A roof complex curved surface curvature analysis optimization method, device, equipment and medium

Abstract

The application relates to a roof complex curved surface curvature analysis optimization method, device, equipment and medium. The analysis optimization method comprises the following steps: obtaining original point cloud data of a target roof, preprocessing the original point cloud data, and generating a corresponding roof entity point cloud model; establishing a curved surface reconstruction algorithm interface of the roof entity point cloud model, extracting a corresponding spatial coordinate point set, and generating a corresponding curvature parameter set; inputting the curvature parameter set into a preset elastic mechanics model to determine a corresponding critical region; performing parameterized adjustment on the critical region to generate optimized curvature data, converting the optimized curvature data into plate rolling process parameters, and generating a corresponding optimization scheme; and based on a cloud collaborative platform, the optimization scheme is pushed to each application terminal. The accuracy and efficiency of complex curved surface modeling and analysis are improved, closed-loop collaboration of design, analysis and manufacturing is realized, and the problems of modeling distortion, lagging mechanical analysis and data isolation in the traditional method are solved.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing, and in particular to a method, apparatus, equipment, and medium for analyzing and optimizing the curvature of complex roof surfaces. Background Technology

[0002] Currently, with the diversification of architectural styles, the demand for complex curved metal roofs is constantly increasing. To achieve the architectural appearance of free-form surfaces, the design process requires high-precision modeling and stress analysis of the roof shape, but existing technologies still have shortcomings in data acquisition and mechanical correlation.

[0003] Existing solutions often employ total station manual sampling combined with Rhino software modeling. This method has low equipment costs, but the sampling point density is limited, easily leading to distortion in surface fitting. When manually calculating curvature, local abrupt changes are often ignored, affecting the accuracy of stress identification. Another solution, based on photogrammetry to generate a triangular mesh model, can quickly obtain the overall roof shape, but it lacks correlation with material mechanical properties, and the discretized model is difficult to synchronize with stress calculation results in real time, resulting in a lag in analysis results.

[0004] Therefore, existing technologies generally suffer from insufficient modeling accuracy, disconnect from stress analysis, and low data collaboration efficiency, making it difficult to meet the needs of integrated design and structural optimization for complex curved metal roofs. Summary of the Invention

[0005] To address the problems of insufficient modeling accuracy, disconnected stress analysis, and low data collaboration efficiency in existing technologies, this application provides a method, apparatus, equipment, and medium for optimizing the curvature analysis of complex roof surfaces.

[0006] The above-mentioned objective of this application is achieved through the following technical solution:

[0007] A method for analyzing and optimizing the curvature of complex roof surfaces, comprising:

[0008] Obtain the original point cloud data of the target roof, preprocess the original point cloud data, and generate the corresponding roof entity point cloud model;

[0009] A surface reconstruction algorithm interface for the roof solid point cloud model is established. Based on the surface reconstruction algorithm interface, the corresponding spatial coordinate point set is extracted to calculate the principal curvature radius and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, thereby generating the corresponding curvature parameter set.

[0010] The curvature parameter set is input into a preset elasticity model to generate the corresponding stress distribution results. Based on the stress distribution results and the determined allowable stress threshold of the material, the corresponding critical region is determined.

[0011] The optimization algorithm library is called to perform parameterized adjustment on the critical region, generate optimized curvature data, and convert the optimized curvature data into plate rolling process parameters to generate the corresponding optimization scheme.

[0012] Based on the cloud-based collaborative platform, the optimization scheme is pushed to various application terminals.

[0013] By adopting the above technical solution and establishing a complete analysis chain from point cloud acquisition to optimized output, high-precision modeling and mechanical optimization of complex curved metal roofs were achieved. Through algorithmic and closed-loop data processing of each stage of acquisition, modeling, analysis, and optimization, it significantly improved design accuracy and data synergy, solving the problems of low modeling accuracy, delayed stress analysis, and data disconnect in traditional manual measurement and discrete modeling methods.

[0014] Preferably, the step of preprocessing the original point cloud data to generate the corresponding roof solid point cloud model includes:

[0015] The original point cloud data is acquired and preliminarily filtered according to environmental parameters to extract an initial point cloud subset containing effective spatial coordinate information. The effective spatial coordinate information is used to extract the corresponding spatial coordinate point set through the surface reconstruction algorithm interface.

[0016] Based on the neighborhood density and reflection intensity characteristics of each point in the initial point cloud subset, noise filtering operation is performed to generate corresponding valid point cloud data.

[0017] Based on the temperature field data and scanning device attitude information recorded during acquisition, temperature deformation compensation calculation is performed on the effective point cloud data to generate geometrically corrected standardized point cloud data.

[0018] Based on the standardized point cloud data, the spatial surface node distribution is reconstructed to generate the corresponding roof entity point cloud model.

[0019] By adopting the above technical solutions, the original point cloud data of the roof is cleaned and corrected during the input stage. Through environmental parameter screening, noise filtering and temperature compensation, comprehensive correction of measurement errors, optical interference and thermal deformation is achieved. The output solid point cloud model is more stable and reliable in geometric accuracy, providing a high-fidelity foundation for subsequent surface reconstruction and curvature analysis.

[0020] Preferably, the step of calculating the principal radii of curvature and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, and then generating the corresponding curvature parameter set, includes:

[0021] Generate a neighborhood point set centered on each coordinate point in the spatial coordinate point set, and establish a local coordinate system for each neighborhood point set, using the tangent plane of the local coordinate system as the corresponding coordinate reference plane;

[0022] The least squares quadratic surface fitting is performed on the neighborhood point set projected in the coordinate reference plane to generate the corresponding local surface expression, and the first principal curvature and the second principal curvature at the corresponding coordinate point are calculated based on the local surface expression.

[0023] The corresponding principal curvature radius is calculated based on the first principal curvature and the second principal curvature. Based on the principal curvature radius, the first principal curvature and the second principal curvature, the corresponding Gaussian curvature and mean curvature are calculated, and integrated to generate local curvature result data containing principal curvature radius, Gaussian curvature and mean curvature.

[0024] The local curvature result data is associated with and stored with the corresponding coordinate points to generate a corresponding curvature parameter set.

