5859results about "Fluid speed measurement" patented technology

A method and apparatus for measuring optical turbulence using an unmanned aerial vehicle are provided. The unmanned aerial vehicle may include a central body, at least one motor operatively connected to the central body, a mounting element, a three-dimensional anemometer mounted on the mounting element, a first differential temperature sensor mounted on the mounting element, a second differential temperature sensor mounted to the mounting element, and a base mounted to the central body via a payload mounting interface including a first barometric pressure sensor, a central processing board, memory operatively connected to the central processing board, and a processor configured to generate refractive-index structure coefficient information.

The invention discloses a device for measuring flowability of explosive modeling powder, which comprises a step-press-loading analogue unit, a timing and weighing unit and a computer control unit, wherein the step-press-loading analogue unit directly and indirectly drives a screw rod which extends into a blanking bin to rotate and perform reciprocating movements along an axial line and drives a pusher dog in the blanking bin to perform the reciprocating movements along an arc section through the combined action of a cylinder and a pneumatic reversal valve so as to ensure that the explosive modeling powder in the blanking bin falls into the timing and weighing unit, and the process more truly imitates an explosive conveying process of an explosive step-press process. The timing and weighing unit transmits a weighing value of the explosive modeling powder which falls in the timing and weighing unit to the computer control unit in real time, and the computer control unit calculates the instantaneous flow speed of the explosive modeling powder of a north side and generates a flow speed-time curve according to sampling data. The device can measure the flowability of the explosive modeling powder so as to provide an objective basis for choosing a proper explosive step-press process for the explosive modeling powder.

The invention discloses a high-temperature airflow two-dimensional temperature field and velocity field synchronous measurement system and method based on laser-induced phosphorescence, and the system comprises phosphorescence particles, a low-frequency double-pulse laser, an image collection device, a synchronous controller, and an image processing device. The image processing device analyzes the gray intensity ratio of different wave band images acquired by the two PIV cameras at the same time, and combines a temperature response function calibrated by an experiment to realize inversion of a temperature field; meanwhile, a double-frame time-resolved image acquired by any PIV camera is subjected to cross-correlation calculation, particle displacement is extracted, and then a velocity field is reconstructed. According to the invention, synchronous acquisition of temperature and speed based on the same data source is realized, and the system has the remarkable advantages of simple structure, high measurement precision and wide application environment.

The invention provides a wind turbine generator array wake flow management method and system for Doppler laser wind measurement, and relates to the technical field of laser, and the method comprises the steps: collecting the real-time wind speed data, wind direction data and turbulence intensity data of each generator in the front and back direction through deploying a Doppler laser radar in a wind turbine generator array; establishing a wake flow influence model containing a wake flow influence coefficient, an attenuation coefficient and a diffusion coefficient based on the data, and calculating to obtain a wake flow influence range, loss power and a recovery distance; according to the method, the wind turbine generator array is cooperatively controlled, and the power generation efficiency of the wind turbine generator array is optimized by adjusting the yaw angle or the pitch angle of the upstream unit and the rotating speed of each unit. The wind speed data acquisition precision of the wind field is improved, the wake flow influence evaluation accuracy is enhanced, and the overall power generation efficiency of the wind field is remarkably improved.

The invention relates to the technical field of three-dimensional observation, in particular to a geological deformation three-dimensional observation system and method, and the method comprises the steps: multi-dimensional data collection: synchronously obtaining data, and collecting ground temperature gradient field data and underground water flow velocity field data of a monitoring region; data space-time calibration processing: performing space-time reference unification processing on the acquired data to generate a multi-source displacement data set after space-time calibration; cold door parameter extraction: generating an environment coupling parameter matrix based on ground temperature gradient field data and underground water flow velocity field data in multi-dimensional data acquisition; modeling a three-dimensional deformation field: generating an initial three-dimensional deformation field model; dynamic model correction: performing iterative correction on the initial three-dimensional deformation field model to generate an optimized three-dimensional deformation field model; and visual early warning output: generating an early warning signal with a risk level identifier. According to the method, a multi-source heterogeneous data fusion system is constructed, and a cold geological parameter dynamic compensation mechanism is combined, so that high-precision three-dimensional deformation field modeling and early warning are realized.

