790 results about "Radiation field" patented technology

The invention, which relates to the technical field of image processing, discloses a city component automatic three-dimensional reconstruction method based on a sub-meter high-resolution remote sensing image, comprising the following steps: acquiring a sub-meter high-resolution remote sensing image of a target area, and establishing an initial ground-image projection mapping relation based on a rational polynomial coefficient model; acquiring a ground control point, correcting the mapping relation, and outputting a registration image; performing multi-view geometric matching on the registered image to generate dense earth surface point cloud, and inputting the dense earth surface point cloud into a semantic neural radiation field network to generate dense point cloud; performing cross-modal feature alignment and fusion on the dense point cloud and the vector data, and outputting a fused multi-source dense point cloud; according to the method, through fine correction of the multi-source remote sensing image, the problems of large registration error, more point cloud sparse noise and semantic deficiency are solved, and high-precision and automatic three-dimensional reconstruction of urban components is realized.

The invention relates to the technical field of unmanned aerial vehicle control, provides a visual environment generation method, system and device based on a neural radiation field and a storage medium, and solves the problem of poor visual environment generation effect. The method comprises the steps that semantic segmentation is carried out on a corrected image, image data with semantic tags are generated, and the semantic tags are used for marking categories of objects in an outdoor scene; updating the neural radiation field model based on the image data with the semantic tag, mapping the semantic tag to a voxel feature space corresponding to the neural radiation field model, and constructing a semantic point cloud; identifying a non-key area in the multi-view image, performing redundant voxel cutting on the non-key area, and generating a cut semantic point cloud; and utilizing the clipped semantic point cloud to drive a neural radiation field model, and generating any visual angle scene of the outdoor scene. According to the technical scheme, lightweight semantic modeling and efficient free viewpoint rendering of the outdoor visual environment are achieved, and the new visual angle generation efficiency and quality of the complex environment are improved.

The invention discloses a bronze ware ornamentation and pattern digital restoration method based on an image enhancement technology, and relates to the technical field of image restoration, and the method comprises the steps: building a space mapping matrix; extracting multi-modal data features by using the surface state of the topological insulator, and registering a joint data volume; forming a super-resolution image through super-resolution reconstruction; obtaining a material degradation coefficient by using a wavelet finite element method and a graph neural network; generating an adversarial network by utilizing physical constraints, and generating an embarrassment repairing result; a material sensing three-dimensional model is constructed by adopting a wavelet packet decomposition and neural radiation field fusion technology, texture mapping is dynamically adjusted based on a graphene Moire effect, and virtual-real fusion is performed through holographic waveguide AR; by combining advanced technologies such as a metamaterial lens, micro-distance laser scanning, a topological insulator film, a graphene heterojunction and a nerve radiation field, high-precision three-dimensional digital restoration and repair of bronze cultural relics are realized, and immersive augmented reality display experience is provided.

The invention relates to the technical field of safety monitoring of constructional engineering, in particular to an intelligent construction safety monitoring system and method based on multi-modal data fusion, and the system comprises a plurality of modules: a 5GMEC-based heterogeneous data space-time alignment module which completes coordinate system conversion between laser point cloud and a BIM model by using an improved Fast-ICP algorithm; the feature level fusion network comprises a geometric feature branch (improved unscented Kalman filter processing point cloud normal vector) and a time sequence feature branch (LSTM processing stress sensor data); the NeRFXL fusion engine is used for fusing the point cloud and the video data by adopting a multi-scale neural radiation field; the multi-task anomaly detector is used for constructing a hierarchical Transform architecture and introducing a modal gating mechanism; and the dynamic knowledge graph engine constructs a knowledge graph updating module based on a graph neural network, and all the modules are in communication connection with one another and work cooperatively, so that functions of data processing, fusion, anomaly detection, knowledge updating and the like are realized.

