66 results about "Energy functional" patented technology

The invention relates to the technical field of detection, in particular to a complex shell detection method and system based on structured light scanning. The method comprises the following steps: calculating a wrapped phase value and a phase modulation amplitude of each pixel point under each frequency, calculating discrete probability distribution containing candidate stripe series and a corresponding probability for each pixel point based on a multi-frequency wrapped phase difference, generating an initial pixel confidence map, and constructing an energy function; the penalty weight of the smooth item is determined according to the phase modulation amplitude and the wrapped phase gradient local variance, obtaining an initial fringe order distribution diagram, updating discrete probability distribution by using an initial pixel confidence map, re-minimizing an energy function to obtain a corrected fringe order distribution diagram, and reconstructing a final three-dimensional shape. And iteratively optimizing a projector principal point and a radial distortion coefficient in system calibration parameters. According to the scheme, the geometric details of the surface can be reserved, and the processing effect and the measurement precision of the complex curved surface and the high-curvature area are improved.

The invention discloses a high-speed rail canopy steel structure corrosion image recognition and evaluation method based on deep learning, and the method comprises the following steps: obtaining and calibrating a multi-view image, and organizing the multi-view image into an observation sequence; performing normalization and quality checking on the observation sequence, and extracting a state vector and an observation driving vector; constructing an energy function and a structure matrix in the Hamiltonian neural network, and promoting state vector time evolution to obtain an evolved corrosion state vector; inputting the evolution result into a decoder, generating a pixel-level corrosion mask and a boundary position, and obtaining a corrosion segmentation result; the corrosion type is judged based on the segmentation result, and corrosion severity indexes are calculated and graded; and extrapolating and predicting the severity index by using time evolution, outputting a predicted maintenance time window and priority, and finally generating a detection report. According to the method, the Hamiltonian neural network is introduced to realize identification, grading and evolution prediction of steel structure corrosion, and the detection stability and the engineering availability are improved.

The invention discloses an event causal relationship identification-oriented energy contrast learning and knowledge verification method, and belongs to the technical field of deep learning and natural language processing. The invention provides a multi-stage knowledge verification system fusing multi-source external knowledge and large language model driven causal reasoning to solve the problems that an existing model is low in quality and prone to introduction of a pseudo causal positive example in comparison sample construction. Comprising a concept-level event heterogeneous graph construction module, a multi-level positive and negative sample pool construction module, a multi-source causal verification module, a lightweight model-driven distillation module, a large model-guided fine screening and sorting module and an energy contrast learning module. By introducing a stochastic gradient Langevin dynamics method, an antagonistic negative sample is dynamically generated, and a causal discrimination boundary between positive and negative samples is modeled through an energy function, so that the recognition capability of the model on the event causal relationship is improved.

The invention relates to the technical field of intelligent optimization design, in particular to a bridge prestressed steel beam intelligent optimization design method based on multi-factor coupling, and the method comprises the steps: carrying out the quantitative modeling of a plurality of parameters in the arrangement process of a bridge prestressed steel beam, achieving the precise expression of controllable variables, and improving the design precision of the bridge prestressed steel beam. The overall search capability of the arrangement scheme under multi-target tradeoff is enhanced, the rationality and stability of steel beam distribution are integrally improved, the structure local overload risk is reduced, an energy function sequence is constructed through indexes such as a midspan displacement value, a section stress ratio and the total length, the quality of a solution set is controlled by utilizing an energy difference value, intervention and screening of a residual value are introduced, and the stability of the structure is improved. The robustness of the design under the multivariable condition is enhanced, through logic judgment of displacement and counterforce, unqualified arrangement is eliminated, feasible arrangement output under structural consistency is achieved, structural efficiency and material use economy are enhanced, and design reliability, optimization solution efficiency and structural response control precision are remarkably improved.

