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

283results about How to "Fast output" patented technology

Transient state control method and device for network construction type converter

The invention specifically discloses a transient state control method and device for a network construction type converter. The method comprises the following steps: after detecting that a grid-connected point system side has a fault, calculating a fault steady-state power reference value under an optimal transient voltage support target according to an equivalent voltage source and equivalent line impedance of the grid-connected point system side; on the premise of not exiting a virtual synchronous control power outer ring of the network construction type converter, calculating steady-state virtual impedance for correcting the internal potential of a bridge arm, and skipping the slow characteristic of the outer ring to quickly output the required steady-state power; and calculating first time-varying virtual impedance after the fault occurs according to the steady-state virtual impedance and transient virtual impedance for limiting the impact current. After detecting that a fault occurs, setting a power reference value of the network-forming converter as a fault steady-state power reference value, and increasing first time-varying virtual impedance at the same time; and after the fault is cleared, recovering the power reference value to the normal power reference value, and adjusting the first time-varying virtual impedance to the second time-varying virtual impedance.
Owner:HUAZHONG UNIV OF SCI & TECH

Forest fire audio recognition method based on BP neural network, medium and product

The invention discloses a forest fire audio recognition method based on a BP neural network, a medium and a product in the technical field of forest fire recognition. The method comprises the following steps: acquiring forest fire audio data to be detected; extracting a Mel-frequency cepstrum coefficient (MFCC) based on the frequency domain features of the forest fire audio data to be detected; inputting the Mel-frequency cepstral coefficient MFCC into a pre-trained forest fire audio recognition model based on a BP neural network, and outputting a forest fire category; wherein the forest fire category comprises a forest fire and a non-forest fire. Compared with a traditional visual monitoring means, the method can cover a wider forest area, in the same monitoring range, in addition, model training based on the BP neural network can efficiently process a large amount of audio data and rapidly output an identification result, the efficiency and accuracy of forest fire identification are further improved, and the method is suitable for popularization and application. The problems of limited coverage range, high cost and low accuracy in the existing forest fire identification technology are solved.
Owner:NANJING FORESTRY UNIV

Smart energy consumption analysis method and system

The invention is suitable for the technical field of energy consumption analysis, and particularly relates to a smart energy consumption analysis method and system, and the method comprises the steps: drawing a technological process PID diagram, marking energy consumption equipment, positioning a control node of the energy consumption equipment, defining a standard working condition, reading a valve position of the control node through a preset DCS central control system, and carrying out the control of the energy consumption equipment. The fluctuation range of the valve position under the standard working condition is configured; and traversing the technological process PID diagram, determining the energy type of each control node, and clustering the fluctuation range based on the energy types. By generating the monitoring tree, the energy analysis result can be quickly output, the abnormal node can be found out, the energy consumption abnormal position can be accurately positioned, the more effective energy consumption management strategy can be formulated, and by drawing the change trend chart, the energy consumption condition can be visually displayed, the energy consumption state can be comprehensively known, and the energy consumption abnormity can be timely found and processed. And stable operation of a production system is ensured.
Owner:SHANDONG LIKONG ENERGY CO LTD

Small sample power transmission line pin defect detection method based on graph convolutional network

The invention belongs to the technical field of electric power engineering monitoring, and discloses a small sample power transmission line pin defect detection method based on a graph convolutional network, and the method comprises the steps: collecting a power transmission line pin image through image collection equipment; marking pins in the image based on event logic guidance to obtain a transmission line pin data set with logic association; introducing a cross-domain interaction enhanced pyramid network into the graph convolutional network to obtain an improved graph convolutional network model, and training to obtain an original target detection model; a knowledge graph relation reasoning module is introduced into the original target detection model, and a power transmission line pin defect detection model is obtained; and detecting the preprocessed power transmission line pin image by using a pin defect detection model, so as to generate a pin image with marked pin position classification and confidence. The method can effectively solve the problem that the sample size is small, and improves the recognition accuracy of the pin and the defect of the pin, thereby facilitating the improvement of the efficiency of detecting the defect of the pin of the power transmission line by inspection personnel, and guaranteeing the stable operation of a power system.
Owner:INFORMATION & TELECOMM COMPANY SICHUAN ELECTRIC POWER

Depression auxiliary diagnosis system based on electroencephalogram and voice and data analysis method thereof

