filtering algorithm; the space-time fluid modeling module is used for constructing a Lagrange model to extract a flow velocity field and a diffusion coefficient; the scheduling optimization module is used for generating an aeration and dosing scheme by adopting an improved multi-target Pareto optimization algorithm based on a space-time sensitive boundary; the execution module is used for controlling an air blower, an aeration pipe and a dosing pump to complete oxygenation and dosing operations; and the self-adaptive updating module is used for collecting feedback data to adjust filtering gain and optimizing parameters so as to realize closed-loop control of the system.

The invention relates to a wellbore multiphase flow model numerical solution and gas-liquid distribution state inversion method and system, and belongs to the technical field of petroleum engineering, and the method comprises the steps: 1, constructing and training a physical information neural network for drilling wellbore multiphase flow dynamic simulation and overflow gas distribution state inversion; determining input and output of the physical information neural network; determining a loss function of the physical information neural network; training a physical information neural network; 2, designing an adaptive optimization algorithm, optimizing the final solution precision and convergence speed of the physical information neural network, and obtaining an adaptive physical information neural network; designing an adaptive activation function; designing a self-adaptive sampling mechanism based on residual errors; 3, based on the self-adaptive physical information neural network, numerical solution and gas-liquid distribution state inversion of the shaft multiphase flow model are achieved. According to the method, the problem that a traditional numerical method usually needs high-precision grid division and a large number of computing resources is effectively solved.

The invention relates to the technical field of oil exploitation, and provides a CFD-based electric submersible pump oil-gas-water three-phase flow adaptability analysis method and system, and the method comprises the steps: constructing a three-dimensional geometric model of an electric submersible pump, carrying out the initial grid division through CFD software, and optimizing the grid density through a self-adaptive grid refinement algorithm; setting oil well boundary conditions, a turbulence model and cavitation model parameters; steady-state and unsteady-state simulation calculation is carried out, and a flow field distribution diagram in the electric submersible pump is obtained; key performance parameters are extracted; simulating flow characteristics of oil-gas-water three-phase flow by adopting a turbulence model optimization algorithm based on multiphase flow coupling and combining a turbulence model, a multiphase flow model, an interphase turbulence correction term and an interphase interaction force model; and carrying out adaptability analysis on the oil-gas-water three-phase flow of the electric submersible pump. All-around technical support can be provided for design, operation and maintenance of the electric submersible pump, and technical progress and development of the oil exploitation industry are powerfully promoted.

The invention provides a digital twinning-based water flow dynamic analysis method and a big data analysis system, and the method comprises the steps: obtaining a historical water flow data set of a target water area, collecting a real-time water flow monitoring data set, and constructing a digital twinning water flow model corresponding to the target water area; performing multi-modal feature fusion processing on the historical water flow data set and the real-time water flow monitoring data set to generate a dynamic water flow feature set, loading the dynamic water flow feature set into a digital twin water flow model based on a spatial distribution topological structure of the digital twin water flow model to generate a water flow dynamic change rule set, and performing dynamic water flow change on the dynamic water flow change rule set. And generating a water flow optimization strategy set according to the water flow dynamic change rule set, and feeding back the water flow optimization strategy set to the water flow regulation and control system to execute dynamic regulation and control operation. By adopting the technical scheme of the invention, the space adaptability and the dynamic response capability of the water flow optimization strategy decision can be obviously improved.

The invention relates to the technical field of computational simulation, in particular to a fluid mechanics calculation method and system based on CFD simulation optimization. The method comprises the following steps: acquiring a flow field CFD original simulation model corresponding to fluid mechanics; generating a fluid mechanics flow field key grid area by setting the size of a flow field calculation domain grid and performing calculation domain grid division and flow field key area identification; the method comprises the following steps of: obtaining a grid length-width ratio and torsion resistance corresponding to each grid subunit in the grid, and carrying out grid constraint updating to generate a fluid mechanics flow field updating grid region; a corresponding Reynolds number and a turbulence scale are obtained through the fluid mechanics flow field updating grid area, turbulence model dynamic selection modeling is carried out, and a flow field grid area dynamic turbulence model is generated; and carrying out finite volume division and error simulation correction optimization on the dynamic turbulence model of the flow field grid region to obtain a corrected fluid mechanics flow field quantity calculation result. According to the method, collaborative improvement of fluid mechanics calculation precision and efficiency can be realized.

