Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

31 results about "Recursive model" patented technology

A recursive model is a special case of an equation system where the endogenous variables are determined one at a time in sequence. Thus the right-hand side of the equation for the first endogenous variable includes no endogenous variables, only exogenous variables.

Multivariable artificial pancreas method and system

Methods and modules for using physiological (biometric) variables to advance the state of the artificial pancreas. The method and system includes one or more modules for recursive model identification, hypoglycemia early alert and alarm, adaptive control, hyperglycemia early alert and alarm, plasma insulin concentration estimation, assessment of physical activity (e.g., presence, type, duration, expected effects on insulin sensitivity and GC), detection of acute stress and assessment of its impact on insulin sensitivity, detection of sleep and its stages and assessment of sleep stages on GC, sensor fault detection and diagnosis, software and controller performance evaluation and adjustment and / or pump fault detection and diagnosis.
Owner:ILLINOIS INSTITUTE OF TECHNOLOGY

Image description method of bidirectional multi-mode recursive network

The invention provides an image description method of a bidirectional multi-mode recursive network. The image description method comprises the steps that downward images serve as a training set, and images in the training set and description sentences corresponding to the images are obtained; words emerging in the sentences in the training set are extracted, and a vocabulary is established; a pre-trained convolutional neural network is utilized to extract characteristics in the images in the data set; a bidirectional multi-mode recursive model is established, and the extracted image characteristics are fused with corresponding text characteristics; the bidirectional multi-mode recursive model is trained; a picture is input into the pre-trained model to obtain a corresponding description sentence.
Owner:南通斑马智能科技有限公司

Multi-state system dynamic reliability assessment method

The invention discloses a multi-state system dynamic reliability assessment method. According to state information monitored by multi-state systems and constitution logic of units in the multi-state systems, current state probabilities of the units in the multi-state systems are calculated by building a Bayes recursive model, and therefore the state probabilities and reliability of the multi-state systems in the surplus service period are deduced. The method makes full use of the state information monitored by each system to update a reliability assessment model. Compared with an existing reliability assessment method, the multi-state system dynamic reliability assessment method can achieve the fact that more accurate and dynamically updated reliability assessment values of each system can be obtained, and therefore each system can be effectively prevented from losing efficacy, and more accurate maintaining strategies are generated in a guided mode.
Owner:UNIV OF ELECTRONIC SCI & TECH OF CHINA

Adaptive unscented Kalman particle filtering method

PendingCN110455287AHigh precisionThe number of receiving stars is smallNavigation by speed/acceleration measurementsRecursive modelFilter gain
The invention discloses an adaptive unscented Kalman particle filtering method. The method utilizes the theory of the Sage filtering windowing method, also combines the idea of fading, estimates a true covariance matrix of the observed quantity by collecting an epoch innovation vector, and compares the true covariance matrix with the covariance matrix of a filtering recursive model, when a deviation exists between the two covariances, the observed covariance matrix of the system is adaptively adjusted according to the difference. Based on the process, an adaptive fading factor is designed, theobservation noise is further modified, the modified observation noise participates in the solution of a gain matrix, and thus the state estimation can be adaptively adjusted. The scheme of the invention can effectively perform filtering correction on a strongly nonlinear satellite / inertial integrated navigation system, especially when the external noise is abnormal, the filtering gain can be effectively and adaptively adjusted to improve the robustness and positioning accuracy of the system.
Owner:NANJING UNIV OF SCI & TECH

Gesture identification method based on recursive model

The invention discloses a gesture identification method based on a recursive model. The method comprises the basic steps of: 1, carrying out preprocessing on static and dynamic gesture images; 2, extracting static and dynamic gesture space sequences; 3, according to the gesture space sequences, constructing a gesture recursive model; and 4, by the gesture recursive model, carrying out gesture classification. According to the gesture identification method disclosed by the invention, in a form of converting the gesture space sequences into the recursive model, problems caused by different lengths of acquired gesture space sequences and incomparability of data values of sequence points are effectively solved, and robustness of a gesture identification algorithm is improved.
Owner:NORTHWEST UNIV