The invention relates to an electroencephalogram and voice-based depression auxiliary diagnosis system and a data analysis method thereof, and the auxiliary diagnosis system comprises a data processing module, a detailed diagnosis mode module, a simple diagnosis mode module and a patient information management module. The data processing module comprises a data preprocessing unit and a fixed electroencephalogram feature extraction and visualization unit; the detailed diagnosis mode module is used for carrying out personalized feature extraction and mode recognition on electroencephalogram data by scientific researchers and checking the recognition accuracy rate, a visual graph and an evaluation index statistical table of a selected machine learning model, and the simple diagnosis mode module is used for rapid diagnosis. Comprising a single-mode electroencephalogram data processing unit, a single-mode voice data processing unit and an electroencephalogram voice fusion data processing unit, the simple diagnosis mode module generates a diagnosis result, and the result is in a healthy or depression character form. The result obtained by the auxiliary diagnosis system is objective, meticulous and reliable.
Owner:TIANJIN UNIV

Method for automatically segmenting brain structure of multi-center applicable human brain magnetic resonance image

The invention relates to a multi-center applicable automatic segmentation method for a brain structure of a human brain magnetic resonance image, and the segmentation method specifically comprises the steps: obtaining MRI data of different platforms, and carrying out the N4 bias field correction and image standardization processing of the MRI data; u-Net is used as a basic framework, a self-attention mechanism module is fused, and an MRI brain image structure segmentation network model suitable for multiple platforms is constructed; and inputting the processed MRI data into a segmentation network model, training the segmentation network model by using transfer learning and domain adaptation technologies, performing uncertainty estimation on an output result, and further performing model training by using screened high-quality unlabeled data so as to realize automatic segmentation of the brain structure of the human brain magnetic resonance image. Compared with the prior art, the method has the advantages that brain structures of different magnetic resonance imaging platforms can be accurately and quickly segmented, a more universal, efficient and reliable tool is provided for the field of brain image analysis, and wider application and research exploration are facilitated.
Owner:RUIJIN HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE

Continuous wind tunnel pressure measurement test data monitoring and correcting method

The invention discloses a continuous wind tunnel pressure measurement test data monitoring and correcting method, and relates to the technical field of wind tunnel pressure measurement tests, and the method comprises the steps: constraining a corresponding sampling frequency for each sensor in a sensor group; acquiring wind tunnel operation data by a sensor group, constructing a corresponding abnormal coefficient according to the operation data, and judging whether the current operation of the wind tunnel is abnormal or not according to the abnormal coefficient; performing a simulation test on a to-be-tested sample by using the wind tunnel flow field digital twinborn model, constructing the reliability of the wind tunnel flow field digital twinborn model according to test data, and if the reliability is insufficient, analyzing to obtain a corresponding difference point; and giving a corresponding optimization scheme by the model optimization knowledge graph, optimizing the wind tunnel flow field digital twin model, and performing simulation test on a to-be-tested sample by the optimized wind tunnel flow field digital twin model. The reliability of the digital twinborn model of the wind tunnel flow field is improved, the output simulation test data is more fit with the actual test data, and the reliability of the simulation test is improved.
Owner:CHANGZHOU INST OF TECH

Cleansing oil biological extraction processing device for tissues

The invention discloses a cleansing oil biological extraction processing device for tissues, and relates to the technical field of cleansing oil, the cleansing oil biological extraction processing device comprises an equipment shell, an emulsifying mechanism is arranged at the bottom of the inner side of the equipment shell, a driving mechanism is arranged at the top of the inner side of the equipment shell, and the bottom end of the driving mechanism is connected with a powder throwing mechanism and a stirring mechanism; the stirring mechanism is positioned outside the powder throwing mechanism; and the driving mechanism drives the powder throwing mechanism and the stirring mechanism to descend synchronously, so that the powder throwing mechanism reaches the throwing station, and the stirring mechanism reaches the stirring station. Compared with the prior art, the device is higher in automation degree, the situation that mixed powder is agglomerated when being added into a premix, and consequently stirring needs to be conducted for a longer time can be avoided, meanwhile, cleansing oil can be output more rapidly, cleansing oil residues in a container are reduced, the cleansing oil preparation efficiency is improved, and meanwhile the preparation cost of the cleansing oil is reduced.
Owner:JINGDE WANFANG DAILY NECESSITIES CO LTD

