46results about How to "The recognition effect is accurate" patented technology

This invention provides a multimodal fusion-based method for correlation analysis of deep-sea environmental data outside the Yangtze River Estuary, belonging to the field of deep-sea environmental analysis technology. This invention achieves accurate data registration by establishing a spatiotemporal standardization model for multi-source data and employing an adaptive spatiotemporal kriging interpolation algorithm. It utilizes a sparse coding marine signal separation algorithm to construct an overcomplete dictionary to separate mixed signals and extract pure features. Based on an attention mechanism, a feature extraction network is constructed to automatically learn deep feature representations of physical, chemical, and biological parameters. A matrix rank deficiency detection algorithm is used to automatically supplement feature compensation vectors to ensure feature integrity. A cross-scale attention mechanism based on wavelet transform is constructed to fuse multi-scale features. A Shapley value interpretability evaluation system is established to quantify the importance of correlated features. This invention solves the technical problem of inaccurate correlated feature extraction during the fusion of multi-source heterogeneous marine environmental data.

The application belongs to the technical field of material engineering and failure analysis, and particularly relates to a metal fatigue micro-damage detection method, device, medium and equipment, the method comprising the following steps: acquiring a longitudinal wave sound velocity of a metal material to be detected; calculating a normalized damage index of the metal material to be detected based on the longitudinal wave sound velocity; taking the normalized damage index as an input of a fatigue micro-damage evaluation model that has been constructed, and obtaining a plastic strain of the metal material to be detected, so as to realize fatigue micro-damage detection of the metal material to be detected. The application can improve the sensitivity of metal fatigue micro-damage detection.

This invention relates to the field of bid document management technology, and in particular to an automatic bid document review method and system based on natural language processing. The method includes: identifying target sections; determining historical performance and financial information; judging whether false performance exists; analyzing the complete sentences containing target keywords; calculating material scores; determining price deviation; and determining the review result. This invention achieves multi-dimensional and comprehensive review of bid documents by intelligently analyzing multiple sections such as qualifications, risks, materials, and pricing. This effectively improves the comprehensiveness and depth of the review. Utilizing natural language processing technology, it can accurately identify and extract key information from bid documents, overcoming the subjectivity and limitations of traditional manual review. Quantitative assessment based on risk level significantly improves the accuracy and relevance of risk identification. By comprehensively weighing material scores and price deviation, it significantly improves review efficiency.

The application relates to the technical field of low-voltage electrical apparatus, in particular to a magnetic flux tripping device, a disconnecting switch and a power supply system, which comprise a support, an electromagnetic coil and a top rod; the electromagnetic coil is installed on the support, and the top rod is slidably arranged in the electromagnetic coil; at least two moving iron cores are arranged on the top rod in the electromagnetic coil and are axially spaced; when the electromagnetic coil is electrified, at least one moving iron core moves along the top rod in the axial direction and drives the top rod to move. According to the embodiment of the application, at least two moving iron cores are arranged in the magnetic flux tripping device, which is beneficial to realizing differentiated responses for different faults.

The application relates to a power grid risk detection method, device and equipment based on a knowledge graph. The method comprises the following steps: acquiring multi-source detection data of a power grid to be detected; performing feature extraction on the multi-source detection data to obtain a plurality of feature data; performing mapping processing on the feature data and a preset knowledge graph according to the label of each feature data, and determining a target knowledge graph comprising the plurality of feature data according to the mapping result; wherein the preset knowledge graph is used for representing various types of preset entities, preset attributes of each type of preset entity, and constraint relationships between the preset entities; clustering target entities corresponding to the feature data with a category label according to the target knowledge graph to obtain a plurality of feature data clusters; performing risk detection on each feature data cluster, and determining a risk detection result of the power grid to be detected according to the detection result. The method can improve the accuracy of power grid risk detection.

