51results about How to "Guaranteed calculation accuracy" patented technology

The invention discloses a deep tunnel surrounding rock mechanical parameter inversion method based on a three-dimensional brittle failure zone contour and sparrow optimization algorithm-information vector machine (SSA-IVM) combined optimization algorithm. The engineering technical problem that due to the fact that excavation instantaneous displacement is difficult to monitor, deep tunnel surrounding rock mechanical parameters are difficult to reasonably obtain through displacement back analysis is solved. The method comprises the following steps: firstly, constructing a tunnel FLAC3D numerical simulation model with the same ground stress condition at the occurrence position of a three-dimensional brittle failure zone; secondly, taking an absolute error between the total number of computational grid units in the actually measured brittle failure zone and the total number of computational grid units entering a plastic state in the range of the actually measured brittle failure zone after calculation of the FLAC3D numerical model as an optimization objective function; and then, by taking the tunnel surrounding rock mechanical parameters as optimization variables and taking a target function reaching a global minimum value as a target, performing global optimization by combining a tunnel FLAC3D numerical model and adopting an SSA-IVM joint optimization algorithm, thereby obtaining reasonable tunnel surrounding rock mechanical parameters.

The application provides a kind of tower type solar thermal power station mirror field optical efficiency calculation method, belongs to tower type solar power field, solve mirror field optical efficiency large amount of calculation and low precision problem.Its technical scheme is: including the following steps: S1: obtaining mirror field parameters and solar position;S2: determine the atmospheric transmission efficiency and cosine efficiency of each heliostat;S3: calculate the shadow blocking efficiency of each heliostat;S4: calculate the truncation efficiency and optical efficiency of each heliostat.The beneficial effects of the application are: a kind of tower type solar thermal power station mirror field optical efficiency calculation method is designed, the method is gridded to the current heliostat, and the grid point and its adjacent heliostat vertex are projected to the mirror field horizontal plane along the incident light direction or the reflected light direction to calculate the shadow blocking efficiency, the heliostat that may be blocked is selected within a reasonable range, which greatly reduces the calculation amount of heliostat shadow blocking rate, and the operation accuracy is high, the method can ensure the calculation accuracy while improving the calculation speed of tower type solar power station mirror field optical efficiency simulation.

The invention discloses a vehicle time history response calculation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a mass matrix, a damping matrix and a stiffness matrix of a to-be-tested vehicle; inputting the mass matrix, the damping matrix and the stiffness matrix into a pre-constructed time history response calculation model; according to the mass matrix, the damping matrix and the stiffness matrix, the time history response of the to-be-tested vehicle is calculated through a time history response calculation model; wherein the time history response comprises a displacement vector, a speed vector and an acceleration vector. According to the embodiment of the invention, the calculation efficiency can be remarkably improved while the calculation precision is ensured, and the method is suitable for time-history response analysis of the key structure of the commercial vehicle under the complex dynamic load.

The present application relates to a kind of laser radar and camera online self-calibration method and system without induction, the method includes: S1.in the process of vehicle driving, through multi-source trigger mechanism acquisition laser radar point cloud data and camera image data, simultaneously obtain vehicle motion state information and automatic driving perception system output result, the multi-source trigger mechanism includes time trigger, event trigger and cloud data mining trigger parameter degradation model;S2.the pre-processing and feature extraction of the multi-source data collected, obtain laser radar point cloud feature and camera image feature;S3.based on geometric constraint, motion consistency and perception result fusion, constructs multi-modal verification model, and carries out multi-dimensional verification to calibration parameter.The present application not only reduces the artificial maintenance cost, through automatic means maintenance vehicle state to achieve sensor calibration parameter degradation self-detection and self-calibration without induction, and improves the reliability and attendance rate of automatic driving vehicle.

