18results about How to "Reliable extraction" patented technology

This application provides a method, apparatus, equipment, and storage medium for identifying agricultural irrigation districts based on the irrigation-enhanced evaporation stress index (IESI), relating to the fields of agricultural water resources monitoring and management and remote sensing applications. The method includes: constructing a multi-source remote sensing and auxiliary dataset for the target area; calculating potential evapotranspiration and actual evapotranspiration and coupling them with a vegetation growth stability factor to obtain quarterly IESI data for the target area; determining irrigation identification thresholds applicable to plains and mountainous areas respectively; and discriminating the IESI of the target area to generate a binary spatial distribution map of irrigated and non-irrigated areas. This application solves the problems of existing irrigation area identification methods in large-scale applications, such as reliance on statistical data or large training samples, strong empirical thresholds, insufficient adaptability to terrain and regional differences, and complex calculation processes. It achieves irrigation behavior identification centered on evaporation stress response, ensuring computational efficiency while also considering spatial accuracy and regional adaptability.

The present application relates to the technical field of energy storage, more particularly to a portable intelligent shared charging method, system, medium and equipment. The scheme comprises matching a user serial number according to iris and face information, collecting a remaining battery percentage, a current temperature of a battery storage device and a distance index; obtaining one of a basic power index or an advanced power index according to the remaining battery percentage; obtaining one of a basic safety index or an advanced safety index according to the current temperature of the battery storage device; calculating a comprehensive evaluation coefficient according to the classification level; and providing the battery storage device to the user according to the comprehensive evaluation coefficient. The scheme learns user habits and positions through iris and face assistance, and combines online analysis of energy storage system power and system state to intelligently recommend a power source, thereby adapting to user habits and facilitating use while ensuring system safety and device service life.

The invention discloses a satellite communication frame structure security enhancement method and system based on dynamic fragmentation embedding, and the method comprises the steps: carrying out the fragmentation processing of the control information of a satellite communication frame, and carrying out the LDPC error correction coding operation; a sending end collects a satellite state parameter P in real time, and a dynamic mapping rule R is generated through a hash function; the encoded information fragments are embedded into a QPSK symbol phase of a data field according to a dynamic mapping rule R to form an integrated frame and transmit the integrated frame, and meanwhile, a satellite state parameter P is sent to a receiving end in a quantum key encryption mode; a receiving end performs decryption to obtain a satellite state parameter P, reproduces a dynamic mapping rule R, extracts information fragments from the integrated frame, recombines the information fragments into a control information set C, and analyzes service data; and updating the dynamic mapping rule R according to the satellite orbit type and the channel change. The invention provides a technical scheme which does not have an independent frame header and is used for dynamically distributing and embedding control information, and dual security enhancement of frame header physical disappearance and control information non-localization is realized.

The application discloses a lightning arrester resistance current detection method, device and lightning arrester detection system. The method comprises the following steps: determining three-phase third harmonic current capacitive components and three-phase third harmonic current resistance components; determining three-phase third harmonic resistance currents of a three-phase lightning arrester according to the three-phase third harmonic current resistance components; determining three-phase fundamental wave resistance currents of the three-phase lightning arrester according to three-phase interphase capacitances, three-phase fundamental wave current resistance components and three-phase fundamental wave voltage effective values; and determining that the three-phase lightning arrester is in an abnormal state if any one of the three-phase third harmonic resistance currents is greater than or equal to a first preset threshold value or any one of the three-phase fundamental wave resistance currents is greater than or equal to a second preset threshold value. The method can effectively eliminate power grid harmonics and interphase capacitance interference in the case that the power grid contains harmonics, and can realize reliable and accurate extraction of lightning arrester resistance currents in normal and abnormal states of the lightning arrester.

This invention discloses a submillimeter-level diffusion magnetic resonance imaging (DTI) method for extracting the radial index of cortical layered cognitive structures, relating to the field of medical image processing technology. This invention aims to address the problems of existing technologies failing to accurately quantify the directionality of cortical microstructures and neglecting the heterogeneity of cortical layering. The method includes: acquiring DTI data and performing high-fidelity preprocessing such as MP-PCA denoising, Gibbs artifact removal, and Gaussian process distortion correction; estimating the diffusion tensor and extracting the principal feature vector based on the preprocessed data; reconstructing the cortical white matter and pia mater surface using T1 images and extracting the normal vector; calculating the absolute value of the dot product of the diffusion principal feature vector and the surface normal vector to construct a radial index map; and segmenting the cortex into multiple intermediate layers based on the principle of equal volume and extracting layering parameters. Through refined high-resolution data processing and geometric modeling, this invention can accurately quantify the radial alignment integrity of cortical nerve fibers, providing highly sensitive imaging markers for cognitive disorders such as schizophrenia.