The embodiment of the application provides a kind of early warning method and system of energy storage system based on dynamic threshold, belong to safety monitoring technical field.The method includes: the multi-source operating data of energy storage system is collected, and monitoring data set is formed;Feature parameters are extracted based on the monitoring data set, and fusion feature vector is generated based on the extracted feature parameters;According to the fusion feature vector, dynamic threshold determination is executed, and the determined dynamic threshold is obtained;The safety state of the monitoring data set is evaluated based on the dynamic threshold, and the early warning result of energy storage system is output.The application scheme can realize more accurate identification and prompt in the early risk of energy storage system thermal runaway, thereby significantly improve the reliability and adaptability of early warning result, reduce the delay of operation and maintenance intervention and the probability of accident.

Embodiments of the present application disclose a multi-screen demonstration page overflow identification method and device, equipment and a storage medium. The technical scheme provided by the embodiments of the present application configures the screen page number of a demonstration document for each screen in the order of screen display. For the case that the display order value is less than 1 or exceeds the total page number value of the demonstration document, the screen page number of the corresponding screen is configured as 1 or the total page number value. Thus, it is avoided that the screen page number exceeds the page number value range of the demonstration document, so that the corresponding display content of the page number cannot be found. By positioning the screen page number of the corresponding screen as a reference page number, according to the display order determined by the reference page number, for the screen whose display order is within the page number value range of the demonstration document, the corresponding page content of the document is displayed according to the screen page number, and for the screen whose display order exceeds the page number value range of the demonstration document, an overflow page prompt is performed, so that the overflow identification and prompt of the multi-screen demonstration page number are accurately performed.

The embodiment of the application relates to the technical field of optical fiber communication, and discloses a link state monitoring method of an optical communication network, an electronic device and the optical communication network, the link state monitoring method of the optical communication network is applied to the optical communication network, a link of the optical communication network is used for transmitting optical signals back and forth, the method comprises the following steps: acquiring a digital signal corresponding to the optical signals transmitted back and forth; converting the digital signal into a Stokes sequence representing an optical polarization state; identifying a plurality of disturbance points in the link according to the Stokes sequence; and determining the positions of the disturbance points in the link according to time offsets corresponding to the plurality of disturbance points respectively. The application can accurately monitor disturbances occurring in the link of the optical communication network.

The application provides a scanning electron microscope-based device defect point measurement method and detection equipment, and the measurement method comprises the following steps: intercepting a standard pattern area of a defect point to be measured in a GDS layer; marking a pattern hotspot on both side edges of a key part of the standard pattern area; scanning an actual layer to be measured by using a scanning electron microscope, and shooting a scanning pattern area in the layer to be measured, which has the same position and magnification as the standard pattern area; identifying a measurement boundary of the scanning pattern area; overlapping the standard pattern area of the GDS layer and the scanning pattern area of the actual layer to be measured; obtaining two intersection points of a connecting line of the pattern hotspot and the measurement boundary; and measuring the distance between the two intersection points to obtain the actual key dimension of the defect point of the actual layer to be measured. The application can more accurately identify and measure the key dimension (CD) of the defect point, significantly reduces the workload of the operator, shortens the time for fault diagnosis and elimination, and improves the production efficiency.

The application discloses a high-orbit LS dual-frequency full-polarization SAR system based on a ring-shaped reflector antenna, which comprises a dual-frequency radar central control processor, an LS dual-frequency common-aperture full-polarization feed array, a ring-shaped antenna reflector, an L-band full-polarization receiver and an S-band full-polarization receiver. The application has L and S dual-frequency bands and full-polarization ground imaging capability, and dual-frequency band data can be used for ionosphere measurement and ground surface deformation monitoring, thereby improving the application efficiency and competitiveness of the high-orbit SAR system.

This application relates to a method, apparatus, equipment, and medium for identifying and locating leaks in public building restrooms. The method includes: extracting local time-frequency features from a two-dimensional feature matrix of a log-Melogram using a CNN feature extraction module and converting it into a one-dimensional time-series feature sequence; inputting this sequence into a Transformer encoder; capturing the global temporal dependencies of the one-dimensional time-series feature sequence through a multi-head self-attention sublayer; and processing this sequence through a feedforward neural network sublayer to determine a first output feature sequence; inputting this sequence into a Transformer decoder; modeling temporal causality through a masked multi-head self-attention sublayer; and refining the features by fusing global time-frequency features through a cross-attention sublayer to determine a second output feature sequence; and outputting a classification probability distribution by a Softmax layer; if the maximum classification probability is higher than a preset confidence threshold, then the category of the leaking device corresponding to the maximum classification probability is taken as the category of the leaking device in the restroom to be detected. This application enables early detection of leaks, preventing secondary problems caused by the expansion of leaks.

