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

151results about How to "Good estimate" patented technology

Electric vehicle EMB system clamping force estimation method based on pressure sensor-free control strategy

The invention relates to an electric vehicle EMB system clamping force estimation method based on a pressure-sensor-free control strategy. Compared with the prior art, the defect that a pressure sensor of an EMB system cannot meet the actual use requirement is overcome. The method comprises the following steps: estimating load torque; torque estimation balance force is estimated according to the load torque and a transmission model; estimating a characteristic curve estimated clamping force through a characteristic curve dynamic stiffness model; and carrying out fusion estimation on clamping force of the EMB system. According to the method, a non-pressure sensor algorithm is designed to replace a pressure sensor, the clamping force generated when the EMB system works is optimally estimated in real time, and the problems that the cost of the pressure sensor is high, and the braking performance of the electric vehicle is reduced due to the fact that the precision of clamping force measurement is reduced or even the whole is invalid under the severe braking working condition are solved.
Owner:合肥钧联汽车电子有限公司

Gas component detection method, device and equipment based on spectral analysis and medium

The invention relates to the technical field of spectral analysis, and discloses a spectral analysis-based gas component detection method, device and equipment and a medium, the method comprises the following steps: carrying out axial scanning on a gas storage device to obtain hyperspectral image data; performing preprocessing and spectrum standardization on the hyperspectral image data to obtain preprocessed spectrum data; carrying out waveband selection on the preprocessed spectral data to obtain a characteristic waveband; performing abundance estimation on the characteristic wave band to obtain initial gas component content data; optimizing the initial gas component content data to obtain target gas component content data; and performing gas component anomaly detection on the target gas component content data to obtain a gas component anomaly detection report, thereby improving the accuracy of gas component anomaly detection.
Owner:SHENZHEN GAOFA GASES CO LTD

Aerial atmosphere average electric field detection method and system

The invention relates to the technical field of meteorological detection, in particular to an air atmosphere average electric field detection method and system, and the method comprises the following steps: carrying out the historical trend analysis of the temperature, humidity and wind speed data in the atmosphere based on real-time meteorological data, recognizing key meteorological factors affecting the electric field intensity measurement result through the comparison with the real-time data, and carrying out the detection of the electric field intensity. And generating a key meteorological factor list. According to the method, the key meteorological factors are analyzed in combination with the real-time meteorological data and the historical trend, the accuracy and timely response capability of atmospheric electric field intensity measurement are enhanced, and the accuracy and adaptability of electric field intensity prediction are optimized by identifying and calculating the sensitivity of the meteorological factors and adjusting model parameters. By establishing an atmospheric electric field dependency relationship model, the prediction capability of the model on weather change is improved, the prediction capability on the electric field change trend is enhanced, the estimation on the fluctuation range is optimized, and data support is provided for predicting extreme weather events and carrying out climate research.
Owner:YUNNAN NORMAL UNIV

Scale-spatial stream and hierarchical hyper-prior-based end-to-end video coding method research

The invention discloses an end-to-end video coding method based on a scale-spatial stream and hierarchical hyper-prior, and the method employs a hierarchical hyper-prior coding and decoding network to introduce hyper-prior information to assist the generation of entropy model parameters, thereby enabling an entropy model to obtain more accurate estimation probability distribution, and improving the compression efficiency. And meanwhile, the motion information of the video is better estimated in combination with a scale-spatial stream, and the video coding performance is improved by estimating a more accurate entropy model and motion information. Experimental results show that when SSIM and MS-SSIM are respectively adopted as evaluation standards, compared with an HEVC (High Efficiency Video Coding) standard, the coding method provided by the invention has the advantage that the average code rates are respectively saved by 16.40% and 15.63% under the same distortion condition for video sequences with different resolutions. Compared with a traditional video compression method, the quality of the compressed low-resolution video can be effectively improved, and a good visual effect can be obtained through the method provided by the invention.
Owner:SICHUAN UNIV

