5284 results about "Anisotropy" patented technology

The invention relates to the technical field of fan blade fatigue damage prediction. The invention provides a fan blade fatigue damage prediction method and system. The method comprises the following steps: constructing a coupling finite element model based on blade anisotropy parameters; blade surface three-dimensional strain field data, blade vibration acceleration signals, environment temperature and humidity and wind speed and direction data are obtained in real time, and a multi-dimensional monitoring data set is constructed; based on the multi-dimensional monitoring data set, nonlinear coupling features of all the load components are extracted, a multi-dimensional feature tensor is obtained, and a reference stress field matched with the current working condition is generated; inputting the multi-dimensional feature tensor and the reference stress field into a bidirectional long-short-term memory network, and establishing a data-physics combined driven damage evolution model; and positioning a damage area based on a damage probability distribution diagram output by the damage evolution model. The problems that in the prior art, prediction errors are obvious, sensitivity to early damage is insufficient, the false alarm rate is high, and accurate positioning of the damage position and quantitative prediction of the residual life are difficult to achieve are solved.

The invention relates to the technical field of image data processing, and discloses a few-sample scene-oriented industrial product surface defect image analysis method, which comprises the following steps of: obtaining surface gray level image data of a product to be analyzed, calculating a structure tensor matrix and generating an anisotropy degree graph; searching similar blocks in a preset search neighborhood, and constructing a local texture data matrix; performing singular value decomposition on the local texture data matrix to extract a main subspace; constructing a projection operator and utilizing the projection operator to carry out orthogonal projection reconstruction on the local image block to generate a reconstructed background image block; according to the method, through an orthogonal subspace projection mechanism, good product textures and defect signals are separated, random noise is removed, meanwhile, high-frequency structural features are completely reserved, and the method is high in robustness, high in robustness and high in robustness. And the defect detection precision of a complex texture surface in a few-sample scene is improved.

The invention relates to the technical field of path planning, and discloses a robot path planning method, which comprises the following steps that a hybrid cost map is constructed, and the hybrid cost map comprises a static obstacle field, a dynamic obstacle probability prediction field and a terrain energy consumption field; constructing an anisotropic heuristic function, and searching on the mixed cost map to obtain an initial path; parameterizing the initial path into a group of piecewise polynomial curves, constructing a joint optimization target which takes the total curvature, the piecewise polynomial curves and the space-time overlapping integral of a dynamic obstacle probability prediction field, and performing trajectory optimization under the condition of meeting the kinematics constraint of the robot to obtain a smooth space-time trajectory; when the task is executed, the information divergence is continuously calculated, and when the information divergence exceeds a preset threshold value, the current state of the robot serves as a new starting point, and the complete path planning process is executed again. According to the method, the future collision risk is prospectively avoided, the energy consumption of the robot is considered, and the comprehensive quality of the path is improved from the source.

The invention discloses a fatigue life simulation evaluation method for a lightweight aluminum alloy material of a new energy automobile, and relates to the technical field of material life evaluation. A microstructure image is collected, coupling features are extracted through machine learning, and heterogeneous data fusion and enhancement are completed; generating a topological optimization structure based on a GAN, introducing a VPSC model to describe anisotropy according to a stress gradient dynamic grid, and constructing a dynamic finite element model; fusing vehicle driving data, predicting a load by using LSTM, performing VMD decomposition and environment correction, and realizing space-time correlation load spectrum reconstruction; a phase field model is used in a microcosmic mode, cracks are tracked in a macroscopic mode through XFEM, damage parameters are transmitted in a bidirectional coupling mode, and multi-physics field coupling simulation is carried out; fusing simulation and test data by adopting Bayesian reasoning, calculating life probability distribution, and correcting parameters when errors exceed the limit; according to the method, the fatigue life prediction error is finally reduced, the time consumption of single simulation is reduced, full-life-cycle evaluation and visual early warning are realized, an efficient scheme is provided for lightweight design, and industrial technology upgrading is promoted.