The application provides a low, slow and small target fast detection method and system with adaptive wind noise, and belongs to the technical field of target detection. The method first collects unmanned aerial vehicle acoustic data and calls bird acoustic data set, constructs high signal-to-noise ratio data set, training set, test set and verification set; the acoustic signals of the high signal-to-noise ratio data set are subjected to synchronous compression wavelet transform, the high and low frequency information is separated, the waveform features and the spectrogram features are extracted respectively, the feature fusion is carried out, the feature fusion weight is optimized in the fusion process, and the adaptive wind noise fusion features are obtained; the YOLO network is called and its structure is optimized based on the fusion features, and the feature extraction and target detection network model is constructed; after training, testing and verification by the training set, the test set and the verification set, the model is deployed to the mobile terminal or the ground station for low, slow and small target detection. Through the dual-mode feature fusion and network optimization, the detection accuracy and timeliness of the low, slow and small target under dynamic wind noise are improved.

This invention provides a method and system for waterway monitoring based on real-time attitude compensation. The method acquires sensor data collected by a phased-array radar, an optical camera, and an inertial measurement unit (IMU) under a unified time reference. The phased-array radar, optical camera, and IMU are pre-fixed on a buoy, and their sensor coordinate systems are unified to the buoy's reference coordinate system based on calibration parameters. Based on the real-time angular velocity and acceleration data collected by the IMU, the real-time attitude change information of the buoy is estimated. Motion compensation is performed on the sensor data collected by the phased-array radar and optical camera based on the real-time attitude change information. The motion-compensated sensor data from the phased-array radar and optical camera is then spatiotemporally registered and fused to generate fused sensing data for maritime target identification and tracking. This method improves the accuracy and reliability of waterway monitoring.

This application provides a method for flotation separation of chalcopyrite and pyrite, relating to the field of mineral flotation. The method involves mixing and flotation of the minerals to be processed, including chalcopyrite and pyrite, with a chalcopyrite collector to obtain chalcopyrite concentrate and pyrite tailings. The general structural formula of the chalcopyrite collector is: [Formula omitted]. This chalcopyrite collector utilizes the high selective affinity of its propyne ester group for copper-active sites on the chalcopyrite surface and its inertness to iron sites on the pyrite surface, achieving precise identification and collection of chalcopyrite from the molecular structure of the reagent, significantly improving the grade and recovery rate of the copper concentrate. The R group is a hydrophobic group facing the pulp, significantly enhancing the surface hydrophobicity of the chalcopyrite particles, thereby enabling them to adhere to flotation bubbles and float.

The application discloses a kind of space photoelectric sensitive device anti stray light interference drive design method, it contains for capturing target celestial body image and outputting image element gray value image sensor, and with the FPGA of image sensor communication connection, its drive design method includes the following steps: S1, FPGA is configured to image sensor in space photoelectric sensitive device initialization;S2, image sensor is row by row output target celestial body image image element gray value to FPGA, and is operated by FPGA to row by row, to filter out background gray, obtain the image element gray value of target celestial body image after processing;S3, mark the target pixel gray of target celestial body image after processing, and the centroid of the target pixel gray marked is sought, to obtain point target.The present application retains halo, ghost image and the like information as background image, and can more accurately identify and extract point target.

This invention relates to a dedicated clutch chainring assembly for a mid-drive motor. This chainring assembly, used to control the speed of the mid-drive motor, includes a bottom bracket, a first crank, and a second crank. A first chainring is mounted on the bottom bracket, and a rotating component is concentrically mounted on the first chainring. A first spring is provided between the rotating component and the first chainring to generate rotational resistance and to reset the rotating component during rotation. The magnitude of the rotational resistance is positively correlated with the rotation angle of the rotating component. This invention modifies the chainring so that the teeth on the chainring can rotate, and achieves stepless control of the mid-drive motor based on pedaling force. It not only accurately and quickly identifies and responds to pedaling force, allowing the mid-drive motor to adjust accordingly and improve the riding experience, but also integrates sensors with the chainring, simplifying the vehicle's structure and size, making the vehicle more aesthetically pleasing.

