36 results about "Elastic analysis" patented technology

The provided are a price elasticity analysis and prediction method and model based on deep learning. The model consists of a CNN layer and an RNN layer. The method comprises the following steps: S1, collecting historical data and merging the historical data into a multi-dimensional time series dataset; S2, extracting sentiment data and trend data from market news and social media; S3, inputting the data obtained into CNN for data preprocessing and feature extraction; S4, inputting the feature extracted by CNN into RNN for time series analysis; S5, training and optimizing model: using Adam algorithm to adjust the learning rate adaptively, and combining the momentum method and RMSProp algorithm to improve the generalization ability and prediction accuracy of the model. The provided combines the advantages of CNN and RNN, which can understand and predict the complex relationship between price and market behavior more comprehensively and accurately.

The invention discloses a design method of an equivalent simulation component of a wall-type connection metal shear damper, and relates to the field of design methods of anti-seismic components. Comprising the steps that a non-damping structure model without a damper is established, the plane arrangement position of the metal shear damper in a building is determined, the yield bearing capacity of the damper is determined according to the proportion of earthquake shear force shared by the damper in the X direction and the Y direction of the structure, and the yield displacement of the damper is determined according to the design performance target of the damper. And determining the post-yield stiffness ratio of the metal shear damper, establishing a damping structure analysis model with a damper unit and a connecting wall pier unit, calculating the secant stiffness of the metal shear damper, and calculating the stiffness of the metal shear damper connecting the wall pier. According to the design method, the equivalent simulation component of the damper in the construction drawing model can be designed according to the performance parameters of the metal shear damper and the connecting wall pier, and the design method has important significance on correct establishment and equivalent elasticity analysis of the construction drawing model of the damping structure of the metal damper.

The invention discloses a large flexible wing static aeroelasticity analysis method based on a physical information neural network, and belongs to the field of aircraft design. The method comprises the following steps: for the wing with the super-high aspect ratio, firstly, dispersing the wing into n spanwise sections based on a strip theory, and initializing a reference angle-of-attack parameter of each spanwise section; then, a physical information neural network (PINN) is built, unsteady flow field solving is carried out on each section, for the current ith iteration, the physical information neural network is used for sequentially traversing and extracting pressure distribution of the airfoil surface of each section, respective aerodynamic load distribution is calculated, and the generalized force of the airfoil is obtained; and solving a structural dynamics equation based on the generalized force and structural information of the wing, calculating the deformation of the large-deformation wing by using a modal rotation method, and finally, carrying out solving iterative circulation on aerodynamic force and structural deformation until the attack angle is converged, so as to obtain the actual lift force L of the wing. According to the method, the calculation precision and efficiency are remarkably improved, and different flight conditions and wing design can be adapted.

The invention relates to the technical field of building structure engineering, in particular to a simplified elastic analysis and design method for an integrated model of a partition wall structure, and provides a simplified elastic analysis and design method based on a physical mechanism and data driving. And instead, a practical design tool which can be directly used for engineering design, is seamlessly connected with the current specification and has definite physical significance is formed based on intelligent calibration of a large-refinement nonlinear analysis result. According to the method, quantitative correlation between elasticity and nonlinear performance is established, theoretical preciseness is guaranteed, and the method has extremely high engineering practicability and serves as preposition and supplement of refined nonlinear analysis to form a complete technical system from rapid scheme design to accurate performance verification.

The invention relates to the technical field of intelligent power grids, in particular to a multi-dimensional dynamic elastic recognition method and system for key coupling nodes of a power distribution information physical system, and the system comprises a key node screening unit which constructs a unified CPDS model and preliminarily screens a candidate key node set based on structure controllability and structure observability; the fuzzy scene generation unit is used for constructing a dynamic fuzzy disaster scene set by utilizing a Markov chain Monte Carlo method and generating a set containing a large number of dynamic fuzzy disaster scenes; an elastic function construction unit; a node calculation output unit; according to the novel CPDS key coupling node accurate identification method, structure controllability, structure observability, dynamic fuzzy disaster scenes, reverse reinforcement learning and Shapley value comprehensive calculation are fused, so that the accuracy, fairness and adaptability of elastic analysis and decision making of a system are improved; and the rapid response and recovery capability of the power grid to disasters or attack disturbance is improved.

