21results about How to "Shorten calculation time" patented technology

The invention discloses a wind power plant yaw control optimization method based on a sequential optimization algorithm, and the method comprises the steps: obtaining the coordinates of all fans at a current inflow wind direction angle, queuing all fans after the coordinates are converted in sequence, and calculating the yaw angle range of each cycle according to the actual demands; (n-1) times of outer layer circulation are set for the first (n-1) fans in the preliminary optimization process, in each outer layer circulation, yaw angle traversal value taking circulation is conducted on a certain fan according to the obtained yaw range and the uniform step length, and then the optimal yaw combination and the corresponding power of the wind power plant are obtained; and then optimization is carried out to obtain the optimal yaw angle of each fan in the whole field. According to the method, the wake flow secondary deflection effect in the wind power plant and the influence effect of the inflow turbulence intensity on the wake flow are considered, the improved Gaussian wake flow model is adopted to comprehensively consider calculation of wake flow loss in the three-dimensional direction, the calculation result is more accurate, and the final control optimization effect can also conform to the actual engineering situation.

A method for dose calculation in a boron neutron capture therapy planning system based on a track tracking Monte Carlo method comprises the following steps: sampling according to input description source item particles, carrying out transport calculation by using the track tracking Monte Carlo method under voxel grid geometry, calculating a transport distance while calculating the transport distance, and calculating the dose in the boron neutron capture therapy planning system by using the track tracking Monte Carlo method. Counting based on the voxel grid to obtain particle flux and dose; by adopting the operation of track tracking method acceleration based on voxel grid geometry, the surface crossing judgment method is improved, and the problem that the surface crossing operation takes too long time in the calculation process is solved; counting is carried out while the transportation distance is calculated, the counting time is saved on the premise that the counting precision is guaranteed, and compared with a traditional Monte Carlo method based on CSG geometry, the method is more suitable for a voxel model obtained from a medical image, and the calculation speed is higher.

The invention discloses a polyurethane high-pressure foaming process parameter optimization method and system, and the method comprises the steps: building a polyurethane high-pressure foaming process model through Aspen Plus software, and calibrating the polyurethane high-pressure foaming process model through actual operation data; simulation operation data are obtained through the calibrated polyurethane high-pressure foaming process model; optimizing variables and constraint conditions are set, the total public engineering consumption minQ of the whole process is used as a target function, a BP neural network model is constructed, and a data set is constructed by using actual operation data and simulated operation data to train the BP neural network model; introducing the trained BP neural network model into a queue competition algorithm LCA to form a BP-LCA hybrid algorithm; and optimizing the parameters of the polyurethane high-pressure foaming process by using a BP-LCA hybrid algorithm. The method has the advantages of being high in optimization result search speed and good in optimization effect.

The invention relates to an operation debugging method and device of a pump set system, and belongs to the field of pressure supply medium equipment. Calculating the pipeline impedance coefficient of the pipeline between the nodes under the rated flow; respectively determining a valve impedance coefficient and an equipment impedance coefficient; establishing a pump set performance equation according to the pump set performance curve; establishing a flow distribution mathematical model according to the principle that flow conservation and parallel branch pressure drop are the same; calculating the flow distribution coefficient of each pipeline according to the pipeline impedance coefficient, the valve impedance coefficient and the equipment impedance coefficient, and establishing a system main pipeline characteristic equation; the main pipeline characteristic equation and the pump set performance equation are combined, and a pump set operation condition point is calculated; calculating the pressure of each node according to the operating condition point of the pump set and the flow coefficient of each pipeline; and the valve opening is calculated according to the pressure and flow requirements of all the nodes, and debugging is conducted by controlling the valve opening. The method can effectively reduce the calculation duration and the calculation amount.

The invention relates to the technical field of heat storage and energy conservation, and provides a moving bed high-temperature particle flow and heat transfer characteristic simulation and prediction method and system based on deep learning and electronic equipment. The method comprises the steps that high-temperature particle flow characteristic numerical simulation is conducted, and a three-dimensional moving bed high-temperature particle flow numerical model is established; simulating association of a bed structure, particle properties and particle accumulation and flow pattern rules, and establishing a particle distribution regulation and control strategy; performing numerical simulation on heat transfer characteristics of high-temperature particles, establishing association between particle flow characteristics and a temperature field, simulating a gas-solid two-phase composite heat transfer process of the particles, and establishing a temperature field control strategy; intelligent prediction of particle distribution and a temperature field is carried out, intelligent prediction of particle distribution and the temperature field at a specific moment is realized based on deep learning, and a regulation strategy based on numerical simulation is optimized. The particle flow and heat exchange characteristics of the moving bed are clarified, a theoretical support and a technical solution are provided for improving the waste heat recovery efficiency of the blast furnace slag, and the energy utilization rate can be increased.

