27 results about "Nonlinear structure" patented technology

The invention provides a structure vulnerability analysis method and system based on earthquake magnitude, distance and site conditions, a storage medium and a computer program product. The method comprises the following steps: adopting a preset sampling algorithm to obtain preset earthquake magnitude, distance and site conditions, and acceleration time history samples corresponding to the preset earthquake magnitude, distance and site conditions; based on the acceleration time-history sample, performing nonlinear dynamic time-history analysis on a to-be-evaluated structure by using a finite element analysis method to obtain nonlinear structure seismic response corresponding to the to-be-evaluated structure and the acceleration time-history sample; establishing a change relationship between the statistical parameters of the seismic response of the nonlinear structure and the preset magnitude, distance and site conditions by using a regression fitting method; and constructing a vulnerability curved surface of a to-be-evaluated structure based on the preset earthquake magnitude, distance and site conditions based on the statistical parameters of the seismic response of the nonlinear structure and the change relationship between the preset earthquake magnitude, distance and site conditions. According to the embodiment of the invention, the four elements of a seismic source, a propagation path, a site and a structure can be completely coupled, and the method can be suitable for earthquake disaster risk analysis and rapid evaluation of post-earthquake disasters under various medium-short period structure systems.

The invention relates to the technical field of gene editing, and discloses an sgRNA activity prediction method and device based on deep features and automatic machine learning. The method comprises the following steps: acquiring sgRNA training data with editing efficiency labels and discretizing the sgRNA training data into classification labels; after the sgRNA and the PAM sequence are spliced, inputting the spliced sgRNA and PAM sequence into a pre-training depth sequence model to extract high-dimensional features; obtaining a low-dimensional feature vector through nonlinear dimensionality reduction; an automatic machine learning framework is combined with cross validation, and a prediction model is automatically trained and optimized based on low-dimensional features; and finally, carrying out activity prediction and sorting screening on candidate sgRNA by utilizing the model. According to the method, through fusion of deep semantic extraction, nonlinear structure maintenance and a full-automatic modeling process, the accuracy, robustness and development efficiency of sgRNA activity prediction are effectively improved, and an efficient pilot screening tool is provided for a gene editing experiment.

The invention relates to a structure period segment division method based on structure dynamic response similarity, which is characterized in that on the basis of structure dynamic response under seismic action, objective division of structure period segments is realized by constructing response characteristic matrixes corresponding to different structure periods and introducing a fuzzy clustering mechanism to perform unsupervised classification on the structure periods. According to the method, linear and non-linear structure response characteristics are considered at the same time, the optimal period segmentation number and the boundary threshold are determined in combination with the clustering effectiveness evaluation index, and a more accurate thought and method are provided for more rapidly evaluating seismic damage of the structure in the specific period range and matching input vibration of the structure in the specific period range.

The application discloses a kind of sensor fault detection method and device of structural health monitoring system, it is related to structural health monitoring technical field, comprising: obtaining the nonlinear structure monitoring data of sensor system collected by structural health monitoring system, nonlinear structure monitoring data is handled using improved geometric PNL hybrid model, obtain linear to-be-separated mixed signal, using FastICA model to process to-be-separated mixed signal, obtain multiple independent elements, determine the separation matrix of improved geometric post-nonlinear independent component analysis model according to multiple independent elements, using the processing of improved geometric post-nonlinear independent component analysis to real-time collection nonlinear structure monitoring data, determine whether sensor system exists fault and the sensor of fault occurrence.The method can still complete linearization processing to sensor mixed signal under the condition that prior knowledge is unknown, compared with simple linear ICA analysis algorithm, it is more suitable for complex nonlinear structure.

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

The invention provides a seismic data filtering method and device based on kernel principal component analysis and a medium, and belongs to the field of seismic data processing. The method comprises the following steps: extracting a trend time difference attribute of an input three-dimensional seismic data volume; setting a surface element size and extracting a corresponding line data volume according to the surface element size; selecting a target point and calculating surface element coordinates according to the trend time difference data; setting the size of a time window and extracting a small three-dimensional data volume in combination with surface element coordinates; and performing kernel principal component analysis on the small three-dimensional data volume to obtain a first principal component, and taking central point data of the first principal component as filtered data of the target point. According to the method, original data are mapped into a high-dimensional space through nonlinear mapping by adopting kernel principal component analysis, so that nonlinear structures and characteristics in the original data can be better reserved; in addition, the trend time difference attribute of seismic data is also considered, geologic structure data can be more accurately obtained by opening up a time window along the event trend, the problem of data discontinuity caused by the influence of stratum inclination is improved, and the filtering effect is improved.