The invention provides a single-view image three-dimensional modeling method and system based on comparative learning, and the method comprises the steps: starting from a single input image, generating a multi-view candidate image through a pre-training two-dimensional diffusion model in combination with score distillation sampling; performing positive and negative sample division on the candidate image pairs based on texture fidelity and structure coherence; constructing a perceptual contrast learning mechanism, calculating perceptual loss between the images, and optimizing texture consistency in a three-dimensional content generation process; proposing a number-aware triple loss function, and dynamically adjusting the contribution ratio of positive and negative samples in training; then, a super-resolution reconstruction module is embedded to perform detail enhancement on the image, and the quality of a contrast gradient signal is improved; and finally, performing joint training on the perception comparison loss and a neural radiation field or volume rendering module to generate a high-quality three-dimensional grid or volume rendering result. The problems that in an existing diffusion generation method, multi-view textures are inconsistent, structure reconstruction is not coherent, and the semantic distinguishing capacity is insufficient are effectively solved.

The invention relates to the technical field of computer vision and three-dimensional space modeling, and discloses a real-time multi-instance segmentation method and device based on a Gaussian splash radiation field model. The method comprises the following steps: based on a two-dimensional Gaussian splash radiation field model, rendering a visual angle with continuous spatial change to obtain an image sequence, and obtaining a multi-visual-angle consistent two-dimensional instance segmentation mask of the image sequence; and assigning an instance tag to each Gaussian primitive based on the two-dimensional instance segmentation mask. And for a two-dimensional Gaussian splash radiation field model with an instance label, acquiring a coarse instance segmentation mask and a color image at any view angle by using a Gaussian splash algorithm, inputting the mask and the image into a lightweight post-processing network for edge detection and region connectivity repair, and outputting a target two-dimensional instance segmentation mask with a complete structure and a label consistent with a three-dimensional scene. The method does not depend on any training or distillation process, directly acts on a Gaussian splash radiation field model, and has the advantages of high reasoning speed, high semantic consistency, support of multi-target continuous tracking and the like.

The invention provides a virtual reality interaction and content generation method and system based on a large model. According to the method, original point cloud data are collected to be aligned with semantic tags, and a topological graph containing object positions, categories and spatial constraints is constructed; dynamically calibrating the point cloud and mapping the point cloud to a unified coordinate system, and extracting a shielding boundary to generate a parallax mapping table; recognizing a blank area delimited by a user through a gesture, and generating a new object parameter candidate set of physical compliance in combination with the topological graph; screening parameters by using a large model, and reserving physical effective parameters after collision response, gravity and illumination verification; and generating the geometry and texture of the virtual object in the occlusion area based on the incremental neural radiation field, optimizing the depth and the rendering precision in combination with the mapping table, outputting the depth and the rendering precision to an interactive interface, and updating topological parameters. According to the method and the device, a new object which is physically consistent and rendered and optimized is dynamically generated based on user interaction in a virtual reality scene, and the sense of reality and interaction experience are improved.

The invention provides a radiation field high-precision reconstruction method based on dynamic geometry aggregation, and relates to the technical field of radiation field reconstruction and computational physics crossing. The method comprises the following steps: extracting a corresponding attenuation coefficient as a priori value; generating a Gaussian radiation element at the position of the monitoring point; calculating the radiation intensity of any point in the space; suppressing mutation of attenuation coefficients of adjacent primitives; gathering to a high dose zone or dispersing to a low dose zone; and generating three-dimensional radiation dose rate distribution by adopting a differentiable split rendering pipeline, and calculating the radiation intensity of any query point in real time by outputting a parameterized Gaussian primitive set. Through the dynamic Gaussian primitive aggregation-physical constraint optimization dual-drive reconstruction framework, the radiation field distribution can still be accurately restored under the sparse detector condition, the error is greatly reduced compared with the traditional method, and the calculation efficiency is obviously improved.

The invention discloses a flexible surgical instrument-oriented multi-source sensing data adaptive fusion method and a related device. The method comprises the following steps: acquiring optical, mechanical and pose multi-mode sensing data based on a timestamp synchronization technology in a working environment; clock compensation and space coordinate transformation based on an instrument kinematics model are carried out on the multi-modal data, and space-time registration is completed; inputting the registered data into a neural radiation field model to generate continuous space implicit scene representation; inputting the implicit representation into a pre-trained RWKV fusion network to obtain a fusion feature; and superposing the fusion feature and the original low-frequency component through residual connection, and integrating to generate three-dimensional voxelization environment state data. According to the method, multi-source information high-fidelity fusion is achieved through a single path, data redundancy is remarkably reduced, and the real-time performance and precision of intra-operative environment perception are improved.