Reliability degree assessment method for multilevel state monitoring data fusion

The invention discloses a reliability degree assessment method for multilevel state monitoring data fusion. The reliability degree assessment method specifically comprises the following steps of: determining states in a system and unit degradation process according to system and unit degradation laws, determining a unit state combination corresponding to the various states of a system, and collecting the state monitoring data or information of the system and units during a service process; updating the current state probability of the units in the system according to multilevel state monitoring data or information; dynamically estimating the reliability of the multi-state system in the remainder service period. According to the method disclosed by the invention, the state monitoring data or information of a system level and a unit level in the multi-state system is fused, the logical combination relationship between the system and unit degradation laws is combined, and the current state probability of each unit in the multi-state system is determined by constructing a Bayes recursive model, thus predicating the future state and reliability of the system; meanwhile, the errors of the state monitoring data or information are considered, thus the method disclosed by the invention is higher in universality.
Owner:UNIV OF ELECTRONIC SCI & TECH OF CHINA

Method of realizing satellite remote sensing image high precision geometric correction through slightly modifying RPC parameters

ActiveCN105761228APrevent morbidityImproved accuracy of image correctionImage enhancementImage analysisRecursive modelSelf adaptive
Provided is a method of realizing satellite remote sensing image high precision geometric correction through slightly modifying RPC parameters, which realizes image high precision geometric correction through adjusting 78 rational polynomial coefficients in RPC parameters of an RPC model after traditional RPC image space affine transformation parameter orientation, wherein a normal equation ill-conditioned problem utilizes precision information after image space affine transformation orientation to adaptively construct a regularizer and regularization parameters, thereby realizing robust resolution of 78 RPC parameters of satellite remote sensing images. Under the condition of sufficient ground control points, the method can obtain higher geometric correction precision than a traditional image space affine transformation RFM recursive model and a precise model, and has obvious advantages than traditional methods in the remote sensing image automatic matching and correction filed based on existing reference geographic data.
Owner:CHINESE ACAD OF SURVEYING & MAPPING

Industrial data driving prediction control method based on subspace identification

InactiveCN107179689AImprove practicalitySolving nonlinear time-varying problemsAdaptive controlRecursive modelSubspace model identification
The invention discloses an industrial data driving prediction control method based on subspace identification. The industrial data driving prediction control method includes steps of (1) calculating the predication model output and obtaining the predication output expressed by the predication increment according to the subspace model identification; (2) for the nonlinear time-varying characteristic, adopting the adaptive prediction control method of an online recursion identification model and updating the predication error of the before-after predication output and the process output through comparison to determine whether the predication model needs to be updated; and 3) performing constraint processing and for the physical constraints in the system, solving the problem by means of standard secondary programming and reducing the solution computational complexity by means of Lagrange daily functions. The industrial data driving prediction control method has the advantages of good practicality, high control precision, and simplified calculation.
Owner:STAR (CHONGQING) INTELLIGENT EQUIP TECH RES INST CO LTD

AUV cooperative navigation method of maximum correntropy adaptive cubature particle filter

The invention discloses an AUV cooperative navigation method of maximum correntropy adaptive cubature particle filter (MCACPF). The MCACPF is used for completing the state estimation problem in the AUV cooperative navigation process. During AUV cooperative navigation, a state equation and a measurement equation of the AUV cooperative navigation are reconstructed into a nonlinear recursive model, and then maximum correntropy cubature Kalman filter (MCCKF) is adopted in the framework of cubature particle filter (CPF) to generate an importance probability density function required in particle filter (PF), generated particles are then re-sampled by using a Kullback-Leibler distance (KLD) resampling method, and finally the estimation of an AUV state is obtained according to the algorithm flow of the CPF so as to realize the positioning of an AUV and complete the cooperative navigation. The MCACPF method is applied to the AUV cooperative navigation with outliers in measurement noise, higheraccuracy than existing PF, improved PF and robust filtering is obtained, and the computational complexity is lower than an existing improved particle filtering algorithm.
Owner:HARBIN ENG UNIV