This invention discloses a method for calculating the back electromotive force (EMF) of a multi-element winding in a hollow cup armature brushed motor and a motor system thereof. The method includes: obtaining the parameters of a parallel magnetized permanent magnet and calculating the fundamental amplitude of the radial air gap magnetic flux density; obtaining the winding parameters and calculating the flux amplitude linked by a single-turn coil rotating in a magnetic field; calculating the back EMF amplitude per unit element based on the total number of turns and elements, and the coil rotation angular velocity; and vector-combining the back EMF generated by each element according to the electrical angle of the back EMF generated by each element to obtain the magnitude of the synthesized back EMF of the entire coil winding; integrating the waveform of the back EMF based on the magnitude of the back EMF amplitude and the number of commutations of the motor to obtain the average value of the motor's back EMF and the constant value of the motor's back EMF. This invention obtains the analytical formula for calculating the radial air gap magnetic flux density and the fundamental amplitude of the radial air gap magnetic flux density by analyzing the magnetomotive force and air gap permeability, ensuring the accuracy of the motor's back EMF calculation.

The embodiment of the invention provides an electromagnetic scattering calculation method based on a heterogeneous GPU cluster. The method is applied to the field of computational electromagnetism, and comprises the following steps: constructing a hierarchical bounding volume geometric acceleration structure of a target object and adding an edge index, and meanwhile, completely copying and distributing data of the acceleration structure to a video memory of each computational node in a heterogeneous GPU cluster; generating a random ray path starting from an emission source, modeling an electromagnetic scattering process as a ray path set in a probability space, and generating a ray direction through an importance sampling strategy; determining a static scheduling strategy for the ray batch based on the calculation cost of pre-sampling and geometric enhancement, and carrying out non-uniform distribution on task tiles according to the heterogeneous GPU calculation power; and monitoring the execution state of the heterogeneous GPU cluster in real time, and dynamically adjusting the distribution strategy of the residual ray tasks based on execution feedback. According to the method, the calculation overhead can be remarkably reduced while the calculation precision is ensured, and the efficiency and expandability of complex target electromagnetic scattering calculation are improved.

This invention relates to the field of oilfield equipment monitoring technology, specifically proposing a structure and method for monitoring corrosion inside a bimetallic composite plate pressure vessel. The structure includes an inner section and an outer section. The inner section is installed inside the pressure vessel, and its thickness is the same as that of the inner layer of the pressure vessel. The outer section covers the inner wall of the inner section. An anti-corrosion layer is applied to the outer wall of the outer section. Blind holes and through holes are adjacently formed on the outer wall of the inner section, with the end of the through hole near the outer section abutting against the inner wall of the outer section. By detecting the blind holes and through holes in the inner section, the corrosion status of the pressure vessel's inner layer can be deduced. Since grinding or welding repair of the inner section is unnecessary, it avoids affecting the subsequent normal operation of the pressure vessel. Furthermore, it overcomes the shape limitations of the pressure vessel itself, reduces errors in the detection results, and ensures the accuracy of the calculated corrosion rate of the pressure vessel's inner layer.

The invention discloses a small molecule binding protein design method. The method comprises the following steps: S1, a structure acquisition step: acquiring a compound structure of a target small molecule ligand and protein; s2, a candidate sequence generation step: generating a candidate protein sequence set by adopting a protein generation model and adjusting parameters corresponding to the protein generation model according to the compound structure in the step S1; s3, a primary screening step; compounding the candidate protein sequence set in the step S2 with the small molecule ligand in the step S1, predicting a compound structure I, and screening a potential sequence from the compound structure I; s4, a fine screening stage: compounding the potential sequence screened in the step S3 with the small molecule ligand in the step S1, predicting a compound structure II, and screening a preferred protein sequence I from the compound structure II. Through deep fusion of AI generation and physical screening, a layer-by-layer progressive accurate screening funnel is constructed, and the false positive rate is greatly reduced.

