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

53results about How to "Strong precision" patented technology

Congestion data fusion method based on Internet map

The invention discloses a fusion method based on Internet map congestion data. The fusion method comprises the following steps: acquiring congestion data according to different Internet map companies; performing parameter data cleaning on the acquired congestion data to obtain cleaned data; respectively inputting one piece of congestion data and one piece of corresponding cleaned data into a fusion algorithm according to a sequence, and judging until a repeatedly congested road section is obtained; and fusing the repeatedly congested road sections to obtain a fusion result. According to the invention, multi-party navigation map congestion data can be fused, false information is eliminated, and a standardized congestion road condition result is identified and output in real time.
Owner:ROAD TRAFFIC SAFETY RES CENT THE MINIST OF PUBLIC SECURITY OF THE PEOPLES REPUBLIC OF CHINA

Power line loss calculation and prediction method based on deep learning and error correction

The invention discloses a power line loss calculation and prediction method based on deep learning and error correction, and relates to the technical field of power line loss calculation, and the method specifically comprises the steps of power data information collection, data cleaning and preprocessing, data feature extraction, model building, error correction and precision improvement, and hyper-parameter optimization. According to the method, the advantages of support vector regression and a bidirectional long short-term memory network are fused, and a CNN-BiLSTM-SVR calculation model with high robustness is constructed through deep mining and effective utilization of related data in a power system; the problems of complexity and low efficiency of the traditional line loss calculation method in processing large-scale data are solved by introducing a deep learning technology, especially BiLSTM; error correction is carried out on the preliminary calculation result of the model through SVR, the accuracy of line loss calculation is further improved, the efficiency of line loss calculation is improved, the accuracy of the calculation result is ensured, and powerful technical support is provided for optimization management of a power system.
Owner:TAIAN POWER SUPPLY CO OF STATE GRID SHANDONG ELECTRIC POWER CO +1

Image classification method and system based on potential domain and category diversity

The invention relates to the technical field of image classification, in particular to an image classification method and system based on potential domains and category diversity. The method comprises the following steps: acquiring image data, including acquiring image data of a source domain and a target domain; preprocessing the image data of the source domain and the target domain; constructing a domain adaptive image classification model; performing model training on the constructed domain adaptive image classification model; and carrying out image classification by using the trained domain adaptive image classification model. According to the method, the distribution difference of the source domain and the target domain is gradually aligned by generating the potential domain, and the source domain, the potential domain and the target domain are consistent in feature distribution by adopting a class-level and domain-level multi-level alignment strategy, so that the precision of the model in a cross-domain classification task is remarkably improved.
Owner:YANTAI UNIV

Small target detection model in unmanned aerial vehicle aerial photography scene

The invention relates to the technical field of aerial image detection and the technical field of small target detection, in particular to a small target detection model in an unmanned aerial vehicle aerial scene, which is characterized in that an aerial image data set is acquired, an improved YOLOv8s model is trained by adopting the aerial image data set, and the improved YOLOv8s network model comprises a backbone feature network, a detection head and a loss function; an SPD-Conv module is introduced into a P2 layer, a P3 layer, a P4 layer and a P5 layer of the backbone feature network, a Dynamic Head module is introduced into a detection head, a specific small target detection head (SODH) is added, Shape-IoU is used as a loss function, and a to-be-detected aerial image is input into a trained improved YOLOv8s model for detection; the SDSS-YOLOv8 not only can execute a small target detection task in an aerial image shot by an unmanned aerial vehicle, but also has good performance in the aspect of small target detection in an unmanned ship image, the model has strong generalization ability, and although the image environment and target distribution have changes, the SDSS-YOLOv8 can maintain high detection performance in different scenes.
Owner:HUBEI UNIV +1

Statistical method for CPU occupancy rate of SMP architecture real-time operating system, electronic equipment and medium

The invention provides an SMP architecture real-time operating system CPU occupancy rate statistical method, electronic equipment and a medium, and the method does not depend on redundant external hardware equipment, does not need to independently create a statistical task occupying CPU running time, and utilizes a timer generating Tick interruption in an operating system to calculate the CPU occupancy rate of the operating system. Through the scheduler-level high-precision statistics of the operation time of the observed task and the calibration of the total operation time of the CPU, the operation time of the observed task and the total operation time of the CPU are displayed in an accurate granularity, and the CPU occupancy rate of the strong real-time task can be accurately measured. By applying the technical scheme provided by the invention, the technical problem of measurement distortion of the CPU occupancy rate of the strong real-time task in the prior art is solved.
Owner:BEIJING AUTOMATION CONTROL EQUIP INST