Power construction budget estimate planning method and networking system thereof

The invention relates to a budget estimate planning method and the technical field of networks, in particular to a power construction budget estimate planning method and a networking system thereof, realized by a computer system. The networking system comprises a design system inner network and budget estimate system software and is connected with an external network by a firewall and a gateway; the system software also comprises a system main module and a planning module (1), a resource management module (2), a sample database management module (3), an approval module (4), an information statistics and issue module (5) and a system interface and management module (6). The method adopts a tree structure recursive model to solve the problems of the online dynamic regulation and the traversal of a budget tree structure, adopts a multiplex iterative algorithm to solve the convergence problem of an aggregate project amount and adopts a Web Service program to solve the problems of data transmission and information share between distributed real-time heterogeneous databases. The invention already finishes 20 thousand of budget estimate planning and relates to construction amount amount over ten billion.
Owner:SHANGHAI UNIV OF ENG SCI

Indoor positioning method based on ridge regression and extreme learning machine

The invention reveals an indoor positioning method based on ridge regression and an extreme learning machine, and the method comprises the following steps: S1, an offline data set construction step: collecting wireless signal receiving intensity data in a positioning area, and establishing an offline data training set; S2, an offline learning step: learning the relation between the wireless signalreception intensity and the target position in the offline data training set through using the ridge regression technique and the extreme learning machine technology, and performing training to obtain a position-based recursive model; S3, an online data acquisition step: performing the online collection of the wireless signal receiving intensity data at a to-be-estimated position and substitutingthe wireless signal receiving intensity data into the position-based recursive model to obtain a position estimation result. The method has the advantages of good learning stability at the offline phase and high positioning accuracy at the online phase, and can fully meet the actual use requirements. Meanwhile, the method has low sensitivity to abnormal data elements in the offline training dataset and excellent anti-interference performance.
Owner:NANJING UNIV OF POSTS & TELECOMM

Recursive state estimation fused anomaly detection method for dynamic electric power system

ActiveCN110133400AQuantify Potentially Anomalous PropertiesImprove effectivenessElectrical testingElectric power systemStatistical analysis
The invention belongs to the technical field of situation awareness for a dynamic electric power system, and discloses a recursive state estimation fused anomaly detection method for the dynamic electric power system. The method comprises the following steps: firstly establishing a simplified non-linear recursive model of system node voltage according to the dynamic characteristic of the electricpower system, and reasonably representing the influence of the dynamic change of electric power system load on system node voltage; then realizing system node voltage dynamic estimation based on the non-linear recursive model based on a recursive state estimation filtering algorithm, and on this basis, further constructing a residual error random matrix of system node voltage; finally constructinga system residual error dynamic performance index based on characteristic spectrum mean value-square deviation statistical analysis so as to effectively reflect the influence of electric power systemanomaly on the residual error matrix eigenvalue distribution of system node voltage, and then judging according to a self-adaptive statistical threshold value to finally realize effective state estimation and anomaly detection of the dynamic electric power system.
Owner:QINGDAO UNIV

Functional testing method and device for an electronic product

A functional testing method of electronic products includes writing a document defining a functional specification of a product by a structured document according to a recursive model of a functional specification, so that this is comprehensible by human and non-human interpreters, thus automating the setting up of a functional testing apparatus of electronic products. The functional testing apparatus is adapted to interpret the document, is general-purpose and includes an interface with corresponding drivers, replaceable in relation to the type of product subject to functional test.
Owner:CREA - COLLAUDI ELETTRONICI AUTOMATIZZATI

Method for identifying combustion model of circulating fluidized bed on basis of least squares

The invention discloses a method for identifying a combustion model of a circulating fluidized bed on the basis of least squares. The method is characterized in that a method of parameter estimation of basic least squares is used for the control method. The method specifically includes the steps that (a) the model is built; (b) an initial value is set, i.e., parameter estimation is built for the combustion process of the circulating fluidized bed, and the initial value of an algorithm is set; (c) data are sampled, i.e., the data of the fuel quantity (input) and steam pressure (output) provided for a boiler in the combustion process of the circulating fluidized bed are input; (d) parameter recursive estimation is conducted; and (e) iteration convergence is conducted. Through the estimation method based on the least squares, the characteristics of a large time delay, nonlinearity and strong coupling of combustion of the boiler are considered sufficiently, the recursive model is built, and real-time control and on-line correction of a computer are facilitated; therefore, the precision of the built model is greatly improved, and input and output models of other industrial objects are easily built while the reaction speed and position control precision of a process system are increased effectively.
Owner:黄红林