The present disclosure relates to the chip technical field, and proposes a current detection circuit, a current detection method, a chip and an electronic device. The circuit comprises a voltage average module, a voltage compensation module and a current detection module. The voltage average module averages the output voltages of M output terminals of a power supply to obtain an average voltage, and outputs the average voltage to the voltage compensation module. The residual voltage of the output voltage when transmitted to a load through a power distribution network is a load voltage. The voltage compensation module obtains a compensation voltage according to the average voltage and the load voltage, and outputs the compensation voltage to the current detection module. The compensation voltage is less than the average voltage, and the difference between the average voltage and the compensation voltage increases with the increase of the impedance of the power distribution network. The current detection module determines the output current of the power supply according to the compensation voltage, the load voltage and the preset impedance of the power distribution network. The cost of calculating the output current by using the current detection circuit is small, the loss to the load voltage is small, and the accuracy is high.

The application discloses a simulation method for flow heat exchange of a printed circuit board type heat exchanger complete machine, which comprises the following steps: setting physical property parameters of cold and hot channel working substances, selecting a proper physical model, and constructing a single-channel flow resistance model; dividing the cold and hot channels into cold and hot microchannels and cold and hot runner systems, respectively constructing cold and hot microchannel models for the cold and hot microchannels, and respectively constructing cold and hot runner system models for the cold and hot runner systems; dividing a plurality of heat exchange units for the cold and hot microchannel geometric models respectively, constructing three-dimensional flow heat exchange models for each heat exchange unit, and constructing a one-dimensional axial temperature distribution model of the heat exchanger; obtaining flow distribution calculation results of the cold and hot microchannels through simulation; obtaining outlet temperatures and heat exchange amounts of the cold and hot processing units of each heat exchange unit through simulation calculation of each three-dimensional flow heat exchange model according to the flow distribution calculation results of the cold and hot microchannels and temperature working condition tables, and further obtaining a convective heat exchange coefficient and substituting the same into the one-dimensional axial temperature distribution model of the heat exchanger to obtain an axial temperature distribution of the heat exchanger.

The invention discloses a risk assessment and optimization method based on an abnormal operation state of a low-voltage power distribution network, and relates to the field of risk assessment and optimization of the low-voltage power distribution network. The low-voltage power distribution network risk assessment model comprises a mathematical model unit, a deterministic three-phase power flow improved calculation unit, a source-load probability distribution unit and a Monte Carlo probability power flow calculation unit, and low-voltage power distribution network abnormal operation state assessment parameters are defined based on the low-voltage power distribution network risk assessment model. And configuring a risk weight coefficient for the evaluation parameters of the abnormal operation state of the low-voltage power distribution network to obtain a comprehensive risk, and performing evaluation optimization on the risk of the low-voltage power distribution network through a genetic algorithm based on the comprehensive risk Psys. By the adoption of the method, the risk that abnormal operation states such as overvoltage and three-phase unbalance degree out-of-limit happen to the low-voltage power distribution system in the high-permeability distributed new energy region is effectively reduced, and power flow distribution probability statistical data of all phases and the neutral line are obtained through quick and accurate calculation.

The application provides a polymer material life prediction method and system considering bidirectional coupling, and aims to solve the problem that the permeability of the polymer material suddenly increases due to hydrogen-induced damage accumulation under a high-pressure hydrogen environment. The method obtains material parameters and service boundary conditions, converts pressure into surface concentration, alternately performs mechanical and diffusion-damage evolution solving in a finite element increment step, modifies the stiffness by using the damage variable of the last step to calculate the hydrostatic stress of the current step, modifies the effective diffusion coefficient by using the stress and the damage variable of the last step, solves the hydrogen diffusion equation and updates the damage variable of the current step, and constructs a bidirectional positive feedback coupling closed loop. Finally, the residual life is output based on the permeation threshold or the damage critical value. The application is mainly used for life evaluation of polymer materials in high-pressure hydrogen storage and transportation equipment.

The present application relates to a kind of computing method for realizing wide range dynamic noise map system fast update, comprising the following steps: using the data information of system database, based on existing day and night period and city road grade, simplify the structure of traditional road sound level mechanism model;Using big data technology, using hybrid modeling method, regression each grade road sound source (day and night) sound level contribution amount prediction model;Road noise fast calculation method based on sound level contribution amount prediction model is constructed, the fast update of dynamic noise map is realized.Compared with prior art, while ensuring the calculation precision, the operation and update efficiency of noise map system is greatly improved, and the technical constraints of foreign core computing software are broken, the localization of noise map core computing technology is realized, which provides technical support for wide range deep development of noise map.

