Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

174 results about "Nonlinear calibration" patented technology

Soil nutrient spectrum detection and regulation method and system

The embodiment of the invention provides a soil nutrient spectrum detection and regulation method and system, and belongs to the technical field of soil nutrient spectrum detection and regulation. The method comprises the following steps: collecting soil multispectral original data and environmental data, generating a calibration matrix and a nonlinear correction parameter, executing optical reflectivity conversion, and synchronously fusing a time domain reflectometry dielectric constant and a spectral moisture index to obtain fused moisture content; selecting a nutrient diagnosis characteristic wave band pair to obtain a moisture inhibition type spectral index; and predicting the soil nutrient content by using a pre-trained transfer learning model to obtain a soil nutrient content prediction value, and performing fertilization regulation and control based on the fertilization decision risk coefficient. According to the invention, extreme soil moisture measurement deviation is solved through a soil type adaptive moisture fusion technology; through multi-source risk quantitative decision and PID self-adaptive regulation and control, the fertilization amount can be dynamically optimized, execution safety is guaranteed, and a detection-decision-execution precision agriculture closed loop is formed.
Owner:INNER MONGOLIA AUTONOMOUS REGION ACAD OF AGRI & ANIMAL HUSBANDRY SCI

PUF (Physical Unclonable Function) key generation and equipment identity authentication system for cold chain environment

The invention discloses a PUF (Physical Unclonable Function) key generation and equipment identity authentication system for a cold chain environment, and particularly relates to the technical field of information security, comprising temperature change data perception, drift modeling, dynamic error correction and closed-loop optimization, and collecting original response data of PUF hardware and temperature sensor readings by simulating the cold chain environment in a temperature-controllable experiment module; learning a nonlinear mapping relation between the dynamic temperature change and PUF response drift, and outputting a drift compensation matrix; constructing a two-stage error correction mechanism based on the drift compensation matrix; the first-stage error correction unit carries out nonlinear calibration on the original PUF response sequence according to the drift compensation matrix; the second-stage error correction unit adopts a temperature sensing type reconfigurable LDPC coding architecture, an LDPC check matrix is obtained based on a temperature-drift joint constraint model, the error correction performance of a high-drift scene is optimized through the LDPC check matrix, and the problem of key instability caused by PUF hardware response drift in a cold chain environment is solved.
Owner:HUNAN UNIV OF FINANCE & ECONOMICS

Real-time data integration method and system based on ground observation data

The invention relates to the technical field of data processing, and discloses a real-time data integration method and system based on ground observation data. The method comprises the following steps: performing multi-dimensional preprocessing on original marine observation data to obtain time-space standardized observation data; performing multi-parameter cross comparison analysis on the time-space standardized observation data to obtain stratification deviation characteristic data; constructing an adaptive multi-factor correction rule based on the layered deviation characteristic data to obtain a dynamic correction parameter; based on the dynamic correction parameters, performing nonlinear correction on the real-time temperature profile data, and performing intelligent fusion with a preset reference data set to obtain preliminary integrated observation data; performing multi-level quality control and probability uncertainty evaluation on the preliminarily integrated observation data to obtain refined observation data with a credibility index; and performing closed-loop feedback processing on the refined observation data to obtain target integration correction observation data. According to the invention, the efficiency and precision of real-time data integration based on ground observation data are improved.
Owner:SHENGDONG RUDONG OFFSHORE WIND POWER CO LTD +3

Intelligent audio test system frequency response analysis method, device and equipment

The invention relates to the technical field of audio testing, and discloses an intelligent audio testing system frequency response analysis method, device and equipment, and the method comprises the steps: carrying out the audio parameter initialization of an intelligent audio testing system, and obtaining a testing parameter matrix and an excitation signal; performing dual-channel acquisition and time-frequency feature extraction to obtain a time-frequency feature data set; executing double-branch processing of time domain noise reduction and frequency domain enhancement to obtain a purified feature data set and a feature weighting matrix; performing segmented recursive calculation and feature aggregation to obtain a frequency response feature vector; decomposing the frequency response feature vector according to a test frequency band, and performing environment compensation and nonlinear calibration to obtain a standard frequency response data set; and inputting the standard frequency response data set into the deep neural network for feature recognition and mode classification to obtain a frequency response curve and a phase characteristic curve, thereby improving the test precision, the anti-interference capability, the automation degree and the adaptability of the intelligent audio test system.
Owner:SHENZHEN DEWEI AUDIO CO LTD