The invention relates to the technical field of visual perception, and discloses a mechanical arm visual grabbing method and system. Comprising the following steps: collecting depth images of a target scene at different visual angles in real time, and generating initial point cloud data by using all the depth images; processing the initial point cloud data by using a double-flow neural radiation field to generate a geometric field and a capture field; a preset dynamic updating mechanism is adopted, combined dynamic optimization is conducted on the geometric field and the grabbing field, and optimal grabbing parameters corresponding to all moments in the process that the mechanical arm executes the current grabbing task are obtained; and the mechanical arm is controlled to execute the grabbing action based on the optimal grabbing parameters corresponding to all the moments. According to the method, high-precision three-dimensional scene representation is constructed through depth fusion of multi-view depth images, so that the integrity and robustness of geometric reconstruction of an object in a complex environment can be remarkably improved; based on joint modeling of a double-flow nerve radiation field, collaborative optimization of a three-dimensional structure and grabbing parameters of an object is achieved, and stability and adaptability of grabbing performance in a dynamic environment can be effectively improved.

The invention discloses a power distribution station multi-point environment control system and method, and relates to the technical field of power system automation, and the method comprises the following steps: building a time-frequency phase-locked observation baseline based on the scattering relation between an infrared band and water vapor under the condition of sudden humidity increase, inverting aerosol particle size distribution and concentration distribution, and generating a multi-dimensional scattering phase residual field; according to the multi-dimensional scattering phase residual field, a real radiation field is reconstructed by adopting multi-path reverse ray variation solution and combining polarization dual-angle scanning, and a reflection saturation risk spectrum is generated. According to the method, a real radiation field is reconstructed through multi-dimensional observation and inversion, a consistency graph is generated by fusing multi-source data, a misjudgment boundary is accurately identified, a control margin and a switching condition are constructed based on residual playback and time correction, and a steady-state closed-loop control chain is formed in combination with a dynamic regulation and control mechanism. The self-adaptive precise regulation and control of the power distribution station environment and the stability guarantee of the thermal field are realized.

The invention provides a pulse passing rate improving method based on accumulation signal demodulation, and belongs to the technical field of nuclear electronics digital pulse processing. Comprising the following steps: performing baseline deduction and monopulse screening on a radiation field pulse signal; constructing a nuclear pulse signal model, fitting to obtain model parameters, and constructing a system response matrix; modeling a nuclear detection physical process into a mathematical model; solving a constraint optimization problem by using a non-negative least square method; and demodulating and calculating all the pulse signals including the stacked pulses which are discarded by stacking, so as to obtain delta pulses containing energy information. According to the invention, the accumulation signal which is abandoned by a traditional accumulation abandoning algorithm is demodulated, so that the technical problem of increasing the pulse passing rate is solved, and meanwhile, heavy peaks and high-energy trailing in an energy spectrum are inhibited. Compared with an existing accumulation discarding method, the pulse passing rate effect is remarkably improved on the premise that the energy spectrum accuracy is guaranteed.

The invention discloses a software development management method based on big data, and relates to the technical field of software development management, and the method comprises the steps: collecting multi-source development data, transmitting the multi-source development data to a data lake in real time through a distributed message queue, and generating a structured data stream with a timestamp and a time sequence relation graph; performing Monte Carlo sampling on the three-dimensional radiation field model of the neural radiation field and the causal influence graph, simulating the cascade influence submitted by the current code, and outputting a risk value and a dependency chain; loading a neural radiation field three-dimensional code space model, a node risk value and a dependency chain, dynamically rendering a causal influence path, and generating a visual risk report; and generating a code optimization task according to the visual risk report, submitting an optimized code version to a code library, and calibrating parameters of the neural radiation field three-dimensional code space model. According to the method, the spatio-temporal characteristics of code change are analyzed, Monte Carlo simulation is combined, hidden dependence and a risk conduction chain are identified, and the comprehensiveness and predictive ability of framework corruption analysis are improved.