This invention relates to the field of electronic packaging technology and discloses a multi-physics coupled packaging simulation method, including S1, macroscopic equivalent model construction, which establishes a macroscopic packaging model containing multi-physics loads and performs equivalent processing on the microscopic complex structure to efficiently obtain the overall temperature, displacement, and stress distribution; S2, key region identification, which combines macroscopic equivalent modeling with microscopic fine modeling and establishes a macro-micro bidirectional coupling mechanism to enable the macroscopic structural response and microscopic local behavior to be solved collaboratively under the same analysis framework; at the same time, combined with an adaptive iteration strategy, the microscopic model is dynamically introduced only in key high-risk areas to avoid the degree-of-freedom explosion problem caused by global fine modeling, thereby significantly reducing the overall computational scale while ensuring the accuracy of stress and strain prediction in key areas, effectively solving the problem of "difficulty in balancing accuracy and efficiency" in the prior art, and achieving a unity of high efficiency and high accuracy in multi-scale simulation.

The application discloses a high-resistant starch rice screening and identification and content detection method and system, and relates to the technical field of rice screening. The high-resistant starch rice screening and identification and content detection system comprises a rice screening and identification module and a rice content detection module. The application realizes non-destructive, high-throughput and high-precision comprehensive evaluation of the resistant starch of rice by constructing a multi-modal fusion screening system of starch metabolism fluctuation frequency analysis, three-dimensional seed twin modeling, virtual enzyme molecule diffusion simulation and bionic digestion dynamics school, can complete large-scale seed screening under the premise of not significantly increasing sample loss, and improves the ability to describe the dynamic behavior of starch metabolism by introducing frequency domain features and spatial topology analysis, so that the screening result not only reflects the static content difference, but also can represent the dynamic law of the formation process.

The application discloses a kind of hexagonal assembly pressurized water reactor core steady-state neutron diffusion calculation methods, using nonlinear iteration strategy to carry out steady-state neutron diffusion calculation: obtain effective multiplication factor and block average neutron flux density by global hexagonal block coarse mesh finite difference method (CMFD);By local block expansion method (NEM), the accurate neutron flow density of each surface is obtained, the block coupling correction factor is updated to correct the block average neutron flow density obtained by CMFD, to ensure the high-order accuracy of the calculation result;Wherein, local NEM uses the method of conformal mapping, hexagonal block is conformally mapped into rectangular block, and non-physical singular term caused by transverse integration is avoided;Transverse leakage term uses first-order step approximation, and the neutron flow slope is estimated by neutron flux density.The method of the application is suitable for hexagonal assembly pressurized water reactor core physical calculation, has higher calculation precision and calculation efficiency, and meets the engineering application demand of hexagonal assembly pressurized water reactor.

This invention discloses a smoothed finite element adjustable damping implicit integral algorithm for underwater transient acoustic scattering, belonging to the field of underwater transient acoustic scattering numerical simulation technology. First, the computational domain of the underwater transient acoustic scattering field is discretized into a standard quadrilateral element mesh to construct an interpolation scheme for the sound pressure field. Then, each quadrilateral element is divided into multiple smooth domains, and the smoothed sound pressure gradient matrix is ​​obtained through acoustic generalized gradient smoothing technology. Combining differential control equations, the virtual displacement principle, and the Galerkin weighted residual method, the system matrix equation is constructed. An adjustable damping implicit time integral algorithm is used to complete the time-domain discretization, and the numerical results of the transient acoustic scattering field in the entire time domain are obtained through recursive solution. This invention can soften the "overly stiff" stiffness matrix to reduce spatial discretization errors, suppress high-frequency errors through adjustable numerical damping matching, and achieve coordinated control of spatiotemporal errors. Under the same mesh, its accuracy is superior to the standard finite element method, providing an efficient and reliable solution for underwater transient acoustic scattering engineering simulation.

