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

2200results about How to "Good precision" patented technology

Medical visual question and answer method and system based on multi-task modeling

The invention discloses a medical visual question-answering method and system based on multi-task modeling, and the method comprises the steps: carrying out the feature extraction of a to-be-analyzed medical image through a visual encoder, obtaining an image feature, inputting a preliminary question instruction and historical question-answering data into a dialogue large model to generate a question instruction, and obtaining a text feature through a text encoder; carrying out feature fusion on the obtained text features and image features, and carrying out self-attention image importance weighting processing and image-text alignment to obtain image-text fusion representation; and inputting a multi-target output projection layer, carrying out multi-task prediction, outputting question answers, image categories and important region masks, inputting the question answers and the image categories into a dialogue large model, and finally generating diagnosis opinions with detailed description in combination with dialogue context and multi-round interaction data and in combination with the important region masks. According to the invention, the interaction experience and the performance of the question and answer system are improved, and more accurate medical diagnosis in multi-modal complex information is facilitated.
Owner:ZHEJIANG UNIV

Hydropower station gate detection method and system

The invention discloses a hydropower station gate detection method and system, and relates to the technical field of hydropower station gate detection, and the method comprises the steps: collecting environment parameters, building a dynamic environment model, and determining a real-time impact factor on a gate state; synchronously collecting gate vibration and sound wave data to obtain a composite signal; constructing a short-term and long-term trend model, and identifying a potential abnormal trend; automatically adjusting the sampling frequency of the sensor according to an abnormal detection result; performing fault classification on the multi-parameter signals by using an event pattern recognition algorithm; and generating an automatic response strategy according to a fault classification result. According to the hydropower station gate detection method provided by the invention, the accuracy and efficiency of hydropower station gate detection are improved through multi-dimensional parameter fusion and adaptive sampling adjustment. Through monitoring of various parameters, the system can comprehensively analyze the state of the gate, the misjudgment risk caused by a single signal is reduced, and comprehensive recognition of faults is enhanced.
Owner:四川华能泸定水电有限公司

Condensation monitoring method of digital substation

ActiveCN119494559ACondensation monitoring implementationImprove reliabilityCircuit arrangementsForecastingFeature setData information
The invention discloses a condensation monitoring method for a digital substation. The method comprises the following steps: acquiring data information of a target digital substation; a high-risk area where condensation occurs is determined, and monitoring equipment is arranged to obtain monitoring data; selecting a monitoring frequency band, acquiring and analyzing data of the monitoring frequency band, and constructing a feature set related to the condensation degree; acquiring monitoring data of the target digital substation in real time and selecting an electromagnetic wave monitoring frequency band; feature extraction and analysis are carried out to construct a condensation monitoring model, and optimization is carried out; generating a condensation risk prediction result of the target digital substation based on the optimized condensation monitoring model; and giving an optimal anti-condensation measure for the target digital substation according to a prediction result, and completing condensation monitoring of the target digital substation. According to the method, the environmental parameters of the digital substation are acquired and processed, and the condensation prediction model is established, so that the condensation monitoring of the digital substation is realized, the reliability is higher, and the accuracy is better.
Owner:STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED +2

Thread trimming method of double-moving knife thread trimming mechanism

The technical scheme belongs to the technical field of sewing machines, and specifically relates to a thread trimming method of a thread trimming mechanism with double movable knives, comprising a frame, a thread trimming mechanism and a rotary shuttle mechanism; the thread trimming mechanism comprises a first movable knife assembly, a second movable knife assembly and a driving assembly; the first movable knife assembly and the second movable knife assembly are both rotatably sleeved on the outer side of the adapted rotary shuttle mechanism; the driving assembly drives the first movable knife assembly to rotate around an axis between a first position and a second position, and drives the second movable knife assembly to move around the axis between a third position and a fourth position; the first movable knife assembly comprises a thread trimming movable knife 1, which is provided with a thread hole groove for a machine needle to pass through and hook the sewing thread in the sewing start stage, and a thread hooking groove 1 for the sewing thread to hook into in the finishing stage; the second movable knife assembly comprises a thread trimming movable knife 2; the thread hole groove or the thread hooking groove 1 hooks the sewing thread, drives the thread trimming movable knife 2 to rotate around the axis until it abuts against the surface of the thread trimming movable knife 1, and the cutting edges of the two thread trimming movable knives overlap to cut the sewing thread, thereby reducing thread ends and improving production efficiency.
Owner:ZHEJIANG DUMA SEWING MACHINE