The invention discloses a neural radiation field rendering method based on dynamic hash coding, and the method comprises the steps: employing the feature sequence data as the input, calculating the density value and color value of each sampling point through the forward propagation of a neural network, carrying out the volume rendering integral operation according to the ray tracing principle in the direction of a ray, and obtaining the feature sequence data; judging a final color output result of the current pixel point; according to an error value between the color output result and a real image, updating a network parameter weight through a back propagation algorithm, and if the error value is greater than a convergence threshold, continuing to iterate the training process to adjust a feature coding strategy to obtain an optimized neural radiation field model parameter; and after the rendering performance configuration parameters are obtained, optimizing a storage allocation strategy of feature data through a memory pool management mechanism, and if the current memory occupancy rate exceeds a safety threshold, starting a data compression algorithm to reduce the storage space requirement, and obtaining a real-time rendering output result. According to the invention, high-quality real-time rendering of the dynamic scene is realized.

The invention discloses a three-dimensional reconstruction method and system based on deep learning, and belongs to the technical field of computer vision and deep learning. An existing neural implicit method is poor in reconstruction result in a weak texture area and a non-Lambert surface. Traditional geometric supervision depends on noise data, resulting in incomplete surface; in order to solve the problems of low global and local feature fusion efficiency in the optimization process and the like, the multi-view image of a target object is obtained by using a camera; obtaining camera parameters and sparse point clouds corresponding to the multi-view image by using an SfM model; building a three-dimensional reconstruction model based on the neural radiation field, and obtaining a reconstruction result; and evaluating a reconstruction result, and comprehensively evaluating the reconstruction result through the performance indexes. According to the invention, the problems of fuzzy reconstruction and poor precision of the target object in the weak texture area are solved; the problem of data annotation is solved, data acquisition is simple, and extra effective supervision does not need to be introduced; the cultural relic heritage with the weak texture area can be converted into a digital model permanently stored in a computer.

The invention discloses a 3DGS-based integrated visual angle synthesis and sparse visual angle CT reconstruction method, which comprises the following steps: establishing an internal and external parameter matrix through X-ray scanning parameters, constructing an initial voxel space and an initialized 3DGS radiation field by combining sparse visual angle projection data and based on an ACUI strategy, modeling anisotropic radiation intensity by utilizing a radiation intensity response function, and reconstructing a 3D visual angle CT model. And generating a virtual projection by adopting volume consistency rendering. And the optimized radiation field is converted into a voxel grid, density contribution is applied to carry out voxel space reconstruction, a reconstructed voxel space is obtained, and a new 3DGS radiation field is generated. And re-rendering the virtual visual angle projection based on the new 3DGS radiation field, performing iterative optimization by using a loss function, and outputting a new visual angle synthetic image and a CT reconstruction body until a preset number of iterations is reached. And an efficient process of one-time training and dual output is realized. The efficiency and precision of X-ray imaging are improved, the radiation dose of a patient is reduced, and meanwhile, a higher-quality imaging solution is provided for medical diagnosis.

The invention provides a forging forming method and system for an aluminum alloy pipe target based on image processing, and relates to the technical field of image processing.The method comprises the steps that a three-dimensional digital grid model and a topological relation graph are established; a dual-spectrum camera array is adopted to obtain multi-view images and fuse the multi-view images; reconstructing a temperature radiation intensity mapping image through the neural radiation field network; executing image enhancement processing; extracting contour feature data by using a multi-scale texture decoupling network, and separating reflection, oxidation and forging components; a deformation trend is predicted based on the topological relation graph and the contour feature data, and a forging parameter adjusting instruction is generated; and the forging equipment is controlled according to the instruction and optimized in real time until the forming quality reaches the standard. According to the method, accurate monitoring and intelligent control of the aluminum alloy pipe target forging process are achieved.

The invention discloses a dynamic semantic SLAM (Simultaneous Localization and Mapping)-driven robot full life cycle navigation method, which comprises the following steps: synchronously acquiring multi-modal data through a multi-modal sensor array, and carrying out joint coding based on a cross-modal contrast learning framework to obtain embedded features. A dynamic three-dimensional Gaussian radiation field is constructed, a scene is represented as a parameterized Gaussian kernel set, and mixed Gaussian field representation is obtained through micro rendering and joint training optimization. A Gaussian mixture field is divided into a global static layer and a local dynamic layer, retention constraints are applied to the static layer, and an incremental online updating strategy is adopted for the dynamic layer. Based on the optimized Gaussian field parameters and the multi-modal data, a factor graph containing Gaussian rendering residual factors and inertia pre-integration factors is constructed and solved, the corrected robot pose is obtained, and the space occupancy probability is generated. Operation control parameters are adjusted on line according to the pose and the occupancy probability through a strategy network, and autonomous navigation is achieved in combination with path planning and trajectory tracking.