The invention discloses an aerodynamic force / thermal agent model-based rapid calculation method for the thermo-dynamic elasticity of a thermal protection plate of a high-speed aircraft, and the method comprises the steps: building an unsteady aerodynamic force / thermal agent model of a thermal protection wall plate in a high-speed flow based on a Kriging agent model method; a structural dynamics method based on a finite element method is used for establishing an aeroelastic module, a transient heat conduction equation is used for establishing an aerothermal module, and a thermal protection wallboard thermodynamic elasticity analysis frame is built. Finally, the aerodynamic force / thermal agent model is used for carrying out thermal protection wall plate thermodynamic elasticity calculation and analysis. Compared with a traditional high-order method, the calculation efficiency is improved by four orders of magnitude.

The invention relates to the technical field of aeroelastic analysis of aero-engines, in particular to a boosting-energy complementing gliding aircraft thermal / aeroelastic coupling modeling and analysis method considering rigid-elastic coupling. A frame for simultaneously solving rigid body motion and elastic vibration is established, the amplitude and direction disturbance characteristics of thrust pulsation and the rigidity degradation effect caused by pneumatic heat generation-heat conduction are considered, and the problem of prediction deviation caused by neglecting of rigid-elastic coupling and an extreme thermal environment in traditional solving is solved. According to the method, aeroelastic response analysis of the aircraft in different load stages (full load, half load and no load) can be simulated, and hot gas bomb response under the action of thrust disturbance and extreme thermal load is solved, so that the prediction capability of dynamic behaviors of the aircraft under complex working conditions is improved; and a theoretical technical support is provided for aeroelastic response servo suppression of the boosting-energy complementing gliding aircraft in a large impact / extreme thermal environment.

The application discloses a design method of equivalent simulation components of wall type connecting metal shear damper, and relates to the field of aseismic component design methods. X direction and Y direction damper share of earthquake shear force proportion to determine the yield load of the damper, to determine the yield displacement of the damper according to the design performance target of the damper, to determine the post-yield stiffness ratio of the metal shear damper, to establish a vibration reduction structure analysis model with the damper unit and the connecting wall pier unit, to calculate the secant stiffness of the metal shear damper, and to calculate the stiffness of the metal shear damper connecting wall pier. The application can design the equivalent simulation components of the damper in the construction drawing model according to the performance parameters of the metal shear damper and the connecting wall pier, and is of great significance to the correct establishment of the construction drawing model of the metal damper vibration reduction structure and equivalent elastic analysis.

The invention provides a shot peening forming deformation prediction method and system based on three-layer equivalent inherent strain, and the method comprises the steps that the three-layer equivalent inherent strain under preset technological parameters is calibrated based on a calibration sample of a preset size, and the preset technological parameters are technological parameters adopted when a target wallboard is machined; establishing a finite element model of the target wallboard, dividing the finite element model into three layers along the thickness direction of the finite element model, and dividing plane grids; loading the calibrated three-layer equivalent inherent strain to a shot blasting area of the finite element model; and activating the inherent strain field and carrying out elastic analysis to obtain a deformation prediction result. According to the embodiment of the invention, efficient, accurate and universal shot peening forming deformation prediction can be realized.

The invention discloses an XGBoost-based power generation quotation rationality evaluation method, system and equipment and a medium, and relates to the technical field of power market operation and supervision, and the method comprises the steps: collecting historical operation and market environment data, obtaining five evaluation indexes through a prediction model, elastic analysis, matching degree calculation and clustering analysis, fusing the indexes to construct a feature vector, and obtaining a power generation quotation rationality evaluation result. And training a classification model to evaluate the rationality of quotation, and generating a monitoring early warning signal when the matching degree is too low, the price response is too strong, the quotation deviation is too large and the behavior mode is abnormal by continuously tracking the change trend of key indexes. According to the invention, by fusing the multi-dimensional dynamic features and adopting the elastic time sequence matching and interpretable machine learning model, a power generation quotation behavior intelligent supervision closed loop integrating comprehensive evaluation, accurate quantification and active early warning is constructed, and the comprehensiveness, accuracy, objectivity and timeliness of market supervision are significantly improved.