The invention provides a rock mass structural plane intelligent identification method based on three-dimensional point clouds, and belongs to the technical field of rock mass structural plane intelligent identification, and the method comprises the steps: selecting a target collection point, constructing an initial point cloud set, calculating an initial normal vector, setting a spherical accumulator, and rotating the point clouds in unstructured point clouds formed by a rock mass structural plane; obtaining an accurate normal vector; according to an improved region growing algorithm, obtaining a better number of structural surfaces, and obtaining a single structural surface of a plurality of rock mass point clouds; and traversing a single structural surface of each rock mass point cloud, replacing a distance function with an angle error quadratic sum according to an improved K-means + + clustering method, determining an optimal clustering number, and completing the intelligent identification method for the rock mass structural surface. According to the method, the high precision of the normal vector at the edge junction of the structural plane is realized under the normal vector smoothing phenomenon, the high standard of K-means clustering iteration and the high accuracy of the optimal cluster number of selected clustering are realized, and the problems of density anisotropy and the marginalization effect of the point cloud structural plane are solved.

The invention discloses a complex terrain wind field numerical simulation method considering turbulence anisotropy, and the method comprises the steps: considering the turbulence anisotropy of an inflow boundary, and determining the condition type and parameters of the inflow boundary; acquiring ground roughness information of the complex terrain, and correcting a wall surface function; obtaining high-precision topographic data, determining a computational domain range, and generating a computational domain grid; on the basis of an inflow boundary turbulence retentivity principle and a leeward slope flow separation characteristic, a turbulence model closing coefficient is corrected; and the corrected linear pressure strain RSM model is adopted to simulate a complex terrain wind field value, and complex terrain wind field flow field information is obtained. According to the method, the inlet boundary and leeward slope turbulence anisotropy are considered, the wall function is corrected, meanwhile, the complex terrain modeling and grid generation mode is simplified, and the simulation precision is effectively improved.

The invention relates to a multi-modal sparse fusion three-dimensional target detection method in an unstructured environment, and the method is based on a complexity perception candidate region dynamic sampling strategy, and through the cross-domain self-compensation of point cloud geometric features and image spectral features, and the fusion of multi-view sparse features, the detection of a multi-modal sparse fusion three-dimensional target is realized. The perception capability and the recognition precision of the obstacle area, and the remote dynamic target detection performance and the real-time performance are improved; an anti-deformation convolution group and a terrain gradient perception attention module are introduced into a ParScaleNet image backbone network, so that the extraction of edge features of a complex scene is enhanced, and the cross-scale characterization capability of the features is improved; according to the method, a ContraSpaceOpt module with semantic maintenance capability is deployed behind a Transform, excessive smoothness of obstacle features is inhibited through class comparison loss functions and feature space anisotropy constraints, the space separability of obstacles is maintained, and the problems of point cloud fracture and texture misalignment caused by the obstacles are effectively solved.

The invention discloses a machine vision-based intelligent detection method for steel galvanized surface defects, which comprises the following steps: S1, acquiring and preprocessing a steel galvanized surface image to obtain a standardized image; s2, constructing a specular reflection probability graph according to the brightness distribution and the gradient magnitude, and calculating a reflection intensity value; s3, calculating a structure tensor matrix, determining a main direction angle and an anisotropic consistency coefficient, and generating a direction feature matrix; s4, establishing a multi-scale direction adaptive phase kernel function, and performing phase modulation in a frequency domain by adopting an improved phase stretching transformation algorithm; s5, inverse Fourier transform is executed, and a phase response matrix is extracted; s6, performing weighted fusion to obtain a comprehensive phase response diagram; and S7, setting a threshold value according to the noise variance and the statistical characteristics, executing binarization and morphological processing, and outputting a defect region and boundary coordinates. According to the invention, high-precision identification and boundary positioning of steel galvanized surface defects are realized.