The application provides a high-order interaction prediction method and device with mixed graph deep learning, which first constructs a drug molecule graph, a microorganism weighted graph, a disease weighted graph and a supergraph connecting the three based on multi-source heterogeneous data such as drug molecular structure, microorganism classification information and disease semantic network, forming a mixed graph structure. Subsequently, through a mixed graph deep learning module fusing a graph convolution network and a supergraph neural network, nonlinear structure features and high-order interaction features of each entity are extracted, and the adaptive fusion of the features is realized by using an attention mechanism. Then, the fused deep features are mapped to the prior expectation of the latent factor matrix in the Bayesian logic tensor decomposition model, a probabilistic graph model is constructed, and the joint adaptive inference of the model parameters, latent variables and deep learning mapping is carried out through a variational expectation maximization algorithm, so that the high-order correlation probability prediction of the whole tensor space is realized without negative sampling.

The invention provides a variance-based aircraft structure design parameter global sensitivity analysis method, and aims to solve the problems of high calculation cost, difficulty in quantizing parameter interaction effect and coupling propagation influence and the like in the application of existing Sobol and other methods, the method comprises the following steps: firstly, identifying key structure parameters and establishing a probability model of the key structure parameters; then, a Sobol sequence is adopted to generate a sample matrix, and output response is calculated through an aircraft structure system model; constructing a mixed sample matrix to perform variance decomposition, and respectively calculating a first-order sensitivity index and a total sensitivity index of each parameter to quantify main effect and interaction effect contribution; and finally identifying performance key parameters and interaction sensitive parameters according to the index sequence. According to the method, global analysis of a high-dimensional nonlinear structure system is realized under acceptable calculation cost, the result can provide a quantitative decision basis for lightweight design, tolerance allocation and multidisciplinary collaborative optimization of an aircraft structure, and the design efficiency and reliability are remarkably improved.

The invention discloses a typical tree species growth prediction method, system and device based on multi-stage multi-factor regression and a medium, and relates to the technical field of tree species growth prediction.The method comprises the steps that multi-source heterogeneous data are collected and preprocessed; dividing the independent variables into different types of influence factors, and performing statistical test on each factor to obtain a preliminary candidate variable set; calculating a variance expansion factor of the candidate variables, and when the expansion factor exceeds a threshold value, reducing the correlation among the preliminary candidate variables by adopting a collaborative path method to obtain a final variable; performing regression modeling through a three-stage modeling method based on the final variable to generate a regression model, and establishing a regression sub-model for each partition; and based on the obtaining mode of the final variable, extracting a judgment rule of the tree species and outputting the judgment rule in a structured format. According to the method, high-precision prediction of the growth under multi-factor driving can be realized, and the problems of multi-collinearity, unstable variable selection, insufficient nonlinear structure expression and the like in a traditional regression model are solved.

The application relates to the field of electric digital data processing and discloses a sensing data fusion abnormality detection system and method based on edge computing, which comprises a data acquisition module, a feature storage module and a data analysis module. The data analysis module acquires N-path heterogeneous digital signals of the real-time state of a controlled object, constructs an observation vector mapped to an N-dimensional feature space through normalization processing, calls a pre-stored coupling feature matrix, projects the observation vector to a stable manifold space, extracts an orthogonal residual vector of the observation vector and calculates the module length, and when the module length continuously exceeds a judgment threshold for a period reaching a time threshold, it is judged that the controlled object has nonlinear structural decoupling. The application identifies abnormalities by monitoring the topological offset of the observation vector relative to the stable manifold, realizes deep mining of the physical coupling logic among multi-source signals, and effectively resists signal slow drift caused by environmental fluctuations.

The application discloses a wind turbine blade semi-coupling aeroelastic modeling method considering nonlinear deformation and belongs to the technical field of wind turbine simulation calculation. The application combines calculation parameters used by three-party software, establishes a blade structural load model and a blade corrected aerodynamic model, calculates aerodynamic load and structural load, and superimposes the aerodynamic load, gravity load and centrifugal force load of the blade to serve as external load of a blade nonlinear structure control equation. The external load is taken as a calculation parameter and is brought into a self-constructed iteration scheme, and then simulation calculation of the wind turbine is carried out in a semi-coupling mode. The application adopts the above method, constructs a semi-coupling simulation process of the blade nonlinear structure model and three-party wind turbine simulation software, can calculate higher-precision nonlinear motion response characteristics of an ultra-long flexible wind turbine blade under the same simulation environment and load conditions, and can achieve good effects in preliminary structural design and response evaluation of large wind turbine blades.