The invention discloses a woven uniform fabric elasticity retentivity analysis method based on artificial intelligence, and particularly relates to the technical field of fabric elasticity analysis. Comprising the steps of S01, numbering woven elastic uniform fabric, S02, collecting initial fabric elasticity data, S03, evaluating initial fabric elasticity retentivity, S04, analyzing fabric elasticity attenuation trend, S05, outputting the fabric elasticity retentivity, and S06, grading the fabric elasticity retentivity. According to the method, the initial fabric elasticity data of the to-be-evaluated woven elastic uniform fabric is collected, the elastic recovery change rate evaluation index and the plastic deformation change rate evaluation index are calculated, the fabric elasticity is classified, and the elasticity attenuation trend of the fabric is analyzed, so that the attenuation trend prediction result is obtained; and the initial elasticity data is quantified into an indexed result, so that the performance evaluation of the elastic uniform fabric is realized, and the whole-process intelligent management of elasticity retentivity analysis is realized.

The invention discloses a static aeroelasticity analysis method for multi-precision aerodynamic evaluation for multidisciplinary optimization, relates to the technical field of aviation design, and solves the problem of inherent contradiction between distortion of a low-precision method and time consumption of a high-precision method in static aeroelasticity analysis. The aerodynamic and load characteristics of the configuration are calculated through a multi-precision aerodynamic analysis method and a structural analysis tool, and the calculated aerodynamic force and deformation displacement are interpolated to target grid points through an interpolation method based on a radial basis function. And then iteration of a finite step number is carried out, and finally the static aeroelastic convergence configuration appearance and aerodynamic characteristics are obtained. According to the method, the efficiency and precision of static aeroelasticity calculation in the wing design process are improved, and the method has wide applicability and reliability.

The invention discloses a three-dimensional acoustic elasticity calculation method based on combined potential, and relates to the field of ship three-dimensional acoustic elasticity calculation, and the method comprises the steps: constructing a speed potential in an outer watershed of an underwater ship structure into a linear combination form of a single-layer potential and a double-layer potential, and constructing a boundary integral equation on a wet surface of the underwater ship structure; according to fluid-solid coupling boundary conditions on the wet surface of the underwater ship structure, a boundary integral equation on the wet surface of the underwater ship structure is solved by adopting a boundary element method, and virtual source intensity distribution on the wet surface of the underwater ship structure is obtained; according to the virtual source intensity distribution of the wet surface of the underwater ship structure and the dry modal displacement of the structure, acoustic elasticity response parameters are obtained through calculation. By constructing the watershed speed potential outside the underwater ship structure in a linear combination form of single-layer potential and double-layer potential, the irregular frequency of acoustic elasticity calculation is effectively eliminated under the condition that the calculation scale and modeling workload are not additionally increased, and the efficiency of three-dimensional acoustic elasticity analysis can be remarkably improved.

The invention relates to the field of integrated circuit design and computer systems, and discloses a heterogeneous computing task scheduling method, device and equipment, a storage medium and a product, the method comprises the following steps: S1, task graph construction and feature extraction: analyzing an application program to construct a directed acyclic graph reflecting a task dependency relationship, generating a task feature vector containing multi-dimensional attributes for each atomic task; and S2, dependency elasticity dynamic analysis: monitoring the dependency relationship and address access behavior between tasks in real time, and quantitatively calculating a reordering elasticity value representing the adjustability degree of the dependency relationship. According to the method, through a hardware-assisted dependency elastic analysis and speculative out-of-order execution mechanism and in cooperation with a full-dimensional resource state perception and closed-loop feedback model, the technical problems of pipeline blockage caused by weak dependency of tasks and unbalanced resource allocation under a complex load in an existing heterogeneous computing system are effectively solved.

The present application relates to the technical field of building structure engineering, in particular to a simplified elastic analysis and design method for integrated model of partition wall structure, which proposes a set of simplified elastic analysis and design method based on physical mechanism and data driving. The method is not a simple application of traditional empirical coefficient, but an intelligent calibration based on a large number of refined nonlinear analysis results, forming a practical design tool which can be directly used for engineering design, seamlessly connected with the existing specification and has clear physical meaning. The quantitative correlation between elastic and nonlinear performance is established, which not only guarantees the theoretical rigor, but also has strong engineering practicability. As a preposition and supplement of refined nonlinear analysis, the method forms a complete technical system from rapid scheme design to accurate performance verification.