The invention relates to a battery liquid cooling temperature prediction method based on a thermal resistance network, and the method comprises the following steps: analyzing the heat dissipation condition of a geometric model, and mastering the overall heat flow direction; node division is carried out on the whole model, and preparation is made for constructing a thermal resistance network; thermal resistance value calculation, wherein a thermal resistance network is divided into battery heat conduction thermal resistance, liquid cooling plate heat conduction thermal resistance, cooling liquid convection thermal resistance and enthalpy change thermal resistance; combing the series-parallel connection relation of the thermal resistance between the network units to form a complete thermal resistance network model; the transient temperature of all nodes can be calculated through a calculation formula by calculating the thermal resistance value between the nodes. According to the method, the temperature distribution of the battery under the liquid cooling effect is rapidly and accurately predicted, a reliable basis is provided for real-time temperature monitoring, the problem that the thermal resistance calculation of the liquid cooling plate is complex is solved, and meanwhile the technical problem that the complex calculation problem caused by follow-up structure and parameter optimization can be rapidly solved through the universality of the method is needed to be solved at present. Compared with the prior art, the device has good market prospect and development space.

The invention belongs to the technical field of natural gas peak regulation, particularly relates to a natural gas peak regulation method and system based on spatio-temporal information, and aims to solve the problem that a large-range and more comprehensive natural gas peak regulation mode is lacked in the prior art. The method comprises the following steps: acquiring a second index thermodynamic diagram and inputting the second index thermodynamic diagram into a first neural network model to obtain the natural gas consumption of a target area in a first statistical period as a first demand quantity; before the first statistical period starts, natural gas of the first demand quantity is conveyed to a central peak regulation system of the target area; obtaining a fourth index thermodynamic diagram, inputting the fourth index thermodynamic diagram into the second neural network model, and predicting the natural gas consumption of each sub-region of the target region in the first statistical period as a second demand; and before the first statistical period starts, the natural gas of each second demand quantity is conveyed to the corresponding secondary peak regulation system. According to the method, large-range and more comprehensive natural gas peak regulation is realized through a grading direct prediction mode.

The invention relates to a deep learning model training method, device, equipment and medium, a deep learning model to be trained comprises a third-level model, a first-level model and a second-level model, the third-level model and the first-level model are connected in series, and the first-level model and the second-level model are connected in series. The deep learning model training method comprises the steps of obtaining a first sample data set, a second sample data set and a third sample data set; inputting the first sample data set into the three-level model to obtain a first result; obtaining a fourth sample data set based on the first result, and inputting the fourth sample data set into the primary model to obtain a second result; and obtaining a fifth sample data set according to the first result, the second result, the second sample data set and the third sample data set, and training the secondary model based on the fifth sample data set to obtain a trained deep learning model, thereby improving the calculation efficiency of the obtained trained deep learning model and reducing the calculation duration.

The invention discloses an equivalent mechanical performance analysis method of a dual-phase TPMS lattice structure and application of the equivalent mechanical performance analysis method, and belongs to the technical field of material structures. Two materials in the two-phase TPMS lattice structure are equivalent to one material through an equivalent theory method, a shell unit can be used for establishing a model for calculation when a single material is used for simulation, and only one layer of unit is arranged on the thickness of the curved surface wall of the shell model, so that the number of model units is greatly reduced, and the cost is reduced. The coupling effect between the two materials does not need to be considered, so that the calculation efficiency can be improved by performing simulation calculation, and the effectiveness of the simulation calculation is verified; according to the method, the equivalent calculation method of the composite material plate is creatively applied to the curved surface of the structure, the calculation speed and efficiency are greatly improved on the premise that the calculation and analysis accuracy is guaranteed, compared with a common analysis and calculation method using entity units for modeling, the calculation duration is shortened by 95.32%, and the method has important application prospects.

The invention belongs to the field of motors, and discloses a method, system or device for calculating the copper loss of motor windings, comprising the following steps: converting any stator slot type of the motor into rectangular slots of equal area; redistributing the windings so that, except for the stator slots of the top layer, the number of windings placed in the stator slots of the remaining layers is equal, and the remaining windings are placed in the stator slots of the top layer; obtaining the active power of each layer of stator slots after the windings are redistributed; substituting skin effect factors and proximity effect factors into the active power to form an analytical model for the copper loss of the stator slot windings of each layer, superimposing the analytical models of the copper loss of the stator slot windings of each layer to obtain a total loss model of the motor windings, thereby obtaining the copper loss of the entire motor windings; without the need for precise modeling, quickly and accurately predicting the winding copper loss, thereby improving the accuracy of predicting motor efficiency.

