20results about How to "Precise inversion" patented technology

This invention relates to a multi-temporal radiation signal inversion method based on Conditional Transformer, belonging to the field of satellite remote sensing data processing / spatial information science and technology. The method includes: acquiring meteorological time-series data of the target area to establish a dataset; designing a Conditional Transformer deep learning network; combining the target time-series data and meteorological data encoded by time and meteorological code generators with the output of the Encoder layer, and inputting this combination into the Decoder layer to train the Conditional Transformer deep learning network to obtain a surface radiation signal inversion model; inverting surface radiation brightness temperature data and evaluating the inversion accuracy; efficiently capturing long-distance spatiotemporal dependencies of radiation signals; flexibly inverting radiation changes according to the target time and meteorological conditions; removing nonlinear interference from the atmosphere on radiation; and more accurately inverting the true radiation characteristics of the surface.

The present application relates to the technical field of complex radiation field inversion, and particularly relates to a complex radiation field inversion system and method based on a multi-layer source grid, wherein a multi-layer source grid division subsystem is used to perform multi-layer discrete approximation on a complex source term with a known position and shape to be inverted, a detector partition arrangement subsystem is used to set detectors for a radioactive source, all coarse grid volume sources and all fine grid volume sources respectively in different manners for detection, a source term inversion subsystem is used to perform inversion on source intensity distribution of the complex source term according to the radioactive source, all coarse grid volume sources, all fine grid volume sources and first, second and third measurement values, and a radiation field calculation subsystem is used to calculate the radiation field distribution of the inverted complex source term. The technical problem that the complex source cannot be inverted in the traditional inversion is overcome, and the radiation field under the complex source distribution can be quickly and accurately inverted.

The application relates to the technical field of quasi-brittle material mechanical property testing and constitutive inversion, in particular to an inversion analysis method of a quasi-brittle material tensile softening constitutive under monotonic loading, which comprises the following steps: collecting unilateral notched beam specimen size parameters and monotonic loading three-point bending test data; establishing a two-dimensional numerical model comprising an undamaged area and a cohesive crack area; constructing a segmented linear tensile softening constitutive subroutine comprising an elastic stage and a softening stage; integrating the two-dimensional numerical model and the subroutine, iteratively inverting constitutive parameters through an optimization algorithm, and outputting a final segmented linear tensile softening constitutive after the simulation data and the test data reach a preset fitting degree. The method can improve the constitutive inversion accuracy, adapt to the nonlinear fracture characteristics of quasi-brittle materials, and provide reliable support for material performance evaluation.

This invention discloses a method and system for inverting active power and wind speed in wind farms. The method includes: dividing historical active power and center-point wind speed time-series data into multiple continuous sub-series segments, aggregating them using a Transformer encoder to obtain a correlation feature vector of nonlinear coupling between active power and wind speed; concatenating the correlation feature vector with the current active power, mapping it using a linear regression head, and applying physical constraints using the wind farm's equivalent power curve to obtain a center-point wind speed inversion sequence; concatenating the center-point wind speed inversion sequence with static spatial features, feeding it into a selective state-space model based on the Mamba architecture, and outputting a time-varying correlation feature vector at the turbine location level; finally, designing a linear regression head mapping for each turbine location to obtain a regional wind speed inversion time series, and applying physical constraints using a single-turbine power curve to form a wind speed inversion link from the center point to the region. This achieves accurate inversion of wind speed at the wind farm's center point and in the region, improving the precision and reliability of wind speed sensing.

This invention discloses a system and method for intelligent detection of deep rock properties and geological formation inversion, relating to the field of mine safety assessment technology. The system includes a terahertz incoherent detection module, a multi-dimensional external field control module, a signal acquisition and control module, and an intelligent inversion and disaster prediction module. The terahertz incoherent detection module includes a terahertz incoherent wave source, a wavefront optimization unit, and a sample coupling unit. The multi-dimensional external field control module includes a magnetic field control unit and a light field control unit. The signal acquisition and control module includes an intrinsically safe synchronous controller, a high-precision current detector, and a signal preprocessing unit. The intelligent inversion and disaster prediction module includes a feature extraction unit, a correlation model library, and a disaster prediction output unit. This invention achieves high-precision, rapid in-situ detection of rock properties and geological formation conditions, as well as accurate early warning of disaster risks, effectively supporting the safe and efficient mining of deep resources.