Eyeball tracking system and head-mounted device

The invention discloses an eyeball tracking system and head-mounted equipment. The system comprises a light source, an eyepiece group, a light reflecting component and image acquisition equipment, the eyepiece group comprises an eyepiece and an antireflection film, and the antireflection film is located on the outer side surface and / or the inner side surface of the eyepiece; the light source is located at the edge of the outer side surface of the eyepiece and used for emitting light; the reflective component is located on the side, away from the light source, of the eyepiece set and located on the main optical axis of light. The light is reflected by the eyes of the user, passes through the eyepiece group, is reflected by the reflective component and then enters the image acquisition equipment, and the image acquisition equipment is used for shooting images of the eyes of the user. The outer side face and / or the inner side face of the eyepiece are / is plated with the antireflection film, the transmittance of light penetrating through the eyepiece group is improved, the imaging effect of the image acquisition equipment is improved, an eyeball tracking system can conveniently estimate the sight line / fixation point of the eyes of a user, and eyeball tracking of the user is achieved.
Owner:BEIJING 7INVENSUN TECH +1

Tea quality data safety monitoring method and system

The invention relates to the technical field of tea quality, and discloses a tea quality data safety monitoring method and system, and the system comprises a tea data collection module, a tea data analysis module, a tea data safety monitoring module, and a loss prediction module. The tea data collection module comprises a tea growth data collection unit, a tea picking data collection unit, a tea production data collection unit and a tea storage data collection unit, and the tea data analysis module is used for analyzing collected growth problem data, tea condition data, production indexes and storage indexes to obtain quality evaluation data. According to the system, acquired growth problem data, tea condition data, production indexes and storage indexes are compared with standard data one by one and input into a quality evaluation function for quality evaluation, so that quality evaluation data are obtained, and overall production of tea is evaluated; and the overall tea quality safety condition can be reflected from the comprehensive data.
Owner:FUJIAN ZHONGXIN NET SAFETY INFORMATION TECHNOLOGY CO LTD

Method and device for estimating health state of battery pack based on cloud data

The invention discloses a method and device for estimating the health state of a battery pack based on cloud data. The method comprises the steps that S1, a virtual battery model is constructed based on the cloud data; s2, obtaining an effective charging segment, and constructing a reference curve OCV-SOC; s3, calculating the standardized battery capacity of the effective charging segment, and obtaining the health state of the standardized battery; s4, acquiring an estimated battery capacity by adopting a recursive capacity estimation method considering measurement and estimation errors, and acquiring an estimated battery health state; and S5, comparing the SOH estimated in the step S4 with the standardized SOH in the step S3, and verifying the effectiveness of the estimation method in the step S4. The SOH of the battery is estimated on line through information in cloud data, the estimation accuracy is improved, and the actual SOH of the battery pack is reflected. For a lithium iron phosphate battery, an effective charging fragment selection method is provided, the estimation precision of the health state of the battery is improved, and the increasingly accurate evaluation requirement of a new energy automobile on the health state of the battery pack is met.
Owner:JIANGSU UNIV +2

Method for calculating blocking effect of towing tank of underwater vehicle

The invention relates to the technical field of computational fluid mechanics, in particular to a method for calculating the blocking effect of an underwater vehicle towing tank, and the method comprises the steps: building an underwater vehicle physical model; defining each boundary condition of the CFD numerical calculation domain, and solving the total resistance and each resistance component of the underwater vehicle based on the calculation domain grid and the configured numerical calculation condition; and post-processing the total resistance and each resistance component to obtain a calculation numerical result of the underwater vehicle under different blocking ratio working conditions. According to the method, by verifying the independence of the grids, the appropriate number of the grids is determined, and the calculation precision and efficiency are guaranteed.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Scene depth estimation method and device, image processing equipment and storage medium

The invention discloses a scene depth estimation method and device, image processing equipment and a storage medium, and belongs to the technical field of computer vision, and the scene depth estimation method comprises the steps: selecting a single image with shielding, reflection or perspective from a multi-view image set for depth fusion; the improved depth information is spread to other views in a re-projection mode, so that the time overhead is reduced while the reconstruction effect is improved; performing semantic division on the index image to obtain the weight of each semantic factor; the problem that feature points are difficult to match due to a special area is solved by introducing single-view depth estimation; fusing a single-view estimation result and a multi-view depth estimation result under the constraint of semantic information, and spreading the fused result to other view angles in a re-projection manner to obtain a consistent depth estimation result corresponding to the current scene; consistency estimation can be accurately carried out on the depth of each area in the scene.
Owner:HUAZHONG UNIV OF SCI & TECH