The invention provides a medical image segmentation method based on adaptive anisotropic convolution, and the method comprises the steps: obtaining a three-dimensional medical CT data set comprising images and labels of a plurality of abdominal organs and kidney tumors, and carrying out the preprocessing of the data set; dividing a data set into a training set and a test set for model training and evaluation; designing a three-dimensional medical image segmentation network model based on an adaptive anisotropic convolutional layer, and inputting the preprocessed training set into the three-dimensional medical image segmentation network model, the three-dimensional medical image segmentation network model is trained through parallel multi-modal convolution, adaptive attention weight generation, weighted feature dynamic fusion and multi-stage deep supervision, and model parameters are optimized; and applying the optimized three-dimensional medical image segmentation network model to a test set, generating a three-dimensional segmentation result with clear boundary and complete reserved details, and providing support for clinical diagnosis and treatment planning.

The invention provides a real-time registration method from a preoperative model to an intraoperative point cloud based on deep learning, and relates to the field of 3D point cloud registration. The method comprises the following steps: acquiring a pre-reconstructed preoperative model; the invention discloses an in-vivo flexible rapid three-dimensional reconstruction method based on a digital elevation model, and the method comprises the steps: obtaining a real-time intra-operative point cloud; pre-operation vertex features representing anisotropic characteristics of the pre-operation model are extracted, the pre-operation vertex features and the corresponding intra-operation point cloud features are spliced and serve as input of a graph convolutional neural network, and the deformed pre-operation model is reasoned and output; and taking the detection feature point pairs with the corresponding relationship as supervision signals, constructing a loss function training graph convolutional neural network until convergence, and finally outputting a real-time registered grid three-dimensional model. Based on a deep learning network framework including feature extraction, feature point detection and deformation prediction, real-time registration from a non-rigid preoperative model to an intra-operative point cloud is realized, and requirements under a real minimally invasive laparoscopic surgery scene are met.

The invention provides a preparation method of an isotropic Ti2AlNb / TiAl-based interpenetrating composite material, and belongs to the technical field of intermetallic compound-based composite materials. The method comprises the following steps: firstly, designing a Ti2AlNb reinforcement framework of various TPMS configurations by utilizing implicit function modeling; then, carrying out anisotropy research on the TPMS configuration by utilizing finite element simulation; secondly, a Ti2AlNb reinforcement framework of a TPMS configuration is prepared through a selective laser melting (SLM) technology; and finally, the TPMS configuration Ti2AlNb / TiAl-based interpenetrating composite material is prepared through vacuum hot pressing sintering of HPS. Therefore, strong anisotropy of a traditional fiber reinforced composite material in mechanical property is avoided, good matching of strength, plasticity and toughness of the composite material is achieved, and a new thought and a new solution are provided for breaking through the application bottleneck of TiAl in spaceflight power system hot end components.

The invention discloses a two-dimensional magnetic material device and a preparation method and a regulation and control method thereof, and the regulation and control method comprises the steps: enabling ionic liquid to cover the surface of a two-dimensional magnetic material, enabling the ionic liquid to be in contact with a grid electrode, a source electrode, a drain electrode and the two-dimensional magnetic material, and continuously applying current from the grid electrode to the source electrode and to the drain electrode, and the regulation and control of the two-dimensional magnetic material device are completed. According to the two-dimensional magnetic material device and the preparation method and the regulation and control method thereof provided by the invention, the ionic liquid containing the cationic molecular chains with different lengths is selected to perform intercalation on the two-dimensional magnetic material device, so that regulation and control on the two-dimensional magnetic material device are realized, and the regulation and control flexibility of the two-dimensional magnetic material is greatly improved; and the coercive field, the magnetic anisotropy energy and the carrier concentration of the two-dimensional magnetic material can be changed.