[0025] By adopting the above technical solution, and through the establishment of a local coordinate system and fitting with a quadratic surface, a quantitative description of the surface geometry is achieved. The system automatically calculates the principal curvature, Gaussian curvature, and mean curvature of each coordinate point, which not only improves the accuracy of surface curvature identification but also fully reflects the geometric characteristics of local abrupt change areas in complex roofs, providing accurate input for subsequent stress calculations.

[0026] Preferably, the step of inputting the curvature parameter set into a preset elasticity model to generate the corresponding stress distribution results includes:

[0027] Material constants are determined in a pre-defined elastic mechanical model, including the elastic modulus and plate thickness.

[0028] Based on the material constants and the curvature parameter set, the stress values ​​at the corresponding coordinate points are determined;

[0029] Based on the stress values ​​at each of the coordinate points, the corresponding stress distribution results are generated.

[0030] By employing the above technical solution, a mapping relationship between curvature and stress is established based on the mechanical properties of the material's elastic modulus and plate thickness, thereby calculating the bending stress distribution in various regions of the roof. This enables automatic generation of the stress field without relying on external finite element software, improving analysis efficiency and providing a quantitative basis for subsequent stress exceedance identification.

[0031] Preferably, the step of determining the corresponding critical region based on the stress distribution result and the determined allowable stress threshold of the material includes:

[0032] The allowable stress threshold for the corresponding roofing panel is determined in a preset material property database. The allowable stress threshold is a stress limit value preset based on material parameters.

[0033] By comparing the stress values ​​at each coordinate point in the stress distribution results with the allowable stress threshold, a set of coordinate points that exceed the allowable stress threshold is determined.

[0034] Based on the spatial distribution of the coordinate point set, a corresponding critical region is generated to characterize the local area on the roof surface where stress exceeds the limit.

[0035] By employing the above technical solution, the calculated stress distribution is compared with the allowable stress threshold of the material, automatically identifying regions exceeding the safety limit and generating corresponding critical region data, thus accurately locating high stress concentration areas. This result can intuitively reflect the structural risk distribution, providing targeted input for subsequent geometric optimization and reducing potential structural failure risks.

[0036] Preferably, the step of calling the optimization algorithm library to perform parameterized adjustment on the critical region and generate optimized curvature data includes:

[0037] Call the optimization algorithm library to determine the corresponding target algorithm, which includes gradient descent, genetic algorithm and multi-objective iterative algorithm;

[0038] Based on the critical region, an optimization function is constructed with the main objective of reducing the peak stress and the constraint of minimizing the increase in material usage. The optimization function is then parameterized using the objective algorithm to generate the corresponding optimized curvature data.

[0039] By adopting the above technical solution and establishing a multi-objective optimization function, with reducing the maximum stress value as the primary objective and controlling the increase in material usage as a constraint, automatic iterative optimization of curvature adjustment was achieved. The optimized curvature data effectively reduced local stress peaks while maintaining the geometric continuity of the roof, balancing structural safety and material economy.

[0040] Preferably, the step of converting the optimized curvature data into sheet metal rolling process parameters to generate the corresponding optimization scheme specifically includes:

[0041] In the preset sheet metal forming database, the sheet metal material type and the corresponding rolling parameter range corresponding to the optimized curvature data are mapped and matched. The rolling parameter range includes the target thickness range, rolling force range, and forming temperature range.

[0042] By adopting the above technical solution, and mapping and matching the optimized curvature data with the sheet metal forming database, the required thickness, rolling force, and temperature parameter ranges for rolling are automatically generated, thereby achieving the parametric transformation from design results to manufacturing processes. This directly guides the sheet metal processing steps, shortens the conversion cycle between design and production, and improves data loop efficiency and manufacturing accuracy.

[0043] The second objective of this invention is achieved through the following technical solution:

[0044] A device for analyzing and optimizing the curvature of complex roof surfaces, the device comprising:

[0045] The acquisition module is used to acquire the original point cloud data of the target roof, preprocess the original point cloud data, and generate the corresponding roof entity point cloud model.

[0046] A module is established to establish the surface reconstruction algorithm interface of the roof entity point cloud model. Based on the surface reconstruction algorithm interface, the corresponding spatial coordinate point set is extracted to calculate the principal curvature radius and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, thereby generating the corresponding curvature parameter set.

[0047] The generation module is used to input the curvature parameter set into a preset elasticity model, generate the corresponding stress distribution results, and determine the corresponding critical region based on the stress distribution results and the determined allowable stress threshold of the material.

[0048] The adjustment module is used to call the optimization algorithm library to perform parameterized adjustment on the critical region, generate optimized curvature data, and convert the optimized curvature data into plate rolling process parameters to generate the corresponding optimization scheme.

[0049] The push module is used to push the optimization scheme to various application terminals based on the cloud-based collaborative platform.

[0050] The above-mentioned objective three of this application is achieved through the following technical solution:

[0051] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for optimizing the curvature of a complex roof surface.

[0052] The fourth objective of this application is achieved through the following technical solution:

[0053] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for optimizing the curvature of a complex roof surface.

[0054] In summary, this application includes at least one of the following beneficial technical effects:

[0055] This application establishes a complete digital chain from geometric data acquisition to structural optimization and process implementation, comprehensively employing 3D point cloud reconstruction, curvature parameter extraction, elastic stress analysis, and multi-objective optimization calculations. First, 3D scanning data replaces manual measurement, enabling high-density point cloud acquisition of complex roof morphologies. Noise filtering and temperature compensation calculations are introduced during data preprocessing, improving the geometric accuracy of the surface model from the outset. Subsequently, the spatial coordinate point set is automatically extracted through the surface reconstruction algorithm interface, calculating the principal radius of curvature and Gaussian curvature of each point. This transforms curvature identification, previously reliant on manual experience, into algorithm-driven quantitative analysis, avoiding the neglect of areas with abrupt local curvature changes. In the mechanical analysis stage, curvature parameters are combined with material elastic properties to establish an elastic mechanical model, directly generating continuous stress distribution results. This unifies the geometric model with mechanical characteristics, overcoming the limitation of traditional photogrammetric models in associating material properties. Parameterized adjustments are performed through an optimization algorithm library, reducing local stress peaks while constraining the increase in material usage, achieving a balance between structural safety and material economy. The optimized curvature results are then converted into process parameters that can be directly used for sheet metal rolling. These parameters are then pushed to the design, production, and construction ends via a cloud-based collaborative platform, enabling real-time sharing and version consistency of design data. This significantly improves the accuracy and efficiency of complex surface modeling and analysis, achieves closed-loop collaboration between design, analysis, and manufacturing, and solves the problems of modeling distortion, lagging mechanical analysis, and data isolation in traditional methods. Attached Figure Description

[0056] Figure 1 This is a flowchart of a method for analyzing and optimizing the curvature of a complex roof surface according to an embodiment of this application.

