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

50 results about "Nonlinear flow" patented technology

Discrete element simulation method for slope unstable seepage

The invention discloses a discrete element simulation method for slope unstable seepage, effectively solves the problem of nonlinear flow simulation distortion caused by excessive simplification of a traditional seepage model, and improves the calculation precision of transient processes such as rainstorm infiltration. The dynamic porosity feedback mechanism can reflect the influence of the internal structure change of the slope on the seepage field in real time, and more reliable pore water pressure prediction data is provided for landslide early warning. The establishment of a multi-scale coupling framework provides a new technical approach for unstable seepage analysis under complex geological conditions, a physical information neural network effectively avoids the overfitting risk of a pure data driven model, and an improved multi-objective optimization algorithm can quickly position an optimal parameter combination under complex constraint conditions. A dynamic updating mechanism can automatically adjust model parameters according to slope state changes, and the timeliness and accuracy of landslide early warning under the unstable seepage condition are remarkably improved.
Owner:HUANENG LANCANG RIVER HYDROPOWER CO LTD +2

A high-precision venturi valve characteristic nonlinear compression spring preparation method and compression spring

The application discloses a high-precision Venturi valve characteristic nonlinear compression spring preparation method and a compression spring, and realizes accurate matching of compression spring performance and nonlinear flow regulation characteristics of the Venturi valve through multi-step optimization design. The method comprises the following steps: establishing a Venturi valve curve coordinate system, calculating a flow area, calculating an external force work, fitting a spring performance curve, determining a force value range, designing a spring gradual change process, heat treatment stress relief, testing and correction, ensuring that the spring performance meets the design requirements, and completing final standardization. The application provides a calculation method for force change law of a valve core of a Venturi valve and the valve core under different valve front static pressures, obtains a theoretical force curve, calculates compression and spring force compensation required by a damping structure of the valve core of the Venturi valve, and through forward development design and production, improves the independence of air volume and pressure of the Venturi valve and the air volume control precision.
Owner:CHINA ELECTRONICS CHUANGDA CONSTR EQUIP TECH CO LTD +1

Unified optimization method for stilling well-turning section body type of flood discharge vertical well

The invention discloses a flood discharge vertical shaft stilling well-turning section body type unified optimization method. The method comprises the steps that multi-working-condition physical constraints describing body type parameters of a flood discharge vertical shaft, a stilling well and a turning section are obtained, and a combined feasible region is constructed; obtaining a typical flood working condition set; an active sampling strategy is adopted, body type sample data are obtained through iteration aiming at the typical flood working condition set in the joint feasible region, and a flow regime partition model and a hydraulic index agent model are constructed through iteration; according to the active sampling strategy, multi-working-condition uncertainty and flow regime partition boundary information are fused; in the joint feasible region, the flow regime partition model and the hydraulic index agent model are applied, a robust optimization model considering the cross-working-condition flow regime stability is constructed and solved, and a unified optimization body type scheme is obtained. According to the method, by introducing the flow state middle layer and combining the sampling strategy of flow state boundary driving, the capturing capacity and optimization efficiency of nonlinear flow state sudden change are improved.
Owner:HOHAI UNIV +1

Spatial data management method and system based on artificial intelligence

The invention discloses a spatial data management method and system based on artificial intelligence, and relates to the technical field of spatial data management, and the method comprises the steps: defining the number of wavelet decomposition layers, calculating a self-adaptive threshold value, screening edges of an incidence matrix, generating a sparse incidence matrix, constructing a projection matrix, and projecting a feature matrix to a feature vector space through employing a matrix multiplication method. Generating a comprehensive feature matrix; and using a logistic function to define a nonlinear stream function, forming state vectors, calculating a mean value of the state vectors, fusing the mean value with the node feature matrix to form a dynamic feature matrix, and constructing a graph convolutional network model to predict the fault probability of the nodes. According to the method, fine-grained dynamic features of spatial data are accurately mined through combination of multi-scale wavelet decomposition and adaptive threshold screening, feature energy screening and a cosine distance matrix are introduced, the discrimination ability of feature selection and dimension reduction is improved, and the spatial data are extracted by using the graph convolutional network and combining a sparse embedding mechanism. And the generalization ability of the model in node fault prediction is obviously enhanced.
Owner:YUANSHI TECHNOLOGY (SHANGHAI) CO LTD

