44results about How to "High geometric accuracy" patented technology

The invention belongs to the technical field of machining, and particularly relates to a high-precision universal grinding wheel trimming mechanism, a fillet trimming method thereof and a base. The arc-shaped guide rail is fixedly installed on the base and provided with an arc-shaped guide groove, and an arc-shaped conical rack is fixed in the arc-shaped guide groove; the rotary sliding block is slidably mounted on the arc-shaped guide rail, and a position adjusting rod device and a cutter device are mounted on the rotary sliding block; all planes of a grinding wheel can be finished accurately, rapidly and safely, meanwhile, arc surfaces needed for machining of inner and outer circle grinding wheels can be finished, the arc surfaces of machined parts have high geometric precision and surface roughness, the size precision can reach 0.02 mm, the mechanism further has the function of adjusting the radius of the finished arc, and the machining efficiency is improved. Finishing of different arc radiuses can be met, and the machining precision and the machining range of common equipment are greatly improved.

The invention provides a bauxite resource prediction analysis method and system, and relates to the technical field of resource prediction. Performing distortion correction on the earth surface remote sensing image according to the digital elevation data of the target bauxite to obtain an earth surface remote sensing correction image, performing image masking on the earth surface remote sensing correction image to obtain an earth surface remote sensing mask image, and extracting earth surface resource distribution characteristics from the earth surface remote sensing mask image; obtaining geological exploration data of the target bauxite, generating an ore body three-dimensional distribution model through the surface resource distribution characteristics and the geological exploration data, obtaining a bauxite database, and constructing a metallogenic knowledge graph of the bauxite according to the bauxite database; the ore body grade is predicted according to the ore body three-dimensional distribution model and the mineralization knowledge graph of the bauxite, and ore body grade prediction information is obtained, the quality of remote sensing images can be improved, the complementarity of data is enhanced, and the reliability of bauxite resource prediction is improved.

The invention relates to the technical field of battery pack shell processing, in particular to new energy automobile battery pack shell integrated punch forming equipment. Comprising a bottom plate, a workbench is installed at the upper end of the bottom plate, a portal frame fixedly connected with the workbench is erected above the workbench, a male die unit is arranged at the lower end of a horizontal section of the portal frame, a female die unit is arranged at the upper end of the workbench, and a limiting assembly used for circumferentially limiting a plate is arranged at the upper end of the workbench. The limiting assembly is adopted for conducting centering alignment and circumferential limiting on a plate before stamping, and it can be guaranteed that the plate is kept at the fixed and accurate position in the stamping process; the contact area of the male die unit and the female die unit with a punch-formed shell can be reduced through the inward shrinkage assembly and the outward expansion assembly, the friction force and the adsorption force between the male die unit and the shell and between the female die unit and the shell are reduced, the situation that the shell deforms due to external force in the demolding process is avoided, a smoother demolding path can be formed easily, and the demolding quality is improved. The forming quality and the demolding efficiency are improved.

The invention relates to the technical field of forging, and discloses a high-speed forging machine which comprises a placing table, a forging casting is placed in the center of the top of the placing table, a forging block is arranged over the forging casting, a connecting plate is fixedly connected to the top of the forging block, and a downward pressing assembly for driving the forging block to conduct forging is arranged above the connecting plate. And overturning assemblies for driving the forged casting to overturn are arranged on the two sides of the connecting plate, and the forged casting can be overturned by 180 degrees through the overturning assemblies in the ascending and resetting process of the forging block, so that when the forging block carries out downward pressing forging next time, the other face of the forged casting can be forged by the forging block, and the forging efficiency is improved. According to the method, how to repeatedly carry out cyclic forging, the two faces of a forged casting can be evenly forged, it is ensured that metal obtains even deformation in the whole forging process, the problems of uneven stress and deformation caused by single-face treatment are solved, and therefore the geometric accuracy and the structural consistency of products are improved.