Laser rapid detection device and method for heavy metal in solid fuel

The invention belongs to the field of flue gas detection, and particularly discloses a laser rapid detection device and method for heavy metal in solid fuel, and in the detection device, a sample unit is used for placing a sample to be detected; the laser generating unit is used for emitting incident laser to a sample to be measured, the microwave generating unit is used for coupling microwaves to the incident laser, when the content of heavy metal is measured, the laser intensity is 100-300 mJ / fuse, the microwave power is 160-200 W, when the form of the heavy metal is measured, the laser intensity is 40-140 mJ / fuse, and the microwave power is 100-150 W; and the signal receiving unit is connected with the data processing unit. The method does not need to perform pretreatment on the to-be-detected sample, can realize in-situ online detection of the heavy metal in the solid fuel, can realize detection of the content and form of the heavy metal by adjusting the laser intensity and the microwave power, and has the advantages of high speed, high sensitivity, strong accuracy and the like.
Owner:HUAZHONG UNIV OF SCI & TECH

Method for detecting a target on a road using roadside equipment and roadside equipment

The present invention discloses a method for detecting a target on a road using a roadside device, a roadside device, and a computer-readable medium. The roadside device includes a first sensor and at least one second sensor, the first sensor is based on ultra-wideband technology, and the second sensor includes at least one of a camera, a radar, and a laser radar. The method includes: acquiring target detection data from the first sensor and the second sensor; determining a new detection target list based on the target detection data, the new detection target list includes at least one target and its position; performing target matching based on the new detection target list and a historical detection target list to generate a matched detection target list, the historical detection target list includes at least one previously detected target and its position; fusing the positions of the targets in the matched detection target list to generate a fused detection target list; and outputting the fused detection target list and / or the positions of the targets in the fused detection target list.
Owner:欧摩威软件系统开发(重庆)有限公司

A diagnostic agent for identifying melanoma molecular subtype classification and application thereof

The application relates to the field of biomedical technology, and discloses a diagnostic agent for identifying melanoma molecular subtype typing and application, wherein the diagnostic agent comprises a first antibody specifically combined with a SOX10 protein and a second antibody specifically combined with an EGR1 protein; the diagnostic agent can be applied to preparation of a diagnostic product for evaluating the prognostic effect of a melanoma patient, preparation of a diagnostic product for predicting the treatment sensitivity of melanoma to a BRAF inhibitor, and preparation of a diagnostic product for guiding an individualized treatment scheme of melanoma. The diagnostic agent for melanoma molecular subtype typing can be directly transformed into clinical practice, and can assist in realizing real individualized treatment.
Owner:NANKAI UNIV

Assembling structure of sub-control valve electric explosion driving firing pin

The utility model discloses an assembling structure of a sub-control valve electric explosion driving firing pin, which comprises a workbench for placing a valve body, a correlation sensing unit arranged on one side, far away from the valve body, of the workbench, and a distance adjusting assembly fixedly arranged on the workbench and used for adjusting the limit distance between the correlation sensing unit and the valve body. According to the assembling structure of the sub-control valve electric explosion driving firing pin, the length, exceeding the valve body, of the firing pin is monitored through the correlation sensing assembly when the firing pin is assembled, press fitting failure of the firing pin and component interference caused by the fact that the firing pin exceeds the limit distance are avoided, and compared with a manual measurement mode, the assembling structure is higher in accuracy, higher in detection efficiency and higher in practicability. And meanwhile, the limiting distance between the correlation sensing unit and the valve body can be adjusted through the distance adjusting assembly, so that the monitoring and alarming range of the penetrating length of the firing pin is widened, and the overall applicability and practicability of the device are higher.
Owner:ZEPHYR INTELLIGENT SYST (SHANGHAI) CO LTD

Trolley control system integrating functions of tracking, fire searching and extinguishing and obstacle avoidance