The invention discloses a complete machine variable-dimension simulation method based on a circumferential average flow model, belongs to the technical field of aero-engine numerical simulation and multi-scale modeling, and solves the problem that complete machine simulation efficiency and local flow detail precision are difficult to consider at the same time in the prior art. And traditional full-three-dimensional computing is too high in resource consumption and cannot quickly evaluate the performance of the whole machine. According to the method, a zero-dimensional complete machine and component two-dimensional model of the aero-engine is firstly established, dimensionality reduction is carried out by using a circumferential average N-S equation, the two-dimensional model is embedded into the zero-dimensional model, an equivalent replacement variable reconstruction equation set is solved, synchronous convergence of the complete machine and component models is realized, and simulation precision and efficiency are improved. According to the method, a full coupling mode is adopted, two-dimensional dimension reduction modeling is combined, minute-level convergence is achieved, the simulation error is not larger than 5%, the simulation precision is improved, the calculation efficiency is improved, rich S2 flow field information can be provided, and the research and development cost and period are reduced.

The invention provides a bearing / heat exchange integrated outer duct heat exchanger structure and a design method thereof. The design method mainly comprises the steps of heat exchanger three-dimensional modeling design, computational fluid dynamics optimization design and steady-state thermal stress analysis, three-dimensional modeling software is used for designing an inner flow channel structure and an outer fin structure of an outer duct air heat exchanger, and finite element software is imported. The method comprises the following steps: dividing grids, establishing a finite element model, setting a turbulence model, adding boundary conditions of the external duct heat exchanger, performing fluid flow and heat transfer simulation in the heat exchanger to obtain a fluid dynamic model of the external duct heat exchanger, transmitting temperature field simulation data to the finite element model, and performing steady-state thermal stress simulation to obtain a stress distribution nephogram. And structural performance evaluation is performed in combination with strength analysis. According to the method, the simulation efficiency can be improved on the premise that the simulation precision is not lost, organic combination of design / performance is achieved, and theoretical guidance is provided for structural design of the bearing / heat exchange integrated outer duct heat exchanger.

The invention belongs to the technical field of bubble dynamics and multiphase flow and artificial intelligence, and particularly relates to a high-pressure bubble pulsation load prediction and initial parameter inversion method and system based on artificial intelligence. The underwater high-pressure bubble pulsation process is studied, and interface evolution data in the high-pressure bubble pulsation process are obtained; establishing a compressible VOF-PINN multiphase flow model, and predicting unknown parameters and pulsating load characteristics of bubbles in combination with the initial boundary value; dividing a prediction problem into a positive problem and an inverse problem according to known data; establishing a model which can be used for predicting forward and reverse models; for a positive problem, training and predicting the VOF-PINN model by using a gradient descent optimization algorithm; and for the inverse problem, bubble initial parameter identification is realized. The invention aims to solve the problems that recalculation is needed for changing calculation parameters in numerical simulation, grid division is complex and tedious, high-fidelity data cannot be directly included, and initial parameters in experimental research are uncertain.

The invention discloses a source network, plant, river and lake integrated model simulation method and device, a medium and equipment in the technical field of regional water environment pollution treatment. The method comprises the following steps: inputting a boundary condition and an initial condition of a first model into a pre-constructed surface runoff production and convergence model of a target area, and outputting a flow rate of surface runoff and a water quality index time sequence; inputting the boundary condition and the initial condition of the second model into a pre-constructed pipe network model of a target area, and outputting a flow and water quality index time sequence of key nodes in a pipe network system; and inputting the boundary condition and the initial condition of the third model into a pre-constructed riverway and lake grid model of a target area, and simulating the river and lake hydrodynamics and water quality change process of the target area. According to the invention, coupling simulation of surface runoff, pipe networks, rivers and lakes is realized, and a propagation path and an influence mechanism of pollutants are comprehensively reflected; and high precision and reliability of the model are ensured through parameter calibration.