Method for estimating elevation of road surface in front of axis based on laser radar and related equipment

The invention relates to the technical field of automobile intelligent driving, in particular to a method and related equipment for estimating elevation of a road surface in front of an axle based on a laser radar, and the method comprises the steps: obtaining three-dimensional point cloud data of the road surface in front of a vehicle; preprocessing the obtained three-dimensional point cloud data of the road surface in front of the vehicle to obtain preprocessed road surface key point data, and extracting the preprocessed road surface key point data to obtain road surface feature data; the elevation information of the road surface in front of the axle is calculated through the road surface feature data and the three-dimensional point cloud data, the elevation information is estimated to obtain an estimation result, the estimation result is fed back to a vehicle automatic driving system, and the elevation estimation work of the road surface in front of the axle is completed. The accuracy of the road surface information in front of the vehicle is improved, and meanwhile the driving safety and stability are improved.
Owner:CHERY NEW ENERGY AUTOMOBILE TECH CO LTD

Coal slime flotation process control method based on distributed pyramid dynamic Bayesian network

A coal slime flotation process control method based on a distributed pyramid dynamic Bayesian network comprises the steps that the coal slime flotation process is divided into three sub-processes, a global quality index variable and a local quality index variable are determined, and a global dynamic Bayesian network is established; key variables in the sub-processes are determined, correlation among the variables is analyzed, and process time delay in each process is determined; determining the number of time slices of the first layer of dynamic Bayesian network; performing structure learning, and establishing a network structure of a first layer of the model; combining the same nodes of adjacent time slices into one node, and constructing a second-layer dynamic Bayesian network structure; bayesian network parameter learning is carried out; actual working condition data information is collected, and when an abnormal working condition occurs, a sub-process causing abnormity is determined; a local pyramid dynamic Bayesian network is utilized to determine a root cause causing an abnormal working condition; making a control decision scheme according to the abnormal reasons, and eliminating abnormal working conditions; the method can eliminate abnormal working conditions in time.
Owner:CHINA UNIV OF MINING & TECH

Power grid planning method, system and device and computer readable storage medium

The invention discloses a power grid planning method, system and equipment and a computer readable storage medium, and aims to greatly reduce manual operation and improve data processing accuracy and efficiency by automatically collecting and processing GIS map data, a power grid operation state and load prediction data. And path planning is performed by combining an A algorithm with a GIS technology, so that the path is optimal and feasible, and the planning period is remarkably shortened. The system comprises a data acquisition module, a problem definition module, a path planning module, a cost calculation module, a path optimization module, a scheme generation module, a visual display module and the like, all the modules work cooperatively, and systematization and standardization of the planning process are achieved. Through an intelligent optimization algorithm, the planning scheme quality is improved, multiple factors are comprehensively considered, and it is ensured that the scheme is scientific, reasonable and economical. The modular design enables the system to be easy to expand and optimize, adapts to power grid planning problems of different scales and complexities, improves the adaptability and flexibility of planning, and provides a comprehensive and efficient solution for power grid planning.
Owner:ZHONGSHAN XINTONG COMM CO LTD

Route planning for improving braking performance of fuel cell powered vehicles

The application relates to routing for improving braking performance of a fuel cell powered vehicle, in particular to a computer system (130, 140) for a heavy vehicle (100) comprising a fuel cell system (111) and an electrical energy storage system (ESS) (112, 121), where the computer system (130, 140) comprises processing circuitry configured to process the fuel cell system (111) and the ESS (112, 121). The processing circuitry is configured to: identify (S1) a downhill portion (C) of a trip to be made by the heavy vehicle (100), determine (S2) at least two candidate routes (R1, R2) from a starting position (A) along the trip to a starting point (B) of the downhill portion (C) of the trip, predict (S3) for each candidate route (R1, R2) an energy state SoE of the battery system at the starting point (B) of the downhill portion (C), and determine (S3) a state of energy SoE of the battery system at the starting point (B) of the downhill portion (C). And selecting (S4) a suggested route from the candidate routes (R1, R2) based at least in part on the predicted SoE of each candidate route and on an estimated amount of energy regenerated by traversing the downhill portion (C) of the trip.
Owner:VOLVO TRUCK CORP