The invention discloses a trolley control system integrating functions of tracking, fire searching and extinguishing and obstacle avoidance. Belongs to the technical field of vehicle control systems and comprises a chip module, four tracking modules, four obstacle avoidance modules, five flame sensing modules, a power circuit, an L298N driving module, a steering engine module, an L9110 driving module, a motor 1 and a motor 2 which are connected with one another. The invention discloses a tracking trolley control system with a single-chip microcomputer as a core. The system is a control system for realizing the capability of self-handling various emergencies in a specified range of the intelligent trolley. The system has the characteristics of high flexibility, labor cost saving, safety, reliability, energy conservation, environmental protection, strong expandability, easy maintenance, high precision and the like.
Owner:XUZHOU NORMAL UNIVERSITY

A nonlinear time-series estimation method for the state of health of lithium batteries

This invention provides a nonlinear time-series estimation method for the state of health (SOH) of lithium batteries, comprising: collecting feature data during the charge-discharge cycle of the lithium battery and generating a multi-channel standardized time-series dataset; extracting features and compressing dimensions of the data through an encoder; reconstructing and denoising the data through a decoder to output sequence features; mining the global correlation between feature sequences to obtain a context vector; further obtaining the SOH estimation result and synchronously updating the parameters. This method effectively suppresses model overfitting while introducing an improved KL divergence to prevent posterior collapse, achieving high-precision and robust estimation of the SOH of lithium batteries.
Owner:YANCHENG INST OF TECH

Cutting device for standard seamless steel pipe machining

The utility model relates to the technical field of steel pipe cutting devices, and discloses a cutting device for processing standard seamless steel pipes, which comprises a workbench, a placing device arranged at the top of the workbench, and a cutting device arranged at the top of the workbench. And the cutting device comprises a sliding plate, a mounting screw, a screw hole, a limiting sliding seat, a first motor, a cutting knife, a collecting box, an absorbing hopper part, a wafer, a connecting thin rod, a negative pressure fan, a top end connecting strip, a second motor, a screw rod, a threaded sleeve and a limiting L-shaped sliding frame. According to the cutting device for machining the standard seamless steel pipe, the cutting device is arranged, a mounting screw is screwed into a screw hole and a connecting screw hole, a cutting assembly is adjusted front and back, and the cutting position can be further adjusted, so that the cutting device is provided with the cutting assembly capable of transversely moving without adjusting the position of a steel pipe during cutting; and in addition, the precision of manually adjusting the position of the steel pipe is high, and the cutting precision cannot be affected.
Owner:DALIAN HENGXIN MASCH CO LTD

Liquid flow measurement structure and measurement system applying the same

The present disclosure relates to a liquid flow measurement structure and a measurement system using the same. The measurement structure comprises a flow channel body, an electrode sheet assembly arranged inside the flow channel body, the electrode sheet assembly comprising a plurality of capacitive sensing electrode sheets, and a digital capacitive sensing assembly connected to the electrode sheet assembly through signal lines, configured to collect capacitive signals of the plurality of capacitive sensing electrode sheets and output capacitive data associated with liquid level height. The plurality of capacitive sensing electrode sheets are arranged in a multi-layer grid structure inside the flow channel body, the multi-layer grid structure is distributed along the flow direction of the flow channel body, and a single layer grid structure is configured to arrange a single capacitive sensing electrode sheet. Alternatively, part of the capacitive sensing electrode sheets in the electrode sheet assembly are arranged in the sidewall of the flow channel body. The present disclosure has the advantages of simple structure, low cost, high reliability, and adaptability to various extreme application scenarios.
Owner:SUZHOU RONGQI SENSOR TECH CO LTD

A hot die casting water-soluble ceramic core for light alloy investment casting and a preparation method thereof

The present invention discloses a hot-die casting water-soluble ceramic core for light alloy investment casting and a preparation method thereof. The hot-die casting water-soluble ceramic core comprises fused corundum powder, potassium sulfate, plasticizer, lubricant and surfactant in a weight ratio of 60-80:7.7-30:10-15:1-2:1-2, wherein paraffin wax, beeswax, polyethylene, stearic acid and oleic acid are included in a weight ratio of 90-95:2-4:2-4:1-2:1-2. The core is formed by a hot-die casting method and then sintered at high temperature. The hot-die casting ceramic core of the present invention uses refractory aggregate and inorganic salt to form the base material of the ceramic core. Compared with the existing salt core, the core has the advantages of strong stability and high precision, reduces the amount of water-soluble salt used, and maintains good water-soluble disintegration. The hot-die casting process can meet the needs of actual production for complex-shaped cores.
Owner:SOUTHEAST UNIV