The invention relates to a thermal simulation numerical simulation method of a multi-physics field architecture with CFD as a core, and belongs to the technical field of cross of computational fluid mechanics and heat transfer science. The method comprises the following steps: constructing a geometry and a conformal / non-conformal grid, presetting a model library, establishing association between a region and a physical field through physical group division, confirming a boundary and initial parameters, and screening a core simulation model; dividing an independent control volume based on a core numerical model, converting an area component and a volume component through integral operation, discretizing a boundary flux to construct a parameter matrix, then solving an equation set, and synchronously optimizing the grid quality; calculating a boundary flux and matching a discrete format, a turbulence model and a corresponding multi-physical field coupling model; original data are screened and processed, and cloud picture results such as temperature and flow field are generated through visualization. Accurate simulation of a multi-physics coupling scene is achieved, the precision and stability of thermal simulation under complex working conditions are improved, and efficient and reliable technical support is provided for engineering design optimization and performance evaluation.

A worm and worm gear pair heat-fluid-solid coupling analysis method comprises the following steps that 1, a heat-fluid-solid coupling simulation analysis model of a worm and worm gear pair is built, and a three-dimensional geometric model is built based on the worm and worm gear meshing principle; 2, parameterized grid division is carried out on the simulation analysis model, a tetrahedral unstructured grid is adopted for a fluid domain, and a worm and worm gear tooth surface area is densified; 3, based on the fluid dynamics theory and an RNG # imgabs0 # turbulence model, establishing an oil-immersed lubricating oil gas two-phase flow transient simulation model, and solving fluid dynamic pressure and a convective heat transfer coefficient through a pressure-speed coupling algorithm; 4, establishing a three-dimensional transient dynamic simulation model based on a solid mechanics theory, combining a temperature-stress coupling field equation, adopting an explicit dynamic algorithm, and iteratively solving thermal deformation and stress strain of the worm and the worm gear through a finite element method; and 5, bidirectionally transmitting the pressure of the fluid domain, the convective heat transfer coefficient and the thermal deformation data of the solid domain through the fluid-solid interface, and carrying out iterative solution until convergence.

The invention relates to a method for calculating the slag entrapment amount of continuous casting covering slag based on computational fluid mechanics, which adopts a large eddy simulation (LES) turbulence model, a multiphase flow model (VOF) and a discrete phase model (DPM) in CFD calculation, and combines a grid self-adaptive coarsening and refining mechanism and a VOF-to-DPM conversion mechanism. The method is used for numerical simulation and control of the slag entrapment amount of the continuous casting covering slag under the argon blowing condition, a slag entrapment mode calculation result is verified through a water model experiment, and a numerical simulation calculation result obtained through the method is well matched with a water model experiment result. Compared with the prior art, the method has the advantages that the slag entrapment amount of the continuous casting covering slag can be effectively calculated, and a basis is provided for controlling the slag entrapment amount of the covering slag.

The invention discloses a test device and a test method for filling fracture seepage-erosion visualization. The test device comprises a fracture overflowing model, a fluid flow control system and an image and pressure data acquisition and analysis system. The fracture overflowing model has the appearance of a real rock fracture surface, and the opening degree can be quantitatively adjusted through a filler gauge gasket; the fluid flow control system uses a peristaltic pump and a stirrer to provide constant-flow fluid and particle input for the fracture overflowing model; according to the test device, the light transmission principle is utilized, quantitative and visual observation and research of the seepage-erosion process of the filled fracture are achieved, and form and permeability evolution data of a particle erosion area in the filled fracture are accurately obtained.