Intelligent water conservancy design simulation system based on digital twinning

The invention relates to the technical field of computer-aided engineering, and discloses an intelligent water conservancy design simulation system based on digital twinning, which comprises a parameterized geometric feature extraction module, a reduced-order model database, a tangent space linear deduction module and a flow field reconstruction module. According to the method, nonlinear flow field solution is dimensionally reduced into deterministic matrix vector multiplication, traditional statistical regression and iterative solution are replaced, it is ensured that a reconstruction result evolves in the tangential direction of a physical gradient, non-physical guess of a statistical model in a sparse sample area is avoided, and the calculation accuracy is improved. And high-fidelity flow field reconstruction with real-time performance and physical evolution conservation is realized.
Owner:JINZHONG WATER CONSERVANCY SURVEY & DESIGN INSTITUTE CO LTD

Combustor with resonator for gas turbine engine

A combustor includes a wall that defines a combustor interior to receive a fluid. The combustor also includes a slot that extends through the wall. The combustor also includes a resonator coupled to the wall. The resonator includes a resonator box defining a resonator interior between the wall and the resonator box, and a resonator segment disposed within the resonator box. The resonator segment includes a resonator neck having a resonator inlet and resonator outlet, the resonator inlet positioned within the resonator interior, the resonator outlet in flow communication with the combustor interior through the slot. The resonator neck defines a nonlinear flow path between the resonator inlet and the resonator outlet.
Owner:SIEMENS ENERGY GLOBAL GMBH & CO KG

Time-sharing optimization control method for cold storage central air conditioner based on large model

ActiveCN121761464APrevent hypothermia syndromeImprove annual comprehensive energy efficiency ratioData processing applicationsMechanical apparatusCorrection algorithmHigh energy
The invention relates to the technical field of environment control, and discloses a time-sharing optimization control method for a cold storage central air conditioner based on a large model, which comprises the following steps of: firstly, acquiring a system cold demand quantity and an environment working condition predicted value at a future moment through a pre-trained deep learning model, and estimating a current cold storage charging and discharging state in combination with a thermal front degradation correction algorithm; then, a non-linear flow resistance model associated with the porosity and the cold storage state is established, and a hydraulic high-energy-consumption interval in which fluid resistance is highly sensitive to flow change is recognized; and on the basis, deducing the energy efficiency trend of the water chilling unit by utilizing the environment temperature to determine load distribution, actively inhibiting cold storage output in a high flow resistance interval through energy efficiency gating logic, and finally generating a time sequence control strategy containing flow and load instructions to realize optimal scheduling of system-level energy efficiency.
Owner:NANJING DEEPCTRLS TECHNOLOGIES CO LTD

Crack permeability calculation method considering rough wall surface structure of crack

The invention provides a crack permeability calculation method considering a crack rough wall surface structure, and belongs to the technical field of seismic exploration data processing. The method comprises the following steps: determining the physical size of a required rough wall surface crack model, outputting point cloud coordinate data of a crack wall surface, constructing an interpolation function, and creating the crack wall surface; the method comprises the following steps: establishing a cuboid, segmenting the cuboid by using fracture wall surfaces, reserving an area between two fracture wall surfaces after segmentation, namely a fracture calculation domain, performing flow numerical simulation by applying an N-S equation, and simulating to obtain a pressure gradient and a flow rate of fluid flow in a fracture; and fitting a relation curve of the flow and the pressure gradient by using a nonlinear curve, finding a critical point when the linear flow is transited into the nonlinear flow, calculating a critical coefficient and a corresponding critical flow, and calculating the critical permeability of the rough wall surface crack model according to the Darcy law. According to the method, the problems that conventional fracture form characterization is difficult and uncontrollable, and the Darcy law is not suitable for describing nonlinear seepage in the fracture of the rough wall surface are solved.
Owner:PETROCHINA CO LTD

A method for constructing a prediction model of a high-pressure fuel filter and a flow rate prediction method