The invention relates to a vehicle floor assembly (5) having a vehicle floor (4) as a component of a motor vehicle body, which vehicle floor assembly has a flat floor region and forms on two opposite longitudinal sides and on two opposite end sides so as to form the vehicle floor (4), which is arranged between two sills (2). The invention relates to a vehicle floor (4) for a motor vehicle, said vehicle floor (4) having a flat bottom region in which at least one groove (7) is formed which is formed so as to point downwards in the vertical direction (Z) of the motor vehicle, the vehicle floor (4) being produced integrally during the stroke of a press, the vehicle floor (4) being formed integrally with regions of different wall thicknesses and / or different tensile strengths (Rm) from one another.

The invention relates to a preparation method and stretching equipment of a large-proportion pipe. The large-proportion pipe is characterized in that the outer diameter / inner diameter of the pipe is larger than 5. The preparation method comprises the following steps: preparing a pure quartz hollow pipe blank by using OVD, carrying out inner and outer diameter grinding processing on the pure quartz hollow pipe blank to obtain a pure quartz hollow sleeve with small wall thickness deviation, drawing the pure quartz hollow sleeve into a pure quartz pipe by using a vertical melting and drawing device, vacuumizing in the drawing process, and giving a certain relative vacuum degree to obtain the pure quartz pipe. And controlling the ratio of the pipe to the outer diameter / inner diameter to be more than 5. The pure quartz hollow tube blank is prepared through the OVD technology, the requirement for high purity of the quartz tube material is met, the hydroxyl content is low, the machining efficiency is high, and the manufacturing cost is low; the vertical melting and stretching equipment is simple and reasonable in structural arrangement, the annular thermal field is uniformly distributed, and the drawing processing quality of the pure quartz pipe is ensured; and meanwhile, the ratio of the outer diameter to the inner diameter is changed and controlled through the vacuumizing function of the vertical melting and stretching equipment.

The invention provides a surface mine live-action modeling system and method. The method comprises the following steps: automatically acquiring oblique photography images and laser point cloud data of a target mine area through an intelligent data acquisition unit; the data is stably transmitted back to a local data processing center through the data communication and transmission unit; performing automatic preprocessing and quality evaluation on the returned data through a data preprocessing and quality evaluation unit to form a quality control closed loop; a live-action three-dimensional model which is high in precision and supports real-time rendering is generated through a live-action three-dimensional modeling engine unit on the basis of a 3D Gaussian technology and by fusing multi-source data and mine semantic constraints; according to the method, the high-precision live-action three-dimensional model supporting real-time interaction is efficiently and automatically generated, and a powerful data basis is provided for mine digital twinning, safety production and intelligent decision making.

The invention belongs to the technical field of automobile part planing machining, and particularly relates to an automobile part in-shaft spline planing device which comprises a planing table, a side plate is fixedly connected to the planing table, a clamping mechanism used for fixing a workpiece is arranged on the side plate, a mounting ring is slidably connected to the upper end of the planing table in the horizontal direction, and the mounting ring is fixedly connected to the planing table. A planing piece is arranged on one side, close to the workpiece, of the mounting ring; and the intermittent planing mechanism is used for driving the planing piece to intermittently advance so as to avoid excessive loss of the planing piece. The intermittent planing mechanism is arranged, in the planing machining process, an annular plate is pushed through a strip-shaped tooth groove, planing machining of automobile parts is achieved, due to the fact that the pushing distance of a datum plate is smaller than that of the annular plate, the annular plate automatically moves by the distance of one station after being reset, and the machining precision of the automobile parts is improved. And therefore, when the annular plate and the planing piece are propelled next time, the planing piece is deeper into the workpiece, so that the planing piece intermittently planes the automobile parts.