Multi-source heterogeneous data analysis method and system for CNC machine tools based on edge-cloud collaboration

The present invention is applicable to the technical field of CNC machine tool data processing, and proposes a method and system for analyzing multi-source heterogeneous data of CNC machine tools based on edge-cloud collaboration. The analysis method adopts an edge-cloud collaborative architecture, and the analysis system includes a data acquisition source, an edge data lightweight processing node, and a cloud data enhancement processing node. The data acquisition source is responsible for building a hardware system for multi-source data acquisition; the edge data lightweight processing node matches the communication protocol of the CNC machine tool multi-source heterogeneous data and collects the CNC machine tool multi-source heterogeneous data, and pre-processes the processing process data, machine tool status data, component audio data, and workpiece image data; the cloud data enhancement processing node evaluates the performance status of the data analysis model and makes a data set increment judgment based on the performance status, and dynamically updates the data analysis model. The present invention realizes high-efficiency, high-precision, and intelligent analysis of the machine tool status through the coordinated cooperation of the edge data lightweight processing node and the cloud data enhancement processing node.
Owner:JILIN UNIVERSITY

A deep learning-based image segmentation method

The invention discloses an image segmentation method based on deep learning. First, a semantic segmentation model is constructed; the semantic segmentation model is composed of a backbone network, an XY network and a full convolution decoding network; the input of the backbone network forms the input of the semantic segmentation model, the output of the backbone network is connected to the input of the XY network, the output of the XY network is connected to the input of the full convolution decoding network, and the output of the full convolution decoding network is the output of the semantic segmentation model; then, the semantic segmentation model constructed in step 1 is trained using a segmented sample image set to obtain a trained semantic segmentation model; finally, the image to be segmented is sent to the trained semantic segmentation model obtained in step 2, and the trained semantic segmentation model outputs a segmented picture. The XYNet of the invention has achieved good results in robustness, evaluation index, reasoning speed, model size, reasoning floating-point calculation number and image visualization results, and is more balanced than the existing network.
Owner:GUILIN UNIV OF ELECTRONIC TECH

Automatic river curve contradiction detection method

The embodiment of the invention provides an automatic river curve contradiction detection method, and relates to the technical field of geographic information data processing, and the method comprises the following steps: generating river element data and contour line element data through vector map data, traversing the river element data and the contour line element data, and calculating a river curve contradiction; the intersection points and the elevation values corresponding to the intersection points are stored in the river element data; elevation values of all points corresponding to each river element in the river element data are obtained, and all the points of the river elements are sorted according to the descending order of the elevation values; traversing the intersection point coordinate list, calculating to obtain a first direction angle corresponding to the first vector line segment, and calculating to obtain a second direction angle corresponding to the second vector line segment; and judging whether the river element curve has contradiction or not through the angle of the first direction angle, the angle of the second direction angle and the sensitivity value. According to the scheme, through automatic detection, the river curve contradiction detection efficiency is improved.
Owner:Chinese People's Liberation Army Cyberspace Force Information Engineering University

Dual-path nitrous dioxide measurement system and method based on blue laser

The present application relates to a kind of dual optical path nitrogen dioxide measurement system and method based on blue laser, using dual-wavelength laser cavity enhanced absorption spectroscopy technology, carries out NO2 absorption measurement under 405nm and 410nm wavelength, and combined with high reflectivity optical resonator, improve detection precision and sensitivity.Through dual-wavelength comparison method, using dual-wavelength absorption spectroscopy analysis, calculate absorbance difference, to effectively eliminate the influence of environmental factors on measurement accuracy, improve measurement reliability.Using more than 99.9% high reflectivity mirror, to realize high reflectivity optical resonator enhancement technology, laser is reflected in resonator multiple times, optical path is extended hundreds of times, improve NO2 absorption signal intensity, realize ppb grade ultra-low concentration measurement.Compared with traditional optical method, the system has lower cost, higher accuracy and stronger environmental adaptability, provides an efficient, stable solution for atmospheric pollution monitoring.
Owner:UNIV OF SHANGHAI FOR SCI & TECH

A hybridoma cell line capable of stably secreting monoclonal antibodies against conotoxin μ-KIIIA-CTX