ActiveCN117057270BShorten design and development timereduce mistakesData setEngineering
The application discloses a kind of high-pressure fuel filter prediction model construction method and flow prediction method, including two prediction models, method specifically includes: using computational fluid dynamics method carries out fluid dynamics simulation calculation to high-pressure fuel filter, constructs working condition sample data set;The size of filter hole, quantity, filter working pressure, fuel viscosity and filter pressure drop are used as input variable, and filter flow is used as output variable, two new high-pressure filter general nonlinear flow prediction models are established using artificial neural network and regression prediction method respectively, the flow characteristics of different models of filter in working interval can be accurately predicted using the neural network prediction method proposed in the application at any working condition point, and the error is low;The flow of different models of filter under different conditions can be quickly and accurately obtained, the accuracy meets the engineering needs, while greatly shortening the experimental time and calculation time, saving design cost.
Owner:XI AN JIAOTONG UNIV

Analysis method for key local vibration of fluid-structure interaction bridge based on substructure method

The application discloses an analysis method for key local vibration of fluid-solid coupling bridges based on a substructure method, and relates to the technical field of bridge vibration analysis, and comprises the following steps: dividing a response key area in a bridge structure into substructures, performing static condensation, and obtaining a condensed substructure model; establishing a whole bridge-wave coupling model, and adopting a dynamic explicit solving strategy based on a coupling Euler-Lagrange method; independently solving the substructures by using a dynamic implicit method; coupling the substructures to the whole model by an interface coordination condition, and jointly calculating the whole explicit model and the local implicit model. The analysis method adopts an explicit method to process a strong nonlinear fluid-solid coupling process at a whole level, and establishes a fine substructure model through Guyan static condensation at a local area, so that the analysis precision is effectively improved.
Owner:CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Multi-element fusion carotid artery blood vessel monitoring method, system, electronic device and storage medium

PendingCN122642940Astable characterizationaccurate representationEmergency medicineBlood vessel
The application discloses a kind of multi-element fusion carotid vascular monitoring method, system, electronic equipment and storage medium, it is related to medical monitoring field.The method comprises: obtaining the time-domain acoustic signal of carotid artery of the individual to be measured, and the time-domain acoustic signal is carried out frequency domain transformation, and frequency-domain acoustic signal is obtained;Nonlinear flow state feature and topological form feature are extracted based on the frequency-domain acoustic signal;The nonlinear flow state feature and the topological form feature are compared with the corresponding baseline feature in the historical acoustic baseline of the individual to be measured, and feature deviation result is obtained;Risk assessment is carried out based on the feature deviation result, when the feature deviation result exceeds preset range, risk early warning is triggered.The application suppresses the interference such as power frequency, baseline drift, respiratory body movement and environmental noise mixed in time-domain waveform, thereby reducing the false positive rate of carotid vascular acoustic monitoring, and realizing early risk early warning of vascular lesion.
Owner:UNIV OF SHANGHAI FOR SCI & TECH +3

Stator bobbin for e-machine with winding retainers and fluid flow surfaces

A stator bobbin includes a first winding support with an inner radial portion, an outer radial portion, and a winding space defined radially between the inner radial portion and the outer radial portion with respect to an axis of rotation. The winding space is configured to receive a plurality of windings of the e-machine. The inner radial portion and the outer radial portion extend along the axis between a first end of the stator bobbin and a second end of the stator bobbin. The stator bobbin further includes a winding retainer disposed at the first end and configured for receiving and retaining an end of the plurality of windings. Also, the stator bobbin includes a contoured flow surface disposed proximate the second end. The contoured flow surface defines a nonlinear flow path for a fluid coolant of the e-machine.
Owner:GARRETT TRANSPORTATION I INC

An adaptive adjustment method for an oil refining process

The application relates to the field of industrial automation control and discloses an adaptive adjustment method for a grease refining process, which comprises the following steps: synchronously acquiring raw material flow data and load current signals and storing the data into a historical state register sequence; extracting high-frequency power spectrum amplitudes in the load current signals to determine a dynamic correction coefficient reflecting a pipeline slip state; compensating a physical volume model according to the dynamic correction coefficient and calculating material dynamic time delay parameters; reversely searching time sequence associated process parameters in the sequence by using the dynamic time delay parameters; and correcting control gain according to the numerical deviation between the process parameters and the load current signals by a state observer, so as to adjust frying heating power. Through closed-loop compensation of nonlinear rheological characteristics of a transport process, the application ensures that the extracted historical parameters have physical and causal consistency, solves the time delay distortion problem caused by non-uniform materials, and improves system identification accuracy and operation stability.
Owner:HUNAN FOUR SEASONS OIL CO LTD