The application belongs to the technical field of three-dimensional electromagnetic radiation numerical solution, and relates to an electromagnetic radiation simulation analysis method based on local grid self-adaptive division. Firstly, the application carries out finite element modeling on a target antenna, introduces PML boundary and wave port excitation to establish a corresponding finite element calculation domain model, and adopts tetrahedral grid division to classify the calculation domain model; then finite element electromagnetic radiation simulation analysis is carried out to obtain finite element solution, and error estimation and encryption strategy are used to give the encryption size of the grid nodes in the non-PML region; finally, the grid is encrypted, finite element electromagnetic radiation simulation analysis is carried out again, and the process is repeated until the overall solution error is less than the set error limit, the final calculation grid is obtained, and finite element electromagnetic radiation simulation analysis is carried out. The application only encrypts the tetrahedral grid in the non-PML calculation domain, ensures the original characteristics of the tetrahedral grid in the PML calculation domain, and realizes the rapid simulation design of the antenna radiation characteristics while ensuring the calculation accuracy.

A steel shell-UHPC composite beam flexural capacity determination method considering the role of the partition, relates to the field of building design. The steel shell-UHPC composite beam flexural capacity determination method considering the role of the partition is to construct the steel shell-UHPC composite beam structure with partition after four-point loading bending test, determine the failure mechanism, failure characteristics and crack propagation law of the steel shell-UHPC composite beam structure with partition under the action of bending load, establish the cross-section stress diagram of the steel shell-UHPC composite beam structure with partition and calculate the ultimate bending moment. The steel shell-UHPC composite beam structure with partition is established to analyze its failure mechanism, failure characteristics and crack propagation law under the action of bending load, and based on the cross-section stress diagram of the steel shell-UHPC composite beam structure with partition, the ultimate bending moment calculation formula is established to calculate the ultimate bending moment, which can greatly simplify the calculation process while ensuring the calculation accuracy.

The invention provides a multi-time-scale-based multi-physics-field dynamic coupling calculation method for a medium-and-large-sized induction motor, electronic equipment and a storage medium, relates to multi-physics-field calculation coupling, and is suitable for solving simulation analysis of the medium-and-large-sized induction motor in an electromagnetic, thermal and fluid multi-field coupling state. According to the method, electromagnetic and fluid transient characteristics and temperature field hot spot distribution in different operation states are mainly considered, a field-domain coupling calculation method based on multiple time scales is provided, different physical fields adopt differentiated step length calculation strategies according to dynamic characteristics of the physical fields, the calculation precision is effectively improved, and the calculation efficiency is improved. And the waste of computing resources caused by multi-field synchronous solution is avoided. According to the method, millisecond-level accurate analysis can be carried out on an electromagnetic transient stage, long-time scale simulation can be completed by adopting a self-adaptive step length strategy aiming at a steady-state working condition, and multi-physical field dynamic characteristics of the motor under a complex working condition are reflected more accurately, so that performance optimization and structural design of medium and large induction motors are better guided.

This invention relates to a data-driven, multi-agent energy and carbon collaborative decision-making method for low-carbon industrial parks. It constructs a multi-agent dynamic Stackelberg game model, incorporating time-varying grid-side carbon intensity and the carbon offsetting benefits of green electricity into the multi-agent game decision-making process. Energy suppliers act as leaders, and users as followers, aiming to minimize the sum of economic energy consumption costs and carbon costs calculated based on dynamic carbon factors to solve for the optimal energy consumption strategy. A hybrid intelligent solution framework is used to solve the multi-agent dynamic game model. At the game strategy learning level, an improved multi-agent deep reinforcement learning algorithm is employed to approximate the game equilibrium. At the individual optimization level, an improved multi-objective particle swarm optimization algorithm is embedded within the follower agent to solve for the follower's optimal response under the current price strategy. Compared with existing technologies, this invention can coordinate the interests of multiple agents with dynamic carbon objectives, promoting source-load synergy and efficient renewable energy consumption.