The invention provides a bridge structure monitoring method and device based on a microwave deformation radar, and relates to the technical field of bridge structure monitoring, and the method comprises the steps: obtaining the multi-point three-dimensional displacement data of a bridge structure through the microwave deformation radar, carrying out the thermal expansion pseudo displacement compensation and multi-point space smoothing through combining with temperature information, and obtaining a displacement field after environment correction; secondly, extracting a vertical component and separating the vertical component into a static deformation component and a dynamic vibration component by adopting variational mode decomposition; further analyzing and identifying a decoupling region through a time window coherence coefficient, performing recursive quantitative analysis, bispectrum analysis and energy distribution entropy calculation on a dynamic signal of the region, and constructing a high-order damage sensitive feature set; and finally, the dynamic characteristics and the static curvature change are fused to form a comprehensive degradation degree index, the deviation degree is judged according to working condition classification and the mahalanobis distance, and multi-dimensional and cross-working-condition degradation identification and risk early warning of the bridge structure are achieved.

The invention relates to the field of pressure sensors, in particular to a pressure sensor and a processing method, and a chip comprises a silicon substrate, a silicon dioxide dielectric layer, a device layer, a metal electrode and packaging glass. The device layer comprises a silicon carbide single crystal device layer and a silicon device layer; the silicon carbide single crystal device layer is arranged on the silicon device layer; the silicon device layer, the silicon dioxide dielectric layer and the silicon substrate are connected in sequence; the device layer is etched to form a sensitive resistor device layer, an annular sealing region and a micro-channel; the sensitive resistance device layer is isolated from the annular sealing area through the micro-channel; the device layer, the silicon dioxide dielectric layer and the silicon substrate are etched to form a cross beam etching area; the silicon substrate is etched to form a silicon pressure cavity and a beam film; the metal electrode is arranged on the top of the device layer; and the packaging glass anode is bonded at the top of the device layer or the bottom of the silicon substrate so as to solve the problems of low high temperature resistance and low sensitivity of the MEMS pressure sensor.

The invention discloses an indoor water tank sediment starting speed measurement system and method, and aims to solve the technical problem that data accuracy is affected due to the fact that a sensor disturbs a flow field in an existing measurement method. The core of the technical scheme is that the non-contact measurement characteristic of the PIV technology is applied to the whole process from flow field construction to data acquisition. The device is mainly composed of an imaging unit, a laser lighting unit, a movable sliding frame, a water flow adjusting unit and a buffer plate. Optical measurement is carried out through the imaging unit and the laser illumination unit, a physical sensor does not need to be arranged in a flow field, and interference of a measuring instrument on a water flow structure and a sediment starting process is fundamentally avoided. The movable sliding frame which is integrally designed integrates the functions of sediment laying, particle throwing and measuring, so that a test area can be quickly positioned; and the buffer plate and the water inlet and drainage adjusting unit are combined, so that a gradually-changed flow field from weak to strong can be accurately and stably simulated.

The invention belongs to the technical field of river surface flow velocity measurement, and discloses a method and system for predicting river surface flow velocity based on improved optical flow estimation. The RAFT optical flow estimation model established by the invention comprises a query frame residual error estimation module and an optical flow residual error estimation module. The model continuously corrects the deviation between a prediction result and a true value by introducing an IRE mechanism so as to improve the estimation accuracy of a query frame residual estimation module and an optical flow residual estimation module, the query frame residual estimation module is used for performing deep optimization on feature processing and correlation calculation, and the optical flow residual estimation module is used for performing optical flow estimation. The method comprises the following steps: generating query frame estimation through a differentiable internal optimization process, and performing feature convolution operation on the query frame estimation and a query frame image so as to explicitly consider similar areas possibly appearing in a scene. An optical flow residual error estimation module is introduced into a CBAM module, the weight of a feature map is adjusted in a self-adaptive mode, complex water surface information is better captured, and the accuracy of optical flow iteration is improved.