Provided is a turbulent flow simulation method in which a computer uses a large-eddy simulation to analyze a flow field of a fluid, the method comprising: acquiring a simulation condition (S10); performing, on the basis of the acquired simulation condition, analysis of the flow field of the fluid by means of the large-eddy simulation (S20); and outputting an analysis result of the flow field of the fluid (S30). In the analysis of the flow field of the fluid, a turbulent flow model that includes an error term of a Navier-Stokes equation derived from a lattice Boltzmann equation as a correction term associated with coarse graining in the large-eddy simulation is used, the correction term being a body force calculated from eddy stress associated with the coarse graining.

The invention discloses a cross-scale multi-physics-field coupling aero-engine warming-up process analysis method. The method comprises the steps that firstly, an engine air system one-dimensional network model, a fuel and lubricating oil system one-dimensional network model, a wheel disc and cartridge receiver two-dimensional axial symmetry model, a blade parameterization model and a main runner quasi-one-dimensional model are established; then calculating an air system boundary and a fuel and lubricating oil system boundary by using a main runner cavity method, then calculating the fuel and lubricating oil system boundary and the air system boundary by using a one-dimensional transient fluid network method to obtain a heat exchange boundary of a wheel disc and a cartridge receiver, and considering a thermal load and a centrifugal load in an unsteady state heat conduction process; calculating the radial displacement of the wheel disc and the casing by using a two-dimensional axisymmetric finite element method, and calculating the temperature and the radial displacement of the blades by using an engineering algorithm; and finally, integrating the radial displacement of the wheel disc, the blades and the casing and the initial blade tip clearance value to obtain the blade tip clearance value of each stage in the transient process, and feeding back the blade tip clearance value to the mainstream model again to realize iterative calculation. The analysis precision of each physical field is improved, and the calculation time consumption is reduced.

The invention relates to the technical field of water resource management and forecasting, in particular to a deep learning model building and forecasting method based on hydrological mechanism fusion. The method specifically comprises the following steps: constructing a snow melting calculation module and a soil calculation module, splicing to form a runoff production model, constructing a confluence calculation module, executing confluence evolution simulation of a calculation result of the runoff production module by using the confluence calculation module, and constructing a confluence model. In confluence model simulation calculation, according to the number of calculation units, a broadcast calculation strategy and an array-based ordinary differential equation solving method are adopted, parallel calculation of the multiple calculation units is achieved, and runoff production calculation results of the multiple units are obtained; and integrating and calculating runoff production calculation results of each unit through a confluence model to obtain a runoff prediction result of the modeled drainage basin after confluence. The method provided by the invention solves the problems of low model construction efficiency and poor practical application effect faced by the application of the deep learning technology in the hydrological model at present.

The invention discloses a parallel computing simulation method for thermal exploitation of a buried pipe well group in a geothermal reservoir, which comprises the following steps of: dispersing a grid volume unit of a buried pipe by adopting a parallel finite element unit method, and simplifying the buried pipe and circulating fluid in the pipe into a one-dimensional linear finite element unit; constructing a plurality of pipeline flow models arranged in an array, and combining the in-pipe one-dimensional linear units and the out-pipe three-dimensional volume units to obtain a well group type pipeline flow geometric model; a parallel finite element unit method is adopted to be combined with a non-isothermal pipeline flow physical field, an underground water seepage physical field and a porous medium heat transfer physical field to conduct multi-physical-field coupling, and a well group type pipeline flow numerical model is obtained; fluid flow and convective heat transfer in the buried pipe and pipe wall heat conduction are solved in a combined mode; and performing factor sensitivity analysis by changing different thermophysical parameters of the rock-soil body and heat exchange characteristic factors of the buried pipe well group. The invention provides a new method for researching fluid flowing and heat transfer behaviors of the buried pipe well group, and provides a new idea for optimal design and efficient simulation of thermal exploitation of the buried pipe well group in a geothermal reservoir.