The invention belongs to the technical field of aerodynamic performance characteristic analysis of aircrafts, and particularly relates to a geometric nonlinear flutter boundary prediction method based on a chaos phase space principal component. According to the method, nonlinear flutter characteristics are analyzed and flutter boundaries are predicted by analyzing attractor characteristics of system response signals, and planarity of attractors is represented by analyzing variance contribution rates EVR of first two dimensions of a phase space matrix by utilizing characteristics of pie-shaped attractors of the response signals in a phase space when flutter occurs in a geometric nonlinear structure. The flutter characteristics of a wing with geometric nonlinear characteristics are quantitatively analyzed and described, a brand-new extrapolation prediction method of the flutter critical speed is provided based on the rule that the index changes along with the wind speed, and accurate prediction of the nonlinear flutter boundary can be achieved.

The invention discloses a non-linear structure impact load identification method based on physically guided deep learning, and belongs to the technical field of structure health monitoring and intelligent diagnosis. By constructing an enhanced robust neural network, innovatively combining deep learning technologies such as multi-scale convolution, a self-adaptive long-short-term memory network and a multi-head attention mechanism, and integrating knowledge such as physical constraints, high-precision recognition of impact loads of a nonlinear structure system is realized. The core innovation of the method comprises the following steps: designing a self-adaptive preprocessing assembly line, and automatically selecting an optimal processing strategy according to data characteristics; a multi-path nonlinear feature extractor with physical significance is constructed, and nonlinear features of different orders are effectively captured through linear, secondary and tertiary feature path parallel processing; providing a physically guided adaptive loss function, and comprehensively considering a plurality of physical constraints such as time-frequency domain consistency, peak value, energy conservation, gradient continuity and the like; a self-adaptive LSTM block is developed, and the time sequence modeling capability is enhanced through a gating mechanism and residual connection.

The invention provides an electricity purchase side settlement business ticket optimization matching method, device and system, and relates to the technical field of electric power grids. According to the method, key original features are extracted from original settlement data, a deep potential structure is mined through a nonlinear structure, a feature set with high characterization force is formed by fusing an explicit and implicit feature interaction relation, and finally accurate matching is completed by combining dynamic similarity measurement and an adaptive threshold value. The method effectively overcomes the limitation that a traditional linear method is difficult to process a complex non-linear relation, improves the automation degree and accuracy of matching, reduces manual intervention and subjective errors, solves the technical problem that the matching of settlement business tickets is inaccurate by using the linear method, and improves the matching efficiency. And a reliable technical support is provided for rapid and accurate processing of the settlement service of the electricity purchasing side.

The application relates to the field of electric digital data processing and discloses a sensing data fusion abnormality detection system and method based on edge computing, which comprises a data acquisition module, a feature storage module and a data analysis module. The data analysis module acquires N-path heterogeneous digital signals of the real-time state of a controlled object, constructs an observation vector mapped to an N-dimensional feature space through normalization processing, calls a pre-stored coupling feature matrix, projects the observation vector to a stable manifold space, extracts an orthogonal residual vector of the observation vector and calculates the module length, and when the module length continuously exceeds a judgment threshold for a period reaching a time threshold, it is judged that the controlled object has nonlinear structural decoupling. The application identifies abnormalities by monitoring the topological offset of the observation vector relative to the stable manifold, realizes deep mining of the physical coupling logic among multi-source signals, and effectively resists signal slow drift caused by environmental fluctuations.

The invention provides a high-order interactive prediction method and device with mixed graph deep learning, and the method comprises the steps: firstly constructing a drug molecule graph, a microorganism weighted graph, a disease weighted graph and a hypergraph connecting the three graphs based on multi-source heterogeneous data, such as a drug molecule structure, microorganism classification information and a disease semantic network, and forming a mixed graph structure; and then, through a mixed graph deep learning module fusing a graph convolutional network and a hypergraph neural network, nonlinear structure features and high-order interaction features of each entity are extracted, and adaptive fusion of the features is realized by using an attention mechanism. Next, the fused deep features are mapped into priori expectation of a potential factor matrix in a Bayesian logic tensor decomposition model, a probability graph model is constructed, and joint adaptive inference is performed on model parameters, latent variables and deep learning mapping through a variational expectation maximization algorithm, so that the probability graph model is obtained under the condition that negative sampling is not needed; and high-order association probability prediction of the full tensor space is realized.