The present invention specifically relates to a hybridoma cell line 3E11 that can secrete a monoclonal antibody against conotoxin μ‑KIIIA‑CTX. The classification name of the hybridoma cell line 3E11 is anti-conotoxin μ‑KIIIA‑CTX monoclonal antibody hybridoma cell line, which has been registered and deposited with the China General Microbiological Culture Collection Center on December 3, 2021, with a deposit number of CGMCC No. 45004. The anti-conotoxin μ‑KIIIA‑CTX monoclonal antibody secreted by the hybridoma cell line 3E11 has strong specificity, high affinity, and high titer. Based on the hybridoma cell line 3E11 and the monoclonal antibody secreted by it, the present invention establishes an ELISA immunoassay method, which can be applied to the detection of conotoxin μ‑KIIIA‑CTX, and has the advantages of high accuracy, high sensitivity, and easy operation.
Owner:FUJIAN AGRI & FORESTRY UNIV

Desert tree planting vehicle

A pit digging mechanism, a seedling feeding mechanism and a soil filling mechanism are arranged on a vehicle frame of the desert tree planting vehicle, the pit digging mechanism comprises a first driving part, a rotating rod and a spiral blade which are connected with the vehicle frame, the first driving part is in driving connection with the rotating rod and can drive the rotating rod to rotate, and the spiral blade is arranged at the end, facing the ground, of the rotating rod. The seedling conveying mechanism comprises a second driving part and a bearing body which are connected with the frame, and a seedling carrying guide rail and a seedling storage box which are arranged on the bearing body, a seedling falling opening is formed in the bearing body, and the second driving part is in driving connection with the seedling storage box and can drive the seedling storage box to move towards the seedling falling opening along the seedling carrying guide rail, so that a single seedling in the seedling storage box passes through the seedling falling opening; the soil filling mechanism comprises a third driving piece and a push plate which are connected with the frame, and the third driving piece is in driving connection with the upper portion of the push plate and can drive the push plate to reciprocate up and down. According to the automatic tree planting device, the tree planting efficiency is improved, the automatic tree planting process can be achieved, and the labor cost and the complexity of tree planting work are reduced.
Owner:HUNAN AGRI UNIV

Corrugated pipe machining positioning and clamping device

The utility model relates to the field of corrugated pipe machining, and discloses a corrugated pipe machining positioning and clamping device which comprises a base, a square groove is formed in the base, a support is fixedly connected to the interior of the base, a motor is fixedly connected to the top face of the support, the output end of the motor is fixedly connected with a worm, and the output end of the worm is fixedly connected with a clamping device. The worm is provided with clamping assemblies capable of moving inwards at the same time, one side of the worm is provided with a worm gear, the worm gear is meshed with a worm gear, and the worm gear is provided with a fixing assembly capable of moving inwards at the same time. According to the utility model, a worker starts the motor fixed on the top surface of the support, then the worm connected with the output end of the motor starts to rotate, and the first bevel gear fixedly connected with the outer wall of the worm starts to rotate, so that the working efficiency is improved, convenience and rapidness are realized, the time is saved, and the labor intensity of maintenance workers is greatly reduced; and therefore, the stability in use is improved, and the quality of the corrugated pipe is improved.
Owner:ZHONGSHAN OGELONG PLASTIC CO LTD

High-precision wide-range displacement sensor based on grating technology

The invention relates to a high-precision wide-range displacement sensor based on a grating technology. The device comprises a displacement mechanism; the low-power-consumption induction and self-calibration mechanism comprises a driven gear, a double-meshing gear, a driving gear, an automatic reset component, a driving component and an induction device which are sequentially meshed, the driven gear can receive input torque and sequentially drive the double-meshing gear and the driving gear to rotate, and the double-meshing gear can drive the automatic reset component to move through the driving component. The displacement action of the automatic reset component is sensed through the sensing device; the grating mechanism comprises a grating belt driven shaft, a grating belt driving shaft, a grating belt wheel, a grating belt and a grating decoder, and displacement data are obtained through the grating decoder, or the displacement data on the grating belt are obtained through a distributed optical fiber or a grating demodulator. According to the invention, long-term low-power-consumption or power-consumption-free monitoring and regular self-calibration of equipment are realized, and the device has the advantages of long service life, wide application range, strong stability, strong anti-interference capability and the like.
Owner:赵元基