The invention discloses a self-adaptive parameter identification method for an SST turbulence model in shock wave boundary layer interference, and the method comprises the steps: S1, constructing a high-dimensional sample space according to a closed parameter interval range of the SST turbulence model under a determined working condition, carrying out the optimal Latin hypercube sampling, and uniformly obtaining the sample information in the whole space, and enabling the sample information to serve as an input parameter sample; s2, performing numerical simulation based on an input parameter sample and a determined working condition to form a model prior sample set; s3, according to the model prior sample set, constructing a flow field wall surface pressure prediction model under shock wave boundary layer interference based on an improved Bayesian neural network; and S4, based on the flow field wall surface pressure prediction model under the interference of the shock wave boundary layer, performing adaptive parameter identification on the SST turbulence model by adopting a particle swarm optimization algorithm to obtain the optimal closing parameter of the SST turbulence model for realizing the high-precision simulation of the flow field. According to the method, the numerical simulation precision and speed are improved, and technical support is provided for safe and reliable work of the scramjet engine in a complex environment.

The invention provides a cooling fan performance calculation method based on multi-physics field coupling. The cooling fan performance calculation method comprises the following steps that a parameterized geometric model of a fluid domain is established according to the size and the relative position of an engine cooling fan and a wind chamber test bed; respectively inputting the two parameterized geometric models into pretreatment software, respectively carrying out grid division on the two parameterized geometric models by using a grid division tool, and outputting a grid file after geometric discretization of the two parameterized geometric models; the discrete grid file of the engine cooling fan is imported into finite element analysis software, a pretreatment tool is used for defining material parameters for the engine cooling fan, boundary conditions and load constraints are applied, the discrete grid file of a fluid domain is imported into fluid dynamics analysis software, and fluid dynamics analysis is carried out on the engine cooling fan; setting a turbulence model, region and boundary conditions, a solver and the like; establishing a multi-physical field coupling model to realize data exchange among a plurality of physical fields; and operation calculation is carried out, a calculation result is post-processed, and qualitative and quantitative analysis is carried out on the fan performance.

The invention discloses a gas diffusion layer reconstruction and two-phase flow model combination method considering a binder structure, which comprises the following steps of: establishing a gas diffusion layer pure fiber structure by utilizing a random reconstruction method, reconstructing the binder structure by adopting a morphological closed operation algorithm, and regulating and controlling the size of a structure operator to obtain a two-phase flow model. The effective control on the structural volume ratio and the porosity of the binder is realized. A two-phase flow model is established based on reconstruction of a gas diffusion layer with a real structure, so that the flow process of liquid water in the gas diffusion layer is solved and calculated. According to the method, the pore structure of the gas diffusion layer of the fuel cell can be reconstructed more accurately, and structural parameter changes of the gas diffusion layer caused by the existence of the binder, including changes of key parameters such as porosity, pore diameter and tortuosity, can be obtained. The characteristics of the two-phase flow process in the gas diffusion layer can be visually, rapidly and accurately obtained, the relation between the structure of the gas diffusion layer and the two-phase flow process is defined, and the structure of the gas diffusion layer is optimized.

The invention provides a three-phase foam flow injection simulation method for enhanced oil displacement of a high-water-content oil reservoir, and belongs to the field of computational fluid mechanics. An immiscible three-phase flow calculation model is constructed under a lattice Boltzmann framework, and a continuous surface force model and a re-coloring algorithm are introduced into the immiscible three-phase flow calculation model; repulsive force is added between gas-phase foams meeting requirements, so that the three-phase flow model has the capability of simulating non-coalescence foam behaviors; wetting boundary conditions are applied according to a diffusion interface idea, and solid wall surface boundaries with specific wettability under complex geometric conditions are processed; inputting three-phase fluid physical property parameters, providing auxiliary parameters necessary for executing simulation to operate the immiscible three-phase flow calculation model, and obtaining multiple groups of data representing the three-phase flow state in the foam injection oil displacement process through time-marching simulation. According to the invention, the blank of the lattice Boltzmann method in the aspect of simulating the three-phase foam flow of oil, water and gas is filled, and high-precision simulation can be carried out on the three-phase foam injection oil displacement process.