Black tea processing equipment supervision system

The invention discloses a black tea processing equipment supervision system, which relates to the technical field of food processing, and timely captures subtle environmental changes by monitoring a temperature fluctuation parameter Tw and a humidity fluctuation parameter Hw in a fermentation and drying process in real time and utilizing data of a temperature and humidity regulation and control analysis module and a sensor. Environment adjustment is carried out according to the fluctuation response speed coefficient Wrs and the temperature and humidity debugging coefficient Twhc, and the problem that the sensitivity of the system to parameter fluctuation is insufficient is solved; the durability Cnj, the offset Cpy and the response time Cxy of the sensor are evaluated in real time through the sensor detection unit, so that the precision and the stability of the sensor in a high-temperature and high-humidity environment are ensured, and the influence on quality monitoring due to sensor failure is avoided; meanwhile, the data processing module carries out noise filtering and standardization processing on environmental data, data accuracy is ensured, the problem that system data integration is insufficient is solved, data sharing among all procedures is smooth, and the overall production efficiency and the black tea quality stability are improved.
Owner:闽榕茶业有限公司

RSVP type unbalanced electroencephalogram signal classification method based on adaptive channel mixed attention mechanism and decoupling learning

The invention provides an RSVP type unbalanced electroencephalogram signal classification method based on a self-adaptive channel mixed attention mechanism and decoupling learning, and aims to improve the feature extraction and classification performance of RSVP electroencephalogram signals. Firstly, collected RSVP electroencephalogram signals are preprocessed, including common average reference, band-pass filtering and standardization processing, and a training set and a test set are divided; then, multi-scale time and space features are extracted through a parallel convolution layer and a space convolution layer, and the features of different levels are fused through an interpolation method; the training process is decoupled into representation learning and classifier learning, the representation learning uses a triple loss function based on difficult sample sampling, and the classifier learning uses the optimized Focal Loss to perform feature learning and classifier optimization. A self-adaptive channel mixed attention mechanism is introduced, and the flexibility and robustness of the model are enhanced through dynamic weighting and multi-level feature fusion. According to the method, the problem of class imbalance in the RSVP task is solved.
Owner:BEIJING UNIV OF TECH

Alpine region logging data cloud storage system

The invention relates to the technical field of cloud storage, in particular to an alpine region logging data cloud storage system which comprises a network quality monitoring module, a data grading module, a dynamic bandwidth management module and an intelligent data migration module. According to the invention, by collecting the historical data of the network indexes and calculating the score of the current network state, the network condition is effectively evaluated, the data transmission strategy is optimized, the reliability and efficiency of data transmission are enhanced, priority rating is carried out according to the importance and emergency degree of the data, key data can be transmitted preferentially, the network congestion is effectively reduced, and the data transmission efficiency is improved. The data transmission efficiency is improved, the accuracy and the response speed of data management are optimized, the data access speed is improved by predicting the access frequency of the data and dynamically adjusting the storage medium, the storage cost is reduced, the overall data processing capacity and the cost effectiveness are improved, and the method is suitable for popularization and application. And the security and the quick accessibility of the key data in a severe environment are ensured.
Owner:CHINESE ACAD OF GEOLOGICAL SCI +1