The invention discloses a deep foundation pit crack feature coding detection method based on image recognition, and aims to solve the problems that a two-dimensional image is difficult to accurately characterize a three-dimensional crack, and the opening width and the slab staggering height are inaccurately estimated, the deep foundation pit crack feature coding detection method comprises the following steps of: calibrating and collecting through short time sequence and multi-polarization imaging, segmenting the crack to extract a center line, and dividing a left side domain and a right side domain; carrying out local reconstruction in a mask neighborhood by adopting a nerve radiation field or three-dimensional Gaussian sputtering, establishing a left implicit surface and a right implicit surface, fusing a polarization solution line, applying occupancy priori and seam-crossing repulsive potential in a gap region, combining a reference object to obtain an absolute scale, measuring a millimeter-level opening and a dislocation along a central line section, and generating a feature code; and threshold value and time sequence comparison judgment is carried out, and the technical effects of high-precision three-dimensional measurement, reliable risk assessment and traceable management of the deep foundation pit crack are achieved.

The invention discloses a cable accessory nondestructive testing method based on image recognition, and relates to the technical field of data encryption, and the method comprises the steps: extracting a photon signal from an anti-noise coding control template, generating an anti-interference partial discharge light spot image in combination with a compressed sensing reconstruction algorithm, and carrying out the alignment fusion of the anti-interference partial discharge light spot image and LiDAR point cloud data of a cable accessory, generating spatial registration feature data; based on the neural radiation field network, constructing a three-dimensional radiation field model, inputting spatial registration feature data, generating time-space domain deformation field data and partial discharge hot spot distribution data, and generating a defect candidate region by using a spatial weighted fusion algorithm; a deep residual network is used as a framework, a transfer learning strategy is combined, a cable accessory defect model is constructed, a defect candidate area is input, and a cable accessory health state report is generated. According to the method, the three-dimensional radiation field model is constructed by using the neural radiation field network as a framework, accurate positioning and characterization of defects are realized, the detection reliability is improved, and the method is suitable for micro-defect identification.

The invention discloses a geometric spectrum coupling-based neural radiation field high-fidelity representation method and system. The method comprises the following steps of: obtaining sparse multi-view image data and calculating internal and external parameters of a corresponding camera; generating light based on internal and external parameters of the camera, and performing point sampling on the space along the direction of the light to obtain sampling points; constructing a differentiable coding layer, predicting the density of sampling points through forward propagation of a neural network, and obtaining a principal curvature, a density gradient and an included angle between a normal vector of the sampling points and an observation direction based on a density prediction result; constructing a spectrum-geometric coupling function, and calculating to obtain a spectrum coupling coding vector; the spectrum coupling coding vector is used as an input to be transmitted into a NeRF main network, and NeRF volume rendering is carried out according to a density and color prediction result; and performing difference optimization training on the rendering result and the real image to obtain a high-fidelity composite image. According to the invention, the expression ability of the neural radiation field model in the high-frequency detail area can be enhanced.

The invention discloses a radiation safety management method and system based on cloud platform data driving, and relates to the technical field of cloud platform radiation management. The method comprises the following steps: collecting radiation field data and environment state data of a target area through a deployed intelligent sensing node; uploading the radiation field data, the environment state data and the context data from the service module to a cloud platform, performing energy compensation and radiation unmixing, and constructing a multi-dimensional feature vector; and processing the multi-dimensional feature vector by using a pre-trained situational radiation perception model, identifying radiation field features and an environment situation, and generating a situational radiation safety early warning signal. The technical problem that in the prior art, radiation safety monitoring depends on single-point measurement, comprehensive judgment cannot be carried out in combination with environment and service context data, and consequently the radiation field anomaly recognition capability is insufficient is solved, and the purpose that the radiation field anomaly recognition capability is improved through cloud platform data driving and context awareness model fusion is achieved. And the technical effects of high-precision identification and situational safety early warning of the radiation field state are realized.