[0057] Figure 2 This is another implementation flowchart of a method for optimizing the curvature of complex roof surfaces according to one embodiment of this application;

[0058] Figure 3 This is a flowchart illustrating the implementation of step S10 in a method for optimizing the curvature of a complex roof surface according to an embodiment of this application.

[0059] Figure 4 This is another implementation flowchart of step S10 in a method for optimizing the curvature of a complex roof surface according to an embodiment of this application;

[0060] Figure 5 This is a flowchart illustrating the implementation of step S10 in a method for optimizing the curvature of a complex roof surface according to an embodiment of this application.

[0061] Figure 6 This is a flowchart illustrating the implementation of step S10 in a method for optimizing the curvature of a complex roof surface according to an embodiment of this application.

[0062] Figure 7 This is a principle block diagram of a complex roof surface curvature analysis and optimization device according to one embodiment of this application;

[0063] Figure 8 This is a schematic diagram of a device according to one embodiment of this application. Detailed Implementation

[0064] The present application will be further described in detail below with reference to the accompanying drawings.

[0065] In one embodiment, such as Figure 1 As shown, this application discloses a method for optimizing the curvature of complex roof surfaces. This method includes:

[0066] S10. Acquire the original point cloud data of the target roof, preprocess the original point cloud data to generate the corresponding roof solid point cloud model. The original point cloud data is a set of spatial points on the roof surface collected by a 3D scanner or laser rangefinder. Each point has three-dimensional coordinate information and reflection intensity attributes, which can reflect the true geometric contour of the roof surface. However, the original data usually contains noise, voids, or drift errors, which need to be preprocessed by algorithms to restore the true shape. The roof solid point cloud model is a model that transforms the filtered, registered, and compensated point cloud data into a continuous spatial structure. This model can truly reflect the three-dimensional geometric features of the roof, providing a data foundation for surface reconstruction and subsequent stress analysis. For example, when scanning a section of metal roof with a hyperboloid transition, some reflective areas in the original point cloud data may be deficient. The roof solid point cloud model formed by preprocessing can completely restore the curvature transition of this area.

[0067] S20. Establish a surface reconstruction algorithm interface for the roof solid point cloud model. Based on the surface reconstruction algorithm interface, extract the corresponding spatial coordinate point set to calculate the principal radii of curvature and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, thereby generating the corresponding curvature parameter set. The surface reconstruction algorithm interface is a data transmission channel and calculation interface established by the system between point cloud data and curvature calculation algorithms. It is used to call various mathematical fitting algorithms, such as least squares fitting, spline interpolation, or quadratic surface reconstruction, to transform discrete point cloud data into a continuously differentiable surface expression. The spatial coordinate point set refers to the set of computable coordinate points extracted from the solid point cloud model. These coordinate points are arranged in a three-dimensional coordinate system and are used to calculate geometric parameters such as local curvature and surface normal vectors. The principal radii of curvature are two radii that describe the maximum and minimum curvature of the surface at a specific point, reflecting the curvature intensity of the surface. The Gaussian curvature is obtained by multiplying the two principal curvatures and is used to determine whether the geometric properties of the surface at that point are convex, concave, or saddle-shaped. The curvature parameter set is a structured data set generated by the system based on the curvature calculation results of all coordinate points. It includes principal curvature radii, Gaussian curvature, mean curvature, and normal information, and is used to describe the overall geometric distribution characteristics of the roof. For example, in the vaulted area of ​​a metal roof, the principal curvature radius is small and the Gaussian curvature is positive. The system can identify this area as a high bending strength region through the curvature parameter set.

[0068] S30. Input the curvature parameter set into the preset elasticity model to generate the corresponding stress distribution results. Based on the stress distribution results and the determined allowable stress threshold of the material, determine the corresponding critical region. The elasticity model is a mathematical model established based on the mechanical properties of the material. It is used to analyze the stress distribution characteristics of the roof structure under bending conditions. Its main parameters include elastic modulus, plate thickness, and radius of curvature. By combining curvature with material properties, the theoretical stress value of each region can be obtained. The stress distribution result is the output of the elasticity model, which reflects the stress state of the entire roof under curvature changes. It is a set of stress value matrices that correspond one-to-one with spatial coordinates. The allowable stress threshold of the material is the maximum safe stress value determined based on the material properties. Regions exceeding this value are considered to have potential structural risks. The critical region is the spatial region in the stress distribution result where the stress value exceeds the allowable stress threshold of the material. It is used to locate parts where the structural strength is insufficient or the stress is excessively concentrated. For example, when the radius of curvature of a certain section of the roof decreases sharply, the calculated stress value may exceed the allowable stress of the aluminum alloy plate, and the system will mark this region as a critical region.

[0069] S40. The optimization algorithm library is invoked to perform parameterized adjustments on the critical region, generating optimized curvature data. This optimized curvature data is then converted into sheet metal rolling process parameters to generate corresponding optimization schemes. The optimization algorithm library is a set of pre-set algorithms used to automatically search for optimal solutions in mathematical models. These algorithms often include gradient descent, genetic algorithms, and multi-objective iterative algorithms, used to simultaneously consider stress, deformation, and material consumption under multiple parameter conditions. Parameterized adjustment refers to the process of modifying variables such as curvature parameters, thickness parameters, or node positions to make the optimization objective function approach its optimal state. The optimized curvature data is the result of the algorithm's solution, containing the adjusted curvature radius distribution and corresponding coordinate information, used to replace the original curvature design to achieve structural stress minimization and morphological smoothing. For example, when stress concentration is too high in the critical region, the optimization algorithm fine-tunes the curvature radius of this region, slightly reducing its bending degree, thereby lowering peak stress without significantly increasing material thickness. Sheet metal rolling process parameters refer to control parameters used to guide the metal sheet forming process, including rolling force, target thickness, and forming temperature. Their values ​​directly determine the bending shape and structural stability of the metal sheet. The optimization scheme is a set of manufacturing and construction instructions generated by the system based on the optimized curvature data, which is used to guide factory production and on-site installation.