Energy prediction method of high-energy density material structure

The invention discloses an energy prediction method for a high-energy-density material structure, and solves the problems that an existing method cannot effectively characterize and extract features of basic parameters of a material, considers correlation among data and cannot accurately evaluate detonation performance of the high-energy-density material, and the method comprises the steps of obtaining the basic parameters of the high-energy-density material; constructing a crystal structure directed graph, calculating a density value of the high-energy density material based on a first principle and in combination with the crystal structure directed graph, executing a generation enthalpy prediction model, and outputting a predicted generation enthalpy of the high-energy density material; according to the method, the density value of the high-energy density material is calculated by constructing the crystal structure digraph and combining the crystal structure digraph based on the first principle, and the enthalpy prediction model can fully consider the correlation between data, so that the important characteristics of influencing the density value and predicting and generating an enthalpy prediction result are highlighted; and accurate evaluation of the detonation performance of the high-energy-density material is ensured.
Owner:HEFEI UNIV

Self-adaptive model prediction control method and system for building heating ventilation air conditioning system

ActiveCN119289478ADynamically adjust operating parametersMinimize consumptionMechanical apparatusLighting and heating apparatusControl engineeringClassification rule
The invention provides a self-adaptive model prediction control method and system for a building heating ventilation air-conditioning system, and belongs to the technical field of intelligent building self-adaptive control, and the method comprises the steps: obtaining operation data of the heating ventilation air-conditioning system under different working conditions, and carrying out the preprocessing of the obtained data; for the preprocessed data, calculating the marginal fitness measurement of each data point to each class, calculating the fitness measurement of the data point to each class by combining the marginal fitness measurement of all descriptors, and obtaining the global fitness measurement; setting a global fitness measurement threshold, and classifying the current operation state of the system according to a classification rule; after classification, model parameters of each class are fixed, so that adaptive control strategies are adopted for different operation states.
Owner:SHANDONG UNIV

6G dynamic channel map construction method based on machine learning and image processing

The invention discloses a 6G dynamic channel map construction method based on machine learning and image processing. The method comprises the following steps: 1) obtaining dynamic channel maps of different scenes and carrying out data analysis; 2) extracting a building mask based on the channel data; (3) constructing a dynamic channel map data set by taking the signal intensity of a receiver as a main characteristic, and superposing a building mask to serve as heterogeneous data to enhance the predictive capability; 4) dividing the data set into a known scene and an unknown scene; and 5) a pooling encoder is designed to extract multi-scale information to obtain channel map features, a self-attention mechanism is introduced to carry out feature fusion, and finally, a full-scale decoder is used to realize construction of a dynamic channel map. The dynamic channel map construction method provided by the invention can capture channel map changes in different scenes, has better performance in the aspect of channel map construction in an urban environment, and can be used for assisting in key technologies such as optimizing channel estimation and assisting beam alignment in 6G communication.
Owner:SOUTHEAST UNIV +1

Substance identification method based on adaptive quantitative decomposition

The invention discloses a substance identification method based on self-adaptive quantitative decomposition, which comprises the following steps of: establishing a polynomial relationship among coefficients, energy and effective atomic numbers participating in substance identification in the interaction of rays and substances, and scanning and reconstructing by using various known materials as calibration substances; based on the linear attenuation coefficients of different energy regions of the calibration object, the real effective atomic number and density of the calibration object and the polynomial relation obtained before, effective energy of the corresponding energy region is determined; in actual operation, after scanning reconstruction is carried out on a to-be-decomposed substance, due to the fact that effective energy is determined through calibration and linear attenuation coefficients reconstructed in different energy regions are only related to effective atomic numbers and densities, two ray and substance interaction formulas containing variable parameters are simultaneously established, and solving is carried out; and the effective atomic number and density of the scanned substance can be accurately obtained. According to the invention, correlation coefficients can be automatically adjusted according to different substances, so that the decomposition precision is improved.
Owner:INST OF HIGH ENERGY PHYSICS CHINESE ACAD OF SCI