Material simulation test method and platform for mold flow analysis

The invention provides a material simulation test method and platform for mold flow analysis, and relates to the technical field of material simulation testing, and the method comprises the steps: carrying out the product demand analysis of a target test material, and obtaining the product demand information; performing injection molding analysis to obtain an injection molding control parameter threshold; obtaining an injection molding simulation test model; carrying out an injection molding simulation test, and carrying out image pre-acquisition to obtain a first pre-acquired image; defect feature analysis is carried out, attention area distribution is carried out, and a target attention area is obtained; an injection molding defect area image is obtained, and defect feature information is obtained; and feedback testing and parameter optimization are carried out, optimized injection molding control parameters are obtained, and injection molding control is carried out. The technical problems that in the prior art, injection molding analysis generally depends on a fixed mathematical model and limited technological parameters, and problems in the molding process cannot be recognized and adjusted in real time, so that the production efficiency and the product quality are low are solved.
Owner:SUZHOU BANGKESI INFORMATION TECH CO LTD

Three-dimensional geological model construction method based on multi-source data fusion

The invention belongs to the technical field of three-dimensional geologic modeling, and particularly relates to a three-dimensional geologic model construction method based on multi-source data fusion, and the method comprises the steps: 1, extracting drilling data, and constructing a drilling database; 2, constructing a topographic and geomorphic surface model, and completing the fusion of topographic and geomorphic data and drilling data; 3, coupling information of strata, rock mass, fracture, ore body and the like, and constructing a geologic body comprehensive model; 4, extracting geophysical and geochemical data, and constructing a geophysical model and a geochemical model; and 5, coupling the borehole database, the landform surface model, the geologic body comprehensive model and the geophysical model, and constructing a multi-source data fused three-dimensional geologic model. The method improves the accuracy and precision of the three-dimensional geologic model, improves the data processing and analysis speed, improves the data analysis capability and depth, provides technical support for uranium resource potential analysis and prediction exploration, and guides uranium exploration.
Owner:BEIJING RES INST OF URANIUM GEOLOGY

Terminal data automatic backup and recovery method and system

The invention discloses a terminal data automatic backup and recovery method and system, and relates to the technical field of data backup and recovery, and the method comprises the steps: dynamically adjusting the priority, and generating a personalized backup strategy; capturing data change in real time and executing incremental backup; and encrypting the backup data for version recovery. According to the terminal data automatic backup and recovery method provided by the invention, accurate analysis and priority division are performed on the terminal data through the classification model, so that the backup plan can be dynamically adjusted according to the importance of the data in the backup process. Data change is captured in real time, incremental backup is executed, and the real-time performance and efficiency of backup are effectively improved. An incremental backup algorithm is adopted, only a file change part is recorded, and a change area of a data block is quickly positioned by utilizing hash value comparison, so that the requirement of a storage space is reduced, and meanwhile, the transmission overhead of backup data is reduced. According to the method, better effects are achieved in the aspects of backup real-time performance, backup accuracy, backup pertinence and backup efficiency.
Owner:GUIZHOU POWER GRID CO LTD

Surface water river-entering sewage draining exit pollution abnormity tracing method based on intelligent internet of things

The invention discloses a surface water river-entering sewage draining exit pollution abnormity tracing method and device based on intelligent Internet of Things. The method comprises the following steps: constructing a database according to surface water pollution basic data; all pollution sources in the database are divided into different levels of pipeline logic relations according to the upstream and downstream communication relation of the land parcel area, the pipe network and the water system, and a pollution source-land parcel-pipe network-monitoring station intelligent Internet of Things grid is constructed; carrying out preprocessing and feature analysis on all data in the intelligent Internet of Things grid to construct a model database; a traceability model and a pollution contribution model are built based on the model database, the traceability model is used for calculating the pollution contribution rate of each pollution source, and a target discharge port or a target pollution discharge node is determined according to the pollution contribution rate; the pollution contribution model is used for generating and displaying a pollution contribution value of the target discharge port or the target pollution discharge point in response to an input instruction. The problem that a pollution source cannot be quickly and accurately determined in surface water environment management is solved.
Owner:BEIJING LONGTAO ENVIRONMENTAL REMEDIATION CO LTD +1