The invention belongs to the technical field of image recognition and processing, and aims to provide an intelligent homework reviewing method and system, electronic equipment and a program product. According to the method, page structure adaptive recognition is realized through template matching, high-precision image correction is completed by using anchor geometric constraints, character recognition is performed through a single character recognition model, and objective question answering information is automatically scored. According to the invention, the problem of low recognition accuracy of subjective questions and complex answering scenes caused by recognition of handwritten texts of students depending on OCR in the prior art is solved, and the problem of low recognition accuracy of OCR caused by poor handwriting of students in the prior art is effectively solved; in addition, full-process high-precision intelligent reviewing from image acquisition, area positioning, character recognition to automatic objective question scoring and subjective question scoring summarization is realized, and homework reviewing efficiency and accuracy are greatly improved.

The invention discloses an AWTA-ELCNN-based fault diagnosis method and diagnosis system. The method comprises the steps of obtaining a strong time-varying fault vibration signal of a rotating machine; inputting the strong time-varying fault vibration signal into the trained AWTA-ELCNN fault diagnosis model to obtain a fault diagnosis result of the rotating machine; wherein the AWTA-ELCNN fault diagnosis model adopts a single-layer architecture, and the AWTA-ELCNN fault diagnosis model comprises a scale adaptive wavelet convolution layer, an adaptive threshold time sequence attention enhancement layer, a global average pooling layer, a first full connection layer and a second full connection layer. Dynamic matching of strong time-varying fault features is realized through the scale adaptive wavelet convolution layer, feature enhancement and noise suppression are cooperatively performed through the adaptive threshold time sequence attention enhancement layer, and a single-layer lightweight architecture is adopted, so that the calculation efficiency is balanced while the time-frequency feature precision is guaranteed, and the diagnosis performance under a complex working condition is remarkably improved.

This invention provides a method for segmenting rock mass structural surfaces in a three-dimensional mesh model of the tunnel face, relating to the fields of three-dimensional laser point cloud processing and tunnel geotechnical engineering. The method involves collecting multimodal sensing data of the tunnel face during excavation, generating a colored three-dimensional mesh model based on this data, and performing tensor quantization on the colored three-dimensional mesh model data. Each vertex of the three-dimensional mesh model is encoded as a normal vector tensor, and the saliency of the vertices is determined based on the tensors to extract the vertex data of the structural surfaces. The structural surface vertices are then clustered, and structural surfaces are extracted from the obtained clustered vertices. Based on the orientation of the structural surfaces, they are grouped, and rock mass parameters are calculated. This invention solves the technical problems in existing technologies where structural surface rock mass segmentation easily leads to over-segmentation or under-segmentation, and where manual geological sketching is inefficient and inaccurate.

The invention discloses a legal map construction method based on multi-subject behavior recognition and role extraction, and belongs to the technical field of natural language processing and judicial intelligent analysis. The technical problems that multi-subject behavior semantics in criminal case texts are difficult to completely recognize, master-slave roles are inaccurate to judge, and behavior cross relations are difficult to extract are solved. According to the technical scheme, the method comprises the following steps of 1, data acquisition and preprocessing; step 2, semantic role labeling SRL; step 3, multi-level semantic feature extraction; 4, performing combined extraction on entities and relationships; step 5, behavior cross relation identification; and step 6, knowledge storage and application. According to the method, the behavior logic and role relationship of multiple subjects can be accurately described in a single case context, and efficient data support is provided for judicial semantic understanding, evidence chain construction and sentencing assistance.