Training-free image style migration method and device based on diffusion model and medium

The invention discloses a training-free image style migration method and device based on a diffusion model and a medium. The method comprises the steps that text embedding corresponding to a style image is generated based on a multi-mode BLIP-2 encoder in BLIP-Diffusion; based on a U-Net residual module and a self-attention module, key intermediate features are extracted from a content branch and a style branch through a de-noising diffusion implicit model DDIM inversion technology; the intermediate feature is used as a spatial feature to be replaced in a target branch; according to different requirements of contents and styles, selectively replacing a residual block and a specific layer of a self-attention module in content injection, and replacing the specific layer of the self-attention module in style injection to realize optimal fusion of the contents and the styles; and content injection and style injection in the target branch are performed separately by using the gradual characteristics of the diffusion model. According to the method, a training-free mode is adopted, balance between content storage and style injection is achieved, and high-quality image style migration is achieved.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

5-hydroxytryptophan production strain as well as construction method and application thereof

The invention provides a 5-hydroxytryptophan production strain and a construction method and application thereof, the genetic background of the strain is clear, a purFbsubK316Q mutant gene derived from bacillus subtilis is heterologously introduced on the basis of the 5-hydroxytryptophan production strain E.coli HTP11, the transcriptional level of guaB, guaA, gmk and ndk genes of the strain E.coli HTP11 is up-regulated, a gapX gene derived from corynebacterium glutamicum is heterologously introduced, and the mutant gene is a mutant gene derived from bacillus subtilis. According to the 5-hydroxytryptophan gene disclosed by the invention, aromatic amino acid internal transporter serB, tnaB and aroP genes are deleted, the transcriptional level of an intimal efflux transporter yhjV gene is up-regulated, and a pTm-serB plasmid is electrically transferred, so that a direct precursor 5-hydroxytryptophan of 5-hydroxytryptophan can be stably provided, and the 5-hydroxytryptophan gene has efficient 5-hydroxytryptophan output capability.
Owner:TIANJIN UNIV OF SCI & TECH +1

A 5-hydroxytryptophan production strain and its construction method and application

The present invention provides a 5-hydroxytryptophan production strain and a construction method and application thereof. The strain has a clear genetic background and is effective in producing 5-hydroxytryptophan. E.coli HTP11 Subtilis subtilis spores pureF bsu K316Q Mutated gene, upregulated strain E.coli HTP11 of guaB , guaA , gmk , ndk The transcription level of the gene was increased by heterologous introduction of the gapX Gene, missing aromatic amino acid transporter serB , tnaB , aroP Gene, up-regulated inner membrane efflux transporter yhjV The transcription level of the gene was increased and electroporated into the pTm-serB plasmid, which could stably provide 5-hydroxytryptophan, the direct precursor of 5-hydroxytryptophan, and had a high efficiency of 5-hydroxytryptophan output.
Owner:TIANJIN UNIV OF SCI & TECH +1

Decoration effect picture generation method and device based on generative artificial intelligence

The embodiment of the invention discloses a decoration effect picture generation method and device based on generative artificial intelligence. A specific embodiment of the method comprises the steps of obtaining a to-be-transformed indoor image and an expected style prompt word; interference term elimination is carried out on the indoor image to be transformed to obtain an indoor structure image; performing line extraction on the indoor structure image to obtain an indoor line image; performing depth identification on the indoor structure image to obtain an indoor depth image; based on a pre-trained decoration image generation model, performing effect image generation on the indoor structure image according to the expected style cue word, the indoor line image and the indoor depth image to obtain an initial indoor effect image; and performing local redrawing on the initial indoor effect picture to obtain an indoor decoration effect picture. According to the embodiment, the efficiency of generating the decoration effect picture is improved, and waste of computing resources is avoided.
Owner:BEIJING NAT STANDARD CONSTR TECH CO LTD

