28 results about "Shape optimization" patented technology

The invention relates to a node semi-rigid modeling-based complex curved surface reticulated shell multi-objective form optimization method. According to the method, through integration of parametric modeling, numerical simulation and a multi-objective optimization algorithm, efficient optimization design of the irregular boundary free-form surface latticed shell structure is achieved. The control point coordinate matrix of the NURBS curved surface is used for generating a geometric model of the complex curved surface reticulated shell, and high-quality grid division is automatically generated; semi-rigid mechanical behaviors of nodes are simulated through combination of a rigid beam and a spring in a numerical model, semi-rigid characteristics of the nodes are integrated into a rod piece unit, and the mechanical performance of the structure is accurately evaluated; and a non-dominated sorting genetic algorithm is adopted, the minimization of the total strain energy of the structure, the minimization of the total weight of the structure and the maximization of the minimum node configuration degree serve as objective functions, and the multi-objective form optimization design of the complex curved surface reticulated shell is completed. The method is suitable for a single-layer latticed shell structure with any node form and any special-shaped contour boundary, and has wide applicability and good transportability.

The invention discloses a variant reconstruction AUV (Autonomous Underwater Vehicle) shape optimization method based on proxy-assisted multi-starting-point space reduction. The variant reconstruction AUV shape optimization method comprises the following steps: establishing a parameterized model of a variant reconstruction AUV; constructing a variant reconstruction AUV shape modeling-grid division-performance simulation automation framework, realizing input of design variables, and automatically performing variant reconstruction AUV shape modeling and watershed grid division; a variant reconstruction AUV shape hydrodynamic force simulation calculation framework is built, and assessment of variant reconstruction AUV hydrodynamic force performance is achieved; generating a plurality of groups of initial samples for a design space of design variables, calculating target function values corresponding to the samples by utilizing the simulation automation framework and the simulation calculation framework, and importing the samples and corresponding sailing resistance into a sample library; and performing optimization in the design space of the design variables by utilizing an agent-assisted multi-starting-point space reduction method to obtain an optimal solution of the variant reconstruction AUV shape design problem. According to the method, the reliability of an optimization result and the design efficiency can be improved, and the optimization time is shortened.

The application discloses a centrifugal pump impeller design method, which comprises the following steps: initial parameter determination; parameterized geometric modeling, wherein the profile lines of the front cover plate and the rear cover plate of the impeller are constructed based on a cubic spline curve, and a blade surface model is generated by controlling point coordinates, a curvature radius and an inlet and outlet angle parameter; manufacturing process coupling design, wherein three-dimensional modeling software is used for parameterized modeling of the impeller, and a cutter kinematics equation of a five-axis machine tool is synchronously introduced; CFD numerical simulation analysis; construction of an artificial neural network; and compound shape reverse optimization. The application solves a three-dimensional RANS equation in a rotating column coordinate system to perform CFD verification, and combines the design strategy of the artificial neural network and the compound shape optimization algorithm to quickly and optimally select an optimal impeller model. The design of the impeller is based on the cubic spline curve to construct an impeller geometric model, and the generative machining technology of the five-axis numerical control machine tool is combined to realize deep cooperation of hydraulic design, three-dimensional modeling and manufacturing process.

The present application belongs to the technical field of image processing, and specifically relates to a three-dimensional face model automatic generation method, which is characterized by the following specific steps: data loading processing, user model generation based on computer vision, user model grid re-topology, model grid local shape optimization, model grid fusion splicing, and output result model. The grid generation method ensures 2D mapping accuracy according to face key points; the grid deformation and smoothing method makes the user model and the standard face model closer in 3D space under the premise of reasonable deformation, so that the mapping is more accurate; the re-topology model grid local shape optimization utilizes original grid information to correct the grid deformity and improve the quality of the model. The model grid fusion splicing adopts the grid deformation and grid smoothing method, so that the output result meets the design requirements, guarantees the integrity and high quality of the model, and reduces the post-processing work.

This invention belongs to the field of vehicle shape optimization design and discloses a method, system, device, and medium for global optimization design of vehicle aerodynamic shape. The method includes: constructing a parametric model of the vehicle based on free deformation technology; dividing the parametric model into regions and arranging control points in each candidate deformation region; analyzing the drag reduction rate of each candidate deformation region under typical deformation modes to obtain an initial design space; reducing the dimensionality of the design variables in the initial design space using principal component analysis to obtain a dimensionality-reduced design space; constructing a Kriging surrogate model and performing global optimization on the Kriging surrogate model using a genetic algorithm to obtain a preferred region; and applying adjoint optimization to the preferred region to obtain the globally optimal shape design scheme. The technical solution of this invention achieves intelligent and efficient global optimization of complex shapes under given constraints.