The invention discloses a 3D printing path planning method based on electric arc additive anisotropy and a stress field, and the method comprises the steps: constructing a CAD three-dimensional model of a part, and obtaining the stress field of the part through finite element simulation; determining a slice plane; mapping the stress field to a slice plane to form a force flow line; according to the obtained force flow line, rotation transformation regeneration is carried out according to the anisotropy of the used electric arc additive, and a reference trajectory considering the anisotropy of the material is obtained; under the principle of alternate arc starting and extinguishing, the corresponding printing sequence in the layers and between the layers is further planned, and the reference trajectory lines are connected end to end to be planned into a continuous path; and generating a code file, and printing according to the printing sequence. The comprehensive mechanical property of a printed piece is improved.

The invention relates to the technical field of glacier information processing, in particular to a glacier surface moraine identification method based on multi-source remote sensing parameters, which comprises the following steps: performing radiation-atmosphere joint correction and geometric-reprojection on optical, thermal infrared, synthetic aperture radar and digital elevation data to generate physical consistency data; deducing the surface temperature under the driving of short-wave albedo, downward radiation and turbulent flux by using a cross-modal visual conversion network and a symmetric neural operator, and obtaining a thickness-existence degree posterior through a normalized flow; an uncertainty field is constructed according to information entropy and variance, a representative pixel unmanned aerial vehicle radar sampling and value measurement backflow fine tuning model is selected by means of quantum annealing, and then a spatial continuous thickness field is output through anisotropic diagram diffusion. According to the method, the future thickness is integrated according to mass conservation in combination with day-by-day weather forecast, and the future thickness is coupled with the existence degree index to form a burst risk grid, so that high-precision and iterable moraine dam early warning is realized.

The invention relates to the technical field of image processing, in particular to a craniocerebral disease area identification and detection method and system based on an MRI (Magnetic Resonance Imaging) image, and the method comprises the steps: obtaining a plurality of sub-images with different scales according to a gray level image of the craniocerebral MRI image; performing multi-scale analysis on the gradient value of any pixel point according to each sub-image to obtain a multi-scale gradient coefficient of any pixel point; obtaining a multi-scale local anomaly degree according to the gray values of the pixel points in different local ranges of any pixel point and the distribution in the gradient direction; optimizing the gradient value of any pixel point according to the multi-scale gradient coefficient and the multi-scale local anomaly degree to obtain a self-adaptive gradient value, and performing image enhancement on the grayscale image by using an anisotropic diffusion filtering algorithm according to the self-adaptive gradient value of each pixel point so as to identify a craniocerebral disease region. And the effect of performing image enhancement on the MRI image by using the anisotropic diffusion filtering algorithm is improved.

The invention relates to the technical field of slope monitoring, and discloses a slope partition anisotropy stability analysis method and device, and the method comprises the steps: obtaining the geological structure information of a slope; building a finite element model according to the geological structure information; carrying out partition anisotropy analysis on the slope rock-soil body based on a finite element model; constructing a partition anisotropy whole-process change analysis model under the dynamic load application; and carrying out coupling analysis processing on the whole-process change analysis model and the seepage field to obtain a slope stability analysis result. According to the method, the finite element analysis model is constructed for the slope, the whole-process change form of rock-soil body strength parameter partition anisotropy is analyzed in a graded load applying mode, the seepage field is coupled for slope stability analysis, and the mechanical behaviors of the slope under different working conditions can be simulated more accurately; and the difference response of rock-soil bodies in different areas in the slope under the stress effect is captured in time.

The invention discloses a communication encryption method based on a two-dimensional inorganic / inorganic Van der Waals heterojunction polarized photoelectric detector, and belongs to the technical field of photoelectric devices. The photoelectric detector comprises a substrate, two-dimensional MoSe2 material layers, two-dimensional ReS2 material layers and a thin film electrode, wherein the two two-dimensional material layers form a Van der Waals vertical heterojunction and are of an II-type heterostructure; due to anisotropic light absorption of ReS2, effective carrier collection and transport capabilities of MoSe2 and an inhibition effect of heterojunction on dark current, the photoelectric property of the two-dimensional ReS2 / MoSe2 photoelectric detector is obviously improved, and meanwhile, the two-dimensional ReS2 / MoSe2 photoelectric detector has high responsivity of 89.4 A / W, fast response speed of 30.5 s and polarization sensitive characteristics, and can be applied to the field of photoelectric detectors. On the basis, information is subjected to multiple encryption by means of a polarization state information encryption technology, so that the concealment and security of an information transmission process can be greatly improved, and a new possibility is provided for the development of a security communication technology in the future.