Comprehensive energy system optimized operation method and system based on model prediction control framework

The invention discloses a comprehensive energy system optimization operation method and system based on a model prediction control architecture. The method comprises the steps of obtaining source loadhistorical data; carrying out multi-step prediction on the source load historical data by adopting a recursive ARIMA model to obtain source load prediction data; obtaining a predicted value of the error through a grey prediction model according to the error between the measured data and the predicted data, and correcting the predicted value of the source load by using the predicted value of the error; and inputting the corrected source load prediction value into a rolling optimization model, and optimizing and outputting the prediction value of the output of each device by adopting a geneticalgorithm. In a feedback correction link, aiming at time lag of loads such as cold and heat, equipment cannot compensate prediction errors in a short time in a real-time adjustment stage, error multi-step prediction is introduced, and errors in a prediction link are compensated in advance, so that the equipment output is adjusted in advance, and the influence of fluctuation of renewable energy andload prediction on the operation of the system is reduced more effectively.
Owner:SHANDONG UNIV

Freight flight gate allocation method, device and equipment and storage medium

The invention discloses a freight flight gate allocation method, device and equipment and a storage medium. The freight flight gate allocation method comprises the steps of determining input information of a recursive model according to freight flight information and gate information; according to the input information, the recursion model outputs the corresponding relation between the flights meeting the constraint condition and the gate positions with the recursion frequency equal to the number of the flights needing to be allocated with the gate positions as the end condition; and allocating flight gate positions according to the corresponding relationship. According to the technical scheme provided by the embodiment of the invention, the problem of airport gate position allocation canbe solved through a recursive function-based backtracking algorithm.
Owner:SF TECH

Method for predicting critical micelle concentrationof surfactant based on ab initio model

The invention discloses a method for predicting the critical micelle concentration of a surfactant based on an ab initio model. The method comprises the following steps: obtaining a recursive model according to statistical thermodynamics of chemical potential; after the occupied volume and the chemical sites of micelles with different sizes are obtained through molecular dynamics simulation calculation, adopting the recursion model to express the concentration of the (n + 1) polymer into an analytical function of the concentrations of the monomer and the n polymer; ff the monomer concentration is used as a starting point, sequentially calculating the concentrations of n polymers with different sizes by using the recursive equation, wherein n is equal to 2, 3,..., so that the size of the CMC is deduced. The method provided by the invention can be applied to various types of surfactants.
Owner:SHENZHEN JINGTAI TECH CO LTD

A Dynamic Reliability Evaluation Method for Multi-state Systems

The invention discloses a method for evaluating the dynamic reliability of a multi-state system. Specifically, according to the state information monitored by the multi-state system and the composition logic of the units in the system, a Bayesian recursive model is constructed to calculate the location of the units in the current multi-state system. Each state probability, from which the state probability and reliability of the multi-state system in the remaining service period are derived. The method of the present invention makes full use of the monitored state information of each system to update the reliability evaluation model, and compared with the existing reliability evaluation method, it can obtain a more accurate and dynamically updated reliability evaluation value for each system, This can effectively avoid the failure of each system and guide the formulation of a more lean maintenance strategy.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

A Kalman Filter Based Identification Method for Angle of Attack and Angle of Sideslip

The invention provides a method for identifying angle of attack and sideslip angle based on Kalman filter, comprising: establishing a recursive model and an observation model of angle of attack α and angle of sideslip β; obtaining a step of angle of attack α and angle of sideslip β Predicted value Xpre; get one-step predicted mean square error Ppre; get measurement matrix H and measurement quantity Z; get filter gain K; get Kalman filtering angle of attack α(k+1) and Kalman filtering side slip angle β( k+1); get the updated error variance matrix P'; get the updated one-step predicted value Xpre' of the attack angle α and sideslip angle β, and return to S4 based on the updated error variance matrix P' and the updated one-step The predicted value Xpre' is used for the next iteration. The present invention establishes the recursive model and the observation model of the angle of attack α and the sideslip angle β, and performs Kalman filtering based on the recursive model and the observation model of the angle of attack α and the sideslip angle β, so that the angle of attack α and the sideslip angle can be realized. High-precision online identification of angle β. The present invention is used under the condition of no measuring device for the angle of attack and the sideslip angle, saves a set of sensing collection equipment, and can realize synchronous measurement of the angle of attack and the sideslip angle.
Owner:BEIJING AEROSPACE TECH INST

Gear Remaining Life Prediction Method Integrated with Kernel Estimation and Random Filtering

InactiveCN109883691BRemaining Life PredictionMachine part testingRecursive modelFeature extraction
A kernel estimation and random filtering theory-based gear residual service life prediction method belongs to the technical field of mechanical reliability. The method comprises the following specificimplementation steps: 1, monitoring a gear degradation state in a main test gearbox in real time by using an acceleration sensor; 2, performing feature extraction on the gear degradation state; 3, performing non-parametric estimation on a probability density function of a continuous degradation state of the gear by using the characteristic that a kernel function does not make any assumption aboutdistribution of the data and starts from the data sample to obtain the probability density function of the degradation state of the gear based on the real-time state monitoring data; 4, updating a random filter recursive model parameter by using the real-time state monitoring data, and establishing a kernel estimation and random filtering-combined prediction model; and 5, predicting the remainingservice life of the gear through the kernel estimation and random filtering-combined prediction model. The kernel estimation and random filtering theory-based gear residual service life prediction method has the advantages that the degradation state and the real-time residual service life of the gear can be effectively predicted and a basis is provided for preventive maintenance of the gear.
Owner:TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Agent-based solar sail distributed simulation system

An Agent-based solar sail distributed simulation system comprises an orbit recursive model unit, an earth shadow model unit, a thermal control system model unit, a power supply system model unit, an attitude control model unit and an orbit control model unit, each model unit is an independent Agent module, and interconnection and data interaction between the Agent modules are achieved through the TCP / IP protocol. According to the system, microscopic behaviors of each component system, namely on-orbit status of each subsystem of a solar sail, can be described, the Agent modules can also be combined to describe macroscopic characteristics of the solar sail, so that each component unit and the integral body of the solar sail can be fully simulated conveniently, and the problems in the design stage of the solar sail can be found timely. In addition, distributed design is adopted by the system, complexity can be reduced, and simulation efficiency of the system can be largely improved.
Owner:北京航天驭星科技有限公司

An Online Recursive Calculation Method for the Occurrence Rate of Metallurgical Furnace Dust

The present invention provides an online recursive calculation method for fume occurrence rate of a metallurgical furnace. The method comprises: according to independent historical data in an uncertain interval period, constructing a nonlinear regression constraint model; performing nonlinear transformation and normalization processing on sample data; and calculating a coefficient matrix of a recursive model with a least square partial differential method. According to the method, the data is stored by using a fixed-length time sequence queue to facilitate updating of the historical data, and the regression coefficient matrix of the recursive model is calculated with the least square partial differential method, so that online prediction of the fume occurrence rate is implemented and data support is provided for online control and production decision of the metallurgical furnace.
Owner:金川集团信息与自动化工程有限公司

Functional testing method and device for an electronic product

A functional testing method of electronic products is described, which includes writing a document defining a functional specification of a product by means of a structured document according to a recursive model of a functional specification, so that this is comprehensible by human and non-human interpreters, thus automating the setting up of a functional testing apparatus of electronic products. Said functional testing apparatus, being adapted to interpret said document, is general- purpose and comprises interface means with corresponding drivers, replaceable in relation to the type of product subject to functional test.
Owner:CREA - COLLAUDI ELETTRONICI AUTOMATIZZATI

A method and system for online identification of tire cornering stiffness

The invention discloses an online identification method and system for tire cornering stiffness. The method comprises the following steps: step 1, establishing a vehicle dynamics model; step 2, simplifying the vehicle dynamics model based on a linear lateral tire force model to obtain a vehicle Simplified model of dynamics; Step 3, discretize the simplified model of vehicle dynamics to obtain a recursive model with the cornering stiffness of the front and rear wheels of the vehicle as the parameter to be estimated; Step 4, use the finite memory recursive minimum with forgetting factor The two times online identification method is used to identify the front and rear wheel cornering stiffness of the vehicle in the recursive model. The front and rear wheel cornering stiffness can be identified through the finite memory recursive least squares online identification method with forgetting factor, which can avoid the dimension disaster phenomenon, increase the real-time identification, and use limited historical data to achieve online identification Tire cornering stiffness, and overall suitable for most environments, with simple internal mechanical devices, high stability, and high algorithm efficiency.
Owner:NAT UNIV OF DEFENSE TECH

Reliability Evaluation Method of Multi-level Condition Monitoring Data Fusion

The invention discloses a reliability evaluation method for multi-level state monitoring data fusion, which specifically includes: according to the system and unit degradation law, determining the state of the system and the unit during the degradation process, and specifying the unit state combination corresponding to each state of the system; collecting system and the state monitoring data or information of the unit during service; update the current state probability of the unit in the system according to the multi-level state monitoring data or information; dynamically estimate the reliability of the multi-state system in the remaining service period. The method of the present invention combines the state monitoring data or information of the system level and the unit level in the multi-state system, and combines the logical combination relationship of the system and the unit state degradation law, and determines the current state of each unit in the multi-state system by constructing a Bayesian recursive model. state probability, so as to predict the future state and reliability of the system; at the same time, the method of the present invention considers the error of state monitoring data or information, making the method more general.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

A Speech Recognition Method Based on Power Spectrum Gabor Eigen Sequence Recursive Model

The invention discloses a speech recognition method based on the power spectrum Gabor feature sequence recursive model. The basic steps of the method include: 1. Preprocessing the speech input signal; 2. Extracting the power spectrum features and dynamic spectrum Delta features respectively; 3. .Use the spatiotemporal Gabor filter to filter the spectral features, and obtain the speech feature sequence through PCA dimensionality reduction processing; 4. Construct a recursive graph based on the speech feature sequence; 5. Complete speech recognition by performing distance detection on the speech recursive model. The present invention preprocesses the speech signal, obtains the speech feature sequence through feature extraction, and then converts the speech feature sequence into a recursive model for similarity detection, which effectively solves the problem of unstable noise and low signal noise in the current automatic speech recognition system. This improves the robustness of the speech recognition algorithm because the recognition rate is not ideal and the performance is prone to deterioration in complex situations.
Owner:XIAN MITE ELECTRONICS TECH CO LTD

A Bidirectional Multimodal Recurrent Network Image Description Method

The invention provides an image description method for a bidirectional multimodal recursive network, comprising: downloading images as a training set, acquiring images in the training set and their corresponding description sentences; extracting words appearing in the sentences in the training set and constructing a vocabulary ; Use the pre-trained convolutional neural network to extract the features of the images in the data set; build a bidirectional multimodal recursive network model, and fuse the extracted image features with the corresponding text features; train the bidirectional multimodal recurrent network model ; Input a picture into the pre-trained model to get the corresponding description sentence.
Owner:南通斑马智能科技有限公司

A Distributed Simulation System of Solar Sail Based on Agent

An Agent-based solar sail distributed simulation system comprises an orbit recursive model unit, an earth shadow model unit, a thermal control system model unit, a power supply system model unit, an attitude control model unit and an orbit control model unit, each model unit is an independent Agent module, and interconnection and data interaction between the Agent modules are achieved through the TCP / IP protocol. According to the system, microscopic behaviors of each component system, namely on-orbit status of each subsystem of a solar sail, can be described, the Agent modules can also be combined to describe macroscopic characteristics of the solar sail, so that each component unit and the integral body of the solar sail can be fully simulated conveniently, and the problems in the design stage of the solar sail can be found timely. In addition, distributed design is adopted by the system, complexity can be reduced, and simulation efficiency of the system can be largely improved.
Owner:北京航天驭星科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products