The invention relates to an optical parameter detection device and method, in particular to an optical system wavefront detection device and method based on phase modulation. In order to solve the problems in the prior art that a multi-frame acquisition strategy adopted by a phase recovery method based on a point spread function is difficult to adapt to a dynamic test scene, a single-frame acquisition strategy is difficult to stably invert wavefront with conjugate symmetry, and iterative inversion operation time is relatively long and may fall into a local optimal solution, the invention provides a phase recovery method based on a point spread function. The invention discloses an optical system wavefront detection device based on phase modulation. The optical system wavefront detection device comprises a module, a first imaging lens, a first plane mirror, a beam splitter, a microscope objective, a second plane mirror, a partition phase plate, a second imaging lens and a photoelectric detector, and asymmetric phase coding is achieved through the partition phase plate. Based on the device, according to the method, the unsupervised deep neural network is combined with the physical driving layer, so that accurate inversion of different optical systems to be detected is realized.

The invention relates to the technical field of power system monitoring, and discloses an icing torsion inversion method, system and device based on a physical constraint neural network, and a medium, and the method comprises the steps: collecting the torsion angle data, environmental parameter data and historical icing thickness data of a transmission conductor; establishing a physical constraint model between the torsion angle and the icing thickness based on a wire mechanics principle; constructing a first neural network based on the physical constraint model, and defining a composite loss function including a data driving loss function and a physical constraint loss function; training a first neural network by using historical icing thickness data, and optimizing network parameters through a back propagation algorithm to minimize a composite loss function; and inputting the torsion angle data and the environmental parameter data into a trained first neural network for prediction to obtain an icing thickness prediction value of the current wire. According to the method, the mechanical physical model is embedded into the neural network training process, so that accurate inversion from the wire torsion angle to the icing thickness is realized.

The invention provides a flame pulsating heat release rate determination method and device, equipment and a medium, and relates to the technical field of optical measurement, and the method comprises the steps: obtaining flame interference fringe images and phase diagrams of a combustion region at different continuous moments; extracting a plurality of background lines from the background area; performing phase inversion according to the phase difference of each pixel point at the moment to obtain the pulsating heat release rate of each pixel point at the moment; based on the pulsating heat release rate of each pixel point at different moments, determining a pseudo heat release rate time sequence of different background pixel points on each background line at each moment; according to the pseudo heat release rate time sequence of different background pixel points at each moment, spatial expansion is carried out, and the target heat release rate of each pixel point at each moment is determined; and based on the pulsating heat release rate of each pixel point at each moment and the target heat release rate of the pixel point at the corresponding moment, the flame pulsating heat release rate of the combustion area at each moment is obtained. According to the method, the accurate flame pulsating heat release rate can be obtained.

The invention discloses a natural gas pipeline cleanliness degree evaluation method and device, equipment and a medium, and relates to the technical field of natural gas pipeline monitoring, and the method comprises the steps: constructing a full-working-condition simulation database of a natural gas pipeline; generating a data-driven flow-roughness response model based on the pressure feature spatial index; performing pressure feature matching and roughness inversion on the actual pressure and the actual flow by using the flow-roughness response model; the roughness serves as an absolute index, a performance index is determined based on the planned flow and the actual flow, an economic index is determined based on the actual flow and the theoretical flow, the absolute index, the performance index and the economic index are input into a three-dimensional pipeline cleanliness evaluation system, and a comprehensive cleanliness degree score is calculated based on an evaluation method; the method is advantaged in that problems of strong physical model dependence, model misalignment, low calculation efficiency and poor multi-condition adaptability are solved, and reliability, accuracy and timeliness of natural gas pipeline cleanliness evaluation are improved.

This invention discloses a water level error correction system and method for steam generators, belonging to the field of industrial measurement and control. The system includes a differential pressure sensor with a Wheatstone bridge as its core, a precision resistor connected in series in its power supply circuit, and a multi-channel signal acquisition and processing unit. The method simultaneously acquires the output voltages of the two channels of the bridge and the voltage of the precision resistor, first calculating the sensor chip temperature; then constructing two characteristic quantities—voltage and voltage difference—and intelligently judging the system operating condition based on their changes; finally, adaptively calling a pre-stored compensation model according to the operating condition, calculating the system static pressure, and performing comprehensive dynamic correction of the original differential pressure for static pressure error and temperature drift, thereby calculating the accurate water level. This invention eliminates the need for additional sensors, achieving real-time compensation for the inherent error of the differential pressure sensor under all operating conditions solely through innovative signal fusion and adaptive algorithms, significantly improving the accuracy and stability of water level measurement, while also being low in cost and simple in structure.