The invention relates to the technical field of control or regulation systems, and discloses a cooperative control method for a photovoltaic intelligent manufacturing equipment production line, and the method comprises the steps: a control unit collects the stock and change rate of materials in a physical cache region in real time; establishing and mapping the physical cache region into a virtual viscoelastic dynamic model with non-Newtonian fluid characteristics; calculating a virtual elastic restoring force enabling the stock to return to a balance point and a virtual viscous damping force preventing the stock state from changing based on the model; wherein an asymmetric anisotropic damping generation strategy is executed, and a damping coefficient is dynamically split according to a material flowing trend; and finally, superposing the virtual adjustment correction after vector synthesis to the basic transmission speed to generate a dynamic speed instruction, and by constructing a virtual dynamic field with rheological characteristics and an asymmetric damping mechanism, the problem of nonlinear cascade oscillation in discrete logistics transmission is solved, and differential self-adaptive suppression of accumulation and evacuation risks is realized.

The invention relates to the technical field of artificial intelligence and remote sensing image processing, and particularly provides a hyperspectral image and laser radar data classification method based on a dynamic fusion network. The method comprises the following steps: preprocessing acquired multi-modal data, and constructing multi-scale input; a dual-scale local attention module is designed, and context information of different scales is fused in a self-adaptive weighted mode through gating soft pooling; a dynamic down-sampling feature enhancement module is designed, the down-sampling rate is dynamically adjusted according to the complexity of the feature map, and deep multi-scale interaction is carried out based on a Mama backbone; constructing a directional interactive attention module, extracting features in horizontal, vertical and diagonal directions through directional gating convolution, and capturing an anisotropic structure of a linear ground feature; through the design of a double-path classifier, fusing shallow space details and deep semantic information; and the model is trained, optimized and reasoned to obtain data classification, and the method improves the classification precision and the calculation efficiency.

The invention discloses a morphological gradient region replacement method based on SAM semantic segmentation and user guidance, and relates to the technical field of computer vision and image processing, and the method comprises the steps: carrying out the semantic segmentation of a to-be-processed image through an SAM model, extracting a multi-level semantic feature, carrying out the standardization and dimension reduction, extracting a causal factor based on independent component analysis, and carrying out the user guidance. A directed causal factor association graph is generated through Granger causal relationship test, and a causal attribution probability graph is generated through reverse mapping; constructing a structured causal graph, and generating a causal mask through a graph convolutional network; encoding the original interaction signal into a guide thermodynamic diagram; constructing a diffusion equation, forming a gradual change control equation by dynamically fusing and guiding the intensity distribution of the thermodynamic diagram and an image semantic diffusion item, and iteratively solving the gradual change control equation; generating an anisotropic morphological operation kernel according to the geometric curvature characteristics of each region in the replacement mask; and fusing the optimized replacement mask with the target content based on a gradient domain optimization algorithm to generate a gradient replacement image.

The invention provides an electrolytic bath three-dimensional temperature field reconstruction method and system based on multi-physics field coupling, and belongs to the technical field of energy equipment thermal management, and the reconstruction method is applied to a reconstruction system comprising an acquisition module, a first processing module, a second processing module, a third processing module, a fourth processing module and a rendering module. The method specifically comprises the following steps: layering a three-dimensional model of the electrolytic cell according to a Z-axis direction, establishing a hierarchical database and setting a reference layer; generating initial temperature field distribution of the reference layer based on an anisotropic radial basis function interpolation algorithm; and establishing an electric-thermal-flow coupling equation, solving according to the hierarchical database, obtaining temperature field distribution of a reference layer, mapping the temperature field distribution to a three-dimensional space, correcting the temperature field distribution by combining interlayer temperature attenuation and a transverse thermal diffusion effect, obtaining target temperature field distribution, and carrying out visualization processing on the target temperature field distribution. Nonlinear temperature distribution of the electrolytic cell can be completely reproduced, and the accuracy of three-dimensional temperature field reconstruction of the electrolytic cell is guaranteed.