Method for detecting content of alumina in aluminum-manganese-calcium alloy

ActiveCN117706021Bsolve effective separationSolve the detection needs of alumina contentChemical analysis using titrationMaterial electrochemical variablesManganeseAlloy
This invention discloses a method for detecting the alumina content in aluminum-manganese-calcium alloys, mainly solving the technical problem that existing methods cannot accurately and rapidly detect the alumina content in aluminum-manganese-calcium alloys. The technical solution is as follows: a method for detecting the alumina content in aluminum-manganese-calcium alloys, comprising: 1) sample preparation: after removing the oxide layer on the sample surface, the sample is placed in a reagent bottle containing organic solvent for storage; 2) alumina extraction from the sample: first, alumina is extracted from the sample by electrolysis, the sample is placed in an electrolytic cell for electrolysis, the sample is the anode, a platinum electrode is the cathode, and a saturated calomel electrode is the reference electrode; 3) detection of alumina in the sample: the filter membrane and filter material from step 2) are placed in a platinum crucible, and the filter membrane is removed by high-temperature ashing; 4) calculation of the mass percentage of alumina in the aluminum-manganese-calcium alloy. The method of this invention for determining the alumina content in aluminum-manganese-calcium alloys has a relative standard deviation (RSD) of less than 3%, indicating good precision, accuracy, and reliability of the detection data.
Owner:SHANGHAI MEISHAN IRON & STEEL CO LTD

Generator set vibration trend early warning method based on deep time sequence model

PendingCN122263019AOvercome the problem of feature instabilityAchieve high-precision modelingBiological modelsAlarmsData streamFeature set
The application discloses a generator set vibration trend early warning method based on a deep timing model, comprising the following steps: collecting generator set operation data and performing data preprocessing; constructing an enhanced Neural RDE model; running a conditional rough driving construction unit to generate a logarithmic signature feature set; running a frequency band gate vector field unit to generate a gate coefficient set and a hidden state sequence; running a physical consistency constraint unit to calculate and generate a constraint signal sequence; based on the hidden state sequence, the logarithmic signature feature set and the constraint signal sequence, calculating and generating a trend index set and a risk index set; calculating a joint loss function and updating model parameters; inputting a real-time collected continuous data stream and combining the model parameters and a threshold set to generate a vibration trend early warning result and an early warning lead time. The application significantly improves the vibration trend prediction accuracy, prolongs the early warning lead time and enhances the operation reliability under complex working conditions.
Owner:SHANGHAI JINHAILONG INTELLIGENT TECHNOLOGY CO LTD

Satellite data traffic measurement method and system

The invention discloses a satellite data traffic measurement method and system, and belongs to the technical field of satellite networks. In order to solve the problems of poor satellite network flow measurement precision and high complexity in the prior art, the invention provides a satellite data flow measurement method, which comprises the following steps: determining a satellite node for data flow measurement, and initializing a configuration probability data structure algorithm and an imitation learning algorithm; sampling network flow in a period of time, judging whether a data flow jitter value in the period of time exceeds a threshold value or not, and if the data flow jitter value exceeds the threshold value, generating a flow value according to a label value and an expert strategy by utilizing an imitation learning algorithm; if not, using a probability data structure algorithm to measure and record a label value, and generating an expert strategy according to the label value; and completing measurement. According to the method, resource utilization is reasonably optimized while the measurement accuracy is improved, high-precision and high-timeliness satellite flow measurement is achieved through mutual complementation of the probability data structure algorithm and the imitation learning algorithm, and the method is low in hardware dependency, high in precision, high in intelligence and high in adaptability.
Owner:SHANGHAI DONGHAI VOCATIONAL & TECH COLLEGE

A method for judging heliostat failure by comparing historical heliostat data

The application discloses a kind of to judge heliostat fault method using historical heliostat data contrast, comprising the following steps: S1, camera installation and configuration;S2, image acquisition;S3, image pre-processing;S4, image segmentation;S5, shape recognition;S6, feature extraction;S7, historical data contrast;S8, anomaly detection;S9, machine learning detects abnormal heliostat;S10, real-time monitoring and feedback.The application introduces historical data contrast and machine learning technology, significantly improves the accuracy and efficiency of heliostat fault detection, and the specific advantages include: high accuracy, combined with image processing and historical data contrast effectively identify a variety of abnormal types, reduce the misjudgment rate;High degree of automation, through automatic exposure algorithm, region growing algorithm and machine learning model realize full-process automatic detection;Wide adaptability, considering the influence of weather, season and other factors, suitable for complex and changeable operating environment.
Owner:BEIJING JUSHUHE TECH CO LTD