This invention relates to the field of microfluidic control technology and discloses a method and system for detecting and controlling microfluidic droplet formation. The method first constructs an ideal concentric ring geometric model by acquiring the target parameters of the microcapsule and establishes a force-shape coupling response matrix. Based on this, a preset velocity triplet is solved to generate the initial droplet. Then, droplet image sequences are acquired and fitted with real-time concentric ring groups. These are geometrically superimposed with the ideal concentric ring geometric model to generate a deviation ring domain, which is then decomposed hierarchically to obtain geometric deformation characteristic components. Finally, a coordinated velocity adjustment vector is calculated using the force-shape coupling response matrix, a composite fluid correction field is constructed, and the deviation ring ablation cycle is iteratively executed until geometric convergence is achieved. This invention effectively solves the oscillation problem caused by strong parameter coupling in multiphase flow fields by constructing a quantitative mapping and inverse decoupling mechanism between fluid and geometric shape, achieving coordinated and precise control of the microcapsule's external dimensions and internal structure.

The invention discloses a three-dimensional model reconstruction method based on a sheet metal bent part expansion drawing, and the method is characterized in that the method comprises the following steps: S1, analyzing a sheet metal expansion drawing, classifying the analyzed primitive entities, and storing the primitive entities in corresponding primitive sets; s2, primitive preprocessing: performing de-weighting, breaking and discrete processing on the primitive, and screening out a metal plate bending line; s3, closed contour searching; s4, judging whether a closed contour exists or not, if not, repeating S3, and if yes, entering S5; s5, contour segmentation and topology construction: performing inner row segmentation on the outer contour and the inner contour by using a bending line, and establishing a geometric adjacency relation between the inner contour and the outer contour; s6, bending deduction is conducted, specifically, a deduction value is calculated according to the workpiece and bending information, and contour deduction is conducted on the contour; and S7, performing three-dimensional reconstruction, and constructing a three-dimensional entity model. According to the method, the technical defects that three-dimensional model reconstruction cannot be correctly carried out on a complex sheet metal expansion drawing and the model size error is large are overcome.

This invention discloses a method for constructing a realistic depth estimation training dataset based on a 3D mesh and 3D Gaussian splashing, relating to the field of UAV aerial surveying technology. The method involves acquiring aerial image sequences using a visible light camera mounted on a UAV platform, and filtering and preprocessing the image quality; generating a dense point cloud and a 3D mesh; training and generating a 3DGS model based on camera pose and image sequences consistent with the 3D mesh; unifying the 3D mesh, camera pose, and 3DGS model to the same world coordinate system; and using Z-buffer rasterization to output pixel-by-pixel depth and validity masks; generating RGB images of the corresponding viewpoint in the 3DGS renderer; and encapsulating the dataset according to a recommended data organization structure. This invention can accurately generate realistic RGB and geometrically accurate depth, with strict pixel alignment between the RGB images and depth maps, adapting to the needs of real-world application scenarios such as UAV aerial surveying and actual terrain mapping.

The present invention discloses a method for extracting line features of building three-dimensional point clouds based on deep learning, including: firstly, using a ground fixed station laser scanner to obtain laser point cloud data of buildings in a survey area, then slicing the acquired three-dimensional point cloud of buildings, projecting the sliced ​​point cloud to a two-dimensional occupancy probability image, and calculating the PCA1 based on the weight center decomposition of each pixel according to the density of the sliced ​​point cloud to generate a sub-image; then manually marking the building contour line and making a training sample data set; then constructing a line feature extraction neural network LALine‑Net, obtaining the neural network model parameters through network training and model evaluation; applying new data to perform model prediction, extracting the line features of the laser point cloud of buildings in the survey area; finally, refitting and optimizing the extracted line features to obtain the final building contour line features. The present invention can quickly extract the urban building contour line from the laser point cloud, has better integrity and geometric accuracy, and can meet the needs of building mapping based on laser three-dimensional point clouds.

The present application relates to the technical field of simulation sandbox, and particularly relates to a simulation sandbox data base construction method and device, wherein the method constructs compatible domain object models in the localization BIM forward design stage; according to unstructured drawings, localization BIM models and other data types, SHP data, geometric feature data and structured topology data are extracted or generated; simulation element data is obtained through field-level direct mapping, SHP data is converted twice and coordinates are unified, and then geometric feature completion, line segment merging and topology reconstruction are performed, object construction and labeling are completed based on the simulation element data, and simulation sandbox data base is obtained. The present application solves the problems of low construction efficiency, poor compatibility and insufficient geometric accuracy, realizes standardized data processing and efficient construction, can be directly loaded into a simulation sandbox, is suitable for airport and other scenes, and improves simulation accuracy and reliability.