Road service life comprehensive evaluation and analysis method and system

The invention discloses a road service life comprehensive assessment analysis method and system, and relates to the technical field of road health assessment, and the method comprises the steps: collecting and preprocessing road multi-dimensional data, and extracting road features based on the preprocessed multi-dimensional road data; performing space-time correlation analysis on the road features, and constructing a road life evaluation data framework; preliminarily calculating a road health index by using the road health prediction model based on the road life evaluation data framework; dynamically adjusting the comprehensive weight of the road features by combining the preliminarily calculated road health index and historical data; and according to the adjusted comprehensive weight of the road feature, updating a road health index, and evaluating a road safety level. According to the method, the problems of insufficient multi-dimensional data integration and lack of dynamic analysis are solved, the scientificity and the practical application value of an evaluation result are remarkably improved, and a reliable basis is provided for road management and safety decision making.
Owner:JILIN COMM POLYTECHNIC

Hybrid collision detection method in virtual operation simulation system

The invention discloses a mixed collision detection method in a virtual operation simulation system. The method comprises the following steps: 1) constructing a surgical instrument and soft tissue model; 2) dividing a virtual space into grids with the same size, indexing an object model, accelerating the construction and updating of a spatial information hash table by utilizing GPU multithreading, mapping the grids occupied by all primitive bounding boxes into the hash table, and determining objects in the same space according to the spatial hash table; 3) before object intersection solving, space reduction is carried out, and hash table data is optimized; 4) constructing a hierarchical bounding box for an object which may collide, and performing intersection detection; if it is detected that a certain node or child nodes of the node intersect, the next step is executed, and otherwise, detection is pushed out; and 5) accurately judging whether the basic triangular units contained in the nodes in the step 4) are intersected or not, and completing collision detection. According to the method, the problem of missed detection and wrong detection in the existing discrete collision detection algorithm is effectively solved, and the detection algorithm has excellent accuracy and calculation efficiency.
Owner:NANCHANG UNIV

Low-light image denoising method based on local-global interactive Transform

The invention discloses a low-light image denoising method based on a local-global interactive Transform, and the method is characterized in that the method comprises the following steps: 1, carrying out the denoising of a low-light image; the method comprises the following steps: step 1, constructing an overall structure of LGIT for recovering a given degraded image; 2, a Top-N Patches selection module is used for selecting N patches most related to the target patch and providing feature input for subsequent modules; step 3, the Patch selects an attention Transform module, and the Transform module is used for carrying out global feature aggregation based on the information of Top-N Patches; and step 4, mixing the double-gate feed-forward network MDGFF for further processing the features output by the PSATB and generating a final de-noised image. According to the method, the self-attention inside the patch and between the patches is effectively calculated on different scales, and accurate removal and detail recovery of low-light image noise are realized.
Owner:ZHONGBEI UNIV

Mineral trace element analysis method using microscopic Raman spectrum

The invention discloses a method for analyzing mineral trace elements by utilizing a micro-Raman spectrum, which comprises the following steps of: fixing a mineral sample on a rotary sample table of a micro-Raman spectrometer, selecting an area to be detected by combining a micro-imaging technology, collecting a Raman background signal under the pre-illumination of low-power laser, and analyzing the trace elements in the area to be detected according to the Raman background signal. The laser focal length, the spot size and the incident angle are adjusted accordingly, the laser is focused on a target area, under the calibrated laser condition, through a multi-angle excitation micro-area, after an algorithm is applied to optimize signals, reduce impurity interference and integrate multi-angle Raman signals, the characteristic spectrum information of the microelements can be extracted, and the microelements can be accurately detected. High-resolution analysis of sample components is realized, and a three-dimensional distribution model of microelements in a microcell is constructed in combination with microscopic imaging data. The method has the characteristics of non-destructiveness, high resolution and rapid detection, and is suitable for mineral component analysis in the fields of geology, material science and the like.
Owner:HEZHOU UNIV