The application discloses a substation equipment identification method and system based on an improved point pair feature matching algorithm, and comprises the following steps: obtaining original point cloud data of equipment in a substation, performing mean value processing on point clouds in a grid by using a grid downsampling method to obtain new point cloud data; wherein the size of the grid is automatically adjusted according to the number of the original point cloud data; performing key point screening on the new point cloud data, randomly selecting a reference point from the extracted key points, and respectively forming point pair features of the reference point and other points in the scene; matching the point pair features with pre-stored equipment model point pair features in a hash table to obtain matched point pair features, and identifying substation equipment based on the matched point pair features. By optimizing and screening the key points, the application reduces invalid points and redundant points, thereby improving the calculation speed and matching accuracy, and finally accelerating the substation equipment identification speed.

The application discloses a variable cycle engine double-loop closed-loop mode switching control method, which comprises the following steps: determining the tail nozzle network model parameters according to the dynamic thermodynamic mechanism analysis of a tail nozzle component, constructing a tail nozzle data-driven network model based on a BP neural network, and combining a component-level dynamic model of a main component in an upstream flow path to obtain a hybrid dynamic model of the variable cycle engine; according to the influence of an adjustable geometry component on performance parameters of the variable cycle engine, designing a double-loop closed-loop control scheme with variable speed and thrust feedback by taking thrust performance as an optimization target, and designing a mode switching control method of the model based on the hybrid dynamic model of the variable cycle engine. The tail nozzle model with a long time consumption in the variable cycle engine is simplified to reduce the time consumption of the whole machine dynamic model calculation, the double-loop closed-loop control scheme with variable speed and thrust and containing the mode switching process is proposed based on the model, and the stability of the variable cycle engine during mode switching can be effectively improved.

The application relates to a long and large suspended tunnel bidirectional fluid-structure coupling calculation method under a wave environment, and belongs to the field of marine engineering suspended tunnel structure design. In view of the problems of low calculation efficiency, neglect of structure disturbance to a flow field and incapability of processing complex topography of the existing method, a modeling strategy based on a two-dimensional potential flow wave tank group is provided: key sections are divided along a tunnel axis to establish independent water tanks, section wave loads are obtained by parallel solving of mathematical models of the water tanks, full pipe body load distribution is calculated by interpolation, and dynamic interaction of fluid motion and pipe body vibration is realized by bidirectional coupling iteration. The application efficiently processes kilometer-level suspended tunnel fluid-structure coupling calculation, significantly improves wave load precision, can simulate multidirectional waves and complex seabed topography, comprehensively outputs section forces and moments, is excellent in numerical stability, and provides a reliable analysis means for suspended tunnel engineering design.

The invention provides a novel method (3D-Sa) for calculating fractal dimensions of a three-dimensional surface, and belongs to the field of fractal geometry of mathematics. Firstly, fractal models of isotropic and anisotropic curved surfaces are established based on a W-M function; the three-dimensional morphology of the fractal curved surface under different fractal dimensions is simulated by utilizing MATLAB (Matrix Laboratory) software. The surface parameter of the fractal curved surface is calculated and analyzed to obtain the mapping relation between the fractal dimension and the traditional surface parameter. The invention provides a surface arithmetic mean height method (3D-Sa) capable of accurately calculating the fractal dimension of the machined surface. In combination with a surface arithmetic mean height formula and the definition of the fractal dimension, a calculation formula of the fractal dimension is deduced by taking the surface arithmetic mean height Sa as a main body. And then, optimizing the formula by using a simulation fitting mode to realize fitting parameter correction. The method has relatively low relative errors for anisotropic and isotropic curved surfaces, and the calculation precision is stable.

The invention relates to a driver service duration calculation method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring consumption progress time points corresponding to a plurality of data sources, wherein the plurality of data sources comprise a driver point location data source, an order information data source, a vehicle outgoing and receiving information data source and an order listening mode data source; taking the minimum value in the consumption progress time points as a target consumption progress time point, and determining a target calculation time window based on the target consumption progress time point; obtaining a driver identifier set in a service state in the target calculation time window; configuring each driver identifier in the driver identifier set to a plurality of calculation fragments, and obtaining multi-source event data of a driver corresponding to each calculation fragment in a target calculation time window; based on the multi-source event data, the total duration of each driver in the service state in the target calculation time window is determined, the service duration calculation result of each driver is obtained, and by adopting the method, the driver service duration calculation accuracy can be improved.