[0070] S50, based on a cloud-based collaborative platform, pushes optimized solutions to various application terminals. This cloud-based collaborative platform is a network system that supports the synchronous sharing of design, analysis, and manufacturing data, enabling data transmission and version control between different terminals through a cloud server. Application terminals are the user-end devices connected to the cloud platform, which may include the BIM system at the design institute, the CNC system at the factory, and the on-site verification equipment at the construction end. For example, after optimization is completed at the design end, the system pushes the optimized solution to the cloud-based collaborative platform. The CNC machine tool at the factory automatically reads the rolling parameters and executes the forming process, while the construction end performs installation and positioning based on real-time data, thereby achieving digital integration from design to manufacturing to construction.

[0071] In this embodiment, a method for optimizing the curvature of complex roof surfaces is specifically applied to an analysis system composed of a data acquisition module, a curvature analysis module, an automatic optimization module, and a cloud-based collaborative platform module. In the data acquisition module, a 3D scanner is used to perform high-density spatial measurements on the target roof. The scanner is fixed to designated measurement points on the roof using an adjustable bracket. The raw point cloud data acquired in real-time during the scanning process is input into the system via a point cloud preprocessing unit. This preprocessing unit incorporates a noise filtering algorithm to remove outliers and fly-by points caused by acquisition errors. It also performs temperature deformation compensation calculations based on the temperature field data acquired and the scanning device's attitude information, thereby obtaining standardized point cloud data with higher geometric accuracy. The system reconstructs the spatial surface node distribution based on this standardized point cloud data, generating a corresponding roof entity point cloud model, providing the input basis for subsequent curvature analysis.

[0072] In the curvature analysis module, the system establishes a surface reconstruction algorithm interface for the roof solid point cloud model. It automatically extracts spatial coordinate point sets through a parameter extraction engine and generates neighborhood point sets at each coordinate point. The system uses a least-squares quadratic surface fitting algorithm to calculate the corresponding principal curvature radius and Gaussian curvature distribution, and integrates the calculation results to generate a curvature parameter set containing the principal curvature radius, Gaussian curvature, and mean curvature. Subsequently, this curvature parameter set is input into a preset elasticity model, which defines the material's elastic modulus and plate thickness. The stress value corresponding to each coordinate point is calculated using the formula σ=(E·t / 2)·(1 / R1+1 / R2), thus generating the overall stress distribution result of the roof. The system compares the stress distribution result with the preset allowable stress threshold for the material, automatically identifying the set of coordinate points where the stress value exceeds the safety limit, and generating corresponding critical regions based on spatial distribution relationships to characterize local areas in the roof structure where stress concentration risk exists.

[0073] In the automatic optimization module, the system calls the optimization algorithm library and selects a suitable target algorithm for the current model, such as gradient descent or a multi-objective iterative algorithm. For the identified critical regions, the system constructs an optimization function with the primary objective of reducing the maximum stress value and the constraint of minimizing the increase in material usage. It then executes a parametric solution process, iteratively adjusting the curvature parameters to obtain optimized curvature data. This optimization process effectively reduces local stress peaks while ensuring the overall geometric continuity and shape consistency of the roof, and also considers material usage efficiency.

[0074] The system then inputs the optimized curvature data into the sheet metal parameter adjuster, and, in conjunction with the rolling force-curvature mapping relationship in the sheet metal forming database, calculates the corresponding sheet metal rolling process parameters, including the target thickness range, rolling force range, and forming temperature range, and generates a complete optimization scheme based on these parameters.

[0075] Within the cloud-based collaborative platform module, the system uploads optimized solutions to the platform. The platform includes a built-in visual report generator and a data standard interface, enabling the simultaneous delivery of curvature analysis results, stress distribution results, and optimized process parameters in visual report form to the design-side BIM model, the production-side CNC system, and the construction-side on-site terminal. Through this platform's data sharing mechanism, real-time collaboration between design, production, and construction stages can be achieved, ensuring drawing version consistency, reducing information delays and repetitive modeling operations, and significantly improving overall data flow efficiency.

[0076] In summary, this method achieves a fully digital closed loop, encompassing complex surface data acquisition, curvature calculation, stress identification, parametric optimization, and process mapping. Compared to traditional manual modeling or photogrammetry methods, this approach significantly improves the accuracy and computational efficiency of curvature analysis. It can accurately identify stress concentration areas and automatically generate optimized sheet thickness distribution schemes, reducing structural stress peaks while controlling material gain. This effectively reduces construction rework rates and enhances the overall safety and manufacturing consistency of the roof structure.

[0077] Furthermore, the step of preprocessing the raw point cloud data to generate the corresponding roof solid point cloud model includes:

[0078] S101. Acquire and perform preliminary screening of the original point cloud data based on environmental parameters to extract an initial point cloud subset containing valid spatial coordinate information. This valid spatial coordinate information is used to extract the corresponding spatial coordinate point set through the surface reconstruction algorithm interface. During 3D scanning, the system is significantly affected by external environmental conditions, such as changes in light intensity, humidity, wind speed, temperature gradient, and equipment attitude deviation. These factors can lead to drift points, reflection anomalies, or duplicate sampling points in the scanned data, thereby reducing the geometric consistency and spatial accuracy of the point cloud. The system introduces environmental parameters, such as ambient temperature, light intensity, humidity, and equipment attitude angle during scanning, to compare and calibrate the original point cloud data. This allows for the removal of anomalies significantly affected by external disturbances before the data enters the subsequent reconstruction algorithm, while also correcting local offsets caused by equipment tilt or thermal expansion. After this screening process, the retained initial point cloud subset has high spatial stability and measurement reliability, ensuring that the valid spatial coordinate information it contains accurately reflects the true geometric features of the roof, providing precise input for the subsequent extraction of the spatial coordinate point set by the surface reconstruction algorithm interface.

