18results about How to "Comprehensive" patented technology

The application discloses a brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion, and comprises the following steps: inputting multi-modal medical image data into a Laplacian pyramid multi-modal fusion learning model to generate a fusion graph, then inputting the fusion graph into a U-net segmentation model comprising an encoder and a decoder to obtain a segmentation mask under the multi-modal fusion graph; and finally, based on the multi-modal fusion graph and the segmentation mask, adopting a Marching cubes (MC) algorithm to perform three-dimensional reconstruction visualization of brain regions and brain tumor region labeling. The brain glioma segmentation and three-dimensional visualization model training method and system based on multi-modal fusion provided by the application optimizes the disadvantages of insufficient information and incomplete modeling under single modal, fully utilizes the advantages of the completeness of multi-modal data, performs multi-modal fusion, segmentation and three-dimensional visualization, can more comprehensively assist surgeons in treatment, and improves the accuracy in the operation process.

The application discloses an AFS, ARS and DYC cooperative control method of a distributed electric drive vehicle based on DDPG. The method utilizes a cooperative control method and a deep reinforcement learning method, designs and develops a vehicle stability control method based on a centroid side slip angle and a yaw angular velocity, takes driving signals provided by a driver and measured or estimated vehicle state information as input, and judges the stability of the vehicle. When the active safety system needs to intervene, a DDPG-AAD model trained offline by a strategy deep gradient algorithm is used to coordinately control AFS, ARS and DYC systems, precise and independent control of each wheel is realized, and thus the active safety driving stability of the vehicle is improved.

This utility model relates to the field of communication equipment technology and discloses an emergency communication device for tunnels. The device includes a communication unit with an internal loudspeaker. A sliding groove is formed inside the fixing plate, and a slider is slidably connected inside the groove. A buckle and a limiting ring are engaged. This utility model enables normal communication by fixing an interface to the bottom of the communication unit. During the connection process between the interface and the connecting cable, loosening may occur. In this case, because the buckle is engaged with the bottom of the limiting ring, the spring provides elastic force, and the slider is pushed by the telescopic rod towards the communication unit. Simultaneously, because the buckle and slider are fixedly connected, the sliding action between the slider and the groove keeps the limiting ring constantly pushed to fit against the interface, preventing loosening of the interface and the connecting cable.

The invention provides a natural ecosystem investigation method. The natural ecosystem investigation method comprises the following steps: S1, acquiring a high-resolution remote sensing image and DEM data, and dividing ecosystem types; s2, typical ecological problems of the ecological system are determined, sample plot design and sample plot dynamic arrangement are carried out, investigation points are arranged in a sample plot, and sampling analysis is carried out; and S3, performing data analysis according to the plaque partition map, the sample plot location map and the remote sensing image map. According to the dynamic survey method combining quadrat / transect and sampling point actual ground survey, the mutual verification of ground, remote sensing and model data is realized by combining a satellite remote sensing and model simulation technology with multiple data sources, typical / important ecological problem partitions in a watershed ecosystem range are found out and verified, and a watershed ecological system is established. Support is provided for design and implementation of the ecological engineering project, and a data index basis is provided for acceptance of the ecological engineering project.

The application discloses a multi-parameter fusion and intelligent perception electrocardio health evaluation method and system, relates to the technical field of electrocardio health evaluation, and has the technical scheme as follows: based on the electrocardio function imbalance data of a target evaluation object, a comprehensive electrocardio evaluation path of at least two different types of evaluation dimensions is dynamically generated; if the initial evaluation coefficient indicates that the electrocardio health evaluation has deviation, a feedback evaluation path is dynamically generated based on the type of the abnormal evaluation path segment, and the actual feedback evaluation path of the target evaluation object when performing the evaluation task along the feedback evaluation path is collected; the feedback evaluation coefficient is obtained by comparing the actual feedback evaluation path with the feedback evaluation path; the comprehensive evaluation coefficient is obtained according to the initial evaluation coefficient and the feedback evaluation coefficient, the electrocardio health risk grade of the target evaluation object is output according to the comprehensive evaluation coefficient, and the accuracy and reliability of the evaluation result are improved.

The application is suitable for the field of bioinformatics and molecular diagnosis technology, and provides a TP53 gene heterozygous deletion and copy number variation detection method based on targeted sequencing. Through core technical innovations such as customized probe design, dynamic reference set correction, improved HMM model and KDE bimodal judgment, the application realizes the synchronous and accurate detection of TP53 gene LOH / CNV and mutation. Compared with traditional detection technology, the application effectively solves the problems of CN-LOH missed detection and insufficient integrated analysis of mutations and structural variations, and the coincidence rate with whole exon sequencing reaches 100%. The method has the outstanding advantages of high sensitivity, high specificity, rapid efficiency and controllable cost, can accurately determine the TP53 multiple hit state, and provides reliable molecular diagnosis basis for risk stratification, prognosis evaluation and individualized treatment decision of AML / MDS and other myeloid tumor patients, and is more suitable for clinical routine popularization and application.