A lithium-ion battery fault diagnosis method based on lithium plating detection

The invention discloses a lithium ion battery fault diagnosis method based on lithium plating detection, comprising the following steps: obtaining data such as battery thickness increment, battery temperature, ambient temperature, charge and the like through experiments; establishing a basic model for battery lithium plating layer detection, a thermal expansion compensation model and a lithium embedding expansion compensation model; adding pressure measuring points to repeat the experiment and establishing a gasification expansion compensation model; establishing a lithium ion battery lithium plating layer detection model; inputting the real-time measured battery temperature and ambient temperature, charge and battery thickness increment into each compensation model to obtain a corresponding thickness compensation value, subtracting the thickness compensation values ​​of thermal expansion, lithium embedding expansion and gasification expansion from the real-time measured battery thickness increment value to obtain a basic lithium plating layer thickness value approximately measured in real time; establishing a lithium ion battery lithium plating layer thickness detection estimator, detecting the lithium plating layer thickness online according to the real-time measured battery thickness, ambient temperature, battery temperature and charge and the like data, and performing lithium plating fault diagnosis.
Owner:SOUTH CHINA UNIV OF TECH

Fabric dyeing equipment running machine parameter optimization recommendation method, device, equipment and medium

The invention discloses a fabric dyeing equipment running machine parameter optimization recommendation method and device, equipment and a medium, and the method comprises the steps: obtaining the cloth type information of a plurality of production batches of an order system and the production information of a corresponding batch in a production execution system, carrying out the coding of the cloth type information and the production information, and obtaining cloth type feature data and process feature data, associating the seed distribution characteristic data with the process characteristic data to form process data items, calculating the seed distribution information of a target production batch by adopting a similarity algorithm when the target production batch information is detected, screening out preliminary process data items in a similarity threshold range, and storing the preliminary process data items in a database; and calculating the process characteristic data of the preliminary process data items by adopting a GBDT gradient decision tree to obtain recommended optimal line machine parameter data, so that the line machine parameter data of the dyeing equipment can be quickly output through system recommendation, and meanwhile, the batch quality problem caused by personal errors is reduced.
Owner:FOSHAN JIYAN ZHILIAN TECH CO LTD

A multi-physics field calculation method and system for online simulation of digital twins

The present invention relates to the technical field of physical field simulation, and discloses a multi-physical field calculation method and system for online simulation of digital twins. The method and system establish a multi-physical field coupling simulation calculation model of a simulated object, simplify the multi-physical field coupling simulation calculation model, and reduce the order of the temperature field simulation model, thereby greatly reducing the amount of calculation and improving the calculation efficiency. The low-precision data set obtained by temperature field analysis is used to reduce the amount of data required for the model and reduce the cost of modeling. The basic data-driven model is constructed through the low-precision data set and its corresponding sample space, so that the temperature field distribution result can be quickly output, which further improves the calculation efficiency and reduces the calculation error.
Owner:ELECTRIC POWER RES INST CHINA SOUTHERN POWER GRID CO LTD

Coal mine fine sorting system based on X rays

The invention relates to the technical field of coal mining, and particularly discloses an X-ray-based coal mine fine separation system which comprises a vibration feeding mechanism, a conveying mechanism, an imaging analysis module, an intelligent control module and a mechanical separation module, the imaging analysis module comprises an X-ray emission source and a detector, the vibration feeding mechanism comprises a vibrator, and the vibrator is connected with the conveying mechanism. The intelligent control module comprises a data acquisition module and an image processing and analyzing module, and the mechanical separation module comprises an execution mechanism. By arranging the X-ray technology, tiny differences between materials such as coal and gangue can be accurately recognized, and therefore high-precision sorting is achieved. The technology has the remarkable advantages that the materials do not need to be in direct contact, material pollution and damage possibly caused in a traditional sorting method are avoided, the integrity and quality of the materials can be kept in the sorting process, and the sorting efficiency and the resource utilization rate can be improved.
Owner:YANGZHOU YUNNENG PHOTOELECTRIC TECH CO LTD

Mine unmanned driving virtual scene generation method based on large model

The invention belongs to the field of mine unmanned driving virtual scene generation, and discloses a mine unmanned driving virtual scene generation method based on a large model, which comprises the following steps: collecting network information and mine data, fusing the network data and a mine data set, forming a pre-training data set, and obtaining a sample Token; the sample Token is subjected to two stages of pre-training and weight cyclic fine tuning in sequence, feedback correction and cyclic tuning until a final model generated by the mine unmanned driving virtual scene is output; and inputting a to-be-trained unmanned driving algorithm and a required text to the final model, automatically generating a marked mine unmanned driving data set, scoring a data set generation result, feeding back to the weight cycle fine tuning stage, providing a scoring reference for the data set, and performing cycle tuning to obtain a mine virtual generation final model. According to the method, the problems of data shortage, high data labeling cost, insufficient training data diversity, insufficient virtual scene fidelity, high equipment cost and the like of the mine unmanned driving technology are solved.
Owner:HUAZHONG UNIV OF SCI & TECH