The application relates to the technical field of performance analysis of viscoelastic materials, and discloses a performance analysis method and device of viscoelastic materials, wherein the method comprises the following steps: obtaining elastic operators of a specific viscoelastic material at multiple time points, and dividing the material into coarse element domains and fine element domains by using a multi-scale finite element method. A multi-scale base function is constructed for each coarse element domain, and an equivalent stiffness matrix set is calculated, and then a scale reduction calculation is performed to extract a micro information set. Based on the functional relationship of the micro information, viscoelastic analysis of the specified viscoelastic material is finally realized, and a basis is provided for performance evaluation of the material. The application has the advantages of high calculation efficiency, resource saving and large problem scale expansion compared with the prior art, reduces the historical data storage demand, significantly reduces the degree of freedom of the macro equation, is widely applicable to non-periodic structures, and has the potential to be extended to nonlinear viscoelastic problems.

The application discloses a consumer industry enterprise closing risk early warning method and device and a storage medium, relates to the technical field of business data analysis, and comprises the following steps: multi-source data acquisition; cleaning, missing value filling, duplicate removal and standardization are performed on the collected data; a demand curve is fitted by using a least square method, a demand price elasticity coefficient is calculated, the sensitivity of commodity demand to price is judged, and market stability is evaluated; and an ARMA time series model is adopted to perform stationarity processing and modeling on historical sales data, and to predict short-term and medium-term sales trends. The application adopts demand elasticity analysis and ARMA time series prediction to perform data analysis, and converts qualitative market feelings into quantitative indexes; in the risk evaluation stage, the analytic hierarchy process is adopted to determine weights and the fuzzy comprehensive evaluation method, subjective judgment deviation is effectively reduced, and risk grade determination is more objective and accurate.

This invention relates to the field of structural dynamics analysis and testing technology, specifically to an aeroelastic analysis method for large flexible structures based on dynamic sparse identification. The method includes: determining the dimensional parameters of the large flexible structure and establishing a finite element model of the large flexible structure based on these parameters; determining the aerodynamic load excitation and applying it to the finite element model of the large flexible structure to obtain the dynamic response; establishing a structural dynamics model to be identified, wherein the basis functions of the structural dynamics model to be identified are determined by multiple different deformation shapes of the large flexible structure; performing sparse identification based on the aerodynamic load, dynamic response, and structural dynamics model to obtain nonlinear stiffness coefficients, thus obtaining the identified structural dynamics model; for the flight condition to be analyzed, iterative processing is performed based on the identified structural dynamics model to obtain the deformation displacement and aerodynamic force distribution of the large flexible structure. This invention can improve the efficiency and accuracy of structural order reduction models.

The application discloses a large-scale low-orbit satellite network elasticity evaluation method and system based on graph theory and entropy theory, and integrates dynamic attributes of ISL and satellite nodes into a snapshot topology structure obtained from periodicity and predictability of a satellite network by using a time snapshot-based space-time expansion graph model according to a low-orbit satellite network service scene model and constellation model, to obtain a low-orbit satellite constellation time-varying network topology based on a space-time expansion graph, and further construct a satellite communication model and a satellite state updating mechanism, an elasticity analysis model and an elasticity evaluation index of the LEO satellite network; finally, an optimization problem of network elasticity recovery of the low-orbit satellite communication network under a damaged condition is established, and then network elasticity of the low-orbit satellite communication network under the damaged condition is obtained. The application can ensure that the network can quickly recover service capability after being damaged, and effectively improves adaptive recovery capability and service guarantee level of the LEO satellite network.

The present invention discloses a bridge dynamic interaction analysis method that integrates monitoring data and hybrid substructures. The method first uses hybrid substructure technology to determine the interface constraints of key areas by establishing mathematical equations; then, an expectation-oriented adaptive sparse Gaussian process algorithm is introduced to perform parameter identification of these key areas based on actual monitoring data. Furthermore, the present invention proposes a new theoretical framework to realize the dynamic interaction between substructure nonlinear analysis and main structure linear elastic analysis. The effectiveness of this method is verified by an application example on an actual concrete beam bridge. The present invention not only opens up a new path for the deep integration of monitoring data and finite element models, but also significantly enhances the accuracy of substructure analysis and overall structural performance evaluation.