A display module includes a substrate including a mounting surface and a side surface; a Thin Film Transistor (TFT) layer provided on the mounting surface of the substrate; a plurality of inorganic light emitting diodes mounted on the mounting surface of the substrate; an anisotropic conductive layer provided on an upper surface of the TFT layer and electrically connecting the TFT layer to the plurality of inorganic light emitting diodes; a front cover covering the mounting surface; and a side cover surrounding the side surface. A side end of the front cover extends to a region outside the mounting surface, and the side cover is bonded to a lower surface of the front cover and to the side surface of the substrate which correspond to the region outside of the mounting surface.

The invention discloses a bottom heat flow and deep layer temperature inversion method based on an underground medium heat transfer model, and relates to the field of deep stratum temperature field prediction. The underground medium heat transfer model-based bottom heat flow and deep temperature inversion method mainly comprises the following steps of: constructing an electromagnetic data three-dimensional axial anisotropy inversion parameter target functional to carry out fine inversion on an electromagnetic data electrical structure of a target area to obtain an electrical structure model and an underground heat storage stratum structure model of the target area; a deep stratum heat transfer model is obtained in combination with regional geothermal geological information; and utilizing a Newton-Raphson optimization algorithm to perform inversion on the bottom prior heat flow value distribution boundary condition to obtain temperature field distribution of the deep stratum heat transfer model. According to the bottom heat flow and deep layer temperature inversion method based on the underground medium heat transfer model, the electrical characteristics of the underground medium can be converted into temperature field distribution based on a small number of borehole logging constraints, the prediction precision is high, and the prediction range is wide.

The invention provides a magnetic resonance image self-supervision super-resolution reconstruction method and system based on a prior guide diffusion model. The method comprises the steps of image preprocessing, pseudo-pairing data set construction, prior condition construction, model training, model testing and three-dimensional isotropic volume reconstruction. According to the method, the dependence on a real high-resolution image is remarkably reduced by constructing a self-supervised pseudo-pairing mechanism, and high-quality reconstruction from anisotropic MRI to an isotropic image is realized; meanwhile, by introducing multiple medical priori including high-frequency residual, edge structure and region-of-interest guidance, detail retention and structural boundary definition of the image are effectively improved, the convergence speed and robustness of the model are improved while anatomical fidelity is guaranteed, and the method is suitable for large-scale popularization and application. And a technically feasible and clinically applicable solution is provided for high-resolution reconstruction of medical images.

The invention provides a visual communication advertisement design system and method, and the method comprises the steps: carrying out the cross-modal feature alignment of a background voiceprint feature extracted from environment voiceprint data of an advertisement putting scene and a frequency domain feature of illumination intensity in illumination intensity data, and obtaining an environment perception state tensor; generating a dynamic illumination matrix by combining the spectral irradiance distribution in the environmental perception state tensor with the anisotropic highlight coefficient of each sub-region in the target advertisement picture; determining an audience space domain according to the space depth data of the advertisement putting scene and the audience motion trail, and performing space audio redirection on the target advertisement based on the audience space domain and the sound field energy distribution in the environment perception state tensor to obtain an acoustic beam width angle; and performing acousto-optic synchronous dynamic rendering on the advertisement content of the target advertisement according to the dynamic illumination matrix and the acoustic beam width angle. By adopting the scheme of the invention, acousto-optic collaborative rendering and acousto-optic parameter dynamic adaptation can be performed on the target advertisement so as to realize directional propagation to audiences.