The invention discloses a joint surgical operation data fusion processing method and system based on a multi-modal image, and relates to the technical field of image processing. The method comprises the following steps: performing motion state evaluation based on joint trajectory data of each posture point image in a multi-modal image, and dynamically acquiring a reference joint image of the multi-modal image based on a motion state evaluation result; performing image accuracy evaluation based on joint position data in each reference joint image, and dynamically correcting the joint data based on an image accuracy evaluation result; and forming a joint three-dimensional model based on the corrected joint data, performing dynamic region division based on joint evaluation parameters in the joint three-dimensional model, and dynamically adjusting the model geometric accuracy of the joint three-dimensional model based on a region division result and a joint category. Accurate quantitative analysis of the joint movement function, individualized high-precision three-dimensional model reconstruction and systematic improvement of clinical diagnosis efficiency are achieved.

This invention belongs to the interdisciplinary field of computer vision and 3D reconstruction, specifically relating to a generative 3D reconstruction method and system based on global constraints of location information. The method includes the following steps: S1, inputting multi-view UAV image sequences into a pre-trained feedforward neural network, which predicts sparse point clouds and the camera pose for each image; S2, extracting GNSS location information from the image sequence and using it as a global constraint to jointly optimize the sparse point cloud and camera pose, obtaining optimized point clouds and optimized camera poses in an absolute geographic coordinate system; S3, based on the optimized point cloud, employing a 3D Gaussian splashing method and utilizing the optimized camera pose for differentiable rendering optimization, generating a realistic 3D model with absolute geographic coordinates. This method, while ensuring 3D reconstruction accuracy, rapidly generates a geographic coordinate system 3D model, providing an efficient and scalable technical solution for city-level realistic 3D construction.

The present application provides an image stitching method, device, equipment, storage medium and product, the image stitching method comprises the following steps: fusing the shooting distance value between a plurality of shooting devices and the imaging target surface to generate the reference distance feature corresponding to each frame image; inputting the reference distance feature into a pre-trained stitching parameter prediction model to obtain the stitching parameter required for the current frame image stitching; based on the stitching parameter, the images collected by the plurality of shooting devices are initially stitched to form an initial panoramic image; the region of interest is set in the boundary region of the initial panoramic image, and the images in the region of interest are pre-adjusted; the pre-adjusted initial panoramic image is processed to obtain a final panoramic image. The method can fuse the distance between the shooting device and the imaging target surface in real time, and dynamically update the related stitching parameters according to the distance, combine the image features for fine fusion, and avoid the problems of stitching delay and obvious stitching effect fluctuation.

The present invention provides a semiconductor mask data graphics optimization method and system, which relates to the field of data processing technology. The method includes: obtaining semiconductor mask data, the semiconductor mask data includes a design graphic to be processed; constructing a photolithography imaging model; performing preliminary segmentation on the design graphic to be processed; inputting the design graphic after preliminary segmentation into the photolithography imaging model, and outputting the actual graphic after photolithography processing; calculating the EPE sensitivity of each segment of the graphic based on the difference between the design graphic and the actual graphic; performing fine segmentation on the design graphic after preliminary segmentation based on the EPE sensitivity; sensing the EPE, PV band area and CPU running time of the process variation of each segment of the graphic, controlling the movement of each segment of the graphic after fine segmentation, and performing graphic optimization on the design graphic. The present invention can improve the geometric accuracy of the pattern, improve the efficiency of graphic optimization, and reduce the difficulty of graphic optimization.