Tail end purification node self-adaptive operation decision-making system driven by multi-dimensional water quality characteristics

The invention relates to the technical field of industrial process control, and discloses a multi-dimensional water quality characteristic-driven terminal purification node adaptive operation decision system, which comprises the following steps of: acquiring fluid state parameters, an actuating mechanism driving instruction and a response measurement value, calculating a ratio of the two to construct a transient hydraulic impedance index, and calculating a transient hydraulic impedance value; according to the method, the physical characteristic drift of the assembly is identified by monitoring the ratio of the driving energy to the fluid response in real time, the problem that the static look-up table cannot adapt to the structural variation is solved, and the reliability of the assembly is improved. And realizing stable self-adaptive control on the nonlinear fluid system by using the existing computing power.
Owner:CHENGDU FUTURE WEISDOM TECH CO LTD

Analysis method for key local vibration of fluid-structure interaction bridge based on substructure method

The invention discloses an analysis method for key local vibration of a fluid-structure interaction bridge based on a substructure method, and relates to the technical field of bridge vibration analysis, and the method comprises the following steps: dividing a response key region in a bridge structure into substructures, and carrying out static polycondensation to obtain a polycondensed substructure model; an integral bridge-wave coupling model is established, and a dynamic explicit solving strategy based on a coupling Euler-Lagrange method is adopted; independently solving the substructures by adopting a dynamic implicit method; and coupling the substructures into the overall model through an interface coordination condition, and carrying out joint calculation of the overall explicit model and the local implicit model. According to the analysis method, an explicit method is adopted to process the strong nonlinear fluid-solid coupling process on the overall level, a fine substructure model is established in a local area through Guyan static polycondensation, and the analysis precision is effectively improved.
Owner:CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Vehicle nonlinear inerter double-air-chamber hydro-pneumatic suspension structure and parameter determination method

The invention discloses a vehicle nonlinear inerter double-air-chamber hydro-pneumatic suspension structure and a parameter determination method. The method comprises the following working steps that 1, a nonlinear fluid inerter model is constructed; 2, constructing a 1 / 4 nonlinear inerter hydro-pneumatic suspension model; 3, parameter optimization based on a non-dominated sorting genetic algorithm II; and 4, performing dynamic performance simulation analysis. The method has the beneficial effects that the nonlinear fluid inerter and the double-air-chamber hydro-pneumatic suspension are combined, and the inerter hydro-pneumatic suspension model is constructed; a non-dominated sorting genetic algorithm II is used for optimizing target parameters, the algorithm is an optimization algorithm used for solving a plurality of conflict targets, and finally an optimal solution set of the Pareto graph is found; the overall performance of the suspension system can be effectively improved; and an obvious optimization effect is achieved in the aspect of vehicle vibration.
Owner:JIANGSU UNIV

Three-dimensional rough fracture nonlinear flow field simulation method and system

The invention provides a three-dimensional rough fracture nonlinear flow field simulation method and system, and belongs to the technical field of electric digital data processing. Comprising the following steps: generating an initial geometric opening field of a three-dimensional rough fracture based on a three-dimensional coordinate of the upper side wall surface of the three-dimensional rough fracture obtained by a three-dimensional laser scanning technology; the method comprises the following steps: describing water head distribution of a linear flow field in a fracture by using a Reynolds equation with an opening time-varying item, embedding a Forchheimer equation into the Reynolds equation with the opening time-varying item to obtain an improved Reynolds equation used for describing a nonlinear flow field, and calculating the initial geometric opening field of the three-dimensional rough fracture based on a preset boundary condition and the initial geometric opening field of the three-dimensional rough fracture. And solving the water head distribution of the nonlinear flow field under the control of the improved Reynolds equation. By embedding the Forchheimer equation into the Reynolds equation, the description capability of a nonlinear flow field is improved, the fluid behavior in the three-dimensional rough fracture can be described and predicted more accurately, the application range of the method is widened, and meanwhile, a foundation is laid for researching a long-term corrosion mechanism of the three-dimensional rough fracture.
Owner:CHINA UNIV OF MINING & TECH (BEIJING)