The invention discloses a hybrid neutron gamma detector array and a signal processing method, and relates to the technical field of nuclear physical detection.During detection, eight EJ200 scintillators arranged in an array are used for energy deposition of gamma rays and fast neutrons and generating photons, and meanwhile three EJ426 thermal neutron scintillation screens are used for capturing thermal neutrons and generating photons; the response of gamma rays, fast neutrons and thermal neutrons is realized at the same time, and the detection precision is greatly improved. Meanwhile, if the three EJ426 thermal neutron scintillation screens are alternately stacked front and back, the total reflection of the EJ200 scintillators and the semi-light-proof performance of the EJ426 thermal neutron scintillation screens are utilized to block photon propagation in the X direction and only enable photons to be propagated in the Y direction and the Z direction, and each EJ200 scintillator corresponds to a four-channel photon collection structure to perform high-efficiency collection of the photons, so that the high-efficiency collection of the photons is realized. Therefore, high-precision detection and high-efficiency photon collection are realized, and support is provided for subsequent intense radiation field monitoring or high-precision positioning.

The invention discloses a GPU accelerated multi-particle coupling Monte Carlo calculation method and device. The method comprises the following steps: asynchronously migrating geometric material parameters subjected to CPU serial processing and a basic database to a pre-allocated memory space in a GPU; operation parameters of the GPU are determined, and Monte Carlo simulation of the multi-particle coupling transportation process is realized in the GPU based on the operation parameters and the neutron nuclear reaction database; on the basis of an atom addition function of a CUDA parallel computing architecture, energy transfer data, obtained through Monte Carlo simulation, of particles and voxel grids in a multi-thread environment is efficiently summarized, energy deposition of the particles is determined, and a high-resolution three-dimensional energy deposition spatial distribution data set is generated. According to the method, high precision can be maintained, and meanwhile, the parallel computing capability of the GPU is fully utilized to realize multi-particle coupling transportation synchronous simulation, so that the computing efficiency of a complex radiation field is improved, and the dual requirements of different fields on high precision and real-time performance are met.

The invention discloses a three-dimensional radiation field construction method and system, and the method comprises the steps: firstly obtaining an actual three-dimensional coordinate parameter set and an actual radiation dose rate parameter set of a to-be-measured scene, constructing a standard covariance matrix according to the parameters, selecting a to-be-predicted point, generating an actual covariance vector for the to-be-predicted point, and carrying out the calculation of the actual covariance vector. Generating predicted radiation dose rate parameters based on the standard covariance matrix and the actual covariance vector, and collecting the predicted radiation dose rate parameters of the plurality of points to be predicted into a predicted radiation dose rate parameter set, and finally, generating a three-dimensional radiation field according to the actual three-dimensional coordinate parameter set, the actual radiation dose rate parameter set and the predicted radiation dose rate parameter set. According to the method, the correlation between the trajectory points is represented through the covariance, and the conversion relation between the to-be-predicted point and each trajectory point is established through the conversion relation between the actual covariance vector and the standard covariance matrix, so that the radiation dose rate of the predicted point is calculated, the radiation dose rate of more point positions is obtained, and the precision of the three-dimensional radiation field is improved.

The invention discloses a digital twin three-dimensional city modeling and analysis method based on deep learning, and the method comprises the following steps: S1, collecting multi-view image data, extracting camera parameters, and building a three-dimensional city coordinate system; s2, constructing a volume modeling network based on a NeRF method, and generating a three-dimensional radiation field; s3, extracting semantic features of an intermediate layer, and constructing a spatial feature field; s4, dividing a local area and forming a local feature block; s5, inputting the local feature block into a quaternary capsule coding network, and generating a quaternary capsule unit containing existence, attitude, state and attribute vectors; s6, constructing a dynamic routing mechanism, and generating a structure capsule unit; s7, constructing a structure capsule atlas and binding city operation state data; s8, performing image rendering in combination with the atlas and the radiation field to generate a three-dimensional city model; and S9, performing state recognition, flow clustering and energy consumption classification analysis on the model. According to the invention, an integrated process of city modeling and state analysis is realized.