This invention proposes a method for obtaining the broadband RCS of electrically large targets based on a communication base station. The implementation steps are as follows: 1) dividing the surface of the electrically large target into sections; 2) defining RWG basis functions on the triangular facets; 3) initializing parameters; 4) calculating the Chebyshev frequency sampling points within the frequency band f based on CAT; 5) calculating the surface current at each Chebyshev frequency sampling point using the equivalent dipole moment method and the method of moments; 6) calculating the wavenumber k at each frequency point within the band. a Surface current; 7) Obtain the radar cross section (RCS) of electrically large targets. Based on the Chebyshev approximation method (CAT), this invention combines the equivalent dipole moment method to significantly reduce the calculation time of the impedance matrix and improve the calculation efficiency of the broadband radar cross section of electrically large targets.

The throttling fluid working condition parameter calculation method based on teacher-student architecture and law constraint neural network belongs to the field of computational fluid dynamics. First, the calculation coordinate system, input parameters and predicted output parameters are determined, and the input parameters and predicted output parameters are expressed as input vectors and predicted output vectors respectively, and a teacher network loss function is constructed in combination with the physical laws satisfied by the throttling fluid. Second, the teacher network is constructed based on the teacher network loss function and the teacher network is trained using the teacher network training data set to obtain the trained teacher network, and a student network loss function is constructed using the teacher network output and the real label vector as double benchmarks. Finally, the student network is constructed and trained using the student network training data set to obtain the student network for outputting the throttling fluid working condition parameters. The present application can realize the decoupling of physical law learning and parameter regularization, and give consideration to calculation accuracy, real-time performance, explainability and physical consistency.

The invention discloses a nuclear reactor neutron transport calculation method and device, and the method comprises the steps: carrying out the space merging of a fine network multi-group neutron transport model in each time of source iteration in a process of calculating the fine network multi-group neutron transport model through a source iteration mode, and obtaining a coarse network multi-group neutron transport model; correcting the first coarse mesh multi-group neutron standard flux through the coarse mesh multi-group correction factor to obtain a second coarse mesh multi-group neutron standard flux, and solving the coarse mesh multi-group neutron transport model to obtain a third coarse mesh multi-group neutron standard flux; performing iterative solution on the coarse mesh multi-group neutron transport model to obtain a target coarse mesh multi-group neutron standard flux so as to determine a fine mesh multi-group correction factor; and correcting the initial fine-net multi-group neutron standard flux through the fine-net multi-group correction factor to obtain a target fine-net multi-group neutron standard flux, and calculating the fine-net multi-group neutron transport model through the target fine-net multi-group neutron standard flux to improve the efficiency of nuclear reactor neutron transport calculation.

This invention proposes a temperature control method for aviation plunger pumps based on cycloidal gears to address the temperature rise problem caused by insufficient heat dissipation. This method integrates cycloidal gears within the pump to increase the return oil flow rate, carrying away the high-temperature oil in the housing cavity and reducing the overall temperature of the aviation plunger pump. The invention divides the pump into multiple nodes and establishes temperature analysis models and thermal network equations for the control volume nodes; it establishes a pump energy loss model and analyzes the temperature of each node of the aviation plunger pump under different return oil flow rates using thermal balance equations, thereby determining the design flow rate of the cycloidal gear; it establishes the structural equations of the cycloidal gear and uses theoretical formulas and simulation analysis to analyze the influence of the cycloidal gear structural parameters on its performance; and it determines the cycloidal gear structural parameters based on the pump's size constraints. This invention uses the plunger pump thermal network model established by the lumped parameter method to determine the return oil temperature of the plunger pump under different operating conditions and achieves return oil temperature control of the aviation plunger pump through cycloidal gears.