113 results about "Reduced order" patented technology

Systems and methods are disclosed for blood flow simulation. For example, a method may include performing a plurality of blood flow simulations using a first model of vascular blood flow, each of the plurality of blood flow simulations simulating blood flow in a vasculature of a patient or a geometry based on the vasculature of the patient; based on results of the plurality of blood flow simulations, generating a response surface mapping one or more first parameters of the first model to one or more second parameters of a reduced order model of vascular blood; determining values for the one or more parameters of the reduced order model mapped, by the response surface, from parameter values representing a modified state of the vasculature; and performing simulation using the reduced order model parameterized by the determined values, to determine a blood flow characteristic of the modified state of the vasculature.

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.

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.

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.

A method for offline Koopman system identification is provided which includes generating snapshots representing a thermal comfort quantification index, reshaping these snapshots into 3D tensors, and splitting them into training, validation, and testing datasets. An encoder is used to reduce state space shape, while a dynamic auxiliary network calculates the A and B matrices representing a reduced order system. The auxiliary output advances the reduced order system into a time step with the control of the boundary condition. A decoder is used to reconstruct the system to its original state for another time step, and a loss function for reconstruction, linearisation and prediction is computed.

The invention relates to a rapid prediction method for a temperature field and a stress field of a dangerous part of a key component of a small turbojet engine, belongs to the field of optimization design of small turbojet engines, and solves the problems of high cost and low efficiency of simulating the temperature field and the stress field of the turbojet engine by an existing conventional numerical simulation method. Comprising the steps of establishing a turbojet engine key component geometric model; generating temperature field and stress field data sets under different working conditions; reducing the order by using a POD flow field order reduction model and obtaining a transformation relation; training the deep learning model to obtain a mapping relation; inputting to-be-calculated working condition data to obtain reduced-order data; the distribution of the temperature field and the stress field under the specific working condition is obtained through recalculation by means of the transformation relation, rapid prediction can be achieved, and cost is saved. According to the method, deep learning and a flow field reduced order model are adopted, local dangerous parts under the given working condition can be predicted in time, calculation and time cost is saved, and timely data feedback is provided for prolonging the service life of an engine and keeping good performance of the engine.

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.

Disclosed are methods and systems for implementing optimization techniques for accelerated battery charging protocols. A state estimator model configured as a synthetic data generator generates a synthetic dataset from an input data. The synthetic dataset comprises one or more states of a battery. A surrogate model generates a set of features comprising exotic parameters representing internal attributes of the battery by applying time-series analysis to the synthetic dataset. A reduced order ML model determines a minimum charging time based on an optimization control parameter and a subset of features derived from the set of features while maintaining the optimization control parameter in an acceptable range. One or more charging protocols are generated based on the minimum charging time and the optimization control parameter. In some embodiments, an optimal charging protocol is further selected from the one or more charging protocols.

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

Disclosed is a digital twinning method for monitoring an operation state of a tower of a wind turbine generator system online. The method includes: 1) constructing a simplified model of the tower of the wind turbine generator system, and discretizing the simplified model according to a finite element method to obtain a finite element model; 2) reducing an order of the finite element model of the tower according to proper orthogonal decomposition, analyzing precision of a reduced-order model under different orders, and selecting the reduced-order model having a smallest reduced order as a final reduced-order model on the premise that the precision satisfies actual engineering requirements; and 3) programming upper computer software in a computer, deploying the reduced-order model to the upper computer software, further building a physical entity of the tower, and monitoring a stress and a strain of the physical entity online through the reduced-order model.

Methods and apparatuses that generate a simulation object for a physical system are described. The simulation object includes a trained computing structure to determine future output data of the physical system in real time. The computing structure is trained with a plurality of input units and one or more output units. The plurality of input units include regular input units to receive input data and output data of the physical system. The output units include one or more regular output units to predict a dynamic rate of change of the input data over a period of time. The input data and output data of the physical system are obtained for training the computing structure. The input data represent a dynamic input excitation to the physical system over the period of time. And the output data represents a dynamic output response of the physical system to the dynamic input excitation over the period of time.

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 relates to the technical field of operation state monitoring of large rotating mechanical equipment, and particularly provides a centrifugal impeller monitoring method and system based on a twin reduced-order model.The centrifugal impeller is provided with all-round blades, and the monitoring method comprises the steps that blade tip vibration signals of the all-round blades are collected to obtain original vibration data; preprocessing the original vibration data to obtain blade tip vibration data; processing the blade tip vibration data based on a keyless phase reference method to obtain blade tip vibration displacement; carrying out nonlinear least square curve fitting on the blade tip vibration displacement, and identifying kinetic parameters of each independent blade in the blades of the whole circumference; constructing a twinning reduced-order model of the centrifugal impeller, and determining update parameters of the twinning reduced-order model based on the kinetic parameters; updating the twin reduced-order model based on the update parameters to obtain a digital model; and monitoring the centrifugal impeller based on the digital model. According to the method, the response calculation load is relatively small, the detuning parameters are relatively easy to extract, and the real-time performance and the accuracy are relatively high.

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.

Proposed are an apparatus using root cause analysis (RCA) for predicting blade damage and a method therefor. The method for predicting damage includes generating a reduced-order model that derives damage information indicating damage to a blade according to operation conditions of a gas turbine apparatus and a displacement of the blade, measuring the displacement of the blade through a displacement measurement sensor when an operation of the gas turbine apparatus begins under the operation conditions according to a user's input, and deriving the damage information corresponding to the operation conditions and the displacement of the blade through the reduced-order model.

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.

A method for estimation of temperature distribution of a battery (10) is described. The method is implemented by the battery management system (BMS). The battery has a shell that includes a housing and a cover. The housing and the cover of the shell define an interior space. The method includes determining at least one of a finite element analysis (FEA) and a thermal model and computational fluid dynamic (CFD) thermal model based on at least one temperature value associated with a temperature of the interior space, determining a reduced order model (ROM) based on at least one of the FEA thermal model and the CFD thermal model, and determining a location inside the battery for placement of a battery sensor configurable to measure temperature. The location is determined based upon at least one of the FEA thermal model, the CFD thermal model, and the ROM.

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.

To maintain a healthy and safe battery, the Battery Management System (BMS) require numerous sensors which is a costly process. Immersion cooling applications where the battery stack is cooled with a dielectric coolant fluid has complex flow patterns that are not modeled easily without high fidelity modeling. The present disclosure provides a solution by combining physics-based and data-driven techniques. Initially, a first reduced subspace and a second first reduced subspace are extracted from the high-fidelity or full-order model (FOM) data with the help of proper orthogonal decomposition (POD) in offline. Further, the dynamics of the reduced spaces (first reduced subspace and the second reduced subspace) are captured by computing the reduced coefficients. The reduced coefficients are computed by solving the reduced order equations. The reduced model is solved in the same manner as the high-fidelity or FOM model. The reduced-order solution is constructed once the reduced coefficients are obtained.

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.