The present application relates to the technical field of distributed system testing and operation and maintenance monitoring, and particularly relates to a server test environment automatic monitoring method and system, comprising: collecting a micro-service cluster directed call topology structure, constructing a distributed cell layer with node and edge vector spaces; parsing data serialization rules to extract constraint restriction mapping matrices, assembling a Hodge-Dirac operator; obtaining real-time business state vector groups to splice into zero-order co-chains, using the operator to solve an algebraic Laplace matrix to calculate a quadratic form energy functional; when determining that the quadratic form energy functional is greater than zero, generating an early warning signal, constructing and solving a discrete layer diffusion dynamics equation based on the algebraic Laplace matrix, obtaining a state compensation update matrix; finally, analyzing the state compensation update matrix into reverse rollback and cache erasure instructions, and submitting the instructions to a service mesh data plane proxy component for execution. The present application realizes code-free cross-node semantic conflict quantification and distributed consistency state self-healing closed loop.

The invention belongs to the technical field of equivalent modeling, and discloses a hybrid wind power plant equivalent method and device based on oscillation energy decomposition, and the method comprises the steps: obtaining the operation measurement data of a hybrid wind power plant, carrying out the calculation or frequency scanning of each fan grid-connected branch, and obtaining a broadband equivalent impedance characteristic; constructing a multi-machine oscillation energy equivalent unit comprising a plurality of grid-connected branches according to the broadband equivalent impedance characteristic and the actual grid-connected topology of the wind power plant; establishing an energy function and a dynamic equation according to the multi-machine oscillation energy equivalent unit; performing modal decomposition and branch decomposition on the system oscillation energy, and calculating the oscillation energy contribution degree and the dissipated energy participation degree of each fan grid-connected branch in a dominant oscillation mode to obtain an energy characteristic quantity; performing fan grouping to obtain a fan grouping result of the hybrid wind power plant; and performing differential equivalence and parameter aggregation according to a fan grouping result to obtain a small disturbance equivalence model. The calculation model scale and the calculation complexity of the hybrid wind power plant can be reduced.

The invention relates to a stochastic dynamics system energy prediction method and device, electronic equipment and a medium. The method comprises the following steps: setting a displacement variable of the stochastic dynamics system about time, and establishing an energy function of the stochastic dynamics system according to the displacement variable; constructing a multi-scale data set according to the energy function; the initial model is trained through the multi-scale data set, and a feature extraction model is obtained after training is completed; the feature extraction model is used for extracting dynamic features of the stochastic dynamic system; the dynamic characteristics at least comprise an energy predicted value at the current moment; constructing a drift term according to the drift network and the dynamic characteristics, and constructing a diffusion term according to the diffusion network and the dynamic characteristics; and calculating an energy predicted value of the next moment based on the energy predicted value of the current moment, the drift term and the diffusion term. According to the method, based on the improved discretization incremental energy prediction algorithm, the discretization scheme conforming to the physical law is adopted to improve the energy prediction numerical stability and prediction precision.

The invention discloses a transient stability evaluation method and device for a multi-VSG parallel system. The method comprises the following steps: obtaining a power system model and a transient energy function according to the system; the transient energy function comprises a kinetic energy function and a potential energy function; obtaining a critical stable energy value according to the power system model and the transient energy function in combination with a BCU method; constructing a first model for obtaining a dynamic coupling relationship between VSGs based on a PINN network; training the first model according to a preset data set to obtain a second model; solving a transient energy function according to the real-time state vector of the system, and solving a path related item in the transient energy function in combination with a second model to obtain a real-time energy value; and if the real-time energy value is greater than the critical stable energy value, determining that the system is unstable, otherwise, determining that the system is stable.

This invention discloses a full-format model-free adaptive disturbance compensation control method for unmeasurable disturbances. The method establishes a dynamic linearized data model of the controlled object under unmeasurable disturbances; constructs and solves the cost function, optimizing and updating the pseudo-Jacobi input matrix and pseudo-Jacobi disturbance matrix; designs a full-format model-free adaptive disturbance compensation control scheme for unmeasurable disturbances; constructs and solves the energy function, optimizing and updating the full-format adaptive input matrix and full-format adaptive disturbance matrix; and uses the control scheme of this invention to control the controlled object under unmeasurable disturbances. The control method of this invention can significantly reduce the impact of unmeasurable disturbances on the actual output value of the controlled object system, achieve effective tracking of the desired value trajectory, and significantly improve the disturbance compensation control performance.