Feed system LuGre friction model parameter identification method and system based on improved Gaussian group optimization algorithm, computer readable storage medium and computer program product

ActiveCN119270634Areduce complexityStrong optimization abilityAdaptive controlAlgorithmData mining
The invention belongs to the field of system parameter identification, and relates to a feeding system LuGre friction model parameter identification method and system based on an improved Gaussian group optimization algorithm, a computer readable storage medium and a computer program product, and the method comprises the steps: (1) exciting a feeding system by using an identification excitation signal, and collecting operation data of the feeding system; the operation data are the speed, the acceleration and the corresponding load current of the feeding system under the excitation of the identification excitation signal; (2) dividing parameters of the LuGre model into sliding parameters and pre-sliding parameters; (3) constructing a loss function for identifying the sliding parameter and the pre-sliding parameter; and (4) based on the operation data in the step (1), minimizing the loss function of the sliding parameter by using a Gaussian group optimization algorithm, and minimizing the loss function of the pre-sliding parameter by using the Gaussian group optimization algorithm to obtain the sliding parameter and the identification result of the pre-sliding parameter. The method has obvious advantages in identification precision and usability.
Owner:HUAZHONG UNIV OF SCI & TECH +1

A preferred assembly method for high-precision planetary gear reducer

The present invention discloses a method for optimal assembly of a high-precision planetary gear reducer, the method comprising: hierarchical optimal planetary gear; hierarchical optimal sun gear; planetary gear mechanism assembly; hierarchical optimal single-stage gear ring housing assembly; assembly and fixing of input shaft and rear flange; assembly and fixing of output shaft and front flange; housing assembly and fixing. In the present invention, after hierarchical optimal planetary gear, sun gear and single-stage gear ring housing are optimally graded, the eccentric direction of the inner hole of the planetary gear is marked in the optimal process, and the eccentric direction of the four planetary gears is directed to the same direction after being installed in the assembly process, and the corresponding sun gear and single-stage gear ring housing are adapted to ensure that the sun gear always has a clearance in one direction and is in a tight fit in the other direction, so as to avoid the problems of jamming and vibration under high-precision meshing conditions, further improve the transmission accuracy and stability of the reducer, and achieve multiple performance indicators such as high precision, low side clearance, low noise, and low starting torque.
Owner:HUBEI KEFENG TRANSMISSION EQUIP CO LTD

Network traffic anomaly detection method based on SSM and transformer fusion

This invention discloses a network traffic anomaly detection method based on the fusion of SSM and Transformer, belonging to the field of network traffic monitoring technology. The method includes the following steps: S1, construction of raw traffic observations; S2, construction of joint feature representations; S3, dual-view sample generation: constructing raw view samples and generating corresponding perturbation view samples; S4, multi-scale variable behavior fragment decomposition: performing fragment decomposition on the raw view samples and perturbation view samples at different time scales; S5, hybrid coding feature extraction: extracting intra-session dynamic features using the SSM modeling branch and extracting inter-session correlation features using the Transformer modeling branch; S6, normal behavior representation learning; S7, traffic anomaly determination. This invention captures features at different time granularities through a multi-scale patch hierarchical structure, achieving high-precision and high-stability time-series anomaly detection.
Owner:SOUTHWEST PETROLEUM UNIV +1

Custom AI interaction model-based gift personalized customization method

The invention relates to the technical field of personalized electronic commerce, and discloses a gift personalized customization method based on a custom AI interaction model, comprising the following steps: establishing a custom AI interaction model architecture; s2, designing a user interface terminal according to the customized AI interaction model architecture; s3, guiding the user to enter a user interface terminal for man-machine interaction; and S4, collecting feedback through a dynamic questionnaire and real-time user behavior tracking, and refining and adjusting the user-defined AI interaction model. According to the gift personalized customization method based on the custom AI interaction model, deeper and finer personalized options can be provided, more intuitive and interactive user experience can be provided, consumers are helped to find products meeting the requirements more easily, specific user requirements and product characteristics are met, and the user experience is improved. And an innovative and comprehensive personalized gift customization service is provided for the user in the rural agricultural product market.
Owner:刘帅帅