The invention provides a fan blade health state monitoring method, system, equipment and medium, and the method comprises the steps: capturing the displacement and load of a key position through a sensor on a flexible blade, taking the displacement and load as supervision points for training a PINN, and in the training process, optimizing and adjusting neural network parameters to minimize a total loss function, so as to obtain the health state of a fan blade. Constructing an agent model of blade aeroelastic response; solving the nonlinear structure kinetic equation by using the proxy model to obtain transient time calendar responses of the flexible blade under different working conditions; and collecting current moment data of the sensor, inputting the current moment data into the proxy model, calculating the load and strain distribution of the whole field of the flexible blade to reconstruct the operation attitude, and comparing the operation attitude with a historical reference state to realize structural health monitoring and evaluation. According to the method, through dual optimization of PINN fusion physical model and data driving, physical model simplification and actually measured data deviation in blade analysis are effectively bridged, and the blade load calculation health monitoring precision and reliability are remarkably improved.

The invention discloses a large-span arch bridge geometric nonlinear structure response calculation method, and relates to the technical field of bridge engineering structure analysis. Comprising the steps that a reasonable arch axis is set, and a second-order deflection nonlinear equilibrium equation of the large-span arch bridge is established; discretizing a reasonable arch axis into a polynomial capable of being solved singly, and deriving a nonlinear deflection expression and a nonlinear bending moment expression of the large-span arch bridge based on a second-order deflection nonlinear equilibrium equation; solving unknown parameters in the nonlinear deflection expression and the nonlinear bending moment expression on the basis of the principle that the elastic compression amount and the compression strain are equal along the integral of the arc length of the arch axis, and obtaining the nonlinear deflection and the nonlinear bending moment of the large-span arch bridge; verifying the calculation method by adopting a numerical simulation method considering geometric nonlinearity; and analyzing a change rule and a spatial distribution rule of the non-linear structure response of the large-span arch bridge along with a loading process through numerical simulation. According to the method, a reliable basis is provided for structural safety reserve evaluation and optimization design.

The invention discloses an arch bridge bending moment increasing coefficient determination method and system, and relates to the technical field of arch bridge structure design. Obtaining design parameters of the arch bridge; discretizing a reasonable arch axis of the arch bridge into a series form, and establishing a geometric nonlinear structure response analysis model by combining boundary conditions based on a principle that elastic compression and compression strain are equal along an arc length integral; respectively calculating the total bending moment and the linear bending moment of the arch bridge under the symmetric dead load action through a geometric nonlinear structure response analysis model; calculating an initial bending moment increasing coefficient based on the total bending moment and the linear bending moment; based on the section position distribution of the arch bridge arch rib, determining the applicable values of the bending moment increasing coefficients of different areas, and completing the determination of the arch bridge bending moment increasing coefficient. According to the method, the reasonable arch axis is discretized, the geometric nonlinear analysis model is established, the secondary influence of the axial force on the bending moment is fully considered, the actual bending moment value under the geometric nonlinear effect can be accurately reflected, and the method is suitable for symmetric dead load arch bridges with different spans and different rise span ratios.

The invention discloses a cross-regional power transmission section capacity demand assessment method, electronic equipment and system, and relates to the technical field of power transmission planning, and the method comprises the steps: carrying out the sampling solving based on a high-fidelity steady-state mathematical model, and generating a scene set representing the steady-state operation of a plurality of future power systems; learning and mapping internally-associated high-dimensional structure manifolds in all steady-state operation scenes in the scene set through a physical information learning framework; analyzing geometric features of the high-dimensional structure manifold, and generating a power transmission planning index; according to a power transmission planning index, the capacity demand of a target cross-regional power transmission section is evaluated, and for a future power grid in which high-proportion renewable energy sources and flexible resources coexist, high-dimensional and nonlinear structural distortion caused by space-time dimension coordination interaction of multiple resources can be accurately captured and quantified. And evaluating the structural situation of the steady-state power flow of the power grid from a global view.

The invention belongs to the technical field of transformer oil temperature measurement, and particularly relates to a transformer oil temperature prediction method and computer equipment. The method comprises the following steps: S1, acquiring transformer oil temperature and transformer electrical parameter time sequence data; s2, inputting the data obtained in the step S1 into a trained oil temperature prediction model to obtain transformer oil temperature prediction data in a period of time after the input transformer oil temperature time sequence data; the oil temperature prediction model comprises an SVR-LSTM model, and the SVR-LSTM model comprises an LSTM model and an SVR model; the LSTM model is used for extracting nonlinear features and time sequence features in the input data, and the SVR model is used for performing nonlinear structure analysis on the features extracted by the LSTM model to obtain transformer oil temperature prediction data. According to the method, the technical problems that in the prior art, the requirement of an oil temperature prediction model for computing power is high, and high computing power cost needs to be input are solved.