The application relates to a configuration design method of a three-dimensional orbiting sail with posture stability, and belongs to the field of spacecraft attitude dynamics and structure design.The application is realized by the following method: considering the environmental perturbation of atmospheric resistance, atmospheric resistance moment and gravity gradient moment, an orbit attitude coupling dynamics model of a three-dimensional orbiting sail system is established based on a position vector and Euler angles; the three-dimensional orbiting sail and a spacecraft body are regarded as rigid bodies, and the windward area is considered to be blocked by airflow so as to more accurately describe the orbit movement and attitude movement of the system in the orbiting process; the attitude movement is simplified for the attitude dynamics of the system; the attitude stability of the system in the orbiting process is analyzed by using a phase plane method, a Lyapunov energy function method and other stability analysis methods of nonlinear dynamics systems; the relationship between important structure parameters such as a cone angle and a support rod length of the three-dimensional orbiting sail and the attitude stability is further constructed; and the three-dimensional orbiting sail satisfying the preset attitude stability requirement is obtained based on the relationship, so that the configuration design is realized.

The present application relates to the field of additive manufacturing, and specifically discloses a kind of generation method of manufacturing three-dimensional Chinese character cup model based on energy driving.The present application constructs the smooth time evolution path from multiple outline initial region to single target outline, adopts level set function to describe the outline evolution process, and establishes energy functional including curve length regularization term, adaptive inflation term and shape prior term;Through introducing the dynamic coupling control mechanism based on area difference of region, shape error and boundary length, the adaptive adjustment of inflation coefficient is realized;Then the level set evolution equation is obtained by variational derivation, and after numerical discrete solution, two-dimensional evolution sequence is added to three-dimensional volume field along time axis;Finally, through isosurface extraction and thick shell processing, the 3D printable three-dimensional Chinese character cup model with complete structure and uniform wall thickness is generated.

One embodiment sets forth a technique for creating a generative model. The technique includes generating a trained generative model with a first component that converts data points in the training dataset into latent variable values, a second component that learns a distribution of the latent variable values, and a third component that converts the latent variable values into output distributions. The technique also includes training an energy-based model to learn an energy function based on values sampled from a first distribution associated with the training dataset and values sampled from a second distribution during operation of the trained generative model. The technique further includes creating a joint model that includes one or more portions of the trained generative model and the energy-based model, and that applies energy values from the energy-based model to samples from the second distribution to produce additional values used to generate a new data point.

Provided is a solution system capable of obtaining the optimal state of individual spins with a small amount of memory. The matrix simplification means 93 changes a matrix used in an energy function in a model representing states of individual spins by a first value or a second value into simplified form. In this case, the matrix simplification means 93 deletes elements that have a value of “0” from the matrix, and also deletes some elements that do not have the value of “0” from the matrix, thereby to change the matrix into the simplified form. The spin state derivation means 94 derives the optimal state of each spin based on the matrix changed into the simplified form.

The invention discloses a three-dimensional registration method and device, a computer storage medium and a terminal. According to the embodiment of the invention, for a scene comprising a plurality of objects to be processed and images to be processed collected from more than two viewing angles of AR, residual errors still existing in the pose of a registered target object after rotation pose deviation correction are corrected, and the accuracy of the registration is improved. Performing contour projection on the rotation attitude correction pose on the to-be-processed image, searching to obtain candidate edge points, determining a residual error and a Jacobian matrix of the candidate edge points according to an energy function, expanding contour search to a cross-view angle and a constraint object, and feeding back an observation error on the constraint object to correct the rotation attitude correction pose. The amplification of the rotation error is inhibited; by introducing a normalization equation, solving of pose correction and consistency correction of pose residual errors of all objects to be processed are achieved; and performing pose correction on the registered target object according to the pose correction amount reaching the iteration termination condition, and realizing three-dimensional registration of the scene based on the registered target object without the pose residual error.

The invention provides a text sequence prediction method and system, a storage medium and electronic equipment. The method comprises the following steps: constructing an energy function of a text sequence prediction neural network; constructing a continuous time dynamic equation of a neuron state based on a network function; inputting the text lexical element vector of the current time step into a text sequence prediction neural network, and evolving the text sequence prediction neural network to a first equilibrium state based on a continuous time dynamic equation; adjusting an output layer neuron state of the text sequence prediction neural network into a text lexical element vector of a next time step based on a continuous time dynamic equation, so that the text sequence prediction neural network is evolved to a second equilibrium state; and updating the weight of the text sequence prediction neural network based on the neuron state difference in the first equilibrium state and the second equilibrium state. According to the text sequence prediction method and system, the storage medium and the electronic equipment, rapid prediction of the text sequence is realized based on the neural network evolved by the energy function and the continuous time dynamic equation.