Stator bobbin for e-machine with winding retainers and fluid flow surfaces

A stator bobbin includes a first winding support with an inner radial portion, an outer radial portion, and a winding space defined radially between the inner radial portion and the outer radial portion with respect to an axis of rotation. The winding space is configured to receive a plurality of windings of the e-machine. The inner radial portion and the outer radial portion extend along the axis between a first end of the stator bobbin and a second end of the stator bobbin. The stator bobbin further includes a winding retainer disposed at the first end and configured for receiving and retaining an end of the plurality of windings. Also, the stator bobbin includes a contoured flow surface disposed proximate the second end. The contoured flow surface defines a nonlinear flow path for a fluid coolant of the e-machine.
Owner:GARRETT TRANSPORTATION I INC

Dynamic mode decomposition flow field prediction method based on nonlinear data dimension reduction

The invention belongs to the technical field of computer-aided fluid mechanics, provides a dynamic modal decomposition flow field prediction method based on nonlinear data dimension reduction, and combines orthogonal decomposition and a multi-layer perceptron auto-encoder. Firstly, modal coefficients in the unsteady flow field are extracted through two-step POD, low-dimensional features are formed, then nonlinear feature learning is conducted on the low-dimensional features through a multi-layer perceptron auto-encoder, and therefore complex dynamic behaviors of the unsteady flow field are better captured. According to the unsteady flow field prediction method, the calculation complexity can be greatly reduced, and key features in the unsteady flow field can be reserved. In addition, dynamic modal decomposition and a random forest algorithm are combined, the time evolution prediction precision of the modal coefficient is further improved, and the method is particularly suitable for rapid prediction and reconstruction of a high-dimensional nonlinear flow field.
Owner:BEIHANG UNIV

Stator bobbin for e-machine with winding retainers and fluid flow surfaces

A stator bobbin includes a first winding support with an inner radial portion, an outer radial portion, and a winding space defined radially between the inner radial portion and the outer radial portion with respect to an axis of rotation. The winding space is configured to receive a plurality of windings of the e-machine. The inner radial portion and the outer radial portion extend along the axis between a first end of the stator bobbin and a second end of the stator bobbin. The stator bobbin further includes a winding retainer disposed at the first end and configured for receiving and retaining an end of the plurality of windings. Also, the stator bobbin includes a contoured flow surface disposed proximate the second end. The contoured flow surface defines a nonlinear flow path for a fluid coolant of the e-machine.
Owner:GARRETT TRANSPORTATION I INC

Self-adaptive robust control method for finite time convergence of hydraulic mechanical arm under unknown load

The invention discloses a finite time convergence adaptive robust control method for a hydraulic mechanical arm under an unknown load. The method comprises the steps that a system dynamics model of the hydraulic mechanical arm is reconstructed through a generalized momentum method, and a finite time convergence adaptive law and a nonlinear controller are designed; the state information of the mechanical arm is input into the finite time convergence self-adaption law in real time, the corrected self-adaption gain updating law is output after processing so as to update the self-adaption gain in the nonlinear controller in real time, meanwhile, the expected track and the expected output thrust of the mechanical arm are input into the nonlinear controller, virtual control flow is output after processing, and therefore the self-adaption gain in the nonlinear controller is updated in real time. And after nonlinear flow mapping is conducted, valve port control voltage is obtained, and then a proportional control valve of the mechanical arm is controlled. On the basis of Lyapunov analysis, finite time convergence of parameter estimation and asymptotic convergence of trajectory tracking errors of the method are strictly proved, and the method shows excellent performance in the aspects of tracking precision and load estimation accuracy of a hydraulic mechanical arm platform.
Owner:ZHEJIANG UNIV

Steam turbine high-pressure regulating valve nonlinear flow modeling method and device based on multiple complex factors and storage medium