[0079] S102. Based on the neighborhood density and reflection intensity characteristics of each point in the initial point cloud subset, a noise filtering operation is performed to generate corresponding valid point cloud data. In this embodiment, the noise filtering operation is mainly used to remove outliers and false points in the point cloud data caused by measurement errors, reflection interference, or equipment jitter. The system first calculates the neighborhood density in three-dimensional space for each point in the initial point cloud subset, that is, the number of neighboring points within a given search radius. If the neighborhood density of a point is significantly lower than the average level, the system determines it to be a spatially isolated point or a reflection noise point and marks it as invalid data. At the same time, a double screening is performed based on the reflection intensity characteristics of each point, using a preset intensity threshold to remove false echo points caused by high metal reflection or low incident angle. During the iteration process, the algorithm also performs secondary smoothing on abnormal fluctuation sections by statistically analyzing the variance changes of neighborhood points to restore the natural transition of the continuous surface. The entire filtering process is implemented by multi-threaded parallel computation, which can process data of millions of points in a short time. After this noise filtering operation, the output effective point cloud data has higher spatial consistency and surface continuity, providing an accurate and reliable geometric basis for subsequent temperature compensation and surface reconstruction.

[0080] S103. Based on the temperature field data and scanning device attitude information recorded during acquisition, temperature deformation compensation calculation is performed on the effective point cloud data to generate geometrically corrected standardized point cloud data. Temperature deformation compensation calculation is mainly used to eliminate geometric distortions caused by changes in ambient temperature or device attitude deviations during 3D scanning. During point cloud acquisition, the system synchronously records the temperature field distribution data around the scanning device and the device attitude information. The temperature field data is monitored in real time by a built-in thermistor to track temperature gradient changes within the scanning area, while the attitude information is determined by a combination of a gyroscope and an accelerometer to measure the device's tilt angle, rotation angle, and displacement deviation. The compensation algorithm first corrects the displacement error of each spatial coordinate point in the point cloud along the normal direction based on the material's thermal expansion coefficient. When a slight expansion or contraction of the device structure due to a temperature rise is detected, the system automatically adjusts the corresponding point coordinate values ​​using a scaling factor ΔL = α·L·ΔT to restore its true geometric position at standard temperature. Subsequently, a transformation matrix between the device coordinate system and the world coordinate system is established based on the attitude information. Rotation and translation operations are then used to perform attitude compensation on the entire point cloud, eliminating the overall skew error caused by slight device tilt. Finally, the system overlays and fuses the temperature compensation results with the attitude correction results, and outputs geometrically corrected standardized point cloud data, which can accurately reflect the real spatial shape and curvature characteristics of the roof in the subsequent surface reconstruction stage.

[0081] S104. Based on standardized point cloud data, the system reconstructs the spatial surface node distribution to generate a corresponding roof solid point cloud model. The reconstruction of the spatial surface node distribution transforms the standardized point cloud data into a solid model with continuous geometric relationships. First, based on the spatial distribution characteristics of the standardized point cloud data, the system uses a 3D Delaunay triangulation algorithm to establish the topological connections between points, thus forming a preliminary spatial mesh structure. Subsequently, through normal vector estimation and surface fitting smoothing algorithms, the system calculates the normal direction of each node and corrects the local curvature between nodes, ensuring that the reconstructed surface maintains geometric continuity and smoothness consistent with the real roof surface. To avoid over-interpolation in weak areas, the system adaptively adjusts the node density in high-curvature or sparsely sampled regions, dynamically optimizing the node spacing through the interpolation control parameter λ to ensure higher geometric resolution at key structural points. Finally, the system encapsulates all nodes and their connections into a unified 3D spatial data structure, generating a complete roof solid point cloud model. This model not only accurately reflects the three-dimensional shape of the roof, but also provides a directly callable geometric input interface for subsequent curvature calculation and elasticity analysis, realizing an automated reconstruction process from raw measurement data to a structured geometric model.

[0082] Furthermore, the step of calculating the principal radii of curvature and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, and then generating the corresponding curvature parameter set, includes:

[0083] S201. Generate neighborhood point sets centered on each coordinate point in the spatial coordinate point set, and establish a local coordinate system for each neighborhood point set, using the tangent plane of the local coordinate system as the corresponding coordinate reference plane; using each coordinate point in the spatial coordinate point set as the center, extract the neighborhood point set around that point in three-dimensional space by setting a neighborhood search radius r, and establish a local coordinate system based on these neighborhood points. The z-axis of the local coordinate system is taken as the estimated normal direction of that point, and the x-axis and y-axis form its tangent plane, which serves as the coordinate reference plane for projecting the neighborhood point set into the local two-dimensional space.

[0084] S202. Perform least-squares quadratic surface fitting on the neighborhood point set projected onto the coordinate reference plane to generate the corresponding local surface expression, and calculate the first and second principal curvatures at the corresponding coordinate points based on the local surface expression; perform least-squares quadratic surface fitting on the projected neighborhood point set to generate the local surface expression z=ax²+by²+cxy+dx+ey+f, where a, b, c, d, e, and f are surface fitting coefficients. By taking the first and second partial derivatives of this surface expression, the system calculates the principal curvature directions and the two principal curvature values ​​K1 and K2 at the corresponding coordinate points, and records them as the first and second principal curvatures, respectively.

[0085] S203. Calculate the corresponding principal curvature radii based on the first and second principal curvatures. Calculate the corresponding Gaussian curvature and mean curvature based on the principal curvature radii, the first principal curvature, and the second principal curvature, and integrate these to generate local curvature result data containing the principal curvature radii, Gaussian curvature, and mean curvature. Based on the two principal curvature values, the system calculates the principal curvature radii R1 = 1 / K1 and R2 = 1 / K2, and further obtains the Gaussian curvature K = K1 × K2 and the mean curvature H = (K1 + K2) / 2 at that point. The system integrates the results R1, R2, K, and H to generate local curvature result data, which is used to describe the local geometric features of that point.

[0086] S204. The local curvature result data is associated and stored with the corresponding coordinate points to generate a corresponding curvature parameter set. Based on the two principal curvature values, the system calculates the principal curvature radii R1 = 1 / K1 and R2 = 1 / K2, and further obtains the Gaussian curvature K = K1 × K2 and the average curvature H = (K1 + K2) / 2 at this point. The system integrates the results R1, R2, K, H, etc., to generate local curvature result data, which is used to describe the local geometric morphological characteristics of this point.

[0087] Furthermore, the step of inputting the curvature parameter set into a preset elasticity model to generate the corresponding stress distribution results includes:

[0088] S3011. Determine the material constants in the preset elasticity model. The material constants include the elastic modulus and the plate thickness.

