16 results about "Linear reconstruction" patented technology

The invention provides an effective wave height real-time prediction method and device based on dynamic residual correction, and relates to the field of ocean engineering. The method comprises the following specific steps: acquiring wave height data and performing multi-dimensional feature screening; constructing an integrated filter fusing L1 trend filtering and variational mode decomposition, optimizing parameters by using a sea image optimization algorithm, introducing a causal sliding window to extract features so as to construct a time sequence input tensor, and inputting the time sequence input tensor into a stacked bidirectional long-short-term memory network based on an attention mechanism after noise addition standardization so as to obtain a basic predicted value; calculating a manifold coherent structure, PID dynamics and physical statistical characteristics, and cascading with the basic prediction characteristics to construct a comprehensive element characteristic vector; a LightGBM architecture is constructed, and a prediction residual error is fitted after optimization is carried out through a sea image optimization algorithm; and finally, executing linear reconstruction based on the dynamic safety threshold constraint, and outputting a real-time correction result. According to the method, the error evolution rule is deeply mined by using manifold geometric features, and the real-time precision and robustness of significant wave height prediction are remarkably improved.

The application discloses a structure nonlinear deformation reconstruction method and system based on isogeometric and reduced basis, and the method comprises the following steps: measuring initial strain data of a ship plate structure surface, constructing a plurality of four-node inverse shell elements of the ship plate based on the initial strain data; assembling the plurality of four-node inverse shell elements to obtain a whole stiffness matrix; reconstructing the whole stiffness matrix based on the measured strain data of the ship plate to obtain a linear reconstruction result of the ship plate; correcting the linear reconstruction result based on the reduced basis, and fusing the correction increment to the linear reconstruction result for nonlinear iteration to complete nonlinear deformation reconstruction. On the basis of the principle of isogeometric analysis, the application combines the inverse finite element method to establish a four-node inverse shell element, realizes high-precision ship structure displacement reconstruction through a small number of strain measuring points, and helps designers to intuitively understand and deeply understand the mechanical properties of the structure and to monitor the safety of the structure in real time.

The application provides a temperature and concentration reconstruction method based on a normalized second harmonic linear model, belongs to the technical field of tunable diode laser absorption spectroscopy, and is used for two-dimensional temperature and concentration field reconstruction. The reconstruction system comprises a laser control and generation module, a fiber beam splitter, a sensor, a Mach-Zehnder interferometer, a photodetector, a data acquisition system and a computer. The reconstruction method comprises the following steps: after laser is split, one path is connected to the Mach-Zehnder interferometer and is received by the photodetector, the remaining paths pass through the to-be-detected area after being expanded and are received by a photodetector plate, and normalized second harmonic spectra of transmitted light intensities on each light path are obtained; a normalized second harmonic base matrix is calculated according to discrete temperature and concentration; a linear reconstruction model is established according to the sensor light path arrangement, and an iterative algorithm is used to obtain two-dimensional temperature and concentration distribution. The application effectively utilizes the normalized second harmonic spectrum, increases the number of independent equations, and improves the speed and accuracy of two-dimensional temperature and concentration distribution reconstruction.

The invention relates to the technical field of crossing of artificial intelligence and machine vision, discloses an AI-vision-based machine tool frame casting defect detection method and system, and aims to solve the technical problems that the image quality is reduced and the defect detection accuracy is influenced due to sudden change of instantaneous illumination in an industrial field. According to the method, illumination time sequence data are collected in real time by integrating a main imaging sensor and a high-frequency auxiliary light field sensor array, and future light field distribution is predicted based on a hardware Kalman filter; and generating a pixel-level dynamic gain matrix according to the main image, performing regional adaptive exposure compensation on the main image in a simulation domain, performing linear reconstruction and gain adaptive denoising, and outputting an illumination balanced image for an AI model to detect microcracks and pores. The system realizes microsecond-level illumination abrupt change response and local accurate compensation, and obviously improves the imaging consistency and defect detection rate.

The application discloses a CPU-GPU-based group target RCS high-efficiency parallel calculation method, which converts the linear reconstruction of group target characteristic current from a cycle-level calculation mode to a matrix-level calculation mode of a GPU platform, adopts a multi-layer fast multipole method, and accelerates the calculation of electromagnetic coupling between targets under a CPU-GPU heterogeneous parallel framework, wherein the calculation task division of aggregation and configuration matrix filling is based on the target and facet dimension, the calculation task division of transfer matrix filling is based on the grouping box pair and beam dimension, and the calculation and superposition of group target far-field scattering are based on the parallel processing mode of the target, facet and angle dimension. Through the cooperative calculation of CPU and GPU, the application can significantly improve the RCS calculation efficiency and scalability of large-scale group targets.