The present application relates to the technical field of image processing, in particular to a kind of forging heat treatment deformation detection method and system, the method comprises: first, the gray image of forging is obtained, gradient vector, gray saturation and local entropy are calculated, gradient reliability is determined, and local reliable vector is calculated, and guide vector field is generated by tensor diffusion;Then, based on the initialization active contour model, reconstruct its energy function when iteratively updating: external energy term is driven by the guide vector of contour point;Internal energy term is constrained by anisotropic stiffness tensor calculated based on gradient vector and local entropy, and finally the model converges to hot profile and carries out deformation analysis.The method is systematically modified to the internal and external energy terms of traditional model, suppresses halo and haze interference, solves feature confusion problem, and improves the accuracy and robustness of contour detection under high-temperature strong interference environment.

The application discloses a kind of water transport ship traffic collaborative control methods based on deep learning, specifically includes: obtaining ship operation data set, time index alignment is carried out, and state vector sequence is generated;State vector sequence is encoded to feature, and deep boltzmann machine model is constructed;First conditional energy function, second conditional energy function and energy coupling matrix are established between model layer, and form hierarchical conditional energy function set;Hierarchical conditional energy function set is carried out to hidden variable probability inference, and hidden layer probability state vector sequence is generated;Parameter flow shape is divided to energy function parameter, and policy optimization is carried out under the constraint of confidence domain, and updated energy function parameter set is generated;Updated energy function parameter is carried out to energy calculation, and state probability distribution sequence is generated;State probability distribution sequence is carried out to strategy mapping, and ship traffic collaborative control strategy is generated.The application constructs hierarchical energy coupling model, realizes the collaborative control of multiple ships state.

The application provides a method and system for detecting sub-harmonic oscillation based on a tunable wave trap, and a medium. A direct current digital filter and a tunable digital wave trap are cascaded to obtain a single-frequency oscillation signal detector. A wave trap angle frequency of the tunable wave trap is used as an independent variable, and an energy function is constructed based on a to-be-detected oscillation signal and an output of the single-frequency oscillation signal detector. A gradient descent method is used to iteratively update the independent variable in a negative gradient direction of the energy function with a fixed step length, to search for a minimum value of the energy function. When a gradient of the energy function with respect to the independent variable is zero, the corresponding angle frequency is determined as an angle frequency of the to-be-detected oscillation signal. The implementation process is simple and easy to implement, the calculation amount is small, and the real-time and accurate detection of the sub-harmonic oscillation signal can be realized.

The invention discloses a method for discriminating and tracing oscillation types of different mechanisms of a power system based on dynamic energy. The method comprises the following steps: constructing a low-frequency oscillation simulation model of the power system; analyzing the performance characteristics of the low-frequency oscillation mechanism of the power system, and determining the generation mechanism of different types of low-frequency oscillation; system oscillation energy in the low-frequency oscillation process of the power system is constructed, and energy functions of models such as an engine are derived and defined; and discriminating low-frequency oscillation of different mechanisms according to an energy function method, and positioning and tracing a disturbance source. According to the method, the energy function can be applied to the low-frequency oscillation problem of the power system, the oscillation is suppressed and analyzed more comprehensively, and the main disturbance source is judged according to the energy change characteristics of the generator set and the network branch.

The invention provides a geological reservoir fracture modeling grid cell determination method based on oscillator dynamic energy optimization and high-order interaction, and relates to the field of geology. According to the method, a dynamic energy optimization framework of an Ising machine is introduced into geomechanical modeling through fusion of amplitude dynamics and a high-order interaction model, the defects that in a traditional method, the physical significance of an energy function is fuzzy, and grid size effect correction is insufficient are overcome, and based on the real-value energy function of a complex oscillator variable and gradient descent, the dynamic energy optimization framework of the Ising machine is introduced into geomechanical modeling. Global convergence of mechanical parameters of the fracture network is realized, and the problem of local extremum of a traditional phase model is avoided; the fracture rigidity parameter is converted into a third-order polynomial energy item, and nonlinear characteristics of normal / shear deformation of the fracture surface are accurately described; a three-cycle method and a dynamic energy threshold value are combined, the grid size is synchronously optimized in the position-scale-azimuth dimension, the characterization error of fracture surface density and mechanical parameter anisotropy is reduced, and a standard grid format compatible with commercial software can be directly output.