Ultra-deep soft soil foundation pit safety evaluation method and system

The invention relates to the technical field of safety evaluation, in particular to an ultra-deep soft soil foundation pit safety evaluation method and system, and the method comprises the following steps: obtaining the geological data of an ultra-deep soft soil foundation pit, recording the soil type, soil density, underground water level and temperature data, carrying out the data arrangement and formatting, and generating a geological data record sheet. According to the method, the detailed geological data of the ultra-deep soft soil foundation pit are acquired and arranged, the accuracy and the applicability of the basic data are enhanced, so that subsequent analysis is carried out according to clear actual conditions, and the timeliness and the accuracy of risk prediction are ensured by directly associating prediction of mechanical behaviors with risk assessment; the risk assessment model can be dynamically adjusted, the effectiveness and accuracy of early warning are improved, the risk dependency relationship model and the monitoring scheme are integrated, theoretical and actual operations are effectively linked, the systematicness and adaptability of construction safety management are effectively improved, and the accident prevention capability is remarkably improved.
Owner:OPEN UNIVERSITY OF CHINA

Carbon emission prediction method and system

The invention discloses a carbon emission prediction method. The method comprises the following steps: acquiring carbon emission data information of a target area; performing carbon emission data accounting of the target area based on the carbon emission offset data; constructing a carbon emission prediction model of the target area; and performing carbon emission prediction of the target area based on the set scene information by adopting the carbon emission prediction model. The invention also discloses a system for realizing the carbon emission prediction method. According to the carbon emission prediction method and system provided by the invention, through the acquisition of the historical data, the accounting of the carbon emission data and the construction and evaluation of the prediction model, the prediction of the carbon emission of the target object in the whole life cycle is realized, and the reliability is higher and the accuracy is better.
Owner:STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED +2

Precast beam size matching method and system based on three-dimensional laser scanner

The invention relates to the technical field of medium and small span bridge construction and control, in particular to a precast beam size matching method and system based on a three-dimensional laser scanner, and the method comprises the steps: obtaining precast beam point cloud data, carrying out the preprocessing of the precast beam point cloud data, carrying out the registration of the preprocessed precast beam point cloud data with a BIM model, and obtaining the size of a precast beam. The automatic detection of the structure size is realized; then, by obtaining interface angular points of the precast beams, conducting virtual splicing by aligning the cross section angular points of the adjacent precast beams, simulating the field splicing process and obtaining key construction details, accurate and reliable data support is provided for follow-up construction, it is ensured that each beam section can conform to design specifications during splicing, and therefore potential safety hazards are reduced; the controllability and scientificity of the construction process are improved, the construction efficiency is improved, the construction period is shortened, the service life of the bridge structure is prolonged, and the structural reliability is improved. The problems of low precast beam parameter detection efficiency, high operation difficulty and low accuracy in the prior art are solved.
Owner:XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY

Kitchen garbage shielding object recognition and shielding relation judgment method

The invention discloses a kitchen garbage shielding object recognition and shielding relation judgment method, which comprises the following steps of: constructing a shielding data set of a kitchen garbage image, and marking visible masks, complete masks and categories of target objects in the shielding data set; firstly, an instance segmentation model and a mask restoration model are trained by using an occlusion data set; the input of the instance segmentation model is the kitchen garbage image, and the output is the category and the visible mask of each target object; the input of the mask restoration model is a visible mask and a kitchen garbage image output by the instance segmentation model, and the output of the mask restoration model is a complete mask; secondly, for a kitchen garbage image to be identified and judged, using the trained instance segmentation model and mask restoration model to obtain the category, visible mask and complete mask of each target object; and finally, judging whether each target object is shielded and judging a shielding relationship by combining the visible mask and the complete mask. According to the method, instance segmentation and mask restoration are carried out on the recyclable garbage, and the category, the position, the shielding relation and the complete shape information of the object can be obtained.
Owner:HUNAN UNIV