[0089] S3012. Determine the stress value at the corresponding coordinate point based on the material constants and curvature parameter set;

[0090] S3013. Generate the corresponding stress distribution results based on the stress values ​​at each coordinate point.

[0091] In this embodiment, the generation of stress distribution results is achieved through comprehensive calculation of curvature parameters and material mechanical properties. The system first loads the material constants of the corresponding roof panel into the elasticity model, including the elastic modulus E and the panel thickness t. These parameters are provided by a material performance database and can be automatically retrieved based on the selected metal material (e.g., aluminum alloy, stainless steel). During the calculation phase, the system uses the curvature parameter set as geometric input, substituting it along with the material constants into the elasticity equilibrium equation. The system calculates the stress value at each coordinate point using the surface stress analytical formula σ=(E·t / 2)·(1 / R1+1 / R2), where R1 and R2 are the two principal curvature radii at that point. To improve calculation stability, the system performs spatial weighted smoothing on the stress results of neighboring points, correcting abnormal peak values ​​caused by local fitting errors. After the stress values ​​at all coordinate points are calculated, the system generates stress distribution results based on a three-dimensional coordinate system, mapping the stress values ​​onto the roof solid point cloud model in the form of isosurfaces or pseudo-color heatmaps, thus intuitively reflecting the stress state and stress concentration in different areas. The stress distribution results can be used to identify potential structural risk areas and provide a quantitative input basis for subsequent critical region extraction and parameterized optimization.

[0092] Furthermore, the step of determining the corresponding critical region based on the stress distribution results and the determined allowable stress threshold of the material includes:

[0093] S3021. Determine the allowable stress threshold of the corresponding roofing panel in the preset material performance database. The allowable stress threshold is the stress limit value preset based on the material parameters.

[0094] S3022. Based on the stress values ​​of each coordinate point in the stress distribution results, compare them with the allowable stress threshold to determine the set of coordinate points that exceed the allowable stress threshold.

[0095] S3023. Based on the spatial distribution of the coordinate point set, generate the corresponding critical region to characterize the local area where stress exceeds the limit on the roof surface.

[0096] In this embodiment, the determination of the critical region is used to identify localized areas in the structure where there are potential safety risks or excessive stress concentration, based on the stress distribution results. The system first calls a preset material property database and retrieves the corresponding allowable stress threshold according to the type of sheet material. This threshold is jointly determined by the material's yield strength, elastic limit, and safety factor. For example, for aluminum alloy roof panels, the allowable stress threshold can be calculated based on the standard specification σ_allow = σ_y / n, where σ_y is the material's yield strength and n is the safety factor. This threshold serves as a benchmark value for determining whether the roof stress exceeds the limit.

[0097] Subsequently, the system compares the stress value at each coordinate point in the stress distribution results with the threshold point by point. If the stress value σ_i at a certain point exceeds the allowable stress threshold σ_allow, the point is marked as an out-of-limit point and added to the coordinate point set. To avoid misjudgment of a single outlier, the algorithm adopts a neighborhood averaging strategy during comparison, smoothing the stress gradient of adjacent points. Only when multiple consecutive points in a local area exceed the threshold is it determined to be a valid out-of-limit zone.

[0098] After comparison, the system performs region clustering analysis based on the distribution of coordinate points in three-dimensional space. The DBSCAN spatial clustering algorithm automatically divides the areas of stress exceeding limits into clusters, thereby generating corresponding critical regions. The boundary of each critical region is determined by isostress line fitting, and key feature information such as the region center, area, maximum stress value, and stress gradient direction are recorded parametrically. The final output critical region data is displayed in conjunction with the roof solid point cloud model, allowing for intuitive identification of high stress concentration areas through pseudo-color visualization. For example, in a curved transition zone with drastic curvature changes, if the stress values ​​at multiple points within this zone exceed the material's allowable threshold, the system automatically generates a critical region at that location, indicating that further curvature optimization or plate thickness adjustment is needed.

[0099] Furthermore, the step of calling the optimization algorithm library to perform parameterized adjustments on the critical region and generate optimized curvature data includes:

[0100] S401. Call the optimization algorithm library to determine the corresponding target algorithm. The target algorithm includes gradient descent, genetic algorithm and multi-objective iterative algorithm.

[0101] S402. Based on the critical region, construct an optimization function with the main objective of reducing the peak stress and the constraint of minimizing the increase in material usage. Use the objective algorithm to parameterize and solve the optimization function to generate the corresponding optimized curvature data.

[0102] In this embodiment, parameterized adjustment is used to automatically optimize the local curvature distribution to reduce stress peaks while ensuring the continuity of the structural form. The system first calls the optimization algorithm library and automatically selects the appropriate target algorithm based on the complexity of the roof structure and the characteristics of the stress distribution. When the critical region is relatively concentrated and the curvature changes smoothly, the system preferentially uses the gradient descent method to achieve fast convergence; when the critical region is discrete or the stress distribution has multi-peak characteristics, a genetic algorithm or a multi-objective iterative algorithm is selected to avoid getting trapped in local optima.

[0103] After determining the target algorithm, the system uses the peak stress σ_max as the primary optimization objective, constructing a multi-objective optimization function F=w1·(σ_max / σ_allow)+w2·ΔM, where w1 and w2 are weighting coefficients, and ΔM is the increase in material consumption, used to control the reduction of stress while minimizing material consumption. The algorithm parameterizes variables such as the local radius of curvature R and plate thickness t, and dynamically adjusts the curvature parameters at each coordinate point through iterative optimization, so that the local stress values ​​gradually tend to a uniform distribution.

[0104] During the optimization calculation, the system updates the stress distribution results in real time based on the elasticity model and evaluates the convergence of the objective function after each iteration. The optimization process automatically terminates when the rate of decrease in peak stress falls below a set threshold or the material increase exceeds the constraint conditions. The final output of optimized curvature data contains new curvature radius distribution and plate thickness gradient information, which can be directly used to generate subsequent plate rolling process parameters. For example, when the system detects that the peak stress in a certain arc-shaped transition zone exceeds the limit, the optimization algorithm fine-tunes the local curvature radius of that zone from 3.2m to 3.5m, reducing the maximum stress by approximately 18% while increasing material usage by only about 3%, thus achieving a balance between safety and economy.