The invention discloses a rape phenotype inversion model generation method and device, and relates to the technical field of model training, and the method comprises the steps: collecting rape data of a preset region in a preset time period through an unmanned plane and manual sampling in the preset region of rape growth, vegetation index data collected by the unmanned aerial vehicle and ground actual measurement phenotype data sampled manually are obtained; analyzing the ground actual measurement phenotype data to obtain a phenotype main influence factor; matching and associating the vegetation index data with corresponding ground actual measurement phenotype data to obtain an initial sample set; performing sample layering and sampling on the initial sample set based on the phenotype main influence factor to obtain a training sample set and a test sample set; training the initial machine learning model according to the training sample set to obtain an initial rape phenotype inversion model; verifying the initial rape phenotype inversion model through the test sample set to obtain a verification result; and optimizing the initial rape phenotype inversion model according to a verification result to obtain a target rape phenotype inversion model.

This invention provides a method for dynamic capacity expansion micro-meteorological simulation of transmission lines, belonging to the field of power system technology. The method includes: extracting features from wind field simulation data under different operating conditions based on intrinsic orthogonal decomposition to obtain corresponding modes and constructing a wind field order reduction model; using wind field data from sparse monitoring points as constraints, solving for the weight coefficients of each mode using the least squares method to reconstruct the baseline wind field for the entire line; calculating and correcting the local wind field error at non-monitoring points based on the deviation between the measured wind field data from monitoring points and the reconstructed baseline wind field, thus obtaining the wind field for the entire line; identifying dynamic thermal bottleneck points and determining the maximum allowable current carrying capacity based on the wind speed at these bottleneck points. Beneficial effects: Through offline physical cost reduction, online sparse reconstruction, and residual correction, a limited number of monitoring points can accurately invert the complex wind field of the entire line, achieving low-cost, high-precision micro-meteorological spatiotemporal simulation of transmission lines and improving the safety margin for dynamic capacity expansion.

The present application relates to the technical field of oil and gas drilling engineering, and specifically discloses a multi-field coupling complex fractured formation fracture width distribution inversion method, based on the theory of porous elasticity, a drilling fluid loss model considering fluid-solid coupling effect is constructed, a roughness correction factor is introduced to correct the traditional cubic law, and the application of Darcy's law in the matrix is improved, a drilling fluid loss mathematical model coupled with the matrix and the fracture is established, through numerical simulation, the influence law of key parameters such as fluid viscosity, pressure difference and fracture width on drilling fluid loss is obtained, and on this basis, a fracture width multivariate linear regression inversion equation with fluid viscosity, pressure difference and cumulative loss as independent variables is established, the inversion equation has high prediction accuracy and practicability, can be used for quickly and accurately inverting the fracture width on site, and provides theoretical and technical support for the understanding of the loss mechanism of multi-scale fractured formation and the optimization of leakage prevention and treatment.

This invention discloses a method and system for detecting and evaluating the settlement of buried pipelines based on ground-penetrating radar (GPR). The detection method acquires B-Scan mask images of shallow-buried pipelines, extracts the overall and local characteristics of target hyperbolic reflection signal feature points in the images, removes singular points, performs curve fitting on all valid target hyperbolic reflection signal feature points, and calculates and scores the depth and wave velocity values ​​corresponding to the target feature points to obtain the pipeline burial depth. The evaluation method, based on the pipeline settlement detection results, identifies the location of maximum settlement deformation by using the angle formed by the height change between two points on the pipeline, and predicts the location where the risk of fracture in the detected section may occur. The detection system implements this detection method, and the evaluation system implements this evaluation method. This application solves the problem in engineering measurements where hyperbolic reflection signals with characteristic damage caused by electromagnetic wave attenuation and coupling cannot be effectively calculated, significantly improving the data's processability and analyzability.

The invention discloses a calibration correction method and system for a long-wave infrared focal plane polarization camera, and relates to the technical field of optical detection and photoelectric imaging, and the method comprises the steps: obtaining a long-wave infrared polarization original image set of a target scene, which comprises original images of four polarization channels; acquiring a calibration parameter set which comprises dark current bias data of the detector, gain coefficient data of the detector, actual extinction ratio data of the micro-polaroid array, polarization azimuth angle deviation data of the micro-polaroid array and relative transmittance correction coefficient data of the micro-lens array; according to the calibration parameter set, performing pixel correction processing on the original response value of each pixel in the long-wave infrared polarization original image set to obtain a long-wave infrared polarization correction image set; based on the long-wave infrared polarization correction image set and the long-wave infrared polarization original image set, calibration correction of the long-wave infrared focal plane polarization camera is completed, and the polarization measurement precision of the long-wave infrared focal plane polarization camera can be remarkably improved.