GPS interference phased array monitoring direction-finding antenna system for 1575 frequency band

The invention discloses a GPS interference phased array monitoring direction-finding antenna system for a 1575 frequency band, and relates to the technical field of intelligent antennae, comprising a data integration module for integrating data of satellite ephemeris, carrier attitude and airspace coverage through a weighted average method and generating an environment parameter set, a prediction calibration module for predicting the data of the satellite ephemeris, the carrier attitude and the airspace coverage through a weighted average method and generating an environment parameter set, and a direction-finding antenna module for performing direction-finding on the environment parameter set. The phase drift prediction module is used for inputting an environment parameter set into a bidirectional LSTM network, obtaining a phase drift prediction value, carrying out nonlinear calibration on the phase drift prediction value by adopting a Kalman-particle hybrid filtering algorithm, and synchronously monitoring an IQ signal by utilizing a closed-loop feedback mechanism, and the beam generation module is used for carrying out orthogonal modulation and radio frequency up-conversion processing on the IQ signal, and outputting the processed IQ signal. According to the method, the bidirectional LSTM network is combined with the Kalman-particle hybrid filtering algorithm, so that phase drift caused by factors such as carrier vibration and the like can be accurately predicted and calibrated in real time.
Owner:SHENZHEN RUIXUNTONG INFORMATION TECH CO LTD

Stereoscopic visualization camera and integrated robotics platform with force / torque sensor non-linearity correction

ActiveUS12269180B2Programme-controlled manipulatorDiagnosticsStereoscopic visualizationRobotic arm
New and innovative systems and methods for calibrating and correcting sensors associated with a collaborative robot are disclosed. An example system comprises: at least one robotic arm; a sensor affixed to a location on the robotic arm, wherein the sensor measures force and torque across six degrees of freedom (6DOF); a processor; and memory. The system may receive, from the sensor, sensor input in real-time that indicate a measured force or torque. The system may generate, in real-time, sensor corrections that correspond to offset, linear, and non-linear deviations of the measured force in each sensor axis. The sensor corrections may correspond to offset, linear, and non-linear cross-coupling of the measured force between two or more sensor axes. The sensor corrections may be determined by applying offset, linear, and non nonlinear corrections to each degree of freedom (DOF) from every other DOF.
Owner:DIGITAL SURGERY SYSTEMS INC

Array thermocouple multi-mode compensation and DIC stress field space-time coupling fusion method

The invention relates to the technical field of high temperature sensing and data fusion, in particular to a method for array thermocouple multi-mode compensation and DIC stress field space-time coupling fusion, which comprises the following steps: step 1, in a thermotechnical signal intelligent processing and compensation unit, completing hardware and algorithm collaborative design of an electronic cold junction compensation module; 2, constructing a multi-algorithm fusion compensation module, integrating nonlinear correction, drift compensation and interference suppression functions, and accurately coping with various interference signals through a dynamic weighting strategy; step 3, adopting a sub-pixel-level matching algorithm and a homography matrix calibration technology to realize high-precision space alignment of the temperature and stress measurement units; and establishing a nonlinear incidence relation between the temperature and the stress based on an improved Gaussian process regression model. According to the invention, based on collaborative design of the thermotechnical signal intelligent processing and compensation unit and the DIC vision and temperature data conjoint analysis module, the core precision problem of temperature and stress detection in a high-temperature environment is solved through hardware optimization and algorithm innovation.
Owner:NANTONG UNIV

Confocal microscope camera calibration method based on high-precision motion control

The invention discloses a confocal microscope camera calibration method based on high-precision motion control. The confocal microscope camera calibration method mainly comprises the steps of establishing four coordinate systems, placing a checkerboard calibration plate on a high-precision platform and adjusting the checkerboard calibration plate to the center of the view of a camera, and shooting and recording image coordinates of a calibration point. And based on the imaging relationship between the optical center of the camera and the object point, determining the mapping relationship between the coordinate systems so as to establish a preliminary imaging model. Then, nonlinear correction is performed on the imaging model, lens distortion is eliminated, and corrected image coordinates are converted into pixel coordinates. The non-linear correction parameters are optimized through the multi-view data, the mapping relation between the image plane and the platform physical plane is further calculated, and the mapping relation is optimized through the least square method so as to improve the calibration precision. Finally, pixel coordinates in the image are converted into physical coordinates of a platform through the optimized matrix, and support is provided for the automatic focusing process of the confocal microscope.
Owner:NANJING MUMUSILI TECH CO LTD +2