Social network forwarding behavior estimation method and device based on large model enhancement

The embodiment of the invention discloses a social network forwarding behavior estimation method and device based on large model enhancement, and the method comprises the steps: extracting a vector representation of text information of candidate social media content through a social media content text encoder, and obtaining a first feature vector of the candidate social media content; extracting a vector representation of historical forwarding information by using a user encoder to obtain a second feature vector of the user; generating prompt information according to the model control instruction, the historical forwarding information, the social network platform account ID and the user ID, and inputting the prompt information into a large language model for processing to obtain an intermediate result; the first feature vector, the second feature vector and the intermediate result are spliced and then input to a multi-layer perceptron, the multi-layer perceptron estimates the forwarding behavior of the user for the candidate social media content, and an estimation result is obtained. According to the scheme, the estimation accuracy of the user forwarding behavior is effectively improved.
Owner:PEOPLE CN CO LTD

Anti-SSDF attack communication method and system in CSS with unknown signal-to-noise ratio

The invention discloses an anti-SSDF attack communication method and system in an unknown signal-to-noise ratio CSS, and belongs to the technical field of wireless communication, and the method comprises the following steps: based on local spectrum sensing, judging whether a PU is used or not according to an energy estimation value ej of a secondary user by monitoring a specified frequency band; according to an energy value of local energy detection, obtaining a probability density function of energy vectors of the secondary user and the malicious user; the SNR in the probability density function is estimated through an SEM algorithm, judgment is carried out according to the weight, and secondary users and malicious users are distinguished; secondary users directly participate in the CSS, malicious users are deleted from the CSS, and safe communication is achieved; the SEM algorithm is used for estimating the instantaneous SNR, not only is the current energy value considered, but also the historical energy is considered, different step lengths are distributed for different energy observation values, and the estimation of the SNR is improved; for malicious user processing, local perception and global decision of each secondary user are calculated, normal secondary users and malicious users are identified, and attack strategies of the normal secondary users and the malicious users are determined.
Owner:CHANGAN UNIV

Three-dimensional model line-of-sight direction detection method and terminal

The application discloses a three-dimensional model visual line direction detection method and a terminal. The method comprises the following steps: acquiring basic information, then solving a corneal curvature radius based on the basic information; updating eye diagram information, and taking the corneal curvature radius as a constant to solve a corneal curvature center; taking the corneal curvature radius and the corneal curvature center as constants, solving a distance from the corneal curvature center to a pupil center based on the basic information and a pupil edge point coordinate; finally, calculating a Kappa angle of an eyeball; determining a primary and secondary eye, performing visual line fusion through the primary and secondary eye, and obtaining a final visual line direction. The binocular three-dimensional eyeball model is divided into two monocular eyeball models, and the solving parameters between each model only need to solve the human eye parameters related to the visual line, without mutual constraint of the parameters between the binoculars.
Owner:AEROSPACE LIFE SUPPORT IND LTD

Sound level predicting tool, and sound level predicting method

An object of the present invention is to provide a sound level estimating tool capable of easily estimating a sound level of a noise source at a predetermined position on a map. An object of the present invention is to provide a sound level estimating method capable of easily estimating a sound level of a noise source at a predetermined position on a map. A sound level estimating tool used in contact with a predetermined scale map, the sound level estimating tool comprising: a reference point or a reference line corresponding to a position of a sound source in a real world; and an estimation point or an estimation line corresponding to a position in the real world where sound generated from the sound source is received, the sound level estimating tool indicating that, when at least a part of the reference point or the reference line and at least a part of the estimation point or the estimation line are brought into contact with the map, sound generated from the sound source at a real position corresponding to a position on the map in contact with at least a part of the reference point or the reference line is received at a predetermined sound level at a real position corresponding to a position on the map in contact with at least a part of the estimation point or the estimation line.
Owner:ESPACIO CONSULTANT CORP