The invention discloses a turbine high-pressure control valve nonlinear flow modeling method and device based on various complex factors and a storage medium, and relates to the field of thermal equipment modeling and emulation.The method achieves precise modeling through four steps that firstly, seven kinds of core factors such as the valve position opening degree, the steam temperature and pressure, the viscosity, the flow speed and the accumulative operation duration are selected; collecting data through a distributed sensor and preprocessing the data through weighting standardization; secondly, three correction factors such as an in-valve flow field coupling factor are introduced, and a nonlinear core flow model is constructed; real-time error compensation is realized in combination with an Elman neural network and an improved Sigmoid function, and a final model is formed; and finally, verifying the precision through MAE and RMSE, and optimizing key parameters by adopting a particle swarm algorithm. According to the method, the multi-factor coupling effect is comprehensively described, the data reliability and the model prediction precision are improved, core support is provided for fine control and energy efficiency optimization of the high-pressure regulating valve of the steam turbine, and the method has important engineering value.
Owner:广东粤电靖海发电有限公司

Self-adaptive sliding mode TCP / AQM control method suitable for ship-shore communication

The invention discloses a self-adaptive sliding mode TCP / AQM control method suitable for ship-shore communication. The method comprises the following steps: step 1, establishing a nonlinear TCP fluid model added with uncertainty interference; 2, designing a sliding mode controller; 3, the sliding mode controller outputs the packet loss probability, the packet loss probability is transmitted to the nonlinear TCP fluid model, an error signal of the expected queue length and the instantaneous queue length output by the nonlinear TCP fluid model is transmitted to the sliding mode controller, the control process of the whole system is completed, and finally queue length control is achieved. According to the method, new self-adaptive sliding mode control is provided for a non-linear TCP fluid model with interference, under the condition that the TCP fluid model is interfered uncertainly, the TCP network control is completed through an improved self-adaptive sliding mode controller and a switching controller by utilizing the instantaneous queue length fed back at the previous moment under the uncertain interference, and the TCP network control is completed through a non-linear sliding mode control method. And the buffeting problem of the TCP network can be better suppressed.
Owner:HARBIN UNIV OF SCI & TECH

Separation flow control method and system based on flow field characteristics and reinforcement learning

The application discloses a separation flow control method and system based on a flow field feature and reinforcement learning, and relates to the technical field of flow control.The application combines pre-solution analysis with reinforcement learning to establish an integrated design process from flow sensitivity analysis to control law training.First, the most sensitive input structure of a flow system is extracted by using pre-solution analysis, and the optimal control position is quantitatively screened through effective gain, thereby avoiding the blindness of a traditional trial-and-error method.Second, a closed-loop control law is trained on the position by using reinforcement learning, so that the controller can be self-adaptively adjusted according to a real-time flow field state, and when the control effect is not up to the standard, the joint matching of the control position and the control law is realized through base flow reconstruction and iterative optimization, thereby the design efficiency and the control effect of the separation flow control system can be significantly improved, and the application is especially suitable for the control scheme design of strong non-steady and non-linear flow, such as transonic shock oscillation.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Combustor with resonator for gas turbine engine

A combustor includes a wall that defines a combustor interior to receive a fluid. The combustor also includes a slot that extends through the wall. The combustor also includes a resonator coupled to the wall. The resonator includes a resonator box defining a resonator interior between the wall and the resonator box, and a resonator segment disposed within the resonator box. The resonator segment includes a resonator neck having a resonator inlet and resonator outlet, the resonator inlet positioned within the resonator interior, the resonator outlet in flow communication with the combustor interior through the slot. The resonator neck defines a nonlinear flow path between the resonator inlet and the resonator outlet.
Owner:SIEMENS ENERGY GLOBAL GMBH & CO KG

An edge large model task offloading and scheduling method for multi-user quality of experience

The application provides a multi-user quality of experience oriented edge large model task offloading and scheduling method, which comprises the following steps: a user terminal initiates a large language model inference task request to an edge server; the edge server acquires the system state at the current moment in real time, and constructs a nonlinear streaming user experience quality evaluation model; a target function is constructed, and the target function is constrained based on the system state at the current moment; the constrained target function is solved to obtain an optimal offloading strategy of the current task; the task is distributed to the corresponding edge server based on the optimal offloading strategy, the system is decoupled and scheduled in the pre-filling stage and the decoding stage; the actual parameters of the task are recorded, the prior evaluation parameters in the heuristic search algorithm are fine-tuned based on the actual parameters, and the edge large model task offloading and scheduling are completed; and the application maximizes the global multi-user comprehensive satisfaction degree of the system in the environment where the edge resources are limited and the network state dynamically changes.
Owner:BEIJING INST OF TECH