Analog-to-Digital Converter (ADC) with Reference ADC Path Receiving Attenuated Input to Generate Error Codes for Second and Third Harmonics by Counting Negative and Positive Codes

An interleaved Analog-to-Digital Converter (ADC) has a reference channel receiving an attenuated analog input. The reference channel is also calibrated to remove capacitor-ratio mismatch, static, and dynamic mismatches and produces a linear replica of the data channels with negligible nonlinear errors due to attenuation. Nonlinear errors on the data channels are corrected by Harmonic Distortion HD2 and HD3 coefficients. A counter increments when the sign bit of a nonlinear-corrected channel code is negative. The count is doubled and reduced by a number of samples to generate a HD2 cost function that adjusts the HD2 coefficient in a LMS loop. A HD3 correlation is generated by multiplying the reference channel output by its difference with the nonlinear-corrected channel code. The sign of the correlation code increments a second counter which generates a HD3 cost function whose sign bit adjusts the HD3 coefficient. These 2 counters generate cost functions, eliminating sample storage.
Owner:CAELUS TECH LTD

Computer-aided system for multidimensional generative value assessment and applicant selection

ActiveDE202025107568U1InstrumentsData packData stream
A computer-implemented system for multidimensional generative value assessment and applicant selection, consisting of: a data collection unit configured to electronically receive applicant data consisting of structured academic records, work experience records, digital documentation, and unstructured narrative responses generated from generative self-assessment instruments and contextual interviews; a feature extraction unit coupled to the data acquisition unit, configured to apply computer-assisted text processing, semantic analysis, and token-level attribute identification to transform narrative responses and structured data into multidimensional feature vectors that represent generative indicators of innovation, mentoring, collaborative performance, resilience, social contribution, ethical consistency, and predicted institutional impact; a weighting calculation unit configured to assign weight values ​​to the extracted feature vectors based on a digital generative profile definition matrix that includes dimensions, sub-criteria, indicators, documentation requirements and importance coefficients, with the weighting being distributed across the generative dimensions defined in the digital matrix and configurable according to the institutional context; a quantitative rating unit configured to calculate a generative rating score by aggregating weighted feature vectors derived from self-assessment inputs, interview-based ratings, document analyses, and authenticity predictions, with the aggregation including normalization, nonlinearity correction, conflict handling, and artifact frequency balancing to obtain a consolidated score; a proof verification unit configured to electronically validate referenced digital evidence by performing content extraction, metadata verification, pattern matching, and cross-document correlation to determine authenticity, credibility, and contextual relevance with respect to the calculated feature vectors; a classification determination unit configured to assign a classification level to an applicant by comparing the generative assessment score with a set of system-defined calculation thresholds, including at least a lower threshold, a middle threshold and an upper threshold, the classification levels representing different generative maturity states and determining subsequent eligibility for selection; a decision generation unit configured to produce a digital output data set that includes classification level, feature aggregation summaries, evidence validation results, and recommended organizational actions, wherein the decision generation unit encodes the data set in a digitally signed, tamper-proof format and stores it on a non-volatile storage medium; and A system control unit acts as an operational interface to all other units and is configured to orchestrate data flow, scheduling, process state transitions, and event logging to ensure verifiable traceability, consistency, and auditability of the evaluation and selection processes.
Owner:BERNARDO OHIGGINS UNIVERSITY +3

Fiber bragg grating multi-peak spectrum demodulation method and system

The invention relates to the technical field of multi-peak spectrum demodulation, and particularly provides a fiber bragg grating multi-peak spectrum demodulation method and system. The method comprises the following steps: extracting local spectral features based on an experimental reference spectrum to form initial atoms, and performing translation offset and normalization processing to obtain an over-complete spectral atom dictionary; performing global offset preliminary estimation based on the dictionary, and obtaining preliminary estimation values of peak sites of the measurement spectrum and the reference spectrum through cross-correlation calculation; executing constraint orthogonal matching pursuit sparse recovery based on the estimated value, and recovering atomic displacement from the measurement spectrum by using block sparsity, translation consistency and non-negative constraint; and performing wind speed inversion and calibration based on the atomic displacement, and converting the wind speed into a wind speed estimated value through a nonlinear calibration model to obtain a final result. According to the method, a dictionary based on experimental data is constructed, dependence on large-scale labeled data is reduced, a physical mechanism and sparsity prior are fused, and the problems that a traditional method is insufficient in precision and weak in generalization ability in a complex environment are solved.
Owner:LASER RES INST OF SHANDONG ACAD OF SCI