Data prediction method based on kernel regression primary function Bayesian dynamic linear model

The invention discloses a data prediction method based on a kernel regression primary function Bayesian dynamic linear model, and belongs to the technical field of bridge structure health prediction. A to-be-analyzed bridge is detected by using a structural health monitoring system (SHM), and a time series dynamic model KR-BDLM of a Bayesian dynamic linear model is established to describe a bridge structure strain response changing along with time, so that bridge structure health monitoring data prediction and missing value filling are realized; performing parameter optimization reasoning on parameters of the KR-BDLM model by adopting a maximum likelihood algorithm; providing a time-varying state parameter and an observation prediction value of a bridge structure through the optimized KR-BDLM model, and further realizing SHM monitoring data single-step prediction; and multi-step prediction is carried out on the basis of single-step prediction, so that longer-time prediction of bridge data is realized. The prediction result is high in precision, the engineering structure safety can be effectively guaranteed, and the leading-edge development of the structure health monitoring field is promoted.
Owner:CHINA UNIV OF MINING & TECH

CFD-DEM processing method and system for particles in any shape based on improved immersion boundary and directed distance field

ActiveCN119047285AAccurately accommodateGood calculation efficiencyDesign optimisation/simulationConstraint-based CADParticle flowComputational simulation
The invention discloses a CFD-DEM processing method and system for particles in any shape based on an improved immersion boundary and a directed distance field, and the method comprises the steps: creating a fluid model corresponding to the particles in any shape, and generating first data corresponding to the fluid model; constructing a corresponding first model in real time according to the first data in combination with a directed distance field or an improved immersion boundary; through the first model, performing real-time CFD-DEM processing on particles in any shape, and generating particle behavior data corresponding to the particles in any shape and in a multi-phase particle flow; the invention further discloses a corresponding system and platform, and a universal particle modeling method capable of accurately containing various shape features of the particles and providing the optimal calculation efficiency. That is to say, the scheme has good precision and stability, and has potential to better simulate the behavior of the particles in a complex fluid environment in effective calculation and simulation processing of the multiphase particle flow involving the particles in any shape.
Owner:SUN YAT SEN UNIV +1

Rock mass instability grading early warning method and system based on micro-seismic feature perception and classification enhancement algorithm

The invention discloses a rock mass instability grading early warning method based on micro-seismic feature perception and a classification enhancement algorithm. The method comprises the following steps: acquiring rock mass instability case data information of different geotechnical engineering projects; selecting a plurality of microseismic parameters as rock mass instability risk candidate evaluation indexes, and performing correlation analysis to obtain rock mass instability grading early warning evaluation indexes; constructing a training data set; constructing a rock mass instability grading early warning primary model based on a classification enhancement algorithm and a genetic algorithm, and training to obtain a rock mass instability grading early warning model; and the obtained rock mass instability grading early warning model is adopted to complete rock mass instability grading early warning based on micro-seismic feature perception and a classification enhancement algorithm. The invention also discloses a system for realizing the rock mass instability grading early warning method based on the micro-seismic feature perception and classification enhancement algorithm. According to the method, rock mass instability grading early warning based on micro-seismic feature perception and a classification enhancement algorithm can be realized, the reliability is higher, and the accuracy is better.
Owner:CENT SOUTH UNIV

Method for detecting 25 aldehyde ketone compounds in automotive trim materials and parts