The invention discloses a three-dimensional slit coating simulation method and system, electronic equipment and a computer readable storage medium. The three-dimensional slit coating simulation method comprises the following steps: establishing a three-dimensional geometric model of a coating machine die head; performing grid division on the three-dimensional geometric model; establishing a slurry flow two-phase flow model in the three-dimensional flow field; setting solving parameters, slurry attributes and boundary conditions of a slurry flow model, wherein the boundary conditions comprise a speed inlet and a pressure outlet of slurry and a foil moving wall surface; carrying out initialization solution on the slurry flow model based on the boundary condition, and ending when calculation reaches a convergence condition; and running simulation, analyzing the change of flow velocity distribution and pressure distribution of the slurry in the three-dimensional geometric model, and observing the three-dimensional flow characteristics of the slurry in the three-dimensional geometric model. According to the invention, the flow behavior of the slurry in the coating process can be accurately predicted, especially the problems of edge thickness change and coating uniformity at a slit outlet are solved.

The invention belongs to the technical field of battery energy storage, and discloses a simulation analysis method for heat dissipation of a battery energy storage system, which comprises the following steps of: establishing a three-dimensional model and a three-dimensional simulation model of a heat dissipation module of the energy storage system; establishing finite element simulation models of the liquid cooling plate and the battery module; establishing a two-fluid heat dissipation finite element simulation model comprising an air flow field and a liquid flow field; setting boundary conditions, and performing grid division in fluid simulation software; starting an energy equation in fluid simulation software, and calculating and extracting an air flow field of the energy storage system and a battery module temperature distribution cloud picture by adopting a turbulence model; three-dimensional simulation updating is conducted on the heat dissipation module of the energy storage system, and the arrangement structure of a cooling liquid inlet and a cooling liquid outlet and the structure of an air outlet are changed; and re-extracting the calculation result. According to the method, an electrochemical energy storage system finite element model combining an air cooling heat dissipation system and a liquid cooling heat dissipation system is constructed, so that the diversified requirements of energy storage devices of different scales in practical application are better met.

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 belongs to the technical field of ocean engineering, and particularly relates to a potential flow-viscous flow real-time coupling hydrodynamic analysis method and system for a floating body with a heaving plate. The method comprises the following steps of: 1, establishing a free surface potential flow model based on a three-dimensional potential flow theory, simulating wave-structure interaction, ignoring a viscous effect, converting a frequency domain result of a hydrodynamic load into a time domain load through a frequency-to-hour method, and taking the time domain load as an input for solving a motion state; 2, establishing an unbounded viscous flow CFD model, viscous force not covered by a potential flow model and an updated unbounded turbulent flow field around the heaving plate, and calculating the viscous force of the heaving plate; 3, establishing an unbounded potential flow model, and separating a force component repeated with the potential flow from a viscous flow result; 4, integrating the potential flow force and the viscous force to solve a floating body motion equation, iteratively updating the motion state and feeding back the motion state to the two solvers. The method is used for solving the problems that the efficiency is correspondingly reduced if the precision is improved and the precision cannot meet the requirement if the efficiency is improved in the prior art.

The invention provides a tobacco leaf curing environment parameter optimization method based on computational fluid mechanics, which belongs to the technical field of tobacco leaf curing, and comprises the following steps: firstly, collecting multi-point environment data of a tobacco leaf curing room to establish an initial data set, constructing a three-dimensional grid model and setting boundary conditions; secondly, importing data into fluid mechanics simulation software, setting physical property parameters and a turbulence model, and obtaining distribution of a flow field, a temperature field and a humidity field; then, an unsupervised learning algorithm is applied to identify an environment non-uniform region, and a temperature and humidity gradient model is constructed to generate an optimization curve; then calculating the similarity of temperature and humidity curves of adjacent time sequence frames to determine a key gradient point, and establishing a tobacco leaf quality and environmental parameter multivariate correlation model; and finally, performing comprehensive optimization by applying an environmental parameter fusion optimization function, calculating an optimal baking time sequence control scheme, screening an optimal parameter combination after verification in the model, applying the optimal parameter combination to an actual baking process, monitoring physical and chemical indexes of tobacco leaves, realizing accurate control of baking environmental parameters, and facilitating stable quality of the tobacco leaves.