Nonlinear correction method for infrared hyperspectral remote sensing instrument radiated in non-ideal way

The invention discloses a non-ideal path radiation infrared hyperspectral remote sensing instrument non-linear correction method, aiming at the situation that partial radiation of a stationary orbit GIIRS enters a detector in a non-ideal path in a complex thermal environment, and initial correction is carried out on an original spectrum of a detection target based on a responsivity non-linear correction algorithm during radiometric calibration; during in-orbit operation, a linear calibration model is constructed through a two-point calibration algorithm, and the spectral response rate of the detector and the theoretical radiation spectrum of an observation target are obtained; based on a nonlinear correction spectral response rate and a theoretical radiation spectrum of an observation target, in combination with non-ideal radiation superposed by an original spectrum of the detection target and a fixed error which cannot be corrected by two-point calibration, a function relationship between radiation abutting against a detector in a non-ideal way and the original spectrum of the detection target is constructed; the non-ideal path radiation correction coefficient is obtained, non-linear correction is further carried out, non-ideal radiation errors which cannot be corrected by response rate non-linear correction are eliminated, and the radiation calibration precision of the target black body is improved.
Owner:SHANGHAI INSTITUTE OF TECHNICAL PHYSICS CHINESE ACADEMY OF SCIENCES

Nonlinear correction method for humidity sensor

The invention relates to the technical field of data correction, in particular to a humidity sensor nonlinear correction method, which comprises the following steps of: performing pairwise matching based on ambient humidity initial data and ambient temperature initial data of a humidity sensor, constructing a polynomial fitting initial curve, and utilizing a measurement deviation value of each group of data to obtain a nonlinear correction result; and correcting each curve node parameter in the polynomial fitting initial curve, and generating a humidity and temperature fitting initial parameter group. According to the method, the curvature characteristic and the offset characteristic are analyzed through the Laguerre polynomial curve model, different data segments are distinguished, fine compensation adjustment is carried out, the precision of nonlinear correction is remarkably improved, the real-time correction effect of the measured value is optimized by combining the difference value operation of the curve node parameters and the real-time measured value and dynamic offset trend analysis, and the accuracy of nonlinear correction is improved. The overlay analysis of the correction compensation coefficient and the dynamic offset further improves the humidity measurement stability and accuracy in a complex environment.
Owner:JINAN WENHENG CREATIVE SERVICE INTELLECTUAL PROPERTY AGENCY (GENERAL PARTNERSHIP)

Nonlinear correction method, device and equipment for excitation characteristics of mutual inductor

The invention discloses a nonlinear correction method, device and equipment for excitation characteristics of a mutual inductor, and particularly relates to the technical field of mutual inductors. The method comprises the following steps: acquiring original data corresponding to a mutual inductor, wherein the original data comprises an original current signal, historical magnetic flux and distributed temperature data; performing noise reduction processing on the original current signal to obtain a purified current signal, and determining a magnetic conductivity correction coefficient and a temperature gradient according to the distributed temperature data; inputting the purification current signal and the magnetic conductivity correction coefficient into a hysteresis model to obtain a real-time magnetic flux, and inputting the purification current signal, the distributed temperature data, the temperature gradient and the historical magnetic flux into a magnetic flux correction network to obtain a magnetic flux correction value; and compensating the real-time magnetic flux according to the magnetic flux correction value to obtain a corrected magnetic flux result of the mutual inductor. According to the invention, multi-physical field fusion input can be realized, transient response can be improved, harmonic distortion compensation can be carried out, and high precision of data can be maintained.
Owner:HUBEI ELECTRIC POWER CO JINGZHOU POWER SUPPLY CO