The invention discloses an integrated measurement method and system for hydrological elements in a high-salinity and high-sand environment, and relates to the technical field of hydrological monitoring, and the method comprises the steps: correcting the theoretical signal receiving strength of each sonar through an established sound attenuation model, and then calculating an effective signal-to-noise ratio, thereby achieving the measurement of the underwater topography in the high-salinity and high-sand environment. According to the method, a dynamic weight fusion algorithm is adopted to perform data fusion on the water depth data of each sonar to obtain fused water depth data, and an inversion method based on residual error minimization is adopted to perform iterative optimization on model parameters, so that the accuracy is relatively high. When the water velocity and the flow rate are measured in the high-salt and high-sand environment, iterative decoupling is carried out based on the sediment particle motion comprehensive model to obtain the sediment particle velocity, then the water velocity is updated based on the measured apparent velocity and the difference value, and after the updated water velocity is converged, the flow rate is calculated. And the accurate water flow rate can be calculated by combining the flow cross section area. The measurement precision of the unmanned ship on the hydrological elements in the saline-alkali area can be improved.

The invention discloses a liquid chromatogram flow velocity real-time detection and optimal control method based on multi-point sensing. The method comprises the following steps: S1, constructing a distributed acquisition network; s2, constructing a fluid transmission topological graph and generating a multi-point flow velocity time sequence; s3, inputting the fluid transmission topological graph and the multi-point flow velocity time sequence into a FlowFormer model to generate a flow velocity evolution prediction map; s4, executing local gradient scanning, and generating an optimization control objective function; s5, calling a self-adaptive fox swarm algorithm controller, inputting a flow velocity evolution prediction map and an optimization control objective function, and generating an optimal adjustment strategy; s6, the control parameters of the liquid chromatography system are adjusted in real time and fed back to the FlowFormer model; and S7, when abnormal flow velocity change is detected, triggering an adaptive fox swarm algorithm controller to execute a local escape strategy. According to the invention, multi-point sensing and an intelligent optimization algorithm are fused, and real-time detection and optimal control of the liquid chromatogram flow velocity are realized.

The invention discloses an MEMS device architecture, which comprises a cap layer, a device layer and a substrate layer, the cap layer is bonded with the device layer, the bonded whole is bonded with the substrate layer, the cap layer is manufactured based on a first silicon substrate, the bottom of the cap layer is provided with a cavity structure, and the cap layer is internally provided with a high-deep groove structure. A silicon dioxide film is arranged on the groove wall of the high-deep groove structure, polycrystalline silicon is deposited and filled in the high-deep groove structure, and a silicon dioxide layer is arranged on the upper surface of the first silicon substrate; the device layer is manufactured based on an SOI wafer and comprises a first silicon structure layer composed of top layer silicon, a buried oxide layer and a second silicon structure layer composed of back substrate silicon. The substrate layer comprises a second silicon substrate, a bottom layer cavity is formed in the top face of the second silicon substrate, and exhaust holes are formed in the bottom face of the second silicon substrate. According to the method, deep groove etching, polycrystalline silicon groove filling and bonding technologies are combined, advanced materials such as the SOI wafer and the polyimide layer are utilized, and excellent signal isolation and flexibility of various MEMS IMU applications are achieved.

The invention relates to the field of wind speed and wind direction prediction, and discloses a wind speed and wind direction prediction method based on an improved TCN-LSTM, and the method comprises the following steps: collecting real-time monitoring multi-dimensional meteorological data of an offshore wind station, and carrying out the preprocessing; performing feature fusion and feature enhancement processing on the preprocessed data, wherein the feature enhancement processing comprises spatial feature extraction, tensor reconstruction and time sequence modeling; inputting the data after feature fusion and feature enhancement processing into a wind speed and wind direction prediction model based on an improved TCN-LSTM hybrid neural network, and predicting the wind speed and wind direction at a future moment; the wind speed and direction prediction model comprises a time-space separation TCN network, a multi-head self-attention mechanism, an adaptive Dropblock mechanism, an LSTM network and a Bayesian optimization module; according to the method disclosed by the invention, the accuracy, robustness and calculation efficiency of wind power prediction in a complex marine environment can be improved.