The invention discloses a wind field yaw wake flow hybrid modeling method and device fusing simulation and deep learning. The method comprises the following steps: firstly, introducing a yaw-corrected actuating disc model, constructing a volume force source item under the yaw action of each fan, performing steady-state computational fluid mechanics simulation on the yaw wake flow of the wind field by combining a Reynolds average Navier Stokes method and a k-epsilon turbulence model, and constructing a yaw wake flow database of the wind field; and then, training the yaw wake flow database by using a deep neural network, and learning a nonlinear mapping relationship between a wind field input wind speed and a multi-fan yaw angle combination and an incoming flow wind speed of each fan, so that a wind field yaw wake flow data driving model is established, and real-time prediction of wake flow characteristics under non-consistent yaw configuration is realized. Compared with an existing yaw wake flow model, the method has the advantages that the technical difficulty of wake flow modeling of multi-fan non-consistent yaw is effectively solved, the prediction speed is remarkably increased while the modeling precision is improved, and the method has high engineering application value.

The invention discloses a method for generating a Riemannian manifold data set based on a geodesic interpolation technology, and the method comprises the steps: S1, determining a task manifold, and initializing a neural network; s2, establishing a geodesic interpolation model based on a task manifold, and obtaining an interpolation point set; s3, based on the interpolation point set, calculating and optimizing two neural networks used for approaching a tangent vector field on the task manifold to obtain an optimal neural velocity field network and an optimal neural score field network; s4, establishing a data generation framework on a manifold according to the optimal neural velocity field network and the optimal neural fractional field network; and S5, generating a new priori initial value sample, and using the new priori sample as an initial value to input a data generation framework on the task manifold, simulating unknown distribution data to be generated, and obtaining sufficient new data points as a Riemannian manifold dataset. And a way is provided for further unifying the flow model and the diffusion model on the manifold in the future.

The invention discloses a multi-energy coupling temperature field control method and system based on intelligent optimization, and relates to the technical field of intelligent control, and the method comprises the steps: extracting temperature field space-time features through an ST-CNN space-time convolution network in the aspect of energy efficiency optimization, solving a Pareto leading edge of a multi-objective optimization model in combination with an NSGA-III algorithm, and solving the Pareto leading edge of a multi-objective optimization model; the system achieves the optimal balance among the electro-thermal conversion efficiency, the refrigeration coefficient and the human body comfort level; secondly, in the aspect of control precision, a 3D convolution kernel and an LSTM module are adopted to cooperatively analyze the dynamic law of a temperature field, and in cooperation with CFD turbulence model simulation verification, the temperature control error can be reduced to a small range, and the space temperature uniformity is obviously improved; finally, in the aspect of system intellectualization, autonomous iterative optimization of control parameters is achieved through a near-end strategy optimization algorithm, a closed-loop control system of perception-decision-execution-feedback is formed, and the manual intervention requirement is reduced or eliminated.

The invention relates to a numerical simulation-based energy efficiency evaluation method and system for an energy-saving device in front of a ship propeller, and the method comprises the steps: respectively obtaining geometric models of a ship, a propeller, a rudder and the energy-saving device in front of the propeller, respectively building corresponding three-dimensional numerical models through CAD software, and then assembling the three-dimensional numerical models into a closed geometry; dividing the closed geometry into a plurality of computational domains, performing grid division and encryption of the same scale, and reserving the grids of which the grid number is within a preset number threshold range of each set of encrypted grids; then respectively constructing a light body ship CFD model and a ship CFD model additionally provided with an energy-saving device, and screening out an optimal turbulence model by using an RANS method; then, numerical simulation is conducted on self-propulsion tests of the light body ship CFD model and the energy-saving device added ship CFD model through the reserved grids and the optimal turbulence model, and an equal-vehicle-speed variable-rotation-speed strategy is adopted in the numerical simulation process; and finally, the energy-saving effect of the energy-saving device is calculated based on the propeller rotating speeds and torques of the two models.