MEMS pressure sensor nonlinear correction method, system, equipment and medium

The embodiment of the invention provides an MEMS pressure sensor nonlinear correction method, system and device and a medium. The method comprises the following steps: acquiring an output value of the MEMS pressure sensor; inputting the output value into a pre-established nonlinear correction model to obtain a nonlinear correction value of the MEMS pressure sensor; wherein the nonlinear correction model is pre-established by performing parameter optimization on the support vector machine through a memetic particle swarm optimization algorithm. According to the embodiment of the invention, an efficient MPSO-SVM nonlinear correction algorithm is utilized to carry out nonlinear compensation of the MEMS pressure sensor, the problems of small samples and nonlinearity are well solved, the diversity of particle swarms is kept, and adaptive adjustment is adopted, so that the ergodicity of the algorithm in a solution search space is improved. The measurement precision of an existing MEMS pressure sensor is improved through a software algorithm, and the hardware updating frequency can be reduced, so that the production cost of the pressure sensor and the equipment maintenance cost are reduced.
Owner:NANJING GAOHUA TECH

Method for supplementing missing measurement data of anemometer tower

The invention relates to the technical field of supplementing missing measurement data of an anemometer tower, in particular to a method for supplementing missing measurement data of an anemometer tower. In the data preparation stage, historical observation data of a target anemometer tower needs to be collected, and missing time periods and missing features are determined, so that subsequent method selection is linked; meanwhile, data of surrounding meteorological stations in the same period are obtained, the spatial correlation between the data and the anemometer tower is verified, and a basis is provided for probability distribution mapping and quantile matching in subsequent CDF-t and QDM methods. The nonlinear correction method based on cumulative distribution function transformation and quantile increment mapping shows unique advantages in the field of climate downscaling, the CDF-t can effectively eliminate system deviation by establishing a probability distribution mapping relation between observation data and mode output, and the system performance is improved. The QDM maintains statistical characteristics of historical sequences while retaining climatic change signals through quantile matching, and new possibility is provided for long-period data reconstruction through combination of the two methods.
Owner:新疆维吾尔自治区气候中心(新疆环境资源遥感中心)

Intelligent security alarm method and system based on smart park

The invention relates to the technical field of intelligent security and protection, and discloses an intelligent security and protection alarm method and system based on an intelligent park. The method comprises the following steps: acquiring original security and protection data by using sensing equipment arranged in a smart park; performing standardization and redundancy elimination processing on the original security and protection data, dividing safety areas of the park through a pattern recognition algorithm, calculating a load intensity index of each area, and generating a security and protection situation summary; according to the security situation summary, a heuristic search algorithm is adopted to determine alarm trigger parameter initial values including detection sensitivity and alarm intervals, and a basic alarm parameter group is generated; performing nonlinear correction on the basic alarm parameter group, and outputting an environment perception alarm parameter group; training the historical security data set by adopting a neural network model, and analyzing the interaction between the load and the threat to obtain a threat diffusion model; and comparing the threat diffusion model with the real-time security data points, performing difference measurement, reconstructing alarm trigger logic according to a measurement result, and completing autonomous regulation and control of security and protection of the smart park.
Owner:SHANDONG MODERN BIG DATA TECH CO LTD

Non-linear correction method and system for frequency-modulated continuous wave laser

The embodiment of the invention discloses a nonlinear correction method and system for a frequency-modulated continuous wave laser, and the method comprises the steps: obtaining a phase curve of a to-be-corrected beat frequency signal based on an nth voltage signal, determining the frequency modulation nonlinearity according to the phase curve, carrying out the sampling processing of a plurality of phase points in the phase curve, and obtaining a plurality of target phase points, and finally, an (n + 1) th voltage signal is determined according to the multiple target phase points and the nth voltage signal, the (n + 1) th voltage signal is used for nonlinear correction of a frequency modulation continuous wave laser in the system, and n is an integer greater than 0 in sequence until the frequency modulation nonlinearity is smaller than or equal to a frequency modulation nonlinearity threshold value. Therefore, the nonlinear correction of the frequency-modulated continuous wave laser in the nonlinear correction system of the frequency-modulated continuous wave laser is realized, the distance measurement and speed measurement precision can be prevented from being damaged, and the performance of an FMCW radar is remarkably improved.
Owner:GUILIN UNIV OF ELECTRONIC TECH

Multi-modal self-adaptive preprocessing method for gas sensor based on Mamba state space model