[0105] Furthermore, the step of converting the optimized curvature data into sheet metal rolling process parameters to generate the corresponding optimization scheme specifically includes:

[0106] In the preset sheet metal forming database, the sheet metal material type and the corresponding rolling parameter range corresponding to the optimized curvature data are mapped and matched. The rolling parameter range includes the target thickness range, rolling force range, and forming temperature range.

[0107] In this embodiment, the conversion of optimized curvature data into sheet metal rolling process parameters is used to achieve automatic connection between structural design results and manufacturing process instructions. The system first imports the optimized curvature data into a preset sheet metal forming database, which stores rolling characteristic models and corresponding forming process ranges for different metal materials (including aluminum alloys, stainless steel, titanium alloys, etc.). The system automatically identifies the sheet metal type and its mechanical characteristic parameters that best meet the optimized curvature conditions by mapping and matching the curvature radius, sheet thickness gradient, and stress distribution characteristics with standard samples in the database.

[0108] After determining the plate type, the system calculates the appropriate rolling parameter range based on the material's yield strength and plasticity range. Specifically, the rolling force range is determined using the formula P=f(E,R,t,σ_y), where E is the elastic modulus, R is the target radius of curvature, t is the optimized plate thickness, and σ_y is the material's yield strength. The target thickness range is then calculated by combining the plate thickness variation rate Δt / t0 with process constraints. Simultaneously, the system determines the forming temperature range based on the metal's hot deformation properties and recrystallization characteristics, ensuring the material is rolled within a safe plasticity range.

[0109] Ultimately, the system outputs a sheet rolling process parameter table containing the target thickness range, rolling force range, and forming temperature range, and pushes this table as a core component of the optimization scheme to the production-end CNC system, achieving full-process parameter linkage from digital optimization design to intelligent manufacturing. For example, when the optimized radius of curvature is 3.5m and the sheet thickness is 2.4mm, the system automatically matches a 6061-T6 aluminum alloy sheet with a recommended rolling force range of 180–220kN, a target thickness range of 2.3–2.5mm, and a forming temperature range of 390–430℃, ensuring stable mechanical property output while maintaining shape accuracy.

[0110] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0111] In one embodiment, a device for analyzing and optimizing the curvature of complex roof surfaces is provided, which corresponds one-to-one with the method for analyzing and optimizing the curvature of complex roof surfaces described in the above embodiments. For example... Figure 7 As shown, this device for analyzing and optimizing the curvature of complex roof surfaces includes an acquisition module, a creation module, a generation module, an adjustment module, and a push module. Detailed descriptions of each functional module are as follows:

[0112] A device for analyzing and optimizing the curvature of complex roof surfaces, the device comprising:

[0113] The acquisition module is used to acquire the original point cloud data of the target roof, preprocess the original point cloud data, and generate the corresponding roof entity point cloud model.

[0114] A module is established to establish the surface reconstruction algorithm interface of the roof entity point cloud model. Based on the surface reconstruction algorithm interface, the corresponding spatial coordinate point set is extracted to calculate the principal curvature radius and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, thereby generating the corresponding curvature parameter set.

[0115] The generation module is used to input the curvature parameter set into a preset elasticity model, generate the corresponding stress distribution results, and determine the corresponding critical region based on the stress distribution results and the determined allowable stress threshold of the material.

[0116] The adjustment module is used to call the optimization algorithm library to perform parameterized adjustment on the critical region, generate optimized curvature data, and convert the optimized curvature data into plate rolling process parameters to generate the corresponding optimization scheme.

[0117] The push module is used to push the optimization scheme to various application terminals based on the cloud-based collaborative platform.

[0118] Specific limitations regarding the device for analyzing and optimizing the curvature of complex roof surfaces can be found in the above description of the method for analyzing and optimizing the curvature of complex roof surfaces, and will not be repeated here. Each module in the aforementioned device for analyzing and optimizing the curvature of complex roof surfaces can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0119] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for optimizing the curvature of a complex roof surface.

[0120] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0121] S10. Obtain the original point cloud data of the target roof, preprocess the original point cloud data, and generate the corresponding roof entity point cloud model.

[0122] S20. Establish the surface reconstruction algorithm interface for the roof solid point cloud model. Based on the surface reconstruction algorithm interface, extract the corresponding spatial coordinate point set to calculate the principal curvature radius and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, and then generate the corresponding curvature parameter set.

[0123] S30. Input the curvature parameter set into the preset elasticity model to generate the corresponding stress distribution results, and determine the corresponding critical region based on the stress distribution results and the determined allowable stress threshold of the material.

[0124] S40. Call the optimization algorithm library to perform parameterized adjustment on the critical region, generate optimized curvature data, and convert the optimized curvature data into plate rolling process parameters to generate the corresponding optimization scheme.

[0125] S50, based on a cloud-based collaborative platform, pushes optimization solutions to various application terminals;

[0126] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0127] S10. Obtain the original point cloud data of the target roof, preprocess the original point cloud data, and generate the corresponding roof entity point cloud model.

[0128] S20. Establish the surface reconstruction algorithm interface for the roof solid point cloud model. Based on the surface reconstruction algorithm interface, extract the corresponding spatial coordinate point set to calculate the principal curvature radius and Gaussian curvature distribution of each coordinate point in the spatial coordinate point set, and then generate the corresponding curvature parameter set.

[0129] S30. Input the curvature parameter set into the preset elasticity model to generate the corresponding stress distribution results, and determine the corresponding critical region based on the stress distribution results and the determined allowable stress threshold of the material.

[0130] S40. Call the optimization algorithm library to perform parameterized adjustment on the critical region, generate optimized curvature data, and convert the optimized curvature data into plate rolling process parameters to generate the corresponding optimization scheme.