The invention belongs to the field of indoor air quality detection, and particularly relates to a method for detecting 25 aldehyde ketone compounds in automotive trim materials and parts. Comprising the following steps: collecting a blank sample gas and a sample gas of a to-be-detected sample subjected to equilibrium placement heat treatment by using a DNPH sampling tube to obtain a blank tube and a sample tube, eluting by using acetonitrile respectively, and fixing the volume to obtain a blank solution and a sample solution. Preparing standard working solutions with different concentrations, analyzing by using a high performance liquid chromatograph, detecting by using a diode array detector, and drawing a standard working curve. And analyzing the blank liquid and the sample liquid by using a high performance liquid chromatograph, calculating the difference value between the peak area of the sample liquid and the peak area of the blank liquid, and combining with the standard curve to obtain the actual content of the 25 aldehyde ketone compounds in the sample to be detected after the background blank is deducted. The method provided by the invention can solve the problem that part of target objects are difficult to separate at the same time when various aldehydes and ketones are analyzed by the existing high performance liquid chromatography.
Owner:SHANGHAI HUATEST PINZHENG TESTING TECH CO LTD +1

Lamp panel and display device

The invention discloses a lamp panel and a display device, and relates to the technical field of mass transfer of lamp beads. The lamp panel comprises a bottom plate, a plurality of airflow acceleration assemblies, a mounting plate and a plurality of lamp beads, and an airflow channel is formed in the bottom plate; the plurality of airflow acceleration assemblies are arranged on the bottom plate; the mounting plate is arranged at the end, away from the bottom plate, of the airflow acceleration assembly, a first cavity is formed between the mounting plate and the airflow acceleration assembly, and the air outlet end is connected with the first cavity; the plurality of lamp beads are arranged on the mounting plate; gas enters an airflow acceleration assembly through an airflow channel in the bottom plate, the airflow drives an airflow acceleration part to work so as to pressurize and accelerate the airflow, the airflow is accelerated to enter a first cavity to jack up a mounting plate, and lamp beads on the mounting plate are made to vibrate so as to gradually complete lamp bead mounting; according to the lamp panel, mass transfer of the lamp beads is achieved through the structure of the lamp panel, and the requirement for mass transfer is lowered.
Owner:HKC CORP LTD

Solid-state laser radar and IMU robust tight coupling system under assistance of point cloud intensity

The invention provides a solid-state laser radar and IMU (Inertial Measurement Unit) robust tight coupling system under the assistance of point cloud intensity, which comprises the following steps of: firstly, pre-processing a solid-state laser radar point cloud by the system, eliminating point cloud defect points, correcting a point cloud intensity value and performing down-sampling; and then geometric feature extraction and intensity feature extraction are carried out on the preprocessed point cloud, and intensity calibration of the laser radar point cloud is carried out. And then compensating the motion of the point cloud by using the high-frequency prior information predicted by the IMU. For geometric and intensity feature point clouds, a classical registration method and a fast plane fitting method are respectively adopted to calculate residual errors, and an intensity feature assisted point cloud residual error measurement model is constructed. And a robust strategy based on an IGGIII robust weight function is designed by using a residual error estimation value in a filtering algorithm. According to the invention, on the premise of keeping relatively low calculation cost, the positioning and mapping capabilities and robustness of the small-view-angle laser radar tight coupling system in a complex environment are improved.
Owner:SOUTHEAST UNIV

Ship trajectory reconstruction method based on AIS data quality optimization

The invention discloses a ship trajectory reconstruction method based on AIS data quality optimization, and relates to the technical field of ship trajectory reconstruction, and the method comprises the following steps: S1, employing a box plot method to set speed and steering rate thresholds for each ship; s2, adopting a'segmentation-connection-filtering 'strategy to remove abnormal values and performing trajectory segmentation; s3, interpolation is carried out on missing tracks, short-distance missing is repaired by utilizing adjustment and kinematics principles, and effective migration is carried out on long-distance missing by a method of searching similar tracks; experiments verify that the method shows excellent performance when processing actual AIS data, can effectively recover missing ship trajectories, and provides reliable data support for maritime traffic safety and channel management.
Owner:HOHAI UNIV