Pull-type straw crushing and packing machine

The utility model relates to a pull-type straw smashing and packing machine. Comprising a rack, a picking and smashing device installed at the bottom of the rack and used for replacing the functions of a straw picking device and a straw crusher, a dust removal mechanism connected with the picking and smashing device and used for smashing straw and removing dust, and an auger conveying mechanism used for outputting straw in the dust removal mechanism to a double-bag-outlet packaging device. The traction and power input system is used for providing power; the picking and crushing device is used for synchronously picking and crushing straws collected from the ground, the dust removal mechanism is used for removing dust from the straws in the picking and crushing device and discharging the dust to the ground from the bottom of the rack, and the traction and power input system is used for being connected with a traction vehicle and inputting power of the traction vehicle; the utility model has the advantages that the equipment volume is greatly reduced, and the efficiency can be effectively improved.
Owner:JILIN NAHAI AGRI EQUIP CO LTD

Lithium ion battery electrolyte capable of ensuring low-temperature discharge characteristic and preparation method of lithium ion battery electrolyte

The invention relates to the technical field of electrolyte preparation, and discloses a lithium ion battery electrolyte capable of ensuring low-temperature discharge characteristic, which comprises the following components in percentage by mass: 25% of propylene carbonate (PC), 35% of dimethyl carbonate (DMC), 20% of gamma-butyrolactone (GBL), 20% of ethyl acetate, 1.0 mol / L of lithium salt bis (trifluoromethanesulfonimide) (LiTFSI), 3% of additive 1, 3-propane sultone (PS) (mass fraction: 0.1% of sodium hydroxide (mass fraction: 0.1% of sodium hydroxide), and the balance of water. According to the present invention, the low temperature performance of the solution is improved, the unique solvent formula and the unique solvent ratio enable the electrolyte to have good fluidity in the low temperature environment, and the freezing point of the electrolyte is effectively reduced so as to ensure that the lithium ions can smoothly migrate between the electrodes at the low temperature, such that the lithium ion battery performance is improved, and the lithium ion battery performance is improved. The discharge performance of the battery under a low-temperature condition is obviously improved, and the application scene of the lithium ion battery is expanded.
Owner:北京中科鹦鹉螺软件有限公司

Full-automatic poster making device and method, electronic equipment and medium thereof

The invention relates to a full-automatic poster making device and method, electronic equipment and a medium thereof, and the device comprises a user interface module which provides an interactive interface for a user; the text generation module is used for understanding the requirements of the user by using a large language model technology and generating copywriting conforming to the context according to the requirements; the cue word generation module is used for further processing the copywriting provided by the text generation module and extracting core keywords capable of guiding image creation; the image generation module is used for generating image content conforming to the copywriting theme according to the cue word; the spatial analysis module is used for identifying the optimal spatial position for placing the text on the image through an image processing and analysis technology; the text adapting and typesetting module is used for further adapting and designing the text according to a spatial analysis result; the output module is used for finally generating a designed and edited poster; according to the method, the text can be quickly, automatically and accurately generated and typeset, and the problems of low time efficiency and creativity limitation in manual poster making are solved.
Owner:SHANGHAI SHUHENG INFORMATION TECH CO LTD

Steel bar acceptance system and method based on BIM technology and image recognition technology

The invention relates to a reinforcing steel bar acceptance system and method based on a BIM technology and an image recognition technology, and relates to the technical field of project acceptance, and the method comprises the steps: obtaining the acceptance time of reinforcing steel bar meshes of a plurality of regions; if the current time node is the acceptance time of the reinforcing mesh in a certain area, acquiring the reinforcing mesh image for analysis and identification; acquiring actual position coordinates of each reinforcing steel bar in the reinforcing steel bar mesh image through a BIM (Building Information Modeling) technology; according to the actual position coordinates of each steel bar, the distance between the adjacent vertical steel bars and the distance between the adjacent transverse steel bars in the target steel bar mesh are calculated, and acceptance check results about the positions, specifications, lengths and the distances of the steel bars are output. Data resources generated by checking and accepting the reinforcing steel bars can be reduced, and the checking and accepting result of the reinforcing steel bars can be rapidly output.
Owner:HUNAN FANGYUAN ENG CONSULTANTS SUPERVISION CO LTD