This invention discloses a variational physics information neural network solution method based on self-adjoint operator functional constraints, involving the interdisciplinary field of neural networks and scientific computing. The method includes: S1, constructing an energy functional that forms a directly correlated energy with the constraint terms of the differential equation based on predetermined boundary and initial conditions and leveraging the symmetric conservation properties of the self-adjoint operator; wherein each component of the energy functional is mapped one-to-one with the corresponding physical field quantities in the differential equation, including diffusion coefficient and convection velocity; S2, verifying the correctness of the energy functional constructed in S1; S3, substituting the verified energy functional into the variational physics information neural network for iterative training. This invention, by introducing functional constraints into the variational physics information neural network, can more precisely control the neural network's synergistic satisfaction of multiple constraints (equation-boundary-functional), thereby improving the overall accuracy and spatial stability of the solution.

This invention discloses a power system inertia assessment method based on energy function, comprising the following steps: collecting system port data and preprocessing the data; calculating the magnitude of port energy flow using measurement and calculating each component; calculating the dissipated energy at each generator port, performing linear fitting on the dissipated energy flow to obtain the damping term, calculating the inertial time constant H, comparing it with the true value, and selecting an appropriate time window.

The present application relates to the technical field of detection, and particularly relates to a complex shell detection method and system based on structured light scanning. The method comprises the following steps: calculating the wrapped phase value and phase modulation amplitude of each pixel point at each frequency, calculating the discrete probability distribution containing the candidate fringe order and the corresponding probability for each pixel point based on the multi-frequency wrapped phase difference, generating an initial pixel confidence map, constructing an energy function, determining the penalty weight of the smoothing term according to the phase modulation amplitude and the local variance of the wrapped phase gradient, obtaining a preliminary fringe order distribution map, updating the discrete probability distribution by using the initial pixel confidence map, re-minimizing the energy function to obtain a corrected fringe order distribution map, reconstructing the final three-dimensional topography, and iteratively optimizing the projector principal point and the radial distortion coefficient in the system calibration parameters. That is, the scheme of the present application can preserve the surface geometric details, improve the effect of processing the complex curved surface and the high-curvature area, and improve the measurement accuracy.

The invention belongs to the field of new energy grid connection, relates to a port Hamiltonian energy-based multi-parallel grid-following converter system transient synchronization stability evaluation method and device, and solves the problem of multi-parallel grid-following converter system transient synchronization stability evaluation at the present stage, and the method comprises the steps of establishing a transient model of a multi-parallel grid-following converter system; constructing an energy function of the transient model of the multi-parallel network-following converter system, and further establishing a port Hamiltonian model; the critical energy threshold value of the multi-parallel grid-following converter system is determined by analyzing the maximum value of the total energy in the first swing process of the fault trajectory by using a dominant unstable equilibrium point method, and the critical clearing time is further determined based on the threshold value. According to the method, internal measurement data or model parameters are not needed, and the stability margin of the multi-parallel grid-following type converter system can be accurately and quantitatively evaluated.

The invention relates to an asset risk prediction method and device, a model training method and device, equipment and a medium. The method comprises the steps of obtaining original input data, performing time sequence feature extraction and enhancement processing on the original input data to obtain an input vector, performing prior factor extraction through a factor predictor of a prediction model based on the input vector to obtain a prior factor, and performing decoding through a factor decoder of the prediction model by using the prior factor to obtain a prediction result. The method comprises the steps of obtaining prediction data, inputting the prediction data into a de-noising energy estimator of a prediction model, calculating through the de-noising energy estimator to obtain a gradient of an energy function of the prediction data, and adjusting the prediction data based on the gradient of the energy function of the prediction data to obtain target prediction data. Through the method, the generalization ability can be improved, the asset risk prediction effect is improved, and the prediction accuracy is improved.