This invention relates to the field of image recognition technology, specifically to a tumor detection and recognition method and system based on MRI images. The method includes the following steps: screening candidate lesion regions based on a gradient orientation stability matrix; constructing a spatial projection displacement map; establishing a dynamic boundary framework by combining boundary variation rate; dividing into levels according to a sequence morphological consistency matrix; and performing differential reshaping to generate recognition results. This invention, by constructing a gradient orientation stability matrix and an anisotropy scoring mechanism, quantitatively evaluates the distribution of pixel vector angles; utilizes spatial projection displacement maps and boundary variation rate analysis to dynamically capture structural continuity features between slices; automatically eliminates artifact interference and constructs a high-fidelity dynamic boundary framework; divides into differential levels by combining a sequence morphological consistency matrix; and performs mean adjustment and edge reshaping for regions with different confidence levels. This improves the geometric accuracy and structural integrity of tumor lesion recognition under complex imaging conditions.

The present invention relates to the field of geological exploration technology, and in particular to a method and system for intelligent lithology identification based on deep learning. The method comprises the following steps: obtaining original core image data; extracting texture hierarchy features based on the original core image data to generate core significant texture structure feature data; performing fine rock layer image segmentation processing based on the core significant texture structure feature data to generate fine rock layer segmentation map data; constructing an intelligent lithology identification model; transmitting the fine rock layer segmentation map data to the intelligent lithology identification model to identify the target lithology attributes, and predicting the time series lithology evolution boundary to obtain predicted lithology evolution boundary data; performing lithology spatial distribution pattern recognition based on the predicted lithology evolution boundary data to generate lithology spatial distribution pattern data. The present invention realizes high-precision, automated and rapid lithology discrimination by finely segmenting the rock layers of core images, and significantly improves the efficiency of resource assessment in mining areas.

The utility model discloses a kind of internal gear gear grinding machine workpiece main shaft device, comprising: worm gear mechanism, and worm mechanism, wherein, the worm gear mechanism includes: workpiece main shaft, workpiece main shaft box is installed on the workpiece main shaft, index worm wheel is installed on the workpiece main shaft;The worm mechanism includes: double floating worm, the double floating worm is engaged with the index worm wheel, the end of the double floating worm is connected with power mechanism, and the power mechanism is installed on the workpiece main shaft box. By designing a set of meshing side gap adjustable high-precision double floating worm gear mechanism inside headstock, the precision of main shaft can be adjusted during working process, so that transmission efficiency is high, can bear larger load and torque, realize smooth transmission, and adjustment is simple, convenient for later maintenance.

This invention discloses a triaxial orthogonal array eddy current tensor probe and method based on liquid metal microchannels, belonging to the field of electromagnetic nondestructive testing technology. It includes an excitation coil and a receiving unit disposed within the excitation coil. The receiving unit employs an array of three-dimensional sensing units, each comprising: a cubic frame; and three coil groups respectively disposed on the X, Y, and Z faces of the cubic frame. The coils disposed on the X, Y, and Z faces of the cubic frame are spatially coupled at the intersection edges of adjacent faces using an interlaced weave structure, causing the equivalent electromagnetic centers of the three coil groups to converge in physical space to the geometric center point of the cubic frame. The probe of this invention has a compact structure and is suitable not only for planar surfaces but also for the inspection of pipes or curved workpieces by adjusting the bottom shape. It features a high signal-to-noise ratio and omnidirectional consistency.

The present application belongs to the technical field of high-performance steel production, and discloses a high-performance steel plate processing heat treatment equipment, which comprises a heating chamber, a support component for placing and fixing the steel plate is arranged in the heating chamber, the support components are arranged in multiple groups, the support components in the same group are located on the same vertical plane, and the support components in each group are arranged in parallel and along the horizontal direction; the support component comprises a clamping plate capable of adjusting the interval; the steel plate is changed from the traditional horizontal placement mode to the vertical state for heat treatment, so that the stress of the steel plate in the vertical direction is uniform, and the middle sag phenomenon caused by the weight is effectively eliminated. In the heating and cooling process, the temperature gradient of the steel plate along the thickness direction is more symmetrical, the thermal contraction behavior of the edge and the center region tends to be consistent, and the internal stress imbalance problem caused by asymmetric cooling is significantly reduced.