The application relates to a bridge modal parameter automatic identification method and system considering multi-channel information, which comprises the following steps: S1, generating a stability diagram by directly analyzing multi-channel monitoring signals by using COV-SSI, automatically extracting stable axes by combining a DBSCAN clustering algorithm, and realizing automatic identification of modal frequencies; S2, decomposing multi-channel monitoring data by using MvFIF to generate an intrinsic modal function (IMF) group with modal alignment characteristics; S3, calculating the instantaneous frequency and bandwidth of the IMF in step S2 by using HHT, screening out an IMF component containing a target modal frequency, and performing linear reconstruction; and S4, taking the multi-channel monitoring data after the reconstruction in step S3 as system input of the COV-SSI algorithm, calculating a system matrix and an output matrix, and calculating modal damping ratios by using eigenvalue decomposition; the method can consider the space-time correlation between multi-channel data, realize synchronous decomposition of multi-channel monitoring data, and realize automatic and accurate identification of structural modal parameters under different noise levels.

The application discloses a kind of based on visual measurement's abutment deformation monitoring method, equipment and medium, it is related to optical measurement technical field, comprising: by real horizontal displacement sequence and real height interval sequence, construct height slope distribution and extract slope variation, combine abutment measurement total height to calculate top and bottom corner amount, according to slope variation to top and bottom corner amount is consistent correction, form abutment overall corner amount;According to abutment overall corner amount to real horizontal displacement sequence is linearly reconstructed, obtain linearly reconstructed real horizontal displacement sequence, utilize the difference of linearly reconstructed real horizontal displacement sequence and real horizontal displacement sequence and extract consistency residual quantity, and from real horizontal displacement sequence separate abutment overall translation, form abutment deformation monitoring quantity.The application is linearly reconstructed according to abutment overall corner amount and calculates consistency residual quantity, realizes the separation representation of abutment overall translation, abutment overall corner amount and consistency residual quantity.

A photovoltaic power prediction method based on VMD-ISSA-BiGRU relates to the technical field of new energy power generation, comprising: acquiring a photovoltaic power sequence and a meteorological data sequence; performing variational mode decomposition on the photovoltaic power sequence; extracting time sequence features from each intrinsic mode component and the meteorological data sequence, and analyzing the correlation between each time sequence feature and power output; optimizing the hyperparameters of the BiGRU-Transformer model using ISSA; constructing the BiGRU-Transformer model based on the optimized hyperparameters and the retained time sequence features; inputting the intrinsic mode components into the BiGRU-Transformer model for calculation to obtain the prediction values of each component; and performing linear reconstruction on the prediction results of all components to obtain a photovoltaic power prediction sequence; which is used to solve the problems of low traditional prediction accuracy and poor dynamic processing capability.

The embodiment of the invention discloses a sea wave numerical mode second-order space advection method based on an SCVT unstructured grid, and the method comprises the steps: constructing an SCVT unstructured grid system, building an index mapping relation between a unit and an edge, configuring a wave action quantity at the center of the unit, and configuring an advection speed at the midpoint of the edge of the grid; spatial discretization is carried out on geographic space advection items based on a finite volume method; for flux calculation on each discrete grid edge, a second-order windward format is adopted, an upstream unit is determined according to the flow velocity direction, the wave action quantity and gradient of the upstream unit are obtained, and a high-precision wave action quantity value at the midpoint of the grid edge is obtained through linear reconstruction; and finally, combining spectrum space advection and a source convergence item to finish time integration and sea wave forecasting. According to the method, sea wave advection calculation of the second-order windward format is achieved in the SCVT grid, the precision of sea wave simulation is remarkably improved, numerical dissipation is effectively restrained, meanwhile, variable-resolution grid configuration is supported, and the calculation efficiency is improved on the premise that the simulation precision of key areas such as a near-shore area is guaranteed.

This invention relates to the field of image processing, specifically to a method and system for color difference detection of automotive injection molded parts based on image processing. First, an industrial camera is controlled to acquire multiple frames of images with different exposure times. The grayscale values ​​are mapped to relative irradiance using the inverse function of the camera's photoelectric response function. Then, a linear validity factor is constructed based on the sensor's photoelectric response characteristics to filter data in the optimal linear response region and suppress noise and saturation. Simultaneously, a chromaticity consistency factor across the exposure image sequence is calculated to eliminate color shift caused by single-channel nonlinear response. Finally, the two factors are combined and weighted to generate a high-fidelity radiance map, which is then converted to the CIELAB color space to calculate the color difference. This invention effectively eliminates the purple fringing effect at highlight edges, ensures linear reconstruction of physical reflection energy, and significantly improves the color difference detection accuracy of complex curvature high-gloss trim panels.