The invention discloses a method for rapidly predicting the elastic-plastic mechanical property of a one-dimensional periodic spiral winding structure, and relates to the technical field of spiral winding structure mechanical property prediction. Comprising the following steps: S1, constructing a finite element model of a one-dimensional periodic spiral winding structure, performing linear elasticity analysis on the finite element model, and extracting a strain concentration tensor; s2, based on the extracted strain concentration tensor, clustering the finite element model by using a clustering algorithm to obtain a reduced-order model after partitioning, and calculating an interaction matrix representing a mechanical relationship between blocks in the reduced-order model; and S3, inputting the interaction matrix into an online incremental algorithm to obtain an elastic-plastic stress-strain curve of the one-dimensional periodic spiral winding structure, and realizing prediction of the elastic-plastic mechanical property of the one-dimensional periodic spiral winding structure. According to the method, the elastic-plastic mechanical property of the one-dimensional periodic spiral winding structure can be efficiently and accurately predicted, and the analysis efficiency and optimization efficiency of the one-dimensional periodic spiral winding structure are improved.

The present application relates to the technical field of civil engineering, and particularly provides an analysis method for soil-concrete interaction in super-deep soft soil area, aiming at solving the problem of long construction period in existing soft soil foundation treatment. The present application comprises: obtaining the structure parameters of the target building, respectively establishing a pure structure model and a soil-concrete integrated model based on the structure parameters, wherein compared with the pure structure model, the soil-concrete integrated model increases the preset soil parameters; performing small earthquake elastic analysis, small earthquake elastic time history analysis and large earthquake elastic-plastic time history analysis on the pure structure model and the soil-concrete integrated model respectively; comparing the small earthquake elastic analysis results, comparing the small earthquake elastic time history analysis results, and comparing the large earthquake elastic-plastic time history analysis results; according to the comparison results, the differences of the soil-concrete integrated model compared with the pure structure model are targetedly strengthened. Through the analysis method of the present application, the soft foundation treatment can be carried out after the construction, and the construction period is shortened.

The invention provides a reinforced concrete structure reinforcement calculation process and method, and the method comprises the following specific steps: carrying out the linear elasticity analysis of a plain concrete structure, calculating the internal force of the plain concrete structure, and calculating the initial reinforcement ratio of the concrete structure meeting the bearing capacity limit state; a preliminary reinforcement scheme is given on the basis of the preliminary reinforcement ratio of the structure; and performing nonlinear finite element analysis on the reinforced concrete structure, calculating a concrete damage state and reinforcement stress, performing crack width checking calculation, and adjusting a preliminary reinforcement scheme. According to the method, the requirements of the bearing capacity limit state and the normal use limit state can be met at the same time, the process is clear, and powerful technical support can be provided for reinforcement design of a reinforced concrete structure.

The invention relates to the field of fiber quality analysis, in particular to a multi-scale grading system and method for cotton fiber quality. The system synchronously collects cross section images of cotton fibers through a micro-fluidic chip and double cameras, obtains a fracture curve in combination with a tension test, extracts surface curvature and torsion resistance features based on differential geometry, and obtains a multi-scale grading result. A variable-expansion-rate cavity convolution network is used for fusing multi-dimensional features, fiber length, width and distortion parameters are generated, finally, fracture elasticity analysis is combined, through quality index calculation and a multi-scale grading standard, fiber quality accurate grading is achieved, the multi-scale grading standard from microcosmic to macroscopic is constructed, a feature comprehensive analysis system is combined, and the quality of the fiber is accurately graded. And comprehensive evaluation of the fiber quality is realized.

This invention discloses a time-dependent local stress-strain method for analyzing the strength and life of high-temperature structures. This method targets load-bearing components operating under high-temperature conditions, where the load-bearing components have structural discontinuities. The method comprises: a working condition parameter acquisition step, a material parameter acquisition step, an elastic-plastic analysis step, a limit analysis step, an elastic analysis step, a boundary condition setting step, an iterative calculation step, and a result integration step. The invention also discloses a time-dependent local stress-strain tool software for analyzing the strength and life of high-temperature structures. The tool software comprises: a parameter acquisition component, a finite element modeling and calculation component, an iterative calculation component, and a result presentation component.