The invention relates to the technical field of supervision and control, in particular to a flexible DC converter station edge node voltage stability emergency control system, which comprises a transient energy margin evaluation module used for constructing a current system operation state vector according to a flexible DC converter station edge node voltage amplitude and a phase angle parameter acquired in real time, and substituting into a preset energy function structure for operation to obtain a current system operation energy value. According to the method, the system operation state vector is constructed in real time and substituted into the preset energy function, so that the quantification of the transient stability margin is realized, a dynamically changing stability criterion is provided for subsequent decision-making instead of depending on static and lagged threshold triggering, the transient energy margin is further combined with the voltage sensitivity of the adjacent node, and the voltage sensitivity of the adjacent node is further improved. The comprehensive risk of the domino effect caused by single node disturbance can be quantitatively evaluated, and a control system is changed from paying attention to isolated node safety to maintaining systematic stability of a regional power grid.

According to the power system stability analysis method and device, the storage medium and the computer equipment provided by the invention, the state variable is input into the pre-trained energy prediction model, the evaluation value of the system energy is output, and then the transient stability of the power system is judged. The energy prediction model is obtained by performing iterative optimization by taking a minimum target loss function as a training target, and the target loss function is obtained by fusing a state variable trajectory of the power system and Lyapunov constraint. Core physical constraints from an energy function theory are fused in the training process, physical domain knowledge is integrated into the training process through a target loss function, and an energy prediction model obtained through training can map state variables into an evaluation value of an energy function through single forward propagation. And an efficient and accurate calculation mode is provided for short-term voltage stability evaluation, so that the reliability and the accuracy of an energy function in a power system stability analysis process are improved.

The application provides a unified learning method and system supporting balanced propagation and predictive coding, and belongs to the technical field of neural network calculation and optimization. The method comprises the following steps: determining the network structure and connection type of a unified learning model supporting a balanced propagation algorithm and a predictive coding algorithm based on the calculation graph of the balanced propagation algorithm and the predictive coding algorithm; extracting the energy function of the balanced propagation algorithm and the predictive coding algorithm, configuring the interaction term of the energy function, and taking the configured energy function as the energy function of the unified learning model to support multi-convolution network calculation; and extracting the network structure, connection type and energy function of the unified learning model at a user end to construct a qualified multi-layer neural network structure, and optimizing the multi-layer neural network structure by using an optimizer.

This invention discloses a power system disturbance source localization method based on energy functions. The method first collects response data of the power system after a disturbance, and then calculates the output energy of each generator unit and the potential energy of each load using energy functions. Next, a statistical model is used to perform preliminary analysis of the energy data to screen candidate disturbance sources. Finally, the labeled energy data is fed into a logistic regression classifier for training and online application, constructing a unified disturbance source localization model. This invention combines energy analysis with machine learning to achieve rapid, accurate, and automated localization of different types of disturbance sources, such as random load fluctuations and forced power oscillations of generators. It avoids the problems of misjudgment and insufficient timeliness caused by reliance on human experience in traditional methods, and is particularly suitable for complex power grid environments with a high proportion of renewable energy integration.

This invention relates to the field of energy management and discloses equipment for improving unit power generation and optimizing grid operation based on intelligent dispatching. The equipment includes: a data sensing module for collecting grid status data of the units and preprocessing it to obtain processed data; and a scale modeling module for constructing a unified mathematical model containing fast and slow variables using the processed data. A hierarchical Hamiltonian is used to describe the coupling relationship between fast and slow variables, embedding power balance equation constraints to ensure overall grid power conservation, and introducing Wasserstein distance relaxation unit start-up and shutdown integer constraints to handle non-convex optimization problems. The output is a multi-objective optimization mathematical model containing energy functions and constraints. By utilizing hierarchical Hamiltonian, dynamic characteristics such as synchronous generator rotor angle / angular velocity are incorporated into the same energy framework along with dispatching decision variables such as unit start-up and shutdown, and energy storage charging and discharging. Power balance equation constraints ensure overall grid energy conservation, while Wasserstein distance relaxation unit start-up and shutdown integer constraints are introduced.