The utility model discloses a stock solution extraction module which comprises a mounting table, a stock solution bottle cap breaking mechanism, an extraction mechanism, a transfer bottle cap taking and placing mechanism, a transfer bottle capping mechanism and a transfer bottle shifting mechanism, wherein the stock solution bottle cap breaking mechanism, the extraction mechanism, the transfer bottle cap taking and placing mechanism and the transfer bottle capping mechanism are sequentially arranged along a processing production line and are arranged on the mounting table; the industrial personal computer is electrically connected with the stock solution bottle cap breaking mechanism, the extracting mechanism, the transfer bottle cap taking and placing mechanism, the transfer bottle capping mechanism and the transfer bottle shifting mechanism; the transfer bottle shifting mechanism is used for carrying the stock solution bottles and the transfer bottles and conveying the transfer bottles; the stock solution bottle cap breaking mechanism is used for breaking caps of stock solution bottles, and the extracting mechanism is used for extracting stock solution; the transfer bottle cap taking and placing mechanism places bottle caps and bottle cap plugs into the transfer bottles, and the transfer bottle capping mechanism is used for capping. By means of the scheme, the device has the advantages of being simple in structure, reliable in extraction and the like, and has high practical value and popularization value in the technical field of stock solution extraction.

The utility model discloses a kind of power supply circuit of photovoltaic sensor, including DC-DC power supply chip, voltage sampling circuit is connected with the input end of DC-DC power supply chip, the output end of DC-DC power supply chip is connected with freewheeling circuit, one end of positive feedback circuit is connected in the input end of DC-DC power supply chip, and the other end is connected in the output end of freewheeling circuit.The utility model is sampled in real time to photovoltaic panel input voltage by voltage sampling circuit, and hysteresis threshold is formed using positive feedback mechanism, ensure that power supply is stable and reliable operation near starting voltage critical point, effectively prevent the system frequent start-stop problem caused by photovoltaic panel output voltage fluctuation due to illumination fluctuation, to ensure that power supply circuit can efficiently, stably extract photovoltaic panel energy in very wide input voltage range, provide continuous reliable electric energy for rear-end sensor.

The utility model provides a kind of ion exchanger unloading system and ion exchange system, the ion exchanger unloading system includes ion exchanger, infusion assembly and suction assembly, ion exchanger includes reaction cavity and filter screen, reaction cavity is divided into first chamber and second chamber, first chamber and second chamber are oppositely located the two sides of filter screen;Infusion assembly includes liquid storage bin, infusion pump and infusion pipeline, one end of infusion pipeline is connected liquid storage bin, the other end of infusion pipeline is connected second chamber, infusion pump is located on infusion pipeline, and infusion pump is used to make the liquid in liquid storage bin flow to second chamber;Suction assembly includes suction pipeline, resin storage bin and suction pump, one end of suction pipeline is connected first chamber, the other end of suction pipeline is connected resin storage bin, and suction pump is located on suction pipeline, and suction pump is used to make the resin in first chamber flow to resin storage bin.The utility model can improve the efficiency of resin replacement, improve the continuity and stability of production.

The application provides a magnetic suspension rotor fundamental frequency vibration signal real-time monitoring method and system, and belongs to the technical field of magnetic suspension bearings; the method comprises the following steps: collecting an original displacement signal; using an adaptive wave trap to pre-process the displacement signal; selecting an initial voltage signal according to the real-time rotating speed frequency of the magnetic suspension rotor V c , and inputting the pre-processed displacement signal into a phase-locked loop unit; the phase-locked loop unit is used for tracking the fundamental frequency component in the displacement signal which is synchronous with the rotating speed, and outputs an instantaneous frequency value and an instantaneous phase value which are synchronous with the fundamental frequency component, and two reference signals; a synchronous demodulator is configured, and based on the instantaneous frequency value, the instantaneous phase value, the two reference signals and the original displacement signal output by the phase-locked loop unit, the real-time amplitude of the fundamental frequency vibration component is extracted; and a rotor unbalanced vibration state vector including the real-time amplitude of the fundamental frequency vibration component, the real-time instantaneous phase value and the real-time instantaneous frequency value is output.

The application belongs to the technical field of machine learning, and specifically discloses a plateau wetland landscape component extraction method, system and program product. Through the design of a spectrum-space double-branch interaction model, the spectral features of the image elements are extracted through the image element dimension increasing module and the ViT architecture Transformer encoder in the spectrum branch, the neighborhood spatial features of the image elements are extracted through the multi-scale feature extraction module and the feature enhancement in the space branch, then the features of the two branches are integrated through the cross attention fusion module, and the image element classification result is output, so as to determine the plateau wetland landscape component regions in the remote sensing image according to the image element classification results, and the efficient and reliable extraction of the plateau wetland landscape components can be realized. The application can effectively alleviate the salt and pepper noise problem existing in the traditional pixel-by-pixel classification method, improve the classification accuracy of the plateau wetland landscape components, ensure the lightweight of the network, and provide more accurate technical support for the long-time sequence plateau wetland landscape component extraction.