The invention discloses a light-weight femtosecond pulse waveguide forming process, which utilizes the ultrashort pulse characteristic of femtosecond laser to generate local refractive index change in a transparent dielectric material so as to form a high-quality waveguide structure. According to the technology, the pulse energy, the repetition frequency and the scanning speed of femtosecond laser are accurately controlled, and flexible design and efficient machining of a waveguide path are achieved. Femtosecond laser can freely scan in a three-dimensional space, flexible design and machining of a complex waveguide structure are achieved, the application range of the waveguide is expanded, tiny defects on the surface of the waveguide can be effectively reduced by accurately controlling laser parameters, the transmission loss and geometric accuracy of the waveguide are improved, the femtosecond laser machining speed is high, the process is simple, and the cost is low. The invention provides a waveguide forming process which is efficient, flexible and high in precision, the problems existing in the prior art are solved, and the preparation quality and the application potential of the waveguide are remarkably improved.

This application relates to the field of intelligent mining technology and discloses a method for constructing a digital model of an automated mining face. The method includes: collecting the coordinates of roadway targets and the dip control points of the cutting face; selecting three points to construct a reference plane reflecting the strike and dip of the coal seam; calculating the normal offset of the dip control points relative to the reference plane, constructing an interpolation function and performing spatial mapping to generate a coal seam floor surface; recursively generating multi-segment surfaces along the advancing direction and constructing a three-dimensional solid model in conjunction with the coal thickness; during the mining process, calculating the error between the measured data and the model, decomposing the error into trend and fluctuation terms, and introducing spatial attenuation weights to dynamically correct unmined areas. This invention, by combining a reference plane and offset mapping, takes into account both macroscopic occurrence and local undulation characteristics, and achieves closed-loop updating of the model through error decomposition, thereby improving the accuracy and environmental adaptability of the geological model.

The present application belongs to the technical field of forestry remote sensing monitoring and image processing, and in particular to a forest canopy density estimation method based on a lightweight gradient morphological perception network. The method comprises the following steps: step 1: obtaining a forest canopy remote sensing image dataset; step 2: constructing a tree crown segmentation model based on a lightweight gradient morphological perception network; step 3: training with a boundary-enhanced compound loss function; and step 4: using the trained model for inference and forest canopy density estimation. The present application can efficiently run directly on a consumer-grade unmanned aerial vehicle or a portable device, meet the needs of rapid forestry investigation, accurately capture the small gradient changes between tree crowns, effectively cut the adhered tree crown boundaries, significantly improve the geometric precision of segmentation, effectively filter out redundant information such as undergrowth background and non-tree crown shadows, solve the texture confusion problem, and have extremely high practical value.

The present application relates to the field of tunnel engineering geology and support design, and discloses a soft surrounding rock tunnel deformation risk discrimination method based on shear dilation-shear constitutive, comprising the following steps: constructing a nonlinear coupling model between the shear dilation angle and the shear stress, normal stress and joint parameters, and obtaining the shear dilation angle; establishing a volume strain rate discrimination formula; inverting the initial stress tensor field; reconstructing the irregular tunnel boundary; constructing a risk grade discrimination model and outputting the risk grade; matching the support scheme such as support stiffness, anchor rod parameters and spray layer thickness according to the risk grade; establishing a model to predict the risk trend; generating support adjustment suggestions; collecting monitoring data to dynamically correct the model parameters; and integrating all modules in the deployment system. The present application introduces the coupling relationship between the shear dilation angle and the shear strength, establishes a coupled constitutive discrimination model, and constructs a risk grading system and support correction strategy associated with support response, thereby realizing active early warning and dynamic adjustment of support stiffness in high-risk sections.