[0131] S50, based on a cloud-based collaborative platform, pushes optimization solutions to various application terminals;

[0132] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0133] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0134] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for analyzing and optimizing the curvature of complex roof surfaces, characterized in that, The method for analyzing and optimizing the curvature of complex roof surfaces includes: Obtain the original point cloud data of the target roof, preprocess the original point cloud data, and generate the corresponding roof entity point cloud model; Establish a surface reconstruction algorithm interface for the roof solid point cloud model, and extract the corresponding spatial coordinate point set according to the surface reconstruction algorithm interface; Generate a neighborhood point set centered on each coordinate point in the spatial coordinate point set, and establish a local coordinate system for each neighborhood point set, using the tangent plane of the local coordinate system as the corresponding coordinate reference plane; The least squares quadratic surface fitting is performed on the neighborhood point set projected in the coordinate reference plane to generate the corresponding local surface expression, and the first principal curvature and the second principal curvature at the corresponding coordinate point are calculated based on the local surface expression. The corresponding principal curvature radius is calculated based on the first principal curvature and the second principal curvature. Based on the principal curvature radius, the first principal curvature and the second principal curvature, the corresponding Gaussian curvature and mean curvature are calculated, and integrated to generate local curvature result data containing principal curvature radius, Gaussian curvature and mean curvature. The local curvature result data is associated and stored with the corresponding coordinate points to generate a corresponding curvature parameter set; The curvature parameter set is input into a preset elasticity model to generate the corresponding stress distribution results; The allowable stress threshold for the corresponding roofing panel is determined in a preset material property database. The allowable stress threshold is a stress limit value preset based on material parameters. By comparing the stress values ​​at each coordinate point in the stress distribution results with the allowable stress threshold, a set of coordinate points that exceed the allowable stress threshold is determined. Based on the spatial distribution of the coordinate point set, a corresponding critical region is generated to characterize the local area where stress exceeds the limit on the roof surface. The optimization algorithm library is called to perform parameterized adjustment on the critical region, generate optimized curvature data, and convert the optimized curvature data into plate rolling process parameters to generate the corresponding optimization scheme. Based on the cloud-based collaborative platform, the optimization scheme is pushed to various application terminals.

2. The method for analyzing and optimizing the curvature of complex roof surfaces according to claim 1, characterized in that, The step of preprocessing the original point cloud data to generate the corresponding roof solid point cloud model includes: The original point cloud data is acquired and preliminarily filtered according to environmental parameters to extract an initial point cloud subset containing effective spatial coordinate information. The effective spatial coordinate information is used to extract the corresponding spatial coordinate point set through the surface reconstruction algorithm interface. Based on the neighborhood density and reflection intensity characteristics of each point in the initial point cloud subset, noise filtering operation is performed to generate corresponding valid point cloud data. Based on the temperature field data and scanning device attitude information recorded during acquisition, temperature deformation compensation calculation is performed on the effective point cloud data to generate geometrically corrected standardized point cloud data. Based on the standardized point cloud data, the spatial surface node distribution is reconstructed to generate the corresponding roof entity point cloud model.

3. The method for analyzing and optimizing the curvature of complex roof surfaces according to claim 1, characterized in that, The step of inputting the curvature parameter set into a preset elasticity model to generate the corresponding stress distribution results includes: Material constants are determined in a pre-defined elastic mechanical model, including the elastic modulus and plate thickness. Based on the material constants and the curvature parameter set, the stress values ​​at the corresponding coordinate points are determined; Based on the stress values ​​at each of the coordinate points, the corresponding stress distribution results are generated.

4. The method for curvature analysis and optimization of complex roof surfaces according to claim 1, characterized in that, The step of calling the optimization algorithm library to perform parameterized adjustment on the critical region and generate optimized curvature data includes: Call the optimization algorithm library to determine the corresponding target algorithm, which includes gradient descent, genetic algorithm and multi-objective iterative algorithm; Based on the critical region, an optimization function is constructed with the main objective of reducing the peak stress and the constraint of minimizing the increase in material usage. The optimization function is then parameterized using the objective algorithm to generate the corresponding optimized curvature data.

5. The method for analyzing and optimizing the curvature of complex roof surfaces according to claim 1, characterized in that, The step of converting the optimized curvature data into sheet metal rolling process parameters to generate the corresponding optimization scheme specifically includes: In the preset sheet metal forming database, the sheet metal material type and the corresponding rolling parameter range corresponding to the optimized curvature data are mapped and matched. The rolling parameter range includes the target thickness range, rolling force range, and forming temperature range.

6. A device for analyzing and optimizing the curvature of complex roof surfaces, characterized in that, The device for analyzing and optimizing the curvature of complex roof surfaces includes: The acquisition module is used to acquire the original point cloud data of the target roof, preprocess the original point cloud data, and generate the corresponding roof entity point cloud model. A module is established to create a surface reconstruction algorithm interface for the roof entity point cloud model. Based on the surface reconstruction algorithm interface, the corresponding spatial coordinate point set is extracted, and a neighborhood point set centered on each coordinate point in the spatial coordinate point set is generated. A local coordinate system is established for each neighborhood point set, and the tangent plane of the local coordinate system is used as the corresponding coordinate reference plane. Least square quadratic surface fitting is performed on the neighborhood point set projected in the coordinate reference plane to generate the corresponding local surface expression. The first principal curvature and the second principal curvature at the corresponding coordinate point are calculated based on the local surface expression. The corresponding principal curvature radius is calculated based on the first principal curvature and the second principal curvature. The corresponding Gaussian curvature and the mean curvature are calculated based on the principal curvature radius, the first principal curvature, and the second principal curvature. The local curvature result data containing the principal curvature radius, the Gaussian curvature, and the mean curvature are integrated to generate local curvature result data. The local curvature result data is associated with the corresponding coordinate point and stored to generate the corresponding curvature parameter set. The generation module is used to input the curvature parameter set into a preset elasticity model to generate the corresponding stress distribution results, determine the allowable stress threshold of the corresponding roof panel in a preset material performance database, the allowable stress threshold is a stress limit value preset based on the material parameters, compare the stress value of each coordinate point in the stress distribution results with the allowable stress threshold to determine the set of coordinate points that exceed the allowable stress threshold, and generate the corresponding critical region based on the spatial distribution relationship of the set of coordinate points to characterize the local area of ​​stress exceeding the limit on the roof surface; The adjustment module is used to call the optimization algorithm library to perform parameterized adjustment on the critical region, generate optimized curvature data, and convert the optimized curvature data into plate rolling process parameters to generate the corresponding optimization scheme. The push module is used to push the optimization scheme to various application terminals based on the cloud-based collaborative platform.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for optimizing the curvature of complex roof surfaces as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for optimizing the curvature of complex roof surfaces as described in any one of claims 1 to 5.

Images