The invention provides a flow field reconstruction method and system based on an orthogonal Hermite polynomial, and the method comprises the following steps: S1, carrying out the standardization processing of original high-dimensional flow field data, and carrying out the initial centralization, and obtaining centralized data; s2, performing principal component analysis on the centralized data to obtain low-dimensional representation and a linear basis matrix of the data, and performing calculation to obtain a linear reconstruction flow field; s3, Hermite orthogonal polynomial characteristics are generated; s4, solving a polynomial basis matrix through an elastic network by using the Hermite polynomial feature matrix obtained in the S3, so that the product of the polynomial basis matrix and the Hermite polynomial feature matrix can approximate a residual error; and S5, reconstructing the flow field by using the mean value of the centralized data, the linear reconstruction flow field and the polynomial basis matrix solved in the step S4. The method not only can reconstruct the flow field with high precision, but also can provide representativeness and interpretability of spatial-temporal characteristics of the flow field through sorting and analysis of the linear mode and the nonlinear mode.

The invention relates to the field of image processing, in particular to an automobile injection molded part chromatic aberration detection method and system based on image processing, and the method comprises the steps: firstly controlling an industrial camera to collect multiple frames of image sequences with different exposure times, and mapping a gray value into relative irradiance by using an inverse function of a camera photoelectric response function; then, linear validity is constructed based on photoelectric response characteristics of the sensor, so that optimal linear response region data is screened, and noise and saturation are suppressed; and meanwhile, a chromaticity consistency factor of the cross-exposure image sequence is calculated, and color cast caused by single-channel nonlinear response is eliminated. And finally, combined weighted fusion is carried out by combining the two factors to generate a high-fidelity radiance graph, and the high-fidelity radiance graph is converted to a CIELAB space to calculate chromatic aberration. According to the method, the purple edge effect of the highlight edge can be effectively eliminated, linear reconstruction of physical reflection energy is ensured, and the chromatic aberration detection precision of the highlight decorative plate with the complex curvature is remarkably improved.

The invention discloses an active power distribution network security domain description method considering inertia and voltage support, which comprises the following steps: firstly, establishing a branch load flow model of an active power distribution network, then establishing an energy storage system operation model considering virtual inertia support capability, secondly, establishing an operation model considering voltage-reactive V-Q droop control of the photovoltaic inverter, wherein the model comprises droop control constraint and photovoltaic capacity constraint; and finally, proposing an adaptive piecewise linear reconstruction algorithm, and efficiently and accurately describing a P-Q security domain of interaction between the active power distribution network and the main network, which meets the inertia requirement and the voltage reactive power control, by adaptively adjusting the sampling step length, and further constructing a P-Q-inertia three-dimensional security domain which meets the system inertia requirement and the voltage reactive power control constraint.

This application discloses an adaptive weighted constraint subspace block diagonal representation image clustering method and system. The method includes: acquiring image data to be clustered and establishing a data matrix; calculating class weighting constraints based on the data matrix and Pearson correlation weighting constraints based on the image data; establishing a diagonal representation model objective function based on the class weighting constraints and Pearson correlation weighting constraints, and optimizing the self-representation coefficient matrix of the diagonal representation model objective function; constructing an adjacency matrix based on the self-representation coefficient matrix, and establishing an undirected weighted graph based on the adjacency matrix and image data; and performing spectral clustering processing on the undirected weighted graph to obtain cluster labels. This application integrates the block diagonal regularization of the self-representation coefficient matrix obtained from the linear reconstruction process with the class weighting constraints and Pearson correlation weighting constraints describing data relationships, thereby further improving the block diagonal structure of the self-representation coefficient matrix, enhancing robustness to outliers, and improving clustering performance.

This invention discloses a multi-feature fusion fault diagnosis method for vibration signals of a vehicle axle assembly, belonging to the field of mechanical fault diagnosis technology. The method includes acquiring and preprocessing the raw vibration signals of the vehicle axle assembly. Time-domain, frequency-domain, and time-frequency-domain features are extracted from the preprocessed signals to form a primary feature set. A subset of sensitive features is selected through redundancy analysis and importance ranking. A kernel function is used to map the sensitive features to a high-dimensional space and perform linear reconstruction oriented towards fault categories, resulting in a more discriminative fusion feature vector. This fusion feature is input into a pre-trained probabilistic classification model to calculate the posterior probability of belonging to each fault mode. The fault mode is determined based on the probability, and a diagnostic result is generated. This invention enhances the discriminative ability of fault features through kernel space feature reconstruction and provides a reliability assessment of the diagnostic results using probability output, thereby improving the accuracy of fault diagnosis and the level of decision support.

The invention provides a random simple complex network containment synchronization analysis method based on spectral moments, and relates to the technical field of control and information. The method comprises the following steps: firstly, deriving an analytical expression of first three-order expected spectral moments of an augmented Laplacian matrix, and representing the analytical expression as a function of high-order network local structure properties, so as to establish a quantitative corresponding relation between the expected spectral moments and the network local structure; and then, based on the obtained expected spectral moment set, proposing a piecewise linear reconstruction strategy, performing triangular approximation on feature root distribution of the augmented Laplacian matrix, further estimating a minimum feature root and a maximum feature root, and accordingly realizing pinning synchronization judgment and performance prediction of the random simple complex network. Finally, numerical simulation is carried out by taking a random simple complex network formed by a Lorenz system as an example, and the accuracy and effectiveness of the method are verified.