Generative multi-modal remote sensing image clustering method

The invention discloses a generative multi-modal remote sensing image clustering method, which belongs to the technical field of multi-modal remote sensing image clustering, and comprises the following steps: a training stage, performing standard normalization processing on multi-modal data, parameterizing a non-linear distribution transmission path, setting the input and output of a speed prediction network, and optimizing a path prediction network and the speed prediction network; in a clustering stage, a path-related ordinary differential equation about time is formed based on a speed prediction network by taking a single-modal hidden feature as a sampling starting point, sampling from the starting point to another modal feature is realized by utilizing Euler sampling, a sampling path is used as feature fusion of a multi-modal image, a fusion feature is extracted from the speed prediction network corresponding to a sampling point, and a multi-modal image is obtained. Performing a clustering algorithm on the fusion features to generate a clustering result; according to the method, a generative nonlinear flow matching model is provided, fusion features of the multi-modal image are gradually generated, manifold structures of the multi-modal image are fully fused by means of a probability flow technology, and a better clustering effect and model interpretability are brought.
Owner:CHENGDU TECH UNIV

Multi-scale numerical simulation method and system for wave evolution and effect of wave evolution on ocean structure

The invention discloses a multi-scale numerical simulation method and system for wave evolution and the effect of the wave evolution on an ocean structure. The method comprises the steps that a high-order Boussinesq equation is solved through a finite difference method, a B-FD sub-model is constructed, a Navier-Stokes equation is solved through a smoothed particle fluid dynamics method, and an NS-SPH sub-model is constructed; the B-FD sub-model and the NS-SPH sub-model are subjected to multi-time-step coupling through a two-way boundary opening method, the wave propagation form of the offshore waves propagating to the offshore and the physical quantity interacting with the offshore structure are obtained, the wave propagation form is used for analyzing the evolution characteristics of the wave surface, and the physical quantity is used for analyzing nonlinear flow caused by the waves. According to the method, the efficiency of large-range wave propagation calculation can be ensured, and high-precision nonlinear simulation of the local wave breaking process is also considered.
Owner:OCEAN UNIV OF CHINA

A meta-learning-based method for nonlinear flow reduction modeling and prediction

The present invention provides a method for nonlinear flow reduction modeling and prediction based on meta-learning. The method proposed in the present invention first establishes a flow prediction model with an autoencoder configuration suitable for the current flow problem; secondly, the relationship between flow fields with different parameters is learned through the MAML algorithm, and a meta-model is established; then, the established meta-model is used as the initialization model under new physical parameters, and fine-tuned with a small number of training data points; finally, the flow prediction model after small sample training is used to perform reduction analysis and prediction research on the flow field under the new parameters. By introducing a meta-learning strategy, this method proposes a new solution to the problems of poor generalization ability and long training time of the current model. In addition, the method is simple to implement, has high accuracy, and strong versatility. It can be widely used in the reduction modeling and prediction of complex parameterized flow systems.
Owner:ZHEJIANG UNIV

A large model-based cold storage central air conditioner time-sharing optimization control method

The application relates to the technical field of environment control, and discloses a cold storage central air conditioner time-sharing optimization control method based on a large model, which comprises the following steps: firstly, the system cooling demand and the environment working condition prediction value at a future moment are obtained through a pre-trained deep learning model, and the current cold storage charging and discharging state is estimated in combination with a thermal front degeneration correction algorithm; subsequently, a nonlinear flow resistance model related to porosity and the cold storage state is established, and a hydraulic high energy consumption interval in which fluid resistance is highly sensitive to flow change is identified; on this basis, the energy efficiency trend of a water chilling unit is deduced by using the environment temperature to determine load distribution, and the cold storage output in the high flow resistance interval is actively inhibited through energy efficiency gate logic, so that a time sequence control strategy containing flow and load instructions is finally generated, and optimal scheduling of system-level energy efficiency is realized.
Owner:NANJING DEEPCTRLS TECHNOLOGIES CO LTD