The invention discloses a gas sensor multi-mode adaptive preprocessing method based on a Mama state space model, and relates to the field of gas detection, and the method comprises the following steps: synchronously collecting original signals, environmental parameters and historical time sequence data of a sensor; performing feature extraction on the three types of data to generate a sensor feature vector, an environment feature vector and a historical feature vector; the method comprises the following steps of: obtaining a final fusion feature through processing, mapping the final fusion feature to a 128-dimensional embedding space through a contrast learning encoder, inputting a three-layer residual error connection Mamba time sequence prediction network to output a zero offset, dynamically predicting process noise and observation noise through a neural network, executing adaptive Kalman filtering to output a smooth signal, and outputting a final fusion signal. Adopting a learnable piecewise linear network to carry out nonlinear correction on the filtering signal; the gas concentration value is calculated by integrating the correction signal and the zero offset, and finally a confidence score and a data quality mark are provided; according to the method, high-precision, real-time and robust pretreatment of various gas sensors in a complex environment is realized.
Owner:GUANGDONG COSCO SHIPPING HEAVY IND CO LTD

Non-linear error correction method, system, equipment and medium for FMCW radar

The invention relates to the technical field of frequency-modulated continuous wave radars, and discloses a nonlinear error correction method, system and device for an FMCW radar and a medium, and the method comprises the steps: obtaining a difference frequency signal containing a nonlinear error, and extracting a first time frequency signal; performing phase fitting on the first time frequency signal to obtain a first time frequency signal error coefficient, and performing error coefficient conversion on the first time frequency signal error coefficient to obtain a difference frequency signal error coefficient; constructing a matching signal according to the difference frequency signal error coefficient, and performing demodulation and low-pass filtering on the difference frequency signal according to the matching signal to obtain a residual signal; judging a signal type, and calculating a residual signal error coefficient by adopting a corresponding optimization algorithm; and combining the difference frequency signal error coefficient and the residual signal error coefficient to obtain a phase error correction factor, and performing nonlinear correction on the resampled difference frequency signal according to the phase error correction factor. The estimation precision of the nonlinear error coefficient can be improved, and the overall performance of a radar system is improved.
Owner:SUN YAT SEN UNIV

SAR ADC nonlinear calibration algorithm and device based on harmonic distortion component extraction

The invention discloses an SAR ADC nonlinear calibration algorithm and device based on harmonic distortion component extraction. The SAR ADC nonlinear calibration algorithm comprises the steps of obtaining a digital output matrix of an SAR ADC; separating the digital output matrix according to columns to construct a new digital output matrix; calculating a digital summation vector according to the ideal weight vector and the new digital output matrix; calculating a normalized frequency of the plurality of odd harmonics; for each odd harmonic, the method comprises the following steps: carrying out decimation filtering on a digital summation vector according to a normalized frequency to obtain a harmonic vector; constructing a new linear combination expression of a digital output matrix and a harmonic vector according to the to-be-estimated harmonic weight vector; solving the linear combination expression to obtain a to-be-estimated harmonic weight vector; calculating a total to-be-estimated harmonic weight vector according to the to-be-estimated harmonic weight vectors of all odd harmonics; and calculating a calibration weight vector according to the ideal weight vector and the total to-be-estimated harmonic weight vector. According to the invention, no circuit needs to be embedded, the portability is high, the hardware overhead is small, the calibration time is short, and the calibration precision is high.
Owner:XIDIAN UNIV

Rhatier culture VRAR virtual-real fusion interaction method based on eye movement tracking

The invention discloses a Rhatish culture VRAR virtual-real fusion interaction method based on eye movement tracking, and particularly relates to the technical field of virtual reality and augmented reality man-machine interaction. The method comprises the following steps: acquiring an eye image of a user through a near-infrared image acquisition unit, and inputting the eye image into a double-branch convolutional neural network model to estimate a two-dimensional fixation point of a screen; performing nonlinear correction on a fixation point based on the user personalized sight line offset correction model established in the offline calibration stage; in the online interaction stage, the corrected fixation point is combined with equipment pose data to be converted into three-dimensional space rays, the distance and angle relation between the three-dimensional space rays and an interaction target is calculated, and an interaction instruction is triggered when a threshold condition is continuously met. According to the method and the system, accurate, stable and natural eye movement interaction of the virtual contents of the Rhatish culture and the entity exhibits in the VR / AR environment is realized, and the user experience and the system robustness are improved.
Owner:JINGGANGSHAN UNIVERSITY