The invention relates to the technical field of computer and Internet of Things encryption, and discloses an encrypted data transmission method and system, and the method comprises the steps: carrying out the homomorphic encryption of original sensing data through an Internet of Things terminal, and uploading the original sensing data to an edge node; the edge node performs feature extraction in the ciphertext domain by using a pre-trained light quantum model (only containing a linear layer or a low-order polynomial approximate activation function) to generate compressed second ciphertext data; and then the data is transmitted to a cloud end, subsequent reasoning is completed by a sub-model containing a complete nonlinear structure, and an output result is decrypted. The system comprises a terminal device, an edge computing node and a cloud server which cooperatively realize staged ciphertext processing. Through an edge-cloud collaborative architecture, on the premise that end-to-end data confidentiality is guaranteed, reasoning delay is remarkably reduced, the throughput and stability of the system are improved, and the method is suitable for a large-scale real-time Internet of Things scene.

The invention relates to the technical field of battery management systems, and discloses a BMS background data diagnosis method and system based on MRPCA and a storage medium, and the method comprises the following steps: 1, obtaining the interval training data of a BMS system; 2, decomposing the interval training data into a midpoint matrix and a radius matrix; step 3, establishing an MRPCA model based on the uncertain covariance matrix, and calculating an SPE statistical magnitude control limit and a T2 statistical magnitude control limit; step 4, acquiring test data, and calculating SPE statistics and T2 statistics of the test data by using the MRPCA model; according to the method, the MRPCA model is introduced, information of interval data is fully utilized, the center trend of variables is considered, uncertain fluctuation of the variables is also considered, and therefore adaptability to a complex nonlinear structure is improved; compared with a traditional PCA method, the MRPCA can more accurately capture potential abnormal distribution in the data, and is more stable in performance especially in the environment of a battery management system which is large in dynamic change.

The invention provides a global reliability sensitivity analysis method for a nonlinear structure system, and belongs to the technical field of system reliability analysis, and the method comprises the steps: S10, converting an input variable of an original reliability problem into a normal distribution space; step S20, constructing an important sampling density function according to a cross entropy important sampling principle; s30, sampling based on the important sampling density function to obtain a corresponding failure domain indicator function, constructing a state-related parameter model by using the failure domain indicator function and the input sample, obtaining conditional expectation based on first-order output of the state-related parameter model, and calculating a structure failure probability according to the structure failure probability and the conditional expectation, and finally, calculating global reliability sensitivity indexes of all input variables based on the structure failure probability. According to the method, the modeling sample size of small failure probability reliability problem state related parameter modeling can be remarkably reduced, and then the calculation cost of global reliability sensitivity analysis is effectively saved.

This invention discloses a clustering analysis method and application for high-dimensional single-cell data based on multi-view canonical correlation analysis, belonging to the interdisciplinary field of bioinformatics and computer science. Addressing the issue of insufficient accuracy in cell clustering analysis of high-dimensional single-cell RNA-seq data, this invention generates multi-view feature representations from single-cell sequencing data using various dimensionality reduction methods. A mapping method combining autoencoders and generalized canonical correlation analysis is used to map these multi-view feature representations to a common subspace. Then, the projection matrices of each view in the common subspace are weighted and fused to obtain a fused representation matrix. Finally, the fused representation matrix is ​​clustered using the KMeans method, and the clustering effect is evaluated by adjusting the Land index (ARI) and normalized mutual information (NMI). This invention can fully exploit the high-dimensional nonlinear structure of single-cell data, effectively compensate for the information loss in single-view methods, and significantly improve the accuracy and robustness of high-dimensional single-cell data clustering.

The invention discloses a self-supervised three-dimensional human body behavior prediction method based on hyperbolic Poincare space-time embedding, and relates to a computer vision technology. Comprising the following steps: preprocessing a three-dimensional human body behavior data set to generate a multi-observation-rate sample; designing a self-supervised skeleton feature learning network based on hyperbolic Poincare spatio-temporal embedding, and learning spatio-temporal features of skeleton samples through the network model without manual annotation; calculating the loss sum of the two spaces in the network, and performing end-to-end training on the network through a back propagation algorithm and a stochastic gradient descent method to obtain a most trained model; and testing the three-dimensional human body behavior prediction effect, adding a linear classifier behind the backbone network, classifying the obtained features, and calculating the final prediction precision. Manual marking is not needed, the nonlinear structure of the human body behavior is adapted through double-space joint learning, and the feature discrimination is improved; and a dynamic distribution sampling module is designed to relieve interference caused by observation rate difference. The method can be widely applied to scenes of intelligent monitoring, man-machine interaction and the like.