The invention discloses a river water surface two-dimensional flow field reconstruction method based on effective tracer detection and tracking, and the method comprises the steps: carrying out the distortion correction of an original video image sequence, and setting an ROI region according to the water level detection river water surface range; the method comprises the following steps: collecting a multi-scene floating object data set, screening floating objects with high relative brightness and clear outlines in different scenes, and training a YOLO model to detect the floating objects on the surface of a river; using an OCSORT matching tracking method to track adjacent frames of targets to obtain a trajectory, and filtering according to the length, angle and variance of the trajectory to obtain a stable trajectory; according to the method, object information obtained through target detection is utilized, according to the area, the area change rate and the length-width ratio of a floating object on an image, the following performance and stability of the floating object are evaluated, a track fusion weight is calculated, and the influence of unreliable floating objects is reduced; and gridding the river surface area after orthographic correction, and for a grid with a plurality of tracks, calculating the average flow velocity of the grid according to the confidence coefficient of each track to obtain a gridding two-dimensional flow velocity vector field. The method can accurately identify the floating object which meets the requirements of visibility, following performance and stability on the river surface as an effective water flow tracer, and is suitable for measuring the flow velocity of the river surface in complex scenes such as night, storm, flare, shadow and the like.

The invention provides an intelligent water and soil conservation monitoring and management system, and belongs to the technical field of hydraulic engineering and environment monitoring. The data acquisition layer acquires data in real time by using an acoustic sensor network, machine vision monitoring equipment, Internet of Things monitoring equipment, satellite remote sensing monitoring, unmanned aerial vehicle inspection and other technologies. And the data transmission layer transmits the acquired data to the data processing and analyzing layer by adopting a wireless communication network. The data processing and analysis layer analyzes multi-source data through data fusion and preprocessing, GIS technology application and big data analysis and machine learning. And the decision support and application layer comprises a prevention and control measure generation and optimization unit, a real-time early warning and emergency response unit and a user interaction and decision support unit, provides a water and soil conservation and dike reinforcement strategy for a user, and has a feedback optimization mechanism. By comprehensively applying various monitoring technologies and data analysis methods, the accuracy and timeliness of water and soil loss monitoring are improved, and powerful guarantee is provided for dike safety.

The present invention belongs to the technical field of LiDARs, and particularly relates to a system and method for synchronous detection of atmospheric data in the same path. The detection system comprises a transmitting unit, a receiving unit and a data processing unit, wherein the transmitting unit comprises a plurality of laser devices, and is used for synchronously transmitting laser having different wavelengths in a common path; the receiving unit comprises a receiving telescope, which is symmetrically provided with a plurality of sub-apertures used for receiving echo signals that are generated after the laser having different wavelengths interacts with the atmosphere; and the data processing unit is used for calculating atmospheric data parameters by means of the echo signals. By means of the present invention, synchronous detection of a plurality of atmospheric data parameters in the same path can be implemented.

The invention relates to the technical field of wind power plant wake flow testing, and discloses a 3D scanning type laser radar planning method suitable for wind power plant wake flow testing, and the method comprises the steps: determining a wind power plant wake flow wind measurement region according to a wind measurement demand; determining a mainstream wind direction and a wind speed interval of the wind power plant wake flow wind measurement area based on the wind power plant wind resource data, and obtaining unit coordinates and unit parameters of wind turbine units in the wind power plant wake flow wind measurement area; according to the mainstream wind direction, the wind speed interval, the unit coordinates and the unit parameters, performing simulation calculation on the wake flow field of the wind turbine generator in the wake flow wind measurement area of the wind power plant to generate a wake flow area cloud picture; according to the method, the arrangement position of the 3D scanning type laser radar is determined based on the wake flow area cloud picture and the actual landform of the site, the situation that the arrangement position of the 3D scanning type laser radar is repeatedly adjusted for multiple times due to arrangement errors possibly occurring during arrangement according to experience can be avoided, and the wake flow testing efficiency is improved.