This invention relates to a blockchain-based trusted collaborative control method and system for vehicle platoons, belonging to the field of intelligent connected transportation technology. The method includes steps such as vehicle state perception and data broadcasting, RSU node data verification and blockchain uploading, vehicle comprehensive trust value calculation and updating, predictive control compensation mechanism, abnormal behavior detection and malicious node isolation, and dynamic optimization and adjustment of the platoon structure. The system executes this method, ensuring data consistency and immutability through blockchain technology to enhance information security; utilizing trust value calculation and anomaly detection mechanisms to guarantee platoon security; and dynamically adjusting the platooning order based on priority scoring to improve collaborative control performance. This invention achieves high security, high real-time performance, and high robustness in collaborative vehicle platoon control under complex conditions, and has significant application value.

The utility model relates to wafer processing technical field especially, relates to a wafer cutting machine. The utility model provides a wafer cutting machine, including square through frame, marble base, marble stand, marble crossbeam, laser light path, Z axle, mounting panel, cutting head, connecting block and connecting wire etc., be equipped with marble base on square through frame, marble base rear side symmetry is equipped with marble stand, marble stand top between being equipped with marble crossbeam, be equipped with laser light path on marble crossbeam, marble crossbeam front side is equipped with mounting panel, and the front side mounting of mounting panel has Z axle, and the output end of Z axle is connected with connecting block, and the middle part mounting of connecting block has cutting head, and connecting block and laser light path are connected through connecting wire, still include the right side of connecting block is equipped with visual system. Through the unique visual system that camera one, camera two and camera three constitute, effectively promoted the flexibility and adaptability of cutting machine in the cutting of residual piece.

The application discloses an acute large blood vessel occlusion identification and reperfusion decision method and system, and the method comprises the following steps: S1, obtaining medical record text and head multi-modal CT image data of a patient to be diagnosed; S2, performing natural language processing on the medical record text to obtain text features; S3, processing the multi-modal CT image data, calculating the ASPECTS score of non-enhanced CT, and positioning the blood vessel occlusion position and evaluating the collateral circulation from the CTA image to obtain image features; S4, performing weighted fusion on the text features and the image features to generate fusion features; and S5, inputting the fusion features into a pre-constructed guideline knowledge graph and a decision model to generate an individualized acute large blood vessel occlusion identification result and a reperfusion treatment suggestion. The application can automatically, quickly and accurately generate an individualized identification result and a treatment suggestion by fusing the features of the medical record text and the multi-modal CT image and combining a real-time updated guideline knowledge graph.

The application discloses a kind of based on computer simulation building carbon emission prediction method and system, it is related to building energy saving and carbon emission monitoring technical field.The method is represented by equivalent heat network with the heat conduction process of envelope structure, and heat resistance and heat capacity parameters are set as learnable parameters, and are encoded into differentiable calculation layer by automatic differentiation framework;Obtain time-varying marginal carbon emission factor sequence, and multiply energy consumption simulation value and corresponding marginal carbon emission factor element by element by time step by time step by carbon emission factor coupling layer to generate carbon emission simulation sequence;Residual correction network is based on simulation intermediate state quantity and carbon emission simulation sequence to output residual correction value, and the carbon emission simulation sequence is added to obtain carbon emission prediction value;With prediction error as loss function, physical parameters and network parameters are updated simultaneously by back propagation, to realize physical parameter adaptive adjustment.System includes differentiable thermodynamic simulation module, carbon emission factor coupling module, residual correction module, end-to-end training module and prediction execution module.

