67results about How to "Good estimate" patented technology

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Improved techniques for estimating parameters of a jamming signal. An input signal is identified. This input signal is suspected of being a jammed composite signal. Attributes of a reference signal are determined. The reference signal is an expected signal that was expected to be received. A form fitting operation is performed in which the reference signal is formed fitted with the input signal. The reference signal is subtracted from the input signal to generate an isolated output signal. A suspected portion of the isolated output signal is identified. An estimated symbol rate and an estimated center frequency for the jamming signal are determined based on the suspected portion. The estimated symbol rate and the estimated center frequency are used to facilitate a subsequent mitigation operation of eliminating or reducing an impact of the jamming signal against the signal of interest.

The invention relates to a motor rotor temperature determination method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a first back electromotive force of a motor; inputting the first back electromotive force into a second-order generalized integrator for processing to obtain a first flux linkage value of a motor stator flux linkage; determining a flux linkage null drift value, and obtaining a second flux linkage value of the motor stator flux linkage based on the first flux linkage value and the flux linkage null drift value; obtaining a target flux linkage value of the motor rotor flux linkage based on the second flux linkage value; and obtaining a target rotor temperature based on the target flux linkage value and a preset corresponding relationship between the flux linkage value of the motor rotor flux linkage and the motor rotor temperature. The method can reduce the manufacturing cost of the motor and the fault rate of the terminal.

The application discloses a product environment stress estimation method, system, device and storage medium, which is applied to the product evaluation technical field and comprises the following steps: receiving environment stress time series data of a measured product at each set detection position collected by a sensor; determining each stress extreme position and an environment stress value of the measured product under a determined working condition; constructing a Kriging model; inputting physical size information of the measured product, coordinate information of each set detection position, environment stress time series data, coordinate information of each stress extreme position and the environment stress value into the Kriging model and performing interpolation through grid division to obtain each environment stress field matrix of the measured product output by the Kriging model in time sequence, and determining an environment stress value of a target position at a target time. According to the scheme, the environment stress at each position of the measured product at each time can be conveniently and effectively estimated, and the accuracy is relatively high.

The invention discloses a scene aircraft taxiing hybrid control method and device combining sorting and path planning, and the method comprises the following steps: 1, analyzing scene geographic information into an undirected graph structure, pre-calculating scene structure information and an initial motion mask set in combination with an undirected graph and a scene activity prohibition specification, and constructing a reinforcement learning environment; 2, real-time position information of the aircraft is obtained, and an input observation value of the scene aircraft taxiing hybrid control method is constructed in combination with scene structure information; 3, constructing a scene aircraft taxiing hybrid control model; the scene aircraft taxiing hybrid control model comprises a path planning module, a conflict detection module and a conflict scheduling module; the path planning module is realized based on a neural network, and the structure of the path planning module is a neural network composed of multiple layers of noise adaptation layer units. And the path planning module is used for taking the observation value obtained in the step 2 as input, and obtaining an action probability vector of the aircraft after neural network processing.

The present invention proposes an adaptive model predictive control method and system for a building HVAC system, which belongs to the technical field of intelligent building adaptive control, and includes: obtaining operation data of a HVAC system under different working conditions and preprocessing the obtained data; calculating the marginal fitness metric of each data point for each class for the preprocessed data, calculating the fitness metric of the data point for each class by combining the marginal fitness metrics of all descriptors, and obtaining a global fitness metric; setting a global fitness metric threshold, and classifying the current operating state of the system according to a classification rule; after classification, the model parameters of each class are fixed, so as to adopt an adaptive control strategy for different operating states.

The present invention discloses a control method for an aircraft battery power system and a whole machine communication architecture, the method is as follows: the original data information of the battery system is collected through a battery inspection module; the second CAN transceiver receives the original data information from the battery inspection module and sends it to the whole machine controller and the MCU module at the same time, the MCU module analyzes and calculates the power and safety status of the battery system through the original data information and sends the calculated processed data information to the first CAN transceiver; when the first communication network fails, the whole machine controller directly receives the original data information of the battery system sent by the second CAN transceiver. In the present invention, the first communication network and the second communication network are used in conjunction with each other, ensuring that the whole machine controller of the aircraft can still receive the original data of the battery system in the fault state, greatly improving the ability to estimate the state of the battery system and improving the safety of the aircraft.

The invention discloses an intelligent behavior prediction method and system based on a time interest network, and relates to the technical field of software engineering, and the method comprises the steps: receiving a behavior sequence, dividing the behavior sequence through different time periods, and obtaining a behavior sequence of each time period, inputting the behavior sequence of each time period into a pre-established multi-head self-attention mechanism and a position coding model, and outputting to obtain an interest feature vector of each time period; inputting the interest feature vector of each time period into a pre-established Bi-LSTM model, outputting to obtain an interest sequence result, sequentially inputting the interest sequence result into a pre-established residual network and a Dropout layer to obtain an optimized interest sequence result, inputting the optimized interest sequence result into a pre-established MLP layer, and outputting to obtain a behavior prediction result. And the precision and the pre-estimation capability of intelligent behavior prediction are improved.

The embodiment of the application provides a face posture estimation method, which comprises the following steps: obtaining a target face image, performing feature extraction processing on the target face image through a preset feature extraction network to obtain face angle features of the target face image, performing feature conversion processing on the face angle features through a preset feature conversion network to obtain a rotation matrix of the target face image, and determining a face posture angle of the target face image based on the rotation matrix. Through the above method, the face angle features are extracted and processed, the problem that the face posture estimation precision is not accurate enough and the speed is not fast enough at present is solved, and the face posture estimation effect is improved.

An estimation system includes obtaining means configured to obtain brain wave measurement data and functional magnetic resonance imaging measurement data simultaneously measured from a subject, first calculation means configured to calculate first functional connectivity for each channel combination based on correlation between channels included in the brain wave measurement data, second calculation means configured to calculate second functional connectivity for each brain network based on correlation between regions of interest included in the functional magnetic resonance imaging measurement data, third calculation means configured to calculate a disorder-likelihood label by calculating a score representing disorder-likelihood to be estimated with the use of a plurality of second functional connectivities, and machine learning means configured to determine an estimation model for estimating disorder-likelihood based on prescribed first functional connectivity by machine learning using the first functional connectivity for each channel combination and the disorder-likelihood label.

The application provides a human posture estimation behavior analysis method, comprising: processing human image information into picture data, obtaining global posture features of each group of pictures, and obtaining an image frame sequence with human two-dimensional key point information based on the global posture features; establishing a motion model according to the image frame sequence, estimating the task motion state in the image frame sequence, constructing a Transformer model, and generating posture hypotheses based on a multi-hypothesis generator of the Transformer model to regress each group of posture hypotheses to generate posture hypothesis information; constructing a behavior prediction network, learning based on pre-collected posture data to obtain optimal parameters of the network; applying the optimal parameters to the behavior prediction network, predicting the posture hypothesis information based on the behavior prediction network, and finally outputting predicted posture estimation data. The application does not require manual parameter setting, improves the efficiency and accuracy of neural network parameter searching, is simple to operate, and is convenient for staff to use.