Electric push rod with lubricating structure

The utility model discloses an electric push rod with a lubricating structure. The electric push rod comprises a gear seat, an oil adding groove is formed in the middle of the top end of the gear seat, oil guide sliding ways are arranged on the two sides of a boss, a supporting pipe is fixedly connected to the top end of the boss, a pressurizing air bag is fixedly arranged at one end of a supporting plate, and a lubricating cylinder is fixedly arranged on one side of the top of the supporting plate. The boss is arranged in the oil filling groove, the supporting plate is supported on the top of the boss through the supporting pipe, the lubricating cylinder is arranged on the top of the supporting plate, during oil filling, a valve on the outer side of the supporting pipe can be opened, and then lubricating liquid in the lubricating cylinder enters the supporting pipe through the liquid guide pipe under the action of gravity and is discharged through the oil outlet hole; lubricating oil flows to a gear piece in the gear seat along the inclined oil guide sliding way, so that the gear is oiled and lubricated, the pressurizing air bag at one end of the supporting plate can be pressed, the interior of the lubricating cylinder is pressurized, the lubricating oil is rapidly output, and rapid oiling is achieved.
Owner:NINGBO WANRONG TRANSMISSION TECH CO LTD

Raw material mixing equipment for production of wear-resistant shock pads

The utility model relates to the technical field of raw material mixing equipment, and discloses raw material mixing equipment for producing a wear-resistant shock pad, which comprises a bearing frame, a sealed sealing groove is arranged at the upper part of the bearing frame, a conical mixing barrel for mixing is arranged in the sealing groove, and an inner cavity of the conical mixing barrel is in a conical shape with a wide upper part and a narrow lower part. According to the utility model, the inner cavity is in the shape of the inverted cone, the first driving motor drives the mixing frame to rotate, raw materials move towards the periphery under the action of centrifugal force, the diameter of the conical mixing barrel is gradually reduced from top to bottom, a gradient type constraint space is formed, and the raw materials at the inner bottom of the conical mixing barrel are pushed upwards; circumferential flow driven by centrifugal force is coupled with reaction force of the wall surface, so that a spiral ascending flow state is formed, the mixing efficiency of the raw materials is improved, unmixed raw materials are not left at the bottom in the conical mixing barrel, and the mixing efficiency of the raw materials is improved.
Owner:KUNSHAN OU SHENGWEI ELECTRONIC TECHNOLOGY CO LTD

Hot melt adhesive box folding machine

The utility model belongs to automatic packaging equipment technical field especially is a kind of hot melt adhesive folding box machine. Including folding box machine frame, the inside of folding box machine frame is provided with synchronous feeding mechanism and the material taking assembly located in the both sides of synchronous feeding mechanism, the top of folding box machine frame is provided with the material rack conveying component located in the upper synchronous feeding mechanism. The utility model is through modular layered design and automation collaborative control, realizes the full-process efficient operation of paperboard conveying, glue spraying, stamping and forming, synchronous feeding mechanism and material taking assembly accurate cooperation, ensure material positioning stability, mould stamping mechanism and forming mechanism vertical layout save space, spray gun component realizes even glue spraying, left hinge mechanism, right hinge mechanism and side hinge mechanism timing linkage, guarantee folding accuracy, export conveying line completes finished product rapid output, overall structure is compact, stable operation, have automation efficiency and hot melt adhesive process advantage, applicable to high-precision packaging demand.
Owner:METWAY INTELLIGENT EQUIP (GUANGDONG) CO LTD

High-quality biodiesel combustion performance evaluation system

The present invention discloses a high-quality biodiesel combustion performance evaluation system, including an experimental database retrieval module, a fitting formula calculation module and a machine learning prediction module. The present invention can predict the combustion characteristics and emission characteristics of a mixed fuel after high-quality biodiesel is mixed with other fuels through the use of the three modules, and can calculate the total error through the error curve to compare the accuracy of the fitting formula calculation and the machine learning prediction to determine the actual application method. The present invention mainly solves the problem of evaluating the combustion performance when high-quality biodiesel is added and applied, so as to provide feedback to guide the biodiesel preparation process and regulate and optimize the biodiesel components. At the same time, this invention is not limited to fuel mixed with high-quality biodiesel, and the combustion performance of any fuel type involved in the system after mixing can be predicted.
Owner:JIANGSU UNIV