The present application relates to the technical field of three-dimensional reconstruction, and in particular to an object three-dimensional reconstruction system based on deep learning, which introduces an adaptive cost aggregation method with visibility perception for cost volume aggregation, acquires the visibility of pixel points in the view through a network, and can improve the reconstruction integrity of the occluded area; a variance-based method is used to predict the disparity range of each pixel, and a spatially-varying depth hypothesis surface is constructed for depth estimation in the next stage, and a residual and channel attention guided fusion depth map optimization module is proposed in the last stage to obtain an optimized depth map; an improved depth map fusion algorithm is used to combine the pixel point and 3D point re-projection error for consistency checking to obtain a dense point cloud. Quantitative and qualitative comparison results of the present application and other methods on the DTU dataset show that the present application can reconstruct a scene with better details, and achieves the purposes of reducing GPU memory consumption and computation time.

The present application relates to the technical field of image recognition, and discloses a detection method, device and equipment for distracted driving behavior and a storage medium, which are used to improve the recognition accuracy of distracted driving behavior. The detection method for distracted driving behavior comprises the following steps: obtaining initial driving video data of a driver, performing data processing on the initial driving video data, and obtaining to-be-recognized behavior video data; calling a preset distracted driving behavior model to recognize the to-be-recognized behavior video data; if the driver has candidate distracted driving behavior, performing special behavior detection on the driver and vehicle driving condition detection on a target vehicle in which the driver is located; and if the driver has no special behavior and the target vehicle is in a normal vehicle driving condition, it is determined that the driver has target distracted driving behavior.

The application provides a kind of three-dimensional fracture whole process simulation method of multiphase medium material mesostructure based on space-time sequence prediction, comprising the following steps: S1, sample data acquisition;S2, deep learning model network building and training;S3, model verification: the historical surface crack information of composite material is input into the trained generation network, and the subsequent fracture damage process of composite material can be obtained, the morphology between fracture surfaces is quantified and compared by using Wasserstein distance, and the performance of the model is judged.The application can predict the fracture surface inside the entity according to the historical apparent crack of the composite material without the component distribution information of the composite material;The network model is trained completely from the perspective of observation data, and theoretically, the prediction result can be almost consistent with the observed result in the experiment;The calculation efficiency is high, and the calculation time can be shortened from weeks to seconds;Pixel-level modeling can be realized;The fracture process inside the material can be predicted according to the apparent crack of the material.

The invention belongs to the related technical field of electromagnetic simulation, and discloses a simulation method and system for a target millimeter wave radiation image under an antenna housing, and the simulation method comprises the steps: constructing a lookup table which comprises scattering data packets of the selected antenna housing at different incident angles; simulating a virtual ray according to the reverse direction of the received ray by taking the radiometer as a tracking starting point; calculating an intersection point of the virtual ray and the antenna housing, calculating an incident angle of the virtual ray at the intersection point according to the intersection point, and calculating a virtual ray reflected by the virtual ray after the virtual ray enters the intersection point and a virtual ray transmitted by the virtual ray based on the lookup table; continuously tracking the rays until the rays reach a preset upper limit of scattering times, and ending tracking; and obtaining reflection coefficients and transmission coefficients of different virtual rays based on the lookup table, and calculating brightness temperatures of all the virtual rays to obtain a millimeter wave radiation simulation image of the target. Through the method, the simulation precision and the simulation efficiency can be improved.

The invention provides a replenishment configuration method and device, electronic equipment, a storage medium and a computer program product, and relates to the technical field of supply chains. The method comprises the following steps: according to an execution sequence of a plurality of workflow definitions in a preset workflow arrangement, sequentially reading configuration data corresponding to each workflow definition based on a spark calculation engine for processing, and determining replenishment information corresponding to the preset workflow arrangement; wherein the execution of each workflow definition needs a processing result corresponding to the previous workflow definition. Through the scheme in the embodiment of the invention, the efficiency of replenishment calculation can be improved.

The invention discloses a parallel computing method for flood forecasting of an ultra-large river network, which comprises the following steps of: dividing sub-region boundaries in a research region according to gradient abrupt change points of a reference terrain and confluence points of tributaries, and ensuring that complete water flow confluence ports exist in the sub-regions; constructing a hydrodynamic continuous equation and a hydrodynamic momentum equation of each sub-region, discretizing the hydrodynamic continuous equation and the hydrodynamic momentum equation, and calculating the water depth h and the flow velocity u of each space node in the sub-region; building a parallel computing framework, and inputting the discretized hydrodynamic continuous equation and hydrodynamic momentum equation into each computing node of the parallel computing framework; after each calculation node calculates the water depth and the flow velocity of the space node, the water depth and the flow velocity are accumulated, and flood forecast data of the river channel main stream in the research area are calculated. According to the method, the ultra-large river network is divided into a plurality of sub-regions and parallel calculation is carried out, so that the calculation duration of flood forecasting is greatly shortened, the urgent demand of real-time flood forecasting is effectively met, and more precious time is won for flood control and disaster reduction decisions.