The invention discloses a force-heat coupling simulation and structure optimization method and system for an ultra-complex structure, and the method comprises the steps: generating parameters and data structures required by subsequent simulation and optimization for a given model and a design domain; comprising the following steps: constructing a background coarse grid, constructing a seed point and a radius, modeling a porous structure based on a voronoi structure, and pre-calculating a stress field of the porous structure; calculating a density field, performing thermodynamic simulation on the generated porous structure based on the background coarse grid and the shape function according to the density field, querying a stress matrix corresponding to each seed point according to the obtained stress field, and performing characteristic decomposition and extraction on the stress matrix to obtain a weight matrix corresponding to the seed point; a topological optimization method is used, control parameters are updated through a GCMMA method according to the sensitivity, and therefore the porous structure is updated, material distribution is optimized, and optimization is conducted continuously till the change of the control parameters is smaller than a threshold value. According to the method, the topological optimization problem of the anisotropic porous structure under the multi-physical-field condition can be quickly and effectively solved.

The invention relates to the field of neodymium iron boron magnetic materials, in particular to a high intrinsic coercive force neodymium iron boron magnetic material and a preparation method thereof, and the high intrinsic coercive force neodymium iron boron magnetic material comprises the following raw materials in parts by weight: 52.5-57.2 parts of PrNd, 105-115.3 parts of Nd, 9.0-10.3 parts of B, 15-35 parts of Tb, 70-80 parts of Dy, 10-25 parts of Co and 650-680 parts of Fe. The two rare earth elements Tb and Dy are added into the neodymium-iron-boron magnetic material, so that the magnetocrystalline anisotropy field of the crystal is remarkably enhanced, and the intrinsic coercive force of the neodymium-iron-boron magnetic material is greatly improved.

The invention discloses a steel-wood combined beam-column joint damage identification method and system applying machine vision, and the method comprises the steps: S1, obtaining a visible light, near-infrared and thermal imaging multi-mode image sequence of a steel-wood combined beam-column joint, and carrying out the denoising processing through adaptive anisotropic diffusion filtering, and obtaining a denoised multi-mode image sequence; s2, performing Gaussian pyramid decomposition and Laplacian pyramid feature fusion on the de-noised multi-modal image sequence tensor to obtain a fusion feature map; s3, performing adaptive threshold segmentation and morphological processing on the fused feature map to obtain a final binary image; s4, training the deep learning network to obtain a trained deep learning network; and S5, performing damage identification by using the trained deep learning network. According to the method, the steel-wood combined beam column joint damage can be accurately identified, the segmentation probability graph is obtained, the segmentation result is marked, and the visualization of the damage area is realized.

A thermal processing method for improving high-speed impact resistance of a two-phase titanium alloy includes the steps of: a, heating a two-phase titanium alloy slab blank step by step; b, using a reversing rolling mode to first perform transverse rough rolling, and then reverse a plate blank for longitudinal rolling, and c, water-cooling the rolled plate, and then performing solution heat treatment and aging treatment. According to the method, the anisotropy of transverse and longitudinal properties of the finished plate can be reduced by using a method of two-stage rolling in a β-phase region and an a+β two-phase region, and in combination with rapid cooling after rolling and solid-solution and aging strengthening heat treatment, high strength and excellent high-speed impact resistance of the product can be ensured, and the protective performance of the material is greatly improved.

The invention discloses a liquid crystal compound, the structural formula of the liquid crystal compound is as shown in the following formula I, # imgabs0. The liquid crystal compound has large dielectric anisotropy delta epsilon, high elastic constant K, good low-temperature intersolubility, small rotary viscosity gamma 1 and large elastic constant K, the liquid crystal composition containing the liquid crystal composition has large dielectric anisotropy delta epsilon, high elastic constant K, good low-temperature intersolubility, small rotary viscosity gamma 1 and large elastic constant K, and can be used for developing liquid crystal display elements or liquid crystal displays which have high response speed and can effectively improve residual images.