A method for estimating the age of spontaneous fission sources

The embodiment of the present application provides a method for estimating the age of a spontaneous fission source, which relates to the field of nuclear technology and is used to solve the problem that the estimation process of the age of a spontaneous fission source is relatively difficult. The method for estimating the age of a spontaneous fission source provided in the embodiment of the present application includes: obtaining the radioactivity A of the sum of the first nuclides in the spontaneous fission source; 11 ; According to the radioactivity A of the sum of the first nuclides produced by spontaneous fission of at least one nuclide in the spontaneous fission source 21 and the first estimated age t1 of the spontaneous fission source, and let A 21 =A 11 , calculate t1; wherein the at least one nuclide includes the main nuclide of the spontaneous fission source. The embodiment of the present application provides a method for estimating the age of a spontaneous fission source for estimating the age of the spontaneous fission source.
Owner:CHINA INSTITUTE OF ATOMIC ENERGY

Information processing system, information processing method, and program

In order to facilitate estimation of constituent elements which participated in or were involved in an attack when the attack is detected in a system including a network and a plurality of constituent elements communicating via the network, an information processing system includes an acquisition part configured to acquire log data of a system including a network and a plurality of constituent elements that communicate via the network, and an output part configured to output information of one or more attack vectors including information of constituent elements related to the one or more attack vectors, based on the log data and network configuration information of the system in a case where the attack is detected in the system.
Owner:NTT SECURITY (JAPAN) KK

Water body micro-plastic collection assembly and quantitative collection system

The utility model relates to a water body micro-plastic collecting component and a quantitative collecting system, which comprise a sample barrel, a sampling barrel, a water inlet pipe, a water outlet pipe, a water pump, a flow meter and a valve, a filter screen is arranged in the sample barrel, the sample barrel is assembled in the sampling barrel, a water inlet of the sample barrel is positioned in a water inlet connecting end of the sampling barrel, and a water outlet of the sampling barrel is positioned in a water outlet connecting end of the sampling barrel. The water outlet of the sample barrel is located in the water outlet connecting end of the sampling barrel, the water inlet connecting end is detachably connected with the water inlet pipe, and the water outlet connecting end is detachably connected with the water outlet pipe. The device is simple in structure, enables particles deposited on the filter screen and particles adhered in the sample barrel to be completely brought back to a test room, is simple and convenient to operate, obtains accurate sample amount, is combined with a water pump, a flow meter, a valve and the like to form a collection system, can calculate the water sample amount, and is beneficial to overall estimation of the content of micro-plastics in a water body.
Owner:SHANDONG PROVINCIAL ECO ENVIRONMENT MONITORING CENT

Method for estimating hydrogen desorption rate of hydrogen storage reactor based on BP neural network

The invention discloses a method for estimating the hydrogen desorption rate of a hydrogen storage reactor based on a BP neural network, and the method comprises the steps: obtaining the air flow rate, the air temperature, the heat exchange area between the exterior of the reactor and air, and the hydrogen desorption rate in the state of the air convection heat exchange type hydrogen storage reactor, and constructing a parameter data set, inputting the parameter data set into a BP neural network model for training to obtain a hydrogen desorption rate evaluation model; the air velocity, the air temperature and the air heat exchange area are collected, the collected data are input into the hydrogen desorption rate evaluation model, and an estimation result is obtained; wherein the BP neural network model is obtained by training and testing the parameter data set. According to the method, the model precision can be improved, and the hydrogen supply rate can be better estimated, so that the hydrogen supply rate is controlled to improve the system efficiency.
Owner:SHANGHAI GREENHOUSE ENERGY TECHNOLOGY CO LTD

A pseudo-label-guided multi-view consensus graph semi-supervised network intrusion detection method