The invention discloses a carrier speed estimation method and device based on a millimeter wave radar, and a storage medium, and relates to the technical field of carrier speed estimation. The method comprises the following steps: firstly, carrying out interference suppression processing on a distance-velocity spectrum matrix to obtain an interference suppression spectrum matrix; the first path performs velocity dimension energy aggregation on the interference suppression spectrum matrix to generate a static background energy distribution spectrum and determine a first velocity estimation value according to the static background energy distribution spectrum; a second path screens and verifies an effective ground reflection target from the interference suppression spectrum matrix, and a second speed estimation value is obtained by combining the pitch angle of the effective ground reflection target; and finally, respectively carrying out time sequence filtering and weighted fusion on the outputs of the two paths, and outputting the final carrier speed. According to the method, the problem that a traditional point cloud method fails in an open scene is fundamentally solved, and the robustness, accuracy and stability of a spectrum analysis method in a complex interference environment are remarkably improved.

The application discloses a T-shaped corner weld identification method and system based on laser vision, and belongs to the technical field of automatic welding and machine vision, and comprises the following steps: collecting images, performing enhancement processing on the collected images, and extracting an effective laser stripe area; center lines are extracted from the effective laser stripe area, and the center line coordinates are converted into three-dimensional point cloud data; the three-dimensional point cloud data is subjected to geometric feature optimization processing, and a RANSAC algorithm with spatial geometric constraints is used to fit and identify the geometric features of a T-shaped corner weld structure; based on the geometric features of the T-shaped corner weld structure, the three-dimensional coordinates of the key nodes of the weld are calculated through linear end point distance constraints, three-dimensional intersection calculation and Z-axis height screening. The application can realize automatic and high-precision acquisition of the position of the weld, realize automatic conversion of the weld from a two-dimensional image to a three-dimensional robot coordinate system, and significantly improve the degree of welding automation.

The invention relates to an optic nerve multi-mode image prognostic marker extraction method. The method comprises the following steps: acquiring optical coherence tomography, magnetic resonance imaging and retina electrophysiological data; the inter-modal signal-to-noise change rate is calculated based on the covariance of the regional signal-to-noise ratio, a signal collaborative change region is identified according to a multi-modal noise non-mean fitting error function, and a signal stable coupling region is constructed; calculating the consistency deviation rate of the modal structure, identifying a local area of abnormal splitting of the cross-modal structure, and mapping the local area to corresponding modal original data; calculating the time point difference spectrum skewness of the follow-up visit image sequence of the same tested object, identifying a nonlinear mutation time point, and determining a prognosis event candidate area; respectively calculating a cross entropy approximate value of each modal response, determining a modal redundancy penalty index and a marker exclusive information density, and screening marker feature points with low redundancy and high contribution degree; and calculating a posterior condition transition probability, generating a potential association path of the marker, and judging a structure degeneration direction and a prognosis risk level.

The application discloses an underground pipeline intelligent leakage detection method and device, relates to the field of intelligent leakage detection, collects a high-frequency pressure sequence, establishes a time-temperature equivalent equation to calculate a moving factor, maps the high-frequency pressure sequence to a reduced time axis by using the moving factor, obtains a temperature equivalent pressure sequence, and is converted into a full history stress-strain memory field tensor, constructs a neural lag operator network, takes the full history stress-strain memory field tensor as input, carries out non-local memory characteristic and hysteresis loop analysis, carries out point-by-point difference processing on the high-frequency pressure sequence and the pipe material intrinsic nonlinear hysteresis response signal, extracts a fidelity fluid dynamics abnormal residual error, constructs a spatiotemporal evolution Poincare section, inputs into a convolutional neural network, and determines real leakage negative pressure waves and sensor random drift through attractor shape difference on the spatiotemporal evolution Poincare section, so that periodic false alarms caused by material rheological characteristics are eliminated.