The invention discloses a low-altitude three-dimensional wind field inversion method and system based on a single wind measurement laser radar, relates to the technical field of radar detection, and solves the technical problems that a traditional wind measurement laser radar cannot directly obtain a velocity vector, data missing of a key area is caused by a blocking effect, and detection nodes are not uniform. The method specifically comprises the following steps: S1, executing a multi-elevation-angle body scanning detection mode and a wind profile detection mode by using a wind measurement laser radar, and obtaining radial wind speed data of a target area; s2, quality control is carried out on the radial wind speed, isolated abnormal points are eliminated, and isolated data missing points are filled; s3, carrying out blocking correction on a single scanning surface by using a smooth spline interpolation method; s4, after the radial wind speed is corrected based on the wind profile, an initial background three-dimensional wind field is obtained; and high-precision wind field inversion of a wind field in a three-dimensional space can be realized by using the radial wind speed of multi-layer body scanning of a single wind measurement laser radar.

The invention discloses a flow field measurement method based on an event camera, and the method comprises the steps: generating a PIV data set, each time sequence sample sequence comprising a plurality of frames of continuous particle images, a corresponding velocity vector field, and particle event data at all moments; establishing a flow field data acquisition device based on an event camera and a high-speed camera, acquiring real event data and real image data which are synchronous in time so as to adjust parameters of an event simulator, and verifying and updating particle event data in the PIV data set according to the adjusted event simulator so as to obtain a flow field data acquisition result; obtaining the updated PIV data set as a training data set; building an event camera optical flow method model, and training by adopting the training data set; and on the basis of the trained event camera optical flow method model, event sequences in two adjacent time periods are used as inputs to calculate a velocity vector field corresponding to a middle moment. According to the invention, the flow field velocity field at the required moment can be obtained based on the event data within a period of time.

The invention relates to the technical field of PIV (particle image velocimetry) flow field testing devices, in particular to an internal peeping type PIV testing device and method for an internal flow field of turbomachinery, and the device comprises the turbomachinery, a testing assembly and a connecting assembly. The testing assembly comprises a lighting mechanism, a camera shooting mechanism, a laser mounting pipe arranged on the air inlet pipe, a mounting base arranged on the laser mounting pipe and a camera shooting mounting mechanism arranged on the air inlet pipe, and the connecting assembly comprises an inserting mechanism arranged on the laser mounting pipe and a connecting mechanism arranged on the camera shooting mechanism. Through the arrangement of the mounting base and the camera mounting mechanism, a laser light source emitter and a camera are quickly mounted, the camera can adapt to various special-shaped shells such as volutes, the angle of a sheet light source emitted by the laser light source emitter is quickly adjusted through the arrangement of a rotating pipe, and the angle of the sheet light source is adjusted through the arrangement of a connecting mechanism and an inserting mechanism. And the sheet light source emitted by the laser light source emitter is quickly perpendicular to the shooting direction of the camera mechanism again.

The invention discloses a bridge pier stud crack automatic detection system based on a wall-climbing robot, and relates to the technical field of crack detection, and the system realizes closed-loop operation from accurate crack detection to intelligent repair through a crack detection module and a repair material intelligent spraying detection module. The crack detection module uses a multispectral imaging device, a thermal imaging camera and a laser scanning technology, can collect a multispectral difference value G (x, y), surface temperature distribution T (x, y) and a depth matrix D (x, y) of a crack area, extracts a crack boundary B (x, y) through a high-precision algorithm, and calculates a crack volume Vc. And the repairing material intelligent spraying detection module dynamically calculates the volume Vm of the repairing material according to the volume of the crack, and the SLAM technology is utilized to optimize the spraying path and parameters, so that uniform coverage and efficient utilization of the repairing material are ensured. The system greatly improves the precision of crack detection and repair, and avoids material waste and repair omission.

The present disclosure provides a method for measuring flow velocity of multilayer groundwater using distributed optical fiber with point-source active heating, comprising: setting and optimizing field test parameters; conducting a background temperature monitoring test; performing a point-source active heating distributed temperature measurement test, including conducting multiple rounds of heating tests; denoising the obtained multi-point source thermal plume attenuation signal data of the groundwater; searching for the peak value of temperature-permeability curve based on an automatic multi-scale peak search algorithm; performing secondary processing on the peak data; estimating the groundwater flow velocity. The method of the present disclosure solves the problem that the existing groundwater flow velocity measurement technology cannot simultaneously measure multiple points and multiple layers, and it can avoid groundwater contamination during the measurement process.