ActiveCN115189942Bgood estimateSolve labor costsSecuring communicationInstruments
The present invention discloses a multi-perspective consensus graph semi-supervised network intrusion detection system guided by pseudo-labels, including determining high-confidence pseudo-labels for unlabeled intrusion data, and using pseudo-labels to guide the learning process of the consensus graph. First, the K-nearest neighbor method is used to assign multiple pseudo-labels to the unlabeled intrusion data at each perspective of the intrusion data, and then the pseudo-label information corresponding to the unlabeled intrusion data with consistent pseudo-labels in all perspectives is selected to introduce into the learning optimization process of the multi-perspective consensus graph. The optimal consensus graph finally learned is used to propagate label information to obtain the final network intrusion detection result. The present invention makes up for the defect that the existing semi-supervised multi-perspective network intrusion detection system cannot fully utilize the supervisory information of limited label intrusion data, and can generate additional supervisory information to ultimately obtain better network intrusion detection performance.
Owner:EAST CHINA UNIV OF SCI & TECH +1

System and method for operating a vehicle powertrain

ActiveCN109050514Bkeep the speed constantconstant speedHybrid vehiclesClutches
A method and system are described to provide a powertrain or driveline for operating a hybrid vehicle including two electric machines and a transmission. In one example, vehicle propulsion is maintained while determining transmission operating parameters to improve transmission operation. In particular, a rear drive unit maintains vehicle speed and monitors torque transmitted via the output of the transmission.
Owner:FORD GLOBAL TECH LLC

Lensless microscopy system and method based on self-supervised deep learning

The present invention proposes a lensless microscopic imaging system and method based on self-supervised deep learning. The system includes a multi-height imaging module and a phase recovery module based on self-supervised deep learning. The multi-height imaging module is used to collect diffraction images of an observed object at multiple heights that do not require calibration, including a light source, an observed object and an image sensor placed in sequence, wherein the image sensor can move axially to change the height of the diffraction image; the phase recovery module based on self-supervised deep learning is used to instantly reconstruct the amplitude and phase information of the observed object according to the diffraction image and simultaneously jointly optimize the imaging model parameters. The present invention introduces self-supervised deep learning into the existing lensless imaging system, collects multi-height diffraction image information of the sample, and uses self-supervised deep learning to reconstruct the sample image and jointly optimize the imaging model parameters, thereby achieving label-free, unconstrained, high-performance, and high-quality imaging of the sample.
Owner:NANJING UNIV

Mars underground water-rich ice layer top interface space distribution prediction method

The invention provides a Mars underground water-rich ice layer top interface space distribution prediction method, and relates to the field of planetary exploration, and the method comprises the steps: obtaining a remote sensing image and elevation data of a research region, dividing the research region into a plurality of restricted regions, and carrying out the statistics of the position of a water-rich ice layer visual top interface at the position of a barrier impact pit in each restricted region; extracting a central elevation profile of each restricted area, projecting a visual top interface position of the water-rich ice layer at the position of the barrier impact pit to the profile, and taking a smooth connection line of relatively shallow projection points as a prediction result of the top interface of the water-rich ice layer of each profile; and performing three-dimensional interpolation by combining the water-rich ice layer top interface prediction results of the external expansion area of the research area and all the elevation profiles to obtain a water-rich ice layer top interface space distribution prediction result of the research area. The method has the beneficial effects that the spatial position and the change trend of the top interface of the underground water-ice-rich layer of the Mars can be accurately obtained, and a scientific basis is provided for better estimating the water-ice reserves of the Mars and reasonably developing water-ice resources.
Owner:CHINA UNIV OF GEOSCIENCES (WUHAN) +1

Target detection method and device, vehicle and computer readable storage medium

The embodiment of the invention provides a target detection method and device, a vehicle and a computer readable storage medium, and relates to the technical field of intelligent driving. According to the invention, the image shot by the monocular camera of the vehicle can be obtained; extracting a target in the image, and obtaining the actual height of the target and the height of the target in the image; and determining the depth of the target according to the focal length of the monocular camera, the actual height of the target and the height of the target in the image. The target depth can be estimated based on the visual height easy to estimate in the image shot by the monocular camera, the precision of target depth estimation can be improved, and the technical problem that the target depth is difficult to estimate due to the lack of depth information of the monocular camera is solved.
Owner:GUANGZHOU AUTOMOBILE GROUP CO LTD