The present application relates to a kind of impact dynamic performance test and evaluation method of composite structure of cement-based material of ballastless track, belong to the field of cement-based material performance test.Test sample is layered or embedded composite structure of cement-based material.A certain quality drop hammer is repeatedly dropped from high, drop hammer gravity potential energy is absorbed by sample, and dynamic impact damage is generated to sample.High-definition camera shoots the surface topography of sample after each impact, and the computer program calculated is used to calculate the lateral deformation size of sample, the number and total area of upper surface crack and interfacial separation crack.Innovatively, cumulative drop hammer impact energy, impact expansion coefficient, lateral deformation size, the number and total area of upper surface crack and interfacial separation crack are used to evaluate the impact dynamic performance of composite structure, with the advantages of being able to restore ballastless track entity structure, high intelligent degree, high evaluation index precision and strong comprehensiveness, suitable for high-speed rail ballastless track structure impact dynamic performance evaluation.

The invention relates to the technical field of fuse protection cover detection, and discloses a defect detection method and system for a drop-out fuse protection cover, and the method comprises the steps: obtaining a protection cover image, and obtaining defect features; classifying the defect features into structural defects and surface defects; calculating a structure defect index; comparing the structure defect with a historical structure defect to obtain a structure deterioration index, and judging the grade of the structure defect according to the structure defect index and the structure deterioration index; obtaining pollution characteristics, obtaining pollution characteristic change conditions in a preset time period, obtaining pollution indexes according to the pollution characteristic change conditions, and determining pollution grades according to the pollution indexes; and obtaining a defect degradation grade, and carrying out maintenance early warning. According to the invention, full-process intelligent detection of the drop-out fuse protection cover from image acquisition, feature recognition, defect classification, defect quantification to early warning output is realized.

This invention discloses a temperature and humidity monitoring system for a lithography machine, comprising: a BLG file pre-reading module for reading BLG files generated by the lithography machine, wherein the BLG file includes equipment operating status data and environmental parameter data in binary format based on IEEE 754 floating-point encoding, and the environmental parameter data includes temperature and humidity; the BLG file pre-reading module is also used to decode each data in the BLG file based on the IEEE 754 floating-point encoding standard to obtain decoded data; and a database preprocessing module for preprocessing the decoded data and converting it into structured temperature and humidity data, writing the structured temperature and humidity data into a database, and storing it in the database by category according to temperature and humidity. This invention also discloses a method for monitoring the temperature and humidity of a lithography machine. This invention enables the real-time reading of temperature and humidity data of the lithography machine, thereby achieving monitoring of the machine's condition, improving efficiency, increasing data backup capacity, and enabling analysis of historical data.

This application relates to the field of component analysis technology, specifically a crack resistance analysis method and system based on load factors and environmental factors. The method includes: acquiring historical load data and historical temperature data of the object to be analyzed, wherein the historical load data and historical temperature data are acquired in a simulation model; establishing a load-temperature coupled field model based on the historical load data and historical temperature data; inputting the load-temperature coupled field model into a crack resistance prediction model to obtain crack resistance analysis results, specifically including: obtaining corresponding second variable values ​​based on changes in first variable values ​​in the load-temperature coupled field model; obtaining corresponding first variable values ​​based on changes in second variable values ​​in the load-temperature coupled field model; constructing a variable dataset based on the acquired multiple first variable values ​​and multiple second variable values; and inputting the variable dataset into the crack resistance prediction model to obtain crack resistance analysis results.

The utility model provides a testing device of a laser radar lens. The laser radar lens is a transmitting end lens or a receiving end lens. The test device comprises a light source configured to emit test light to the laser radar lens; the reference plane is fixedly arranged relative to the laser radar lens and is used for calibrating the position of a light-emitting surface or a light-sensing surface corresponding to the laser radar lens; the imaging module is configured to at least move to a first set position and a second set position along the optical axis of the laser radar lens; the first set position is the position when the imaging module images the test light focused by the laser radar lens, and the second set position is the position when the imaging module images the reference plane; the position detection module is configured to obtain coordinates of a first set position and a second set position. Thus, through the testing device provided by the embodiment of the invention, common testing of the defocusing amount and the focal length of the laser radar lens can be effectively realized, and the hardware cost and the process cost are reduced.

The application discloses a kind of development adjusted reservoir engineering research whole-process informatization method, comprising: collecting reservoir static, production, test, monitoring, test data;Divide research and analysis object, carry out data splitting and classification;Automatic process visualization index;Man-machine interactive data iteration verification, and improve data and analysis index;Data export is converted and format conversion;Man-machine interactive scheme deployment optimization.The application can optimize the interactive relationship between reservoir engineering comprehensive researchers and programmatic platform software, form the optimization method of reservoir engineering comprehensive research quality and efficiency, and greatly improve the whole-process work efficiency of development adjusted reservoir engineering research.