The invention belongs to the field of virtual image display, particularly relates to a spherical reflection cavity virtual calibration method based on a neural radiation field, and aims to solve the problems that micron-level deviation is difficult to accurately capture due to interference of a high-reflection surface, and an executable correction instruction cannot be generated by fusing process constraints. The method comprises the following steps: deploying image acquisition equipment around a cavity to synchronously capture a multi-view optical image sequence; inputting a neural radiation field model, reconstructing a three-dimensional geometric structure and optical properties through a volume rendering technology, and dynamically optimizing and fitting reflection characteristics and curvature changes of a carbon fiber material; extracting spherical radius, local curvature and boundary contour parameters, and comparing the parameters with design specifications point by point to generate a deviation distribution diagram; generating a multi-level calibration instruction set based on the deviation distribution diagram in combination with the laying layer tolerance and the assembly clearance; and outputting an instruction to the manufacturing system to execute physical adjustment, and re-collecting the image to verify the calibration effect until the acceptance index is met. According to the invention, the deviation capturing precision is improved, and a correction instruction can be generated.

The invention discloses a temperature control method for low-temperature high-NOx-concentration flue gas denitration in the nuclear industry, and relates to the technical field of flue gas denitration control. According to the method, flue gas temperature time sequence distribution, NOx concentration gradient and environment radiation intensity data are integrated through a space-time alignment algorithm, a synchronous data matrix representing a system coupling state is generated, then a temperature and efficiency response curved surface is established, a high-efficiency temperature area and an inactivation risk area are dynamically divided through fuzzy logic control, and an optimal temperature regulation and control threshold value is recognized. The drift effect of quantitative radiation on the surface temperature of the catalyst is analyzed through regression, a quantitative relation model of radiation dose and temperature zone deviation is established, and real-time correction of anti-radiation compensation parameters is achieved. And finally, optimizing the multi-objective cost function by adopting a non-dominated sorting genetic algorithm, and obtaining dynamic balance between the maximum NOx conversion rate and the minimum temperature fluctuation. And multi-parameter coupling control of a temperature field and a radiation field is realized, and the denitration efficiency stability under a low-temperature condition is remarkably improved.

The invention relates to the technical field of array antennas, in particular to a sparse linear array beam forming method and system with unit rotation and mutual coupling considered. Array elements are obtained, Euler angle derivation is carried out on rotation of the array elements around the z axis, and a radiation electric field after rotation is obtained; setting a beam forming target according to the electric field of the radiation field; according to a beam forming target, optimizing the position, the rotation angle and the excitation phase of an array element by adopting a random optimization algorithm, and generating an initial beam scheme; an active directional diagram is extracted from the initial beam scheme according to full-wave simulation, the active directional diagram is combined with a CAL-SAPSO algorithm to optimize the array element position, the rotation angle and the excitation phase, and a final array element directional diagram is generated; according to the invention, by introducing array element rotation and considering a mutual coupling effect, efficient beamforming of the sparse wiring array is realized, the radiation characteristic of the antenna array can be adjusted more finely, the peak side lobe level and the cross polarization level are effectively reduced, and the overall performance of the system is improved.

The invention provides a two-stage human body posture estimation model lightweight method and system based on pseudo-view data generation and a storage medium. The method comprises the following steps: step 1, in a first stage, performing cross-model knowledge migration based on a multi-scale feature map and a regression logic value; step 2, a data enhancement strategy generated based on a middle visual angle: utilizing existing multi-visual-angle image data, through implicit three-dimensional representation of a neural radiation field learning scene, synthesizing a pseudo-visual-angle image between existing camera visual angles and a corresponding attitude pseudo label, mixing the generated pseudo-visual-angle data with a real data set, and obtaining a data enhancement strategy; commonly used for training a student model; and step 3, a second stage, self-distillation refining and anatomical optimization. The method has the beneficial effects that the knowledge of the teacher model is more finely transmitted to the student model through a structured knowledge migration process, and effective light weight of the model is realized on the premise of ensuring the accuracy and robustness of attitude estimation, so that the model meets the requirements of actual application on efficiency and deployment.