The specification discloses a navigation structure generation method and device, a storage medium and an electronic device, wherein the method comprises: obtaining three-dimensional modeling data corresponding to each building in a target geographical area, and a regional image corresponding to the target geographical area; determining a building road network of at least one floor in each building based on the three-dimensional modeling data; generating a road network structure of the target geographical area based on an outdoor road network in the regional image and the building road network; the outdoor road network is other road network in the regional image except the building road network; mapping the road network structure into a planar graph data structure; obtaining a structure parameter corresponding to the graph data structure; and using the specification, the three-dimensional data of the target geographical area is converted into planar data, and the structure parameter of the graph data structure corresponding to the target geographical area is calculated according to the planar data, so as to improve the accuracy and efficiency of the navigation path.

The application provides a privacy-protected longitudinal federated boosting tree method and relates to the technical field of longitudinal federated learning; the method comprises the following steps: combining secret sharing binary matrix and gradient information to obtain a shared matrix and secret sharing; each training terminal performs row permutation on the shared matrix based on a permutation triple and secret shares the permutation result; linear gain scores of candidate splits are calculated and secret shared, and an indication vector corresponding to the maximum linear gain score is calculated; according to the number of candidate splits, corresponding columns are selected from the matrix, and the indication vector is used to calculate the sample and the permutation matrix of the child node; the splitting step is recursively executed to complete the splitting from the root node to the leaf node, the weight of the leaf node is calculated and stored in a preset set. The binary permutation matrix of the root node of the next decision model is updated based on the weight of the leaf node, and the calculation is continued until all decision tree models are generated; the method can solve the problem of low efficiency of the existing longitudinal federated gradient boosting tree protocol.

The invention discloses a method for obtaining a theoretical spectrum and a method for measuring morphological parameters, which are used to improve the calculation efficiency of the theoretical spectrum and the measurement efficiency of the morphological parameters. The method for obtaining a theoretical spectrum includes: obtaining a morphological model of a sample to be measured, dividing the morphological model into M blocks, obtaining the initial morphological parameters of each block, floating the initial morphological parameters to obtain multiple groups of reference morphological parameters; determining the initial configuration and multiple reference configurations of each block, and the scattering characteristic matrix group of each block includes scattering characteristic matrices corresponding to the initial configuration and multiple reference configurations; from the bottom to the top of the morphological model, any scattering matrix selected from the scattering characteristic matrix group of each block is merged step by step to obtain the scattering characteristic matrix of the incident area of ​​the morphological model; obtaining multiple scattering characteristic matrices of the incident area; obtaining multiple reflected electric fields of the incident area, and obtaining multiple theoretical spectra of the sample to be measured based on the multiple reflected electric fields.

The present invention provides a method for quickly predicting the explosion shock wave load in a ship cabin taking into account the shielding of bulkheads. The method includes the following steps: step S1, discretization of the three-dimensional ship cabin structure model and equivalent charge conversion; step S2, division of the calculation step length; step S3, calculation of the pressure and damage state of each bulkhead; step S4, elimination of the bulkheads that are actually not damaged; step S5, calculation of the pressure load reduction of the damaged bulkhead; the present invention calculates the bulkhead load and damage state by solving the step length, which can greatly improve the calculation efficiency and reduce the calculation time for large-sized ship targets. The present invention constructs the explosion point and the geometric center ray of the bulkhead, and judges whether there is an undamaged wall shielding before the damaged bulkhead based on the cyclic scanning method, thereby eliminating the bulkheads that will not actually be damaged, making the calculation results more realistic.

The invention relates to the field of vacuum system design and calculation, and particularly discloses a vacuum system topology analysis and evacuation time calculation method based on a dual-accounting method, which comprises a main core algorithm, establishment of a directed graph based on connection points of vacuum components, discovery of all physical flow paths from a source point to a sink point by adopting depth-first search, and calculation of the vacuum system topology analysis and evacuation time. The three types of structure fragments are introduced into a virtual component for recursive simplification to obtain equivalent conductance; according to the auxiliary core algorithm, key contacts are recognized, the inflow and outflow relation of the key contacts is judged, serial-parallel equivalent result write-back is locally completed, rapid estimation of the global equivalent through-current capacity is given, and the main core algorithm is verified; and the calculation efficiency of the vacuum system is improved by adopting three-stage pre-calculation. According to the method, non-uniqueness and misrecognition caused by manual splitting are reduced through a dual-core cooperation mechanism combining a main core algorithm and an auxiliary core algorithm, and the series-parallel misjudgment rate of a complex network is reduced.