The application provides a visual positioning, taking and placing method and device for a movable robot blood gas consumable, relates to the technical field of medical automation, and comprises the following steps: acquiring an image through a visual sensor, extracting blood gas consumable features to establish a pose model, calculating adaptive clamp parameters, generating a collision-free trajectory, executing a force control strategy based on material characteristics, adjusting the grabbing strength in real time, and finally accurately placing the blood gas consumable in a target area. The application improves the accuracy and stability of blood gas consumable taking and placing, reduces the risk of damage, adapts to different specifications of consumables, and significantly improves the efficiency of medical automation operations.

The application provides a point cloud anomaly detection method, system and automatic driving vehicle, and the method comprises the following steps: acquiring point cloud data of a vehicle surrounding environment perceived by a laser radar; inputting the point cloud data of the vehicle surrounding environment into a pre-established and trained point cloud anomaly detection network model to output a point cloud anomaly detection result; the point cloud anomaly detection network model is used for classifying and identifying fusion perception data and performing supervised learning training through a preset loss function; the fusion perception data is data fused after a known scene perceived by the laser radar and a pseudo abnormal object generated based on a point cloud deep learning data set; and the application can realize environment perception of the vehicle surrounding environment, accurately classify and identify unknown abnormal objects, improve the generalization performance of point cloud anomaly detection, and further improve the accuracy of point cloud anomaly detection when applied to the automatic driving vehicle.

The application discloses a door and window production whole-process control system and method, which generates a globally unique code for each component in the design and disassembly stage, and attaches a two-dimensional code and RFID dual-mode label to the surface of the component to realize accurate identification in the whole life cycle. The system comprises a cutting plan module, which generates a cutting scheme according to a preset rule based on profile surplus material inventory, and binds the raw material batch; a central control unit maintains component state, order and batch information; each processing station is provided with a code reading, identity verification and equipment interlocking device; a linkage control logic module checks the binding state of the previous procedure and batch. The quality traceability database collects raw material, process, quality inspection, rework and user feedback data, and supports closed-loop tracing from raw materials to end users. The system effectively prevents misloading and mixed orders, improves material utilization, enforces process compliance, and significantly improves production quality and efficiency.

This invention discloses a photovoltaic power plant detection method based on feature decoupling domain adaptation, comprising: constructing a multi-source domain new energy power plant hidden danger dataset; establishing a feature decoupling domain adaptation model, which is based on the DETR detection framework and includes a backbone network for extracting image features, a Transformer encoder / decoder, and a prediction head; setting a domain prompt generation module between the backbone network and the encoder; and connecting the encoder output to the decoder via a feature aligner, query filtering, and channel separation module; pre-training the DETR detection framework using the multi-source domain new energy power plant hidden danger dataset to obtain a pre-trained DETR detection framework; and freezing the core parameters of the DETR detection framework for the target domain data, optimizing only the lightweight domain adaptation module composed of the domain prompt generation module and the channel separation module to obtain an adaptation model for photovoltaic power plant detection. This method maintains detection robustness even under data scarcity conditions.

The application discloses a hierarchical text classification method and system based on a lightweight graph convolutional network, acquires news body text data to be classified and a label with a hierarchical structure corresponding to the news body text data; the acquired data is input into a trained text classification network, and a text classification result is output; the trained text classification network adopts a first BERT encoder to perform encoding processing on the news body text data to be classified, and obtains body text feature representation; a lightweight graph convolutional network is adopted to perform feature extraction on the label with the hierarchical structure, and label text representation is obtained; an attention mechanism layer is adopted to process the body text representation and the label text representation, and a label-aware positive sample is obtained; a second BERT encoder is adopted to process the label-aware positive sample, and label-aware positive sample representation is obtained; and a classifier is adopted to classify the body text feature representation and the label-aware positive sample representation, and a text classification result is obtained.

This application discloses a high-performance laser detection system, a laser detection data analysis method, and an apparatus, relating to the field of laser testing. The system includes: a laser, two optical lens groups, a fiber optic cone, a photodetector, and a signal processing circuit. The laser and the two optical lens groups work together to form two laser screens. The fiber optic cone is coupled to the surface of the photodetector. The photodetector detects the laser signals passing through the two laser screens. The signal processing circuit amplifies the electrical signals using a hyperbolic tangent amplifier circuit to obtain the original laser screen signals. The method includes: sequentially filtering, fragment identification, zero-time explosion identification, and cross-screen matching of the original laser screen signals, and outputting fragment signal matching pairs and their corresponding velocities. This application improves the response speed and dynamic range of the detected light intensity of the laser detection system, while simultaneously achieving accurate identification and parameter calculation of multiple fragments, significantly enhancing the detection capability and analysis efficiency of traditional laser screens.