Powder particle grading and particle size distribution statistical system

A powder particle grading and particle size distribution statistical system of the present invention belongs to the technical field of particle measurement, and comprises: a multi-dimensional parameter acquisition module for acquiring physical parameters of powder particles to be measured; the coupling state judgment module is used for calculating a critical state index based on the physical parameters acquired by the multi-dimensional parameter acquisition module; the nonlinear correction model module is used for receiving the original particle size measurement data and the critical state index of the external laser diffraction measurement unit and calculating the original particle size measurement data based on a preset nonlinear correction model to generate corrected particle size data; and the particle size distribution statistical module is used for performing statistical analysis on the corrected particle size data and outputting a final particle size distribution report, and the method greatly improves the pertinence and accuracy of measurement.
Owner:YANTAI KEBAIDA ENVIRONMENTAL PROTECTION MATERIAL TECH

A nonlinear calibration method and device for laser surface of line structured light 3D camera

ActiveCN117765093BNonlinear calibration implementationRealize 3D reconstructionImage analysisInternal combustion piston enginesNetwork model3d camera
The present invention discloses a nonlinear calibration method and device for a line structured light 3D camera laser surface, including: performing reverse projection according to the camera's intrinsic parameter matrix, lens distortion parameters and extrinsic parameter matrix to obtain the three-dimensional coordinates of the center point of the laser line in the two-dimensional image captured by the line structured light 3D camera in the camera coordinate system; fitting the surface using a trained neural network model according to the three-dimensional coordinates of the center point of the laser line to obtain the surface model of the line structured light 3D camera laser surface in the camera coordinate system; obtaining the ray corresponding to each pixel according to the three-dimensional coordinates of each pixel on the center contour of the laser line in the two-dimensional image captured by the line structured light 3D camera; calculating the intersection of the ray corresponding to each pixel and the surface model of the line structured light 3D camera laser surface to complete the three-dimensional reconstruction of the line structured light 3D camera laser surface. The present invention can effectively improve the accuracy of laser surface calibration and the accuracy of three-dimensional reconstruction results.
Owner:JIANGSU JITRI INTELLIGENT OPTOELECTRONIC SYST RES INST CO LTD

Atomization furnace remote supervision system

The invention discloses a remote monitoring system for an atomizing furnace, belongs to the technical field of remote monitoring of the atomizing furnace, and solves the problems that inert gases such as argon are large in molecular weight and easy to form laminar flow in a pipeline, a traditional turbine flowmeter is based on turbulence calibration, the laminar flow causes non-uniform flow velocity distribution, the linear relation between the rotating speed and the flow is destroyed, and the reliability is poor. And the system misjudges that the flow is insufficient. Comprising a data acquisition module, an abnormity monitoring module, a data processing module and a wireless communication module, and the data acquisition module is used for acquiring temperature, pressure, liquid and gas flow and atomization effect in the furnace and feeding back the temperature, pressure, liquid and gas flow and atomization effect to the data processing module. Flow field characteristics are extracted through multi-sensor fusion, a generalized gas physical property model is constructed, and precise flow measurement is achieved by combining segmented nonlinear correction and vibration suppression; a multi-target robust controller and a dynamic feedforward-feedback collaborative optimization mechanism are designed, and the problem of control instability in a laminar flow / turbulent flow mixed state is solved.
Owner:JIANGSU VILORY ADVANCED MATERIALS TECH CO LTD

Intelligent traffic task execution method and device based on image defogging

The invention provides an intelligent traffic task execution method and device based on image defogging. The method comprises the steps of collecting a road image and calculating atmospheric light of the road image. And screening out the minimum value of a plurality of color channels of each pixel point in the road image to obtain a minimum color channel. And calculating the haze concentration of the road image, introducing a correction coefficient, constructing a nonlinear correction function, and mapping the haze concentration by using the nonlinear correction function to obtain the transmissivity. And inputting the transmissivity and the atmospheric light into an atmospheric scattering model for inversion so as to remove haze in the road image and obtain a defogged image. And inputting the defogged image into an intelligent traffic system, and executing an intelligent traffic task. The defogging algorithm adopted by the invention does not depend on mass data, is efficient in calculation and is suitable for complex real scenes, and the intelligent traffic task execution method based on the defogging algorithm can accurately carry out license plate recognition and target tracking.
Owner:SOUTHWEST UNIV

Rotor turn-to-turn short circuit diagnosis method based on exciting current-shaft voltage harmonic nonlinear correlation coefficient