The invention relates to the technical field of power market and public utility management, in particular to a micro-grid cost dredging mechanism design and evaluation method, system, equipment and medium, which comprises the following steps of: assembling a cost conduction rule based on a cost collection unit delimiting structure and a cost conduction diagram; loading life cycle parameters to carry out cash flow prediction under multiple scenes, and generating a multi-scene economy evaluation set; and based on the multi-scene economic evaluation set, performing parameter disturbance, sensitivity and elasticity analysis, identifying key risk factors and generating allocation suggestions, further performing write-back and versioning management on conduction rule parameters, and generating a cost grooming mechanism after iterative correction. The method has the beneficial effect of effectively supporting scientific decision and efficient operation of multiple types of microgrids in a complex market environment.

The application belongs to the technical field of building structure design, and provides a design method of a self-resetting concrete L-shaped column-base connecting interface, wherein the cross-sectional size of the self-resetting concrete L-shaped column is determined according to the elastic analysis of the overall structure, and ordinary steel bars are configured, the N and M values of the internal force of the self-resetting concrete L-shaped column-base connecting interface design control are reviewed whether they are in the N-M curve, prestressed steel bars are configured according to the review result, the application of the structure design is facilitated, and the popularization of the self-resetting L-shaped column structure system is improved.

This invention belongs to the field of aircraft aerodynamic calculation technology, specifically relating to a method and apparatus for hydrostatic aeroelastic analysis based on multiphysics coupling. The method includes hydrostatic aeroelastic calculation without considering heat; conjugate heat transfer analysis based on the hydrostatic aeroelastic results; and a solution method that uses hydrostatic aeroelastic and conjugate heat transfer results as initial conditions, coupled with unsteady flow field, transient structural heat transfer, and structural dynamics with time effects removed. By employing characteristic time-stepping of structural heat transfer, the hydrostatic aeroelastic numerical equilibrium point can be reached within a relatively small number of time steps. This invention uses the aforementioned initial conditions for hydrostatic aeroelastic analysis, avoiding non-physical solutions and effectively improving numerical stability. To improve computational efficiency, structural deformation velocity and acceleration effects are ignored during the solution process, and structural dynamics with time effects removed are performed. The time step is taken from the characteristic time scale of structural heat transfer, effectively improving computational efficiency.

The invention provides a constitutive model establishment and transient dynamic analysis method considering a plastic domain, and relates to the technical field of constitutive relation and dynamic analysis. The method comprises the following steps: introducing plastic strain parameters corresponding to the yield strength of a material into a J-C constitutive equation at normal temperature, establishing a constitutive model considering a plastic domain, and fitting and solving each parameter in the established constitutive model through test data to obtain a solved constitutive model; the solved constitutive model is subjected to numerical simulation and is compared with test data, so that the reasonability of the solved constitutive model can be verified; the stress deconservative property is verified by establishing an explicit dynamic finite element model and carrying out linear elasticity analysis and elastic-plastic analysis; the method can provide reference for plastic domain constitutive model establishment and transient dynamics deconservative analysis.

The invention relates to a thermoelastic analysis method for a laminated hollow column containing a weak interface, which comprises the following steps: establishing a fractional order heat conduction equation considering an interface effect for a laminated hollow column structure containing the weak interface, and establishing a motion equation, a constitutive equation and a boundary condition which do not consider physical power; performing dimensionless processing on the fractional order heat conduction equation, the motion equation, the constitutive equation and the boundary condition to obtain a control equation; performing Laplace transformation on the obtained control equation, and solving to obtain a mechanical property distribution result; the boundary condition establishing process specifically comprises the step of considering interlayer displacement continuity, heat flow density normal component continuity and temperature discontinuity. Compared with the prior art, by introducing establishment of the weak interface and the fractional order heat conduction equation and Laplacian transformation solution of the control equation, the accuracy of the solution result of the mechanical property distribution rule of the laminated hollow column containing the weak interface can be improved, and the model is more practical.