The present application relates to the technical field of locomotive blind area early warning, and particularly relates to a locomotive lookout blind area visual early warning system, comprising: a data acquisition module, configured to collect image data of the locomotive in real time; a data analysis module, configured to determine whether the pantograph offset is out of limit based on the pantograph offset; a contact analysis module, configured to determine whether the contact stability meets the standard based on the contact pressure fluctuation value, and to increase the pantograph spring tension according to the difference between the contact pressure fluctuation value and the first contact pressure fluctuation threshold; a line analysis module, configured to determine whether the catenary line recovery is qualified based on the line recovery time length, and to increase the preset interval according to the ratio of the preset line recovery time length and the line recovery time length; and a track analysis module, configured to determine whether the pantograph and the catenary line match meet the standard based on the flatness similarity, and to decrease the lowering pantograph spring tension according to the relative difference between the flatness similarity threshold and the flatness similarity, the present application improves the accuracy of the locomotive lookout blind area early warning.

The application discloses an operation and maintenance video abnormal behavior automatic auditing method based on artificial intelligence, and specifically comprises the following steps: collecting operation and maintenance field videos in real time through proxy software, and carrying out pretreatment such as denoising, background removal and image enhancement to improve the accuracy of target detection and behavior recognition; the behavior target of operation and maintenance personnel in the video is identified by using a YOLO target detection model to obtain boundary box coordinates, category labels and confidence scores; the detection result is transmitted to a Kalman filter for continuous tracking of the target to generate motion trajectory data; 3D convolutional neural network (3D-CNN) is used to analyze space-time features, judge and label abnormal behaviors; finally, the labeled information is integrated with the video data, video metadata is embedded through FFmpeg, the quick jump function of the labeled information is realized, the audit personnel are helped to quickly locate and examine abnormal behaviors, and the auditing efficiency and the intelligent level of operation and maintenance management are greatly improved.

The application provides an eye fundus image lesion segmentation method and device, computer equipment and medium, and belongs to the technical field of medical image processing. The method improves the generalization ability of the model through data preprocessing, uses an eye fundus image lesion segmentation model containing an encoder, a global-local attention module, a multi-scale feature capturing module and a decoder, and realizes accurate segmentation of four kinds of sugar net disease lesions in the eye fundus image. The encoder adopts a three-branch structure to extract multi-scale features, the global-local attention module fuses global and local attention features, the multi-scale feature capturing module extracts multi-scale lesion features through different convolution kernels, and the decoder generates the final segmentation result through channel splicing and up-sampling. The application adopts the above-mentioned eye fundus image lesion segmentation method, device, computer equipment and medium, can simultaneously segment four kinds of sugar net disease lesions in the eye fundus image, has fewer calculation parameters, and has good accuracy and robustness.

The invention provides an intelligent electric control system and method of a new energy loader, and relates to the technical field of intelligent electric control, the operation parameters of a driving motor of a target new energy loader are collected, parameter identification is carried out according to the operation parameters, and a power parameter set is obtained; performing disturbance observation according to the historical measurement data and the power parameter set to obtain a load disturbance observation value, performing frequency spectrum extraction on the load disturbance observation value to obtain a power density spectrum, and determining driving operation characteristics according to the power density spectrum; performing working condition matching according to each historical working condition and the driving operation characteristics to obtain a current operation mode, and determining a compensation response moment according to the current operation mode and the load disturbance observation value; and generating a driving motor response torque instruction of the target new energy loader according to the compensation response torque. Accurate working condition identification and real-time compensation control can be realized based on the motor operation parameters and the load disturbance characteristics, and the response speed and the operation stability of the new energy loader driving motor are improved.