Method for estimating position in ship cabin based on Bluetooth technology

The invention provides a method for estimating the position in a ship cabin based on the Bluetooth technology, and particularly belongs to the technical field of high-precision position services in the ship cabin. According to the method, weighted average fusion is carried out on an AoA angle estimation result obtained through direct data collection and an AoA angle estimation result obtained through calculation of a multi-element perceptron; according to the indoor positioning method for the ship cabin, the indoor positioning precision of the ship cabin is improved, and the indoor positioning method for the ship cabin has the advantages that the indoor positioning precision of the ship cabin is improved, the safety of personnel on the ship is guaranteed, and the positioning accuracy of the ship cabin is improved. And the ship operation service level is improved.
Owner:HARBIN ENGINEERING UNIVERSITY SANYA NANHAI INNOVATION & DEVELOPMENT BASE +1

Electronic nose system for identifying mixed gas based on sensing array and application

The invention relates to an electronic nose system for identifying mixed gas based on a sensing array and application. The electronic nose system is composed of a gas distribution system, a sensing array and a signal module, wherein the gas distribution system is composed of dynamic gas distribution equipment and a gas source; the sensing array is composed of a plurality of sensors; and the signal module carries out processing and mode identification on the signal through the upper computer development system. And the electronic nose system obtains response-recovery curve data and performs further processing and pattern recognition on the response-recovery curve data, so that accurate recognition of the low-concentration ethanol, ammonia gas and toluene mixed gas is realized. According to the invention, the mixed gas of low-concentration ethanol, ammonia gas and toluene can be accurately identified, the gas concentration can be accurately judged, and the method has a potential application prospect in monitoring ethanol, ammonia gas and toluene gas in environments such as atmosphere, chemical plants and homes.
Owner:CHENGDU YALIAN TECH CO LTD

Obstacle framing method based on laser point cloud in converter station scene

The invention relates to the technical field of obstacle detection, in particular to a laser point cloud-based obstacle framing method in a converter station scene, which comprises the following steps of: based on a converter station environment, performing three-dimensional scanning through a laser radar, collecting point cloud data, performing noise filtering on the data, performing spatial alignment of the data, and obtaining processed point cloud data. According to the invention, three-dimensional scanning is carried out through the laser radar, the scanning angle and the resolution are adjusted, the coverage rate and the precision of the point cloud data are optimized, the point cloud data are mapped to the adjacent grid center, the data structure is simplified, the point cloud data are horizontally cut, the linear features of the electric wire are identified, and the obstacle identification process is optimized. Through combination of spatial statistical analysis and clustering analysis, the accuracy and the meticulous degree of obstacle recognition are improved, and the obstacles are framed by constructing a bounding box of each obstacle, so that three-dimensional space positioning and form recognition of the obstacles are realized.
Owner:TIANSHENGQIAO BUREAU CSG EHV POWER TRANSMISSION CO

Power system load prediction method and system based on meteorological evolution process

The invention discloses an electric power system load prediction method based on a meteorological evolution process. The method comprises the following steps: constructing a target electric power system load prediction index set comprising meteorological factors; obtaining corresponding historical data and future prediction data to construct a historical data set and a future data set; performing threshold judgment on the temperature change of the day to be predicted; constructing a training data set and training the load prediction primary model to obtain a load prediction model; and adopting the load prediction model to carry out actual load prediction based on the meteorological evolution process on the target power system. The invention also discloses a system for realizing the power system load prediction method based on the meteorological evolution process. According to the invention, through processing and matching of historical meteorological data and meteorological data on a prediction day, a data set conforming to a prediction condition is constructed, and a load prediction model is adopted to learn the data set; therefore, the method not only can realize power system load prediction based on the meteorological evolution process, but also is higher in reliability and better in accuracy.
Owner:STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED +2