79 results about "Reduced order" patented technology

The invention provides a compressor flow field reduced-order modeling method and device based on POD and deep learning, and relates to the technical field of compressor flow field modeling, and the method comprises the steps: obtaining three-dimensional transient flow field data of a compressor flow field region under a plurality of working condition parameters, and constructing a flow field data set containing a plurality of time snapshots based on the three-dimensional transient flow field data; obtaining target flow field snapshot data of the compressor based on the flow field data set; performing intrinsic orthogonal decomposition on the target flow field snapshot data, and obtaining a dimension-reduced time coefficient matrix based on the decomposed data; and constructing a training set based on the working condition parameters and the dimensionality-reduced time coefficient matrix, and training a pre-constructed neural network prediction model by using the training set to obtain a target prediction model. According to the compressor flow field reduced-order modeling method, the target prediction model integrated with the flow physical law can be trained and constructed, and the prediction task under the new working condition can be completed by adopting the target prediction model.

Methods are disclosed of controlling operation of a Li-ion battery system. Such methods include obtaining a predicted state of the Li-ion battery system from a reduced order model either with degradation (in first methods) or without degradation (in second methods), and correcting said predicted state by applying a Kalman filter to the predicted state and battery measurements such that an improved predicted state is generated. In second methods, degradation is modelled through degradation model separated or independent from reduced order model without degradation. Li-ion battery system is controlled based on the improved predicted state of the Li-ion battery system. Systems, computing systems and computer programs are also disclosed which are suitable to perform said methods.

The invention relates to a thermal coupling over-reduced order prediction method and system for a multi-component assembled nonlinear system. The method comprises the following steps: collecting multi-scale physical field data; constructing an intrinsic orthogonal decomposition basis function space of a temperature field and a stress field, and establishing a double-field coupling constraint equation; constructing contact thermal resistance parameterized proxy models of a cylinder contact area, a bolt area and a free deformation area by adopting a domain discrete empirical interpolation method; constructing a parametric intrinsic mode tensor network to obtain a decline model which is used for realizing real-time reconstruction of a mode basis function through acquired tensor slices in an online stage; performing dynamic inversion based on a modal basis function reconstruction result, and outputting a predicted transient displacement field, a predicted temperature gradient field and a predicted contact stress field; and obtaining real-time parameters, and calculating a residual error with a corresponding prediction result so as to dynamically update the primary function and interpolation point distribution. Compared with the prior art, the real-time prediction of the transient thermal coupling of the multi-component contact system is realized on the premise of ensuring the precision.

Systems and methods for controlling an implantable pump are provided. For example, the exemplary controller for controlling the implantable pump may only rely on the actuator's current measurement. The controller is robust to pressure and flow changes inside the pump head, and allows fast change of pump's operation point. For example, the controller includes, a two stage, nonlinear position observer module based on a reduced order model of the electromagnetic actuator. The controller includes an algorithm that estimates the position of the moving component of the implantable pump based on the actuator's current measurement and adjusts operation of the pump accordingly. Alternatively, the controller may rely on position measurements and / or velocity estimations.

The invention discloses a physical field reconstruction method fusing a reduced-order model and a multi-fidelity model, and belongs to the technical field of data-driven physical field reconstruction. The method comprises the following steps of: firstly, carrying out nonlinear dimension reduction on high-dimensional simulation data by utilizing a deep auto-encoder, extracting a low-dimensional feature vector, training an encoder-decoder network, and establishing bidirectional mapping between high-dimensional data and low-dimensional data; then, a mapping model from the working condition parameters to the low-dimensional features is constructed and used for predicting feature vectors under the new working condition; the prediction features are then reconstructed by a decoder into preliminary physical field data as a low fidelity trend. And finally, on the basis of the trend, in combination with sparse high-fidelity measured data, correction is carried out through a multi-fidelity fusion model, and a high-precision reconstructed physical field is obtained. According to the method, the precision and credibility of physical field prediction are effectively improved by fusing multi-source data, and the method is suitable for the fields of structural health monitoring, digital twinning and the like.

To provide favorable systems and methods for determining blood flow characteristics of a patient.SOLUTION: One method includes: receiving, in an electronic storage medium, patient-specific image data of at least a portion of vasculature of the patient having geometric features at one or more points; generating a patient-specific reduced order model from the received image data, the patient-specific reduced order model comprising estimates of impedance values and a simplification of the geometric features at the one or more points of the vasculature of the patient; creating a feature vector comprising the estimates of impedance values and the geometric features for each of the one or more points of the patient-specific reduced order model; and determining blood flow characteristics at the one or more points of the patient-specific reduced order model using a machine learning algorithm trained to predict blood flow characteristics based on the created feature vectors at the one or more points.SELECTED DRAWING: None

The invention relates to a metal additive manufacturing three-dimensional temperature field Gaussian process prediction method, belongs to the technical field of material science, and particularly relates to a metal additive manufacturing three-dimensional temperature field prediction method. Logarithmic transformation is adopted to preprocess a temperature field, and prediction difficulty caused by extreme gradient near a molten pool is avoided; dividing the overall computational domain into a plurality of sub-domains by adopting a domain decomposition strategy to reduce the problem dimension; for each sub-domain, further combining singular value decomposition to extract a temperature field reduced-order base; establishing a local Gaussian process regression model based on a Maren kernel function and carrying out parallel training so as to establish rapid mapping from process parameters to reduced-order output; during online prediction, efficient and accurate prediction of a complete temperature field is realized through parallel calculation and full-field assembly of each local model.

The invention discloses a new energy system frequency domain modeling and equivalent circuit order reduction analysis method, and relates to the technical field of new energy power system modeling and stability analysis. The method is used for solving the problems that in an existing frequency domain modeling means, the automation degree of data acquisition is low, fitting precision and stability are poor, equivalent circuit universality is poor, and order reduction analysis is not systematic. The method comprises the following steps: acquiring system frequency domain response data based on disturbance injection; constructing a system rational function model by adopting an improved vector fitting algorithm; and then model order reduction is realized through state space modeling and an SVD-based balanced truncation method, and response consistency and stability analysis is carried out in a frequency domain and a time domain. The method can be widely applied to modeling analysis of new energy equipment such as wind power equipment, voltage source converters and high-voltage direct-current power transmission equipment, and has the advantages of being high in automation degree, high in modeling precision, good in visualization, clear in structure, suitable for simulation and control design and the like.

Systems and methods are disclosed for determining blood flow characteristics of a patient. One method includes: receiving, in an electronic storage medium, patient-specific image data of at least a portion of vasculature of the patient having geometric features at one or more points; generating a patient-specific reduced order model from the received image data, the patient-specific reduced order model comprising estimates of impedance values and a simplification of the geometric features at the one or more points of the vasculature of the patient; creating a feature vector comprising the estimates of impedance values and geometric features for each of the one or more points of the patient-specific reduced order model; and determining blood flow characteristics at the one or more points of the patient-specific reduced order model using a machine learning algorithm trained to predict blood flow characteristics based on the created feature vectors at the one or more points.

The invention discloses a damage evolution prediction method and device based on dynamic order reduction, equipment, a medium and a product, and relates to the field of aero-engine health management and monitoring. The method comprises the following steps: performing a finite element fatigue / creep-fatigue simulation test on a similar structural member covering stress states under various operating conditions, and extracting a time-physical field matrix of finite element fatigue simulation results under the various operating conditions; performing dynamic order reduction processing on the time-physical field matrix to reduce the dimension of the matrix to obtain an order-reduced matrix; constructing a reduced order model; performing equivalent stress field distribution reduction according to the reduced-order model to obtain a reduced-order reduced physical field; and performing damage distribution evolution and fatigue life prediction under fatigue or creep-fatigue load based on the reduced-order reduction physical field, and performing correction based on a fatigue life prediction model. According to the invention, the efficiency and universality of life prediction can be improved.

The invention discloses a structure configuration generation method, device and equipment and a readable storage medium, and is applied to the technical field of computers, and the method comprises the steps: carrying out the decoupling processing of a global grid model, and obtaining an order reduction model and a structure optimization model; applying an external load and a boundary condition to the reduced-order model, and solving to obtain a displacement load; and inputting the displacement load, the design constraint and the manufacturing constraint into a pre-trained structure configuration optimization model to obtain a generated optimal structure configuration. According to the method, the calculation scale of the structure configuration optimization model is greatly reduced, the calculation efficiency is improved, and the grid resolution in the to-be-optimized target structure area is improved, so that the high-fidelity structure configuration is generated; unnecessary materials can be reduced on the premise that the safety of a train is not influenced; on the premise of keeping the geometric features of the target structure region to be optimized similar, a high-fidelity structure configuration can be generated for any size, external load and boundary conditions, and the universality in a global parameter space is realized.

The invention discloses a reduced order modeling method for online state monitoring of a wind turbine generator blade, which comprises the following steps of: 1) constructing a kinetic equation of the wind turbine generator blade by using a central rigid body-flexible beam model, and dispersing the kinetic equation by using a finite element method to obtain a finite element model; (2) solving the finite element model obtained in the step (1) to obtain a displacement solution set of blade nodes, constructing a transformation matrix through the displacement solution set of the nodes, and performing order reduction on the finite element model obtained in the step (1) by using the transformation matrix to construct an order reduction model; 3) giving the geometric dimension of the wind turbine generator blade and the actual operation parameters of the wind turbine generator, respectively calculating the transverse displacement of the tail end of the blade by using the reduced order model and the finite element model, comparing the precision of the reduced order model with different reduced order numbers, and selecting a proper reduced order number; a calculation result shows that the calculation cost of transient response analysis is effectively reduced on the premise that the blade transient response calculation precision is guaranteed.

A system and method are provided for training a neural network for controlling operation of a system having non-linear dynamics represented by partial differential equations (PDEs). The method includes collecting a digital representation of time series data indicative of an instance of a function space of the system and a measurement of a state of operation of the system. A configuration point corresponding to the solution of the PDE is generated. A neural network is trained using training data including the collected time series data and the configuration points to train parameters of the non-linear operator. The neural network has an autoencoder architecture, the autoencoder architecture comprising: an encoder to encode each instance of training data into a potential space; a non-linear operator for propagating the encoded instance into a potential space using a transformation determined by a parameter of the non-linear operator; and a decoder to decode the transformed encoded instance of the training data to minimize the hybrid loss function.

The invention relates to the technical field of glass production process intelligent control, in particular to a glass production process intelligent control system based on a PLC. The system comprises a data acquisition module, a first processing module, a second processing module, a damage evaluation module, a state determination module and a parameter adjustment module. The system predicts a temperature field in the kiln and calculates thermal stress by collecting PLC and sensor data and using a reduced order model; the core is to track the historical fluctuation of thermal stress and determine the accumulated fatigue damage degree based on the fatigue accumulation theory; converting the temperature into the kiln health degree to determine a health perception regulation factor and a control mode; when the health degree is reduced, the system adaptively adjusts the control parameters of the PLC, so that the control response tends to be gentle and conservative; according to the invention, health perception adjustment of the control strategy is realized, and excessive active control behaviors causing physical damage can be actively avoided.

The invention provides an LNG (Liquefied Natural Gas) flexible pipeline vibration control method based on multi-physics field reduced-order model prediction, which comprises the following steps of: acquiring temperature distribution data and dynamic strain data along an LNG flexible pipeline in real time, and acquiring vibration acceleration signals of key nodes of the pipeline by utilizing an acceleration sensor; a flow field pressure mode and a structure vibration mode under the water hammer-thermal shock coupling effect are extracted through an intrinsic orthogonal decomposition method, and a multi-physical-field reduced-order prediction model capable of achieving online real-time calculation is constructed; dynamically adjusting the allowable vibration amplitude threshold value of each pipe section of the pipeline; inputting the real-time data into a multi-physics field reduced order prediction model, predicting pipeline vibration response and thermal stress evolution trajectory in a future limited time domain, and solving an optimal control input vector by taking maintenance of the pipeline response in an allowable vibration amplitude threshold range as a constraint; the optimal control input vector is decomposed into a fluid side instruction and a structure side instruction. The safety of the LNG flexible pipeline under the extreme working condition is improved.

The application provides a method and system for offshore wind turbine integrated dynamic feature reservation. The full state time series data of the offshore wind turbine multi-physical field coupling system is obtained, the modal parameters of the system are extracted by using a dynamic modal decomposition method, the participation factor matrix is calculated, the participation degree of each state quantity and the corresponding physical link to each mode is quantified, the dominant state quantity of the extracted mode and the corresponding physical link are located, the dominant state set is constructed, the time scale distribution of each mode is quantified, the time scale distribution characteristic atlas of different physical links of the overall system is formed, the fast time scale, analysis time scale and slow time scale boundaries in the atlas are divided according to different research needs, and the offshore wind turbine integrated reduced order model is constructed based on the singular perturbation theory. The application can effectively reserve the dynamic features of the offshore wind turbine multi-field coupling characteristics, and provides a precondition and quantitative basis for physical-based model reduction modeling.

The invention relates to the field of intelligent manufacturing and industrial digital twinning, in particular to a virtual simulation and state prediction system for operation data of a glass production line. The system comprises a data acquisition module, a reduced-order fluid simulation module, a time sequence deep learning module and a reverse optimization module. The system drives a reduced-order physical model based on boundary and disturbance variables to generate virtual flow field features reflecting heat flow coupling, and spatial-temporal feature fusion is carried out to solve the defect occurrence probability; the core of the method is that an invisible high-temperature fluid state in a melting furnace is reconstructed at a second-level scale by utilizing a reduced-order model, and recommended operation parameters are output based on a reverse algorithm when the risk exceeds the limit; according to the method, the measurement blind area of the sensor is effectively filled, the calculation cost is greatly reduced, and real-time perspective and accurate regulation and control of the black box production environment are realized.

The application discloses a small sample high-dimensional flow field data-oriented reduced-order prediction and reconstruction method and relates to the field of neural networks.The small sample high-dimensional flow field data-oriented reduced-order prediction and reconstruction method comprises the following steps: obtaining high-dimensional flow field data samples based on numerical simulation; constructing a unified sampling coordinate system to sample the high-dimensional flow field data samples and performing key flow field weighted reduced-order decomposition; constructing a multi-output proxy model and adopting a Bayesian method to adaptively optimize shared hyperparameters; adopting a genetic algorithm to adaptively optimize training sample grouping weights; and performing high-dimensional flow field prediction and reconstruction under a to-be-measured working condition.The small sample high-dimensional flow field data-oriented reduced-order prediction and reconstruction method can realize sample utilization efficiency under a small sample condition and improve prediction accuracy.

The invention discloses an intermediate frequency sea wind flexible direct current converter valve control method and system based on hot spot migration trajectory prediction, and the method comprises the steps: carrying out the intermediate frequency carrier phase alignment of converter valve operation data, obtaining the fusion data of phase alignment, and obtaining a chip or submodule loss sequence; obtaining a reduced-order thermal model parameter, and constructing a reduced-order coupling predictor based on the phase-aligned fusion data and the chip or submodule loss sequence; according to the reduced-order coupling predictor, obtaining a hotspot migration trajectory prediction and trajectory uncertainty elliptic domain; and according to the hot spot migration trajectory prediction and trajectory uncertainty elliptic domain, solving a thermal-electric cooperative control target, obtaining a gate pole control instruction, and controlling a converter valve. According to the method, the prediction precision is improved through online self-calibration of the model, and active equalization of thermal-electric cooperation is realized by using the uncertainty boundary.

The application discloses a pipeline vibration characteristic prediction method and system, and belongs to the technical field of natural gas station pipeline vibration prediction, wherein the method comprises pipeline three-dimensional model construction, pipeline vibration data obtained by fluid and structure dynamics method calculation, reduced order basis vector obtained based on intrinsic orthogonal decomposition method, reduced order coefficient obtained by using a neural network model, and vibration prediction realized by coupling the reduced order basis vector and the reduced order coefficient. The application can quickly predict the pipeline vibration change condition by combining the reduced order coefficient and the neural network model. The method can perceive the change of the overall dynamic characteristics of the pipeline network caused by the slight change of the key parameters, has very high detection sensitivity for early and local abnormalities which are difficult to be found by the traditional method, and realizes the accurate prediction of the pipeline vibration.

The application discloses a kind of floating wind turbine power motion and structural response reduced-order modeling and integrated fast prediction method, comprising: finite element modal analysis is carried out to floating wind turbine structure, extracts rigid body mode and main elastic mode, constructs low-dimensional modal space and orthogonalizes mass, stiffness matrix, reduces system degree of freedom;According to the initial position of structure, calculate hydrostatic force recovery, mooring, gravity stiffness and external excitation force, static water balance control equation is established by modal space transformation, and generalized displacement is solved by iteration;Based on radiation diffraction theory, water pressure is recalculated at structure grid gauss point, aerodynamic load is calculated by combining blade element momentum theory, and generalized external load is obtained after superposition and modal transformation;Motion equation is established in modal space, and generalized displacement is solved by numerical integration and reconstructs global displacement field, and stress time history is directly calculated, to realize integrated fast prediction.The method can keep the accuracy of key dynamic characteristics and response of structure, significantly improve the calculation efficiency, and provide reliable support for near real-time evaluation of floating wind turbine operation and maintenance.

A polyhedral reduced-order model (ROM) generator is provided for use by an optimization controller in a heating, ventilation, and air conditioning system. The physical model generator includes: interface circuitry for receiving a training dataset via a network connected to an analog computer; a memory for storing the polyhedral ROM for predicting the dynamics of airflow in a room, the training dataset, and instructions for calculating parameters of the polyhedral ROM; and a processor for calculating the parameters of the polyhedral ROM. The computation includes computing a global projection operation from a higher-dimensional state to a reduced-order state, computing a global lifting operation from the reduced-order state to a higher-dimensional state, constructing a local reduced-order model of the reduced-order state dynamics for each physical parameter value in the training dataset, and generating the polyhedral ROM by combining a weighted average of the local reduced-order model with the projection and lifting between the reduced-order state and the full state.

The invention provides a global response reconstruction method and device based on an intelligent enhanced reduced-order model, and the method comprises the steps: obtaining the local structure data of a to-be-reconstructed scene, and enabling the local structure data to be obtained through the collection of the to-be-reconstructed scene based on a sensor; an orthogonal base space matrix under model order reduction is obtained, the column vector of the orthogonal base space matrix is an orthogonal base vector, and the orthogonal base vector is expanded into a low-dimensional subspace; and based on the local structure data and the orthogonal base space matrix, performing reconstruction to obtain a high-dimensional global response of the to-be-reconstructed scene matched with the local structure data. A high-dimensional and complex structure response field is projected to a low-dimensional subspace by using an orthogonal base space matrix with physical consistency, so that the high-dimensional global response of a to-be-reconstructed scene can be obtained through accurate reconstruction and deduction based on local structure data of the to-be-reconstructed scene.

The application discloses a kind of carbon fiber composite material performance optimization method and system based on multi-physical field reduced order model, and it is related to carbon fiber composite material design field.Method includes: generating sample point in design variable space and carrying out high-fidelity simulation, extract full-field response data to construct snapshot matrix;Eigenvalue orthogonal decomposition is carried out to snapshot matrix to extract leading mode and constitute reduced order base, construct deep neural network to establish the nonlinear mapping of design parameter to reduced order coordinate, train network using the total loss function of data fitting loss and physical residual loss weighted summation;Reduced order base and neural network are encapsulated as fast predictor;Predictor is integrated into optimization algorithm, and the process of recommending candidate point, predicting performance, updating historical data is carried out, and the optimal design scheme is output.The application shortens single analysis time from hour level to second level by reduced order technique, and physical information constraint ensures model reliability, to realize the efficient and high-precision optimization design of composite structure.

The application discloses a kind of double-ended flexible DC system stability analysis method and system, the method includes: establishing single-converter-ideal DC source system, and determining dominant mode;Based on double-ended flexible DC system, the transfer function of DC side state variable is determined;According to the dominant mode, the transfer function is simplified, and the reduced order model is obtained;Based on the reduced order model, the analytical condition of system small disturbance stability is determined, and the stability of double-ended flexible DC system is analyzed using the analytical condition.The application simplifies the model of general double-ended flexible DC system by model reduction, reveals the stability mechanism of the DC side of the system, provides the analytical condition of small disturbance stability of the DC side state variable of flexible DC transmission system, which is conducive to fully utilizing the transmission capacity of double-ended flexible DC system and improving the frequency stability of the system.

The invention relates to a nonlinear structure reduced-order model construction method based on sparse recognition and a mixed mode, belongs to the technical field of structural dynamics analysis and aeroelastic mechanics analysis, and solves the problem that complex motion caused by geometric nonlinearity under large deformation cannot be accurately described in the prior art. Comprising the following steps: S1, establishing a nonlinear finite element model of a target large flexible wing to obtain a training data set; s2, solving a mixed modal basis based on the displacement residual error and SVD (Singular Value Decomposition); s3, establishing a nonlinear stiffness coefficient solving problem model, introducing LASSO regression to establish an LASSO regression optimization objective function, and solving to obtain a sparse nonlinear stiffness coefficient; s4, based on the sparse nonlinear stiffness coefficient and the structural kinetic equation, establishing a nonlinear structure reduced-order model; and S5, applying the nonlinear structure reduced-order model to statics response solution and dynamics response solution of the large flexible wing to obtain statics response and dynamics response results.

The embodiment of the application discloses a transformer multi-physical field direct coupling reduced-order processing method and related device, method includes: obtaining and using the geometric parameters, material properties and operation condition of the transformer, establishing the simulation geometric model of the transformer; based on the heat generation, fluid flow and fluid-solid heat transfer process of the transformer operation, the initial coupling model of the thermal-fluid-solid multi-physical field direct coupling of the transformer is constructed; the reduced-order model of the thermal-fluid-solid multi-physical field is established by using the random forest algorithm and the initial coupling model, the multi-physical field operation simulation of the transformer is carried out according to the simulation geometric model and the reduced-order model, and the operation simulation result reflecting the operation condition of the transformer in the multi-physical field is obtained. Through the random forest algorithm for the reduction of the initial coupling model, the complexity of the model can be simplified, the degrees of freedom in the simulation model are reduced, in the multi-physical field operation simulation, the calculation efficiency of the simulation can be improved, the demand for computing resources is reduced, and the reliability of the result is maintained.

The application discloses a dry-type transformer passive measuring point and reduced-order model temperature field reconstruction method and system, and relates to the field of power equipment thermal field monitoring and modeling. The method comprises the following steps: acquiring real-time discrete temperature data of a plurality of predetermined passive measuring points of a dry-type transformer in an operating state to form a measuring point temperature vector; calling a mean field, a multi-scale double-layer reduced-order basis and a measuring point weight which are pre-constructed based on a structure parameter and a temperature field snapshot matrix; mapping the mean field and the reduced-order basis to the measuring point dimension according to the passive measuring point position, and using an adaptive weighted stitching proper orthogonal decomposition algorithm to combine the measuring point weight to weight the residual error, determining an active mode set and solving a mode coefficient according to the residual error change before and after the candidate mode is added; and then combining the mean field, the active mode and the mode coefficient to generate a global temperature field at the current time. Thus, the temperature field reconstruction accuracy, robustness and online calculation efficiency can be improved under the condition of a small number of measuring points.

A system for monitoring corrosion-induced degradation of electronic devices. A modeling processor generates a model of the physical characteristics of an electronic device. The modeling processor generates and validates a complex model of the localized effect of corrosion on the electronic device. The modeling processor then generates a reduced order model based on the complex model. A corrosion monitor processor receives sensor measurements within a cabinet associated with the electronic device. The corrosion monitor processor executes the reduced order model based on the physical characteristics of the electronic device and the sensor measurements to generate a predicted corrosion rate. The corrosion monitor generates an expected lifetime of the electronic device based on the corrosion rates and provides alerts based on expected remaining lifetime.