The invention discloses a rotor turn-to-turn short circuit diagnosis method based on an exciting current-shaft voltage harmonic nonlinear correlation coefficient. The method comprises the following steps: synchronously collecting parameters, and preprocessing the collected parameters through wavelet threshold denoising and temperature normalization; extracting harmonic analysis according to the shaft voltage harmonic characteristics; identifying magnetic saturation, temperature and load nonlinear factors and calculating corresponding coefficients; performing dynamic correction on the Pearson's correlation coefficient through the nonlinear correction coefficient, and combining with fuzzy logic weighting to obtain fuzzy logic weighting; defining a working condition feature vector, and constructing a working condition adaptive dynamic model comprising a linear regression basic model and an LSTM neural network; and calculating a dynamic threshold value based on the basic threshold value and the nonlinear factor, and judging the turn-to-turn short circuit trend of the rotor according to the comparison of the correlation coefficient and the dynamic threshold value and a prediction result. According to the invention, through combination of the nonlinear correction correlation coefficient and the LSTM neural network, dynamic compensation of nonlinear factors is realized, and the accuracy and reliability of rotor turn-to-turn short circuit fault diagnosis are improved.
Owner:HEBEI JIANTOU ENERGY SCI & TECH RES INST CO LTD

Miniature semiconductor temperature sensor nonlinear correction optimization method and system based on deep learning

The invention relates to the technical field of temperature sensor control, in particular to a nonlinear correction optimization method for a miniature semiconductor temperature sensor based on deep learning, which comprises the following steps: acquiring an original temperature sequence of the miniature semiconductor temperature sensor in a preset temperature range, and synchronously acquiring an error related environmental parameter sequence and a sensor aging coefficient; the original temperature sequence is subjected to empirical mode decomposition processing, and main temperature fluctuation mode components including nonlinear errors are extracted, the original temperature signals of the miniature semiconductor temperature sensor are subjected to hierarchical processing through empirical mode decomposition, the main temperature fluctuation mode components carrying the nonlinear errors can be accurately separated and extracted, and the accuracy of temperature fluctuation is improved. In combination with the dual-branch neural network processing data and through the null drift compensation factor and the sensitivity compensation factor, baseline drift and sensitivity attenuation caused by long-term use are corrected in a targeted manner, so that the miniature semiconductor temperature sensor still keeps high precision after long-term use, and the application in a high-precision scene is met.
Owner:SHENZHEN LIGAN TECH CO LTD

Camera monitoring video real-time identification data processing method and system

The invention provides a camera monitoring video real-time identification data processing method and system, and relates to the technical field of computer vision and intelligent monitoring, and the method comprises the steps: extracting a current video frame from a real-time video frame sequence based on a multi-dimensional environment state descriptor, executing adaptive scene partitioning, and obtaining the confidence coefficient weight of each region; taking the confidence coefficient weight of each region as input, and performing joint nonlinear calibration on core parameters of the target detection network through a lightweight neural network model to obtain an optimized detection parameter set; and carrying out multi-target synchronous identification and depth feature abstraction on the current video frame by adopting the optimized detection parameter set to obtain a virtual feature contour set containing personnel and vehicles. Through environment adaptive detection and depth feature abstraction, precise identity verification, abnormal behavior recognition early warning and cross-domain trajectory association and cooperative response, a complete intelligent processing link from complex scene perception to global situation understanding and closed-loop management and control is realized.
Owner:BEIJING BAIXIN BLUEPRINT GIS SCI&TECH CO LTD +1

Neural network measurement calibration system and method for TDL-TDC

The present invention discloses a neural network measurement and calibration system and method for TDL-TDC, the system comprising: a TDL-TDC module, which uses a code density calibration method to complete the initial calibration of the delay chain and obtain an initial calibration value; a temperature sensing module, which collects the system operating temperature on the FPGA chip and obtains operating temperature information; a host computer neural network calibration module, which builds a multi-layer learning network, uses the operating temperature information and the initial calibration value as the input of the network, outputs the delay time of the delay unit, and establishes a corresponding nonlinear change relationship between the temperature information and the delay time of the delay unit. The present invention finds out the corresponding nonlinear change relationship between the delay time data of the delay unit and the temperature data through the learning network, and in actual work, only one calibration and temperature collection are required to obtain a more accurate nonlinear calibration result of each section of the current delay chain.
Owner:SUZHOU INST OF NANO TECH & NANO BIONICS CHINESE ACEDEMY OF SCI