The invention relates to a saline intrusion measurement method, system and equipment based on dynamic ship motion conditions and a medium, and aims to solve the technical problem that the salinity inversion precision is reduced due to spatial-temporal dislocation between particle image velocity measurement flow field data and plane laser-induced fluorescence concentration field data caused by ship six-degree-of-freedom motion. According to the method, future poses are predicted by collecting ship motion parameters and environment disturbance parameters, and space-time compensation parameters are generated in combination with a static calibration matrix; performing three-dimensional coordinate transformation and time synchronization on synchronously acquired original flow field and concentration field data by applying compensation parameters, and eliminating space-time deviation caused by ship movement; a three-dimensional salinity distribution field is calculated based on registration data fusion flow field diffusion characteristics and concentration field distribution; and meanwhile, the pose of the measuring equipment is dynamically adjusted through the closed-loop controller so as to optimize the data acquisition quality. According to the method, ship motion interference is effectively inhibited, and accurate characterization of saline invasion frontal surface spatial characteristics is guaranteed.

The invention discloses an MEMS thermal flow sensor based on a glass film structure and a preparation method of the MEMS thermal flow sensor. The sensor comprises a glass inner silicon substrate, a back cavity, a silicon through column, a heating resistor, a temperature measurement resistor, an environment temperature measurement resistor, a chromium adhesion layer, a PAD port and a silicon nitride protection layer. Wherein the heating resistor is located in the center, and the temperature measuring resistors are symmetrically distributed on two sides of the heating resistor; the back cavity is located on the back of the glass inner silicon substrate, and the heating resistor, the temperature measuring resistor and the environment temperature measuring resistor lead a PAD port to the back of the glass inner silicon substrate through a silicon through column. A thermal temperature difference principle is adopted, and upstream and downstream temperature measuring resistors form a Wheatstone bridge. When the flow velocity is not zero, the Wheatstone bridge outputs, and the larger the flow velocity is, the larger the output is. Based on the glass and silicon composite substrate, the suspension film structure is formed through the silicon etching process, transmission of heat to the substrate is greatly reduced, and the heat utilization rate is increased.

The invention relates to the technical field of wind turbine generators, particularly provides an aeroelasticity analysis method, system and equipment of a fan blade and a medium, and aims to solve the aeroelasticity analysis problem of a flexible fan blade. Therefore, the aeroelasticity analysis method for the fan blade comprises the following steps: acquiring blade parameters and wind speed data of a to-be-analyzed blade; determining the aerodynamic load of the to-be-analyzed blade based on an aerodynamic model, the blade parameters and the wind speed data; based on the blade parameters and the aerodynamic load of the to-be-analyzed blade, determining the structural response of the to-be-analyzed blade; and carrying out aeroelasticity analysis on the to-be-analyzed blade based on the aerodynamic load and the structural response of the to-be-analyzed blade. The method is suitable for aeroelasticity analysis of the flexible blade of the wind turbine generator, and provides reliable reference for aeroelasticity stability evaluation of the flexible blade of the wind turbine generator.

The invention provides a desert photovoltaic sand damage dynamic monitoring method and system based on an unmanned aerial vehicle, and the method comprises the steps: obtaining the flying dust data of a photovoltaic power station region, generating an initial data set, and enabling the flying dust data to be collected through a multi-mode sensor carried by the unmanned aerial vehicle; performing multi-modal data fusion processing on the initial data set to obtain a dust feature matrix, the dust feature matrix being used for representing dust reflectivity, terrain elevation and wind speed correlation features; calculating migration probability distribution of the flying dust particles based on the sand and dust characteristic matrix, wherein the migration probability distribution is used for representing spatio-temporal evolution laws of the particles with different particle sizes; a three-dimensional dynamic sand and dust concentration field model is generated according to the migration probability distribution, a sand damage dynamic monitoring result is output based on the three-dimensional dynamic sand and dust concentration field model, and the sand damage dynamic monitoring result comprises deposition density distribution and an erosion risk area. By adopting the method, the photovoltaic sand damage of the desert can be accurately and dynamically monitored with high timeliness.