This invention provides a method and system for evaluating the heterogeneity of deep massive carbonate reservoirs. The method selects reservoirs in the mid-to-late development stage and delineates target evaluation layers based on sedimentary cycle information; selects strata with physical properties meeting set requirements as tight layers; comprehensively considers different reservoir types, pore structure characteristics, and dynamic / static requirements to determine evaluation parameter types and decide on target index parameters; uses the entropy weight method to determine the weights of target index parameters, calculates a comprehensive heterogeneity evaluation index, draws a heterogeneity distribution map, and formulates heterogeneity grading standards based on the inflection points of the cumulative curves in the distribution map; and constructs a planar heterogeneity distribution visualization model combined with a reservoir geological model. This approach overcomes the shortcomings of existing technologies, such as incomplete parameter consideration, limited applicability, and insufficient accuracy, achieving high-quality evaluation of the heterogeneity of deep massive carbonate reservoirs based on reasonable investment and multi-scale parameters.

The invention relates to the technical field of mining engineering, environmental geotechnical engineering and water and soil conservation, and particularly discloses a coal mining subsidence area water and soil loss similar simulation device and experimental method.The coal mining subsidence area water and soil loss similar simulation device comprises a support and an experimental box, the experimental box is installed on the support, an experimental soil body is arranged in the experimental box, and a subsidence crack simulation system is arranged in the experimental soil body; the top of the experiment box is matched with a rainfall system; the subsidence fracture simulation system comprises a middle box body arranged in the middle of the experiment box, the middle box body is embedded in an experiment soil body of the experiment box, an experiment soil body is also arranged in the middle box body, and one or more fracture plates are embedded in the middle box body in a matched mode. The method can physically reproduce a complete erosion path of'surface runoff collection-fracture preferential flow-lateral matrix infiltration 'of the subsidence area, and accurately quantify the effect of the fracture in acceleration of water and soil loss.

This invention discloses a performance testing system for an air energy storage heat exchange module, comprising a saturated humidification / salting subsystem, a cooling fluid subsystem, a heat storage fluid subsystem, a DCS control subsystem, and a second heat storage fluid subsystem. Stable high-pressure air, generated by a drive motor, air compressor, and high-pressure storage tank, enters the saturated humidification / salting subsystem for humidification / salting, then enters the second heater / first cooler for heating / cooling. Afterward, it enters the heat exchange device under test and exchanges heat with the hot fluids in the heat storage fluid subsystem and the second heat storage fluid subsystem. The cooling fluid subsystem provides a cold source for the first cooler. The high-pressure air after heat exchange passes through a third cooler and a silencer before being discharged into the atmosphere. This invention can conduct tests on the flow heat transfer performance and cycle stability of heat exchange devices under different operating parameters, and features high versatility, a wide operating range, good stability, and strong comprehensiveness.

The present application relates to the technical field of anomaly evaluation, and particularly relates to an anomaly evaluation method based on vulnerability identification, a medium and equipment, a first preset weight set and a target model set are determined through a target object type and a user intention, so that feature fusion and analysis processes accurately adapt to source code vulnerability identification and anomaly evaluation scenarios, and the pertinence and practicality of the scheme are improved, through extraction of structural semantics, environment configuration, and exclusive morphological features of data flow stain analysis features, full coverage of multi-dimensional original features is realized, first fusion feature vectors are generated through first preset weight set weighted fusion of feature coding, the contribution degree of core risk features is amplified, vulnerability automatic preliminary screening is realized through a vulnerability identification model, the identification efficiency is improved, false positives are accurately removed through a false positive filtering model, the artificial audit cost is reduced, and multi-dimensional risks are quantified through a first anomaly evaluation model and divided into grades, so that the anomaly evaluation result has objectivity and comprehensiveness.

The application discloses a power system regulation method, device and equipment and a storage medium. The method comprises the following steps: obtaining real-time operation state information of a current power system and a user input regulation task demand based on a man-machine interaction interface of a large language model, and converting the real-time operation state information and the regulation task demand into regulation task structured information; decomposing the regulation task structured information into a plurality of regulation subtasks; and generating an optimized regulation strategy corresponding to each regulation subtask by a plurality of pre-trained small models. The small models are obtained by training based on prior regulation information and regulation constraint conditions of the power system. The application can fully consider the experience of the user in abnormal conditions of the power system during regulation of the power system, and can effectively generate reliable optimized regulation strategies for different regulation subtasks while complying with regulation constraint conditions through cooperation of the large language model and the pre-trained small models.