Spatial orientation real-time analysis method based on eye movement

The invention discloses a spatial orientation real-time analysis method based on eye movement, relates to the related technical field of flight training, and aims to overcome the defects of low analysis accuracy and poor adaptability in the prior art. The method comprises the following steps: acquiring pilot eye movement data through eye movement tracking equipment, acquiring head space orientation data through a flight helmet space sensor, and acquiring environment data containing instrument visual complexity and aircraft attitude from a virtual flight simulator; performing time synchronization on the three types of data; extracting features such as coordinates of a fixation point from the synchronous eye movement data; comparing the head orientation data with the reference data to generate deviation data; inputting the eye movement characteristics, the deviation data and the environment data into an evaluation model; the model dynamically adjusts parameters according to environment data, and calculates pilot space orientation capability indexes in combination with eye movement characteristics and deviation data. According to the method, accurate integration of multi-dimensional data can be realized, the analysis comprehensiveness and reliability are improved, a dynamic flight scene is adapted, and real-time accurate evaluation is realized.
Owner:AIR FORCE MEDICAL CENT PLA

Cognitive assessment method and system based on eye movement test

The application relates to the technical field of cognitive function assessment, in particular to a cognitive assessment method and system based on eye movement test. The cognitive assessment method based on eye movement test comprises the following steps: a cognitive task covering multiple cognitive subdomains is measured on a subject in a preset order, eye movement data corresponding to each cognitive task is obtained by taking a preset interest area of each cognitive task as a spatial constraint; quality control and preprocessing are performed on the eye movement data, multi-dimensional eye movement features are extracted and standardized; each cognitive task score and overall cognitive ability quantitative score are calculated to obtain standardized individual cognitive parameters; a normal population cognitive parameter distribution is taken as a benchmark to construct a multi-cognitive subdomain parameter distribution model, a subject cognitive state is judged by combining a machine learning classification model, and a mild cognitive impairment assessment result is obtained. The cognitive assessment method based on eye movement test can comprehensively depict the cognitive state of an individual and realize multi-dimensional joint assessment.
Owner:HEBEI MEDICAL UNIVERSITY

Map real-time construction and rescue path dynamic planning system oriented to fire dense smoke scene

The invention discloses a map real-time construction and rescue path dynamic planning system oriented to a fire dense smoke scene, and relates to the technical field of fire rescue. The system comprises a data acquisition and processing module, an environment modeling and path construction module and a post-processing module, based on millimeter wave radar, laser radar and motion sensor data, multi-modal information is obtained, synchronized and converted, a semantic segmentation model is utilized to analyze environment perception data to generate a feasible space, and laser radar point cloud and motion sensor data are fused to realize real-time positioning, map construction and rescue path planning in a fire scene. The path is updated in real time according to fire scene environment change, and a generated result is visually presented through a post-processing module and communicates with a command platform for real-time interaction. The system has the advantages of long-distance sensing of the millimeter wave radar and short-distance high precision of the laser radar, can realize quasi-real-time and high-precision fire scene environment modeling and dynamic path generation, and provides reliable path reference for rapid action decision in fire rescue.
Owner:DALIAN UNIV OF TECH

A multi-channel output converter and control method thereof

The embodiment of the present application provides a multi-channel output converter and a control method thereof, wherein the multi-channel output converter includes: a power conversion circuit and an output circuit, wherein the power conversion circuit includes a transformer or an inductor, and the output circuit includes at least two output units, wherein each output unit includes an output capacitor and at least one switch tube and / or a diode, wherein the at least one switch tube and / or a diode is connected in series with the output capacitor, and each output capacitor is used to connect different loads, respectively, and the method includes: according to the load energy required by the output unit of the corresponding channel, the energy stored in the transformer or the inductor is distributed to the corresponding channel for rated voltage or variable voltage output. The technical solution connects the switch tube in series with the output capacitor at the output end of the converter to form a multi-channel output, and controls it by adopting a dynamic energy distribution method, so as to realize a fast response output of multiple different voltages or variable voltages, has a simple structure, and reduces system losses, etc.
Owner:SHENZHEN YUANNENG ELECTRIC CO LTD