The invention relates to the technical field of gate groove measurement, in particular to a dam gate groove vertical plane measurement system and method based on an intelligent sensor, and the method comprises the steps: collecting a vertical plane image, vertical plane overflowing velocity data, vertical plane water level data, vertical plane height data and vertical plane sealing pressure data of a gate groove; extracting corrosion pit data in the vertical plane image and evaluating the flatness of the vertical plane based on the corrosion pit data; evaluating the vertical plane wetting-drying alternation influence degree based on the vertical plane water level data, and obtaining the vertical plane erosion degree by combining the vertical plane flatness; and integrating the vertical surface erosion degree and the vertical surface sealing pressure data to pre-estimate the gate leakproofness, and performing gate leakproofness early warning according to a gate leakproofness pre-estimation result. According to the method, the scientificity and the accuracy of gate leakproofness evaluation are improved by quantifying the vertical plane flatness of the gate groove of the gate and the influence of the vertical plane dry-wet alternation period on the vertical plane erosion degree.

The invention provides an urban road ponding monitoring and drainage system. The urban road ponding monitoring and drainage system comprises a monitoring module which collects ponding depth, water velocity, rainfall intensity and field image data in real time; the initialization configuration module sets parameters such as an accumulated water depth threshold value; the data transmission module encrypts and transmits data to the central control module; the model algorithm optimization module constructs a three-dimensional ponding diffusion model and outputs a predicted ponding depth and an optimized drainage strategy; the central control module generates a drainage pump rotating speed instruction and the like; the drainage execution module dynamically adjusts drainage pump power and a drainage path; the self-checking and fault-tolerant module calculates a health index of drainage equipment and switches redundant equipment; the early warning module sends risk level information; and the interaction module displays information such as a real-time accumulated water thermodynamic diagram. The urban road drainage efficiency can be improved, the water accumulation risk is reduced, and smooth urban traffic and public travel safety are guaranteed.

The invention discloses a wind speed forecasting system based on deep learning, and belongs to the technical field of weather forecasting. The system comprises a coupled mode framework which integrates a triple nested architecture of an atmospheric mode WRF, an ocean mode ROMS and a sea wave mode SWAN, and transmits variables through a model coupling tool MCT; the deep learning roughness parameterization module is integrated in an MYNN boundary layer scheme of the atmospheric mode WRF and calculates the sea surface roughness in real time; the full-wave spectrum integration module is embedded into the ocean mode ROMS, receives wave spectrum data provided by the ocean mode SWAN and calculates a Stokes drift profile; and the intelligent correction module is used for carrying out spatial interpolation on the wind speed data output by the mode, correcting errors by combining a LightGBM model, and outputting a final forecast product. According to the method, the deep neural network is embedded into the WRF boundary layer model kernel, the sea surface roughness parameter is updated in real time, the wave evolution process is dynamically responded, and the space-time adaptive capacity of wind field forecasting under the complex sea condition is remarkably improved.

The invention belongs to the technical field of ocean remote sensing, and relates to a spaceborne microwave radiometer tropical cyclone wind speed inversion method based on physical constraint deep learning, comprising the following steps: acquiring tropical cyclone parameter information; extracting multi-band brightness temperature data of the satellite-borne microwave radiometer in a corresponding space-time range, and constructing a sample data set; a deep learning inversion algorithm model with physical constraints is loaded and trained; the physical constraint deep learning inversion algorithm model comprises an input layer, a network layer, a physical layer and an output layer; the network layer is composed of a residual neural network, the physical layer is composed of a D matrix remote sensing statistical formula and provides physical constraints for the whole model, and the D matrix is a nonlinear D matrix; and outputting the tropical cyclone wind speed in the current space-time range. According to the method, the brightness temperature information of the satellite-borne microwave radiometer is obtained by utilizing the tropical cyclone trajectory information, and the network model with physical information is constructed by utilizing the combination of the D matrix equation and the neural network, so that more accurate and high-precision tropical cyclone wind speed information is obtained.