The invention discloses a large-area surface multistage complex microstructure composite forming device which comprises an electric field auxiliary micro-rolling forming mechanism and an electric field auxiliary micro-die forming mechanism, the electric field auxiliary micro-rolling forming mechanism comprises a pulse power source, a feeding mechanism, a roughing roller, a finishing roller and a discharging mechanism, and the feeding mechanism, the roughing roller, the finishing roller and the discharging mechanism are sequentially arranged in the conveying direction. The electric field assisted micro die forming mechanism comprises a die pressing mechanism and pressure equipment located above the die pressing mechanism, the die pressing mechanism comprises a male die and a blank groove formed below the male die, and a plurality of microstructures are formed in the bottom end of the male die. According to the forming device, the rough roller, the finish roller and the pulse power source are arranged on the electric field auxiliary micro-rolling forming mechanism, the surface of a material is subjected to rolling forming twice under the heating condition, a basic structure is obtained, then the material is subjected to multi-stage complex microstructure forming through the male die, and the material is subjected to multi-stage complex microstructure forming. The method is suitable for the technical field of machining and plastic micro-forming.

The invention discloses a handheld image point cloud and laser point cloud fusion detection method for a bridge prefabricated part. The method comprises the following steps: synchronously obtaining a laser point cloud and a sequence image of the prefabricated part; reconstructing the sequence image to obtain an image point cloud; performing normalization by taking the laser point cloud as a reference to obtain the laser point cloud and the image point cloud with consistent physical scales; initial attitude alignment of the two sets of point clouds is completed, rigid fine registration is carried out, the laser point clouds are corrected, and fused point clouds are obtained; generating a standard virtual point cloud; performing semantic segmentation on the fused point cloud, and outputting a point cloud set of each sub-component; extracting line-plane features of the key points; calculating the key geometric dimension of the prefabricated part, comparing the key geometric dimension with the standard virtual point cloud, and judging whether the dimension deviation meets a preset deviation or not; and evaluating the flatness quality of the surface of the component, and generating a three-dimensional full-field deviation chromatogram which covers the whole surface of the component. According to the invention, rapid, comprehensive and high-precision detection of the geometric dimension and the appearance flatness of the prefabricated part is realized.

The present application relates to the field of electronic technology, and discloses a method, device and equipment for underwater three-dimensional reconstruction of inspection well based on sonar ring scanning, the method comprising: obtaining sonar ring scanning data, attitude data of different depths of the inspection well and reference sonar ring scanning data of the inspection well; performing translational motion compensation processing on the sonar ring scanning data of each depth based on the attitude data of each depth and the reference sonar ring scanning data, to obtain first target data of the corresponding depth; extracting well wall points from the first target data of each depth, to obtain a first well wall point set of the corresponding depth; constructing a rotation matrix of the corresponding depth based on the attitude data of each depth; determining a second well wall point set of the corresponding depth in a global coordinate system based on the rotation matrix of each depth and the first well wall point set of the corresponding depth; and generating an underwater three-dimensional grid model of the inspection well based on the second well wall point sets of multiple depths, which can completely and intuitively restore the complex spatial topological form inside the inspection well.

This invention discloses a multi-objective Bayesian process parameter optimization method for selective laser melting (SLM) based on geometric feature weighting, belonging to the field of laser selective melting additive manufacturing technology. The method involves inputting an STL model of the part, extracting its geometric features, and assigning corresponding sensitivity weights based on these features to construct a spatial weight field. A weighted multi-objective function coupled with the spatial weight field is established with the optimization objectives of maximizing density, minimizing dimensional error, and minimizing surface roughness as the goals. Experiments are conducted on the process parameters based on Bayesian optimization to search for the Pareto front solution set under the weighted multi-objective function. The Pareto front solution set is then sorted using multi-objective decision-making to select the optimal parameter combination and generate a processing card for forming and manufacturing in a laser selective melting device. By explicitly writing geometric sensitivity into the weighted multi-objective function, a Pareto front that considers ρ, δ, and Ra can be obtained with a small number of experiments. Furthermore, the method can automatically weight parameters according to geometric features, simultaneously optimizing ρ, δ, and Ra while also considering geometric feature sensitivity.