This invention discloses a method for diagnosing hearing aid earplug leakage using ultrasonic features based on intelligent sensors, belonging to the field of non-destructive testing technology. The method includes: acquiring initial state data of the hearing aid, performing signal modulation and parameter calibration to obtain an earplug configuration and control list; emitting ultrasonic detection signals to the hearing aid earplug according to the configuration and control list, simultaneously acquiring echo time-domain data, and performing a fast Fourier transform to generate amplitude-phase frequency response curves; and using an envelope detection method to coarsely extract features from the amplitude-phase frequency response curves to form acoustic impedance anomaly spectrum features. Through the constructed loss acoustic model, accurate inversion of leakage is achieved, significantly improving diagnostic accuracy. The SVM algorithm is used for defect classification, and sealing test instructions are generated according to preset rules, realizing closed-loop control from diagnosis to execution, significantly improving detection efficiency.

The invention discloses an in-cloud particle velocity inversion method based on EarthCard 1B, and aims to solve the problems of insufficient error suppression, poor scene adaptability, disjunction of processing flow and single verification system in the prior art when the in-cloud particle velocity is inversed by EC-CPR data of an EarthCard satellite. A full-link collaborative optimization process of data preprocessing-mask generation-velocity inversion-result output is constructed, invalid value replacement in a preprocessing stage, velocity calibration and a subsequent inversion step are in deep linkage, and mask rules are uniformly applied to Doppler velocity and settling velocity calculation. High-precision inversion of the in-cloud particle velocity in a full-cloud scene is realized, and reliable data support is provided for cloud microphysical process analysis and climate model parameterization optimization.

The invention provides a laser radar extinction coefficient inversion method based on adaptive divergence constraint, and relates to the technical field of atmospheric remote sensing detection, and the method comprises the steps: constructing an inversion model; initializing a search interval of the extinction coefficient at the reference point; selecting a heuristic value of the current extinction coefficient, substituting the heuristic value into the inversion model, and judging a divergence state of the heuristic value based on a process integral state item; if in an over-divergence state, setting the tentative value as a search upper bound; if the search is in the non-divergent state, judging whether the search upper bound is defined or not: if so, setting the tentative value as the search lower bound; if not, increasing the heuristic value, and returning to substitute the heuristic value into the inversion model; judging whether the updated search interval width is smaller than a threshold value or not; if yes, calculating an extinction coefficient profile based on the heuristic value; and if not, updating the heuristic value, and then substituting the heuristic value into the inversion model. According to the method, the physical stability characteristic of forward numerical deduction is used as a constraint, and high-precision independent inversion is realized.

This invention relates to the field of water conservancy engineering technology, specifically to a method for monitoring suspended sediment in the Yellow River Estuary and its adjacent sea areas based on multi-source remote sensing data. The method includes the following steps: selecting complementary multi-source remote sensing data (Landsat 8 OLI, Sentinel-2A / B, GF-1 WFV, GOCI), and performing radiometric calibration, atmospheric correction, and geometric fine correction standardization preprocessing; using an algorithm combining weighted average and principal component analysis to fuse the multi-source data and extract sediment-sensitive characteristic information; constructing an improved semi-empirical radiative transfer model incorporating tidal current, wind speed, and hydrodynamic correction factors to invert suspended sediment concentration, and ensuring the reliability of the results through multi-dimensional verification. This invention significantly improves monitoring accuracy and spatiotemporal coverage, and is adaptable to routine, emergency, and long-term dynamic monitoring of the Yellow River Estuary, providing scientific support for estuary ecological protection and management decisions.

This invention discloses a method for dynamic monitoring of forest resources and automatic database updating based on multi-source remote sensing data, belonging to the field of forestry informatization. This method addresses the inconsistencies in resolution, imaging time, and band coverage of multi-source remote sensing data by dynamically generating multi-scale grids to achieve spatial alignment and fusion of data. Utilizing temporal residual discriminative convolutional networks and sparse attention mechanisms, it intelligently detects changes in forest resources, achieving efficient and automatic attribute inversion. The system also includes automatic differential database updates and multi-version management to ensure information synchronization and reliability. Combined with external climate and fire data, it provides alarms for abnormal changes and suggestions for auxiliary intervention, forming an intelligent closed loop from monitoring to management. This method improves the automation, intelligence, and precision of forest resource monitoring and is suitable for large-scale, dynamic forest resource management scenarios.