The application discloses a direct topology and shape optimization method for an existing engineering structure model, relates to the technical field of topology optimization and shape optimization, and comprises the following steps: mapping a finite element simulation model of an original engineering structure based on a regular hexahedron element to determine an approximate optimization simulation model; determining a typical design mode of multi-component non-interference optimization by transforming a design domain state and range based on the approximate optimization simulation model; determining a compatible unified optimization framework by converting the sensitivity of independent or combined application under different sensitivity algorithms based on the typical design mode; and determining a variable grouping strategy based on the compatible unified optimization framework to uniformly apply various manufacturing process constraints to obtain a structure improvement scheme with strong manufacturability. The application realizes a typical design mode by reconstructing an original optimization simulation model, realizes free combination of different optimization algorithms by constructing a unified discrete adjoint equation, and improves optimization efficiency and engineering practicability of multi-component design.

The application discloses a kind of optimization method of battery pack fixing point quantity and position, comprising: the finite element model of body-in-white and battery pack is built;According to the finite element model of body-in-white, the basic stiffness of body-in-white is analyzed;In the finite element model of body-in-white, battery pack fixing point is arranged in high-density mode;Different stiffness index constraints are set, a group of parameter optimization is run, the optimal key fixing point quantity and optimal initial position are determined;According to the optimization result of optimal key fixing point quantity and optimal initial position, non-key fixing point is deleted, the position variable of key fixing point is set, and the shape optimization of the position of key fixing point is carried out.The optimization method of battery pack fixing point quantity and position of the application finds out the optimal quantity and position of battery pack fixing point for the performance target of battery pack, automatically realizes optimization to the quantity and position of battery pack fixing point, and reduces the workload of manual.

The invention discloses a real-time ball target detection method and system based on artificial intelligence. The method comprises the steps of initial detection of a ball target, bounding box zooming, ball adaptive matching degree enhancement, ball credibility index enhancement, ball motion orbit diameter repair, motion orbit diameter smoothing and output of a real-time detection result. The invention belongs to the field of target detection, and particularly relates to a real-time ball target detection method and system based on artificial intelligence. According to the scheme, scaling factors are dynamically adjusted based on credible indexes, direction sensitive scaling is introduced, and insufficient scaling in the high-speed motion direction is avoided; reducing matching failures during rate mutation based on dynamic scaling distance enhancement; shape misjudgment caused by insufficient pixels is reduced based on micro weighted shape optimization; introducing previous three frames of historical credible exponential attenuation items, and filtering instantaneous noise by using historical trajectory continuity; and focusing candidate matching based on the survivability and carrying out rate enhancement fusion, thereby improving the ball target detection effect.

The application discloses a kind of suitable for six-roller cold continuous rolling mill non-oriented silicon steel transverse thickness difference control method, belong to cold-rolled plate rolling technical field.The method includes: design optimization six-roller cold continuous rolling mill S1-S3 rack's edge drop control work roll new roll shape curve;Build cold continuous rolling mill finite element simulation model and verify;Through finite element model simulation analysis edge drop control work roll shape under the influence law of rolling process parameters to transverse thickness difference;With the shape control characteristics of edge drop control work roll shape, propose six-roller cold continuous rolling mill work roll and intermediate roll bending force control strategy.The application can effectively reduce non-oriented silicon steel transverse thickness difference by work roll shape optimization and bending force collaborative control, improve cold-rolled silicon steel product quality and production stability, suitable for six-roller cold continuous rolling mill non-oriented silicon steel batch production.

The application relates to an acoustic metamaterial with a frequency-doubling filtering characteristic and a shape optimization method thereof, the optimization method comprising the following steps: constructing a two-dimensional finite element simulation model, the two-dimensional finite element simulation model comprising a main plate, a thin adhesive layer and an acoustic metamaterial, the acoustic metamaterial having an initial structure, the initial structure being periodically arranged by an initial unit cell structure, and a free-shape boundary being arranged in the initial structure; constructing an optimization model according to a target that a fundamental frequency is a passband and a frequency double is a stopband; adjusting the free-shape boundary on the basis of the initial structure by using a moving asymptote method; and calculating to obtain an optimal structure of the acoustic metamaterial. Compared with the prior art, the application not only ensures that the optimization target can be achieved, but also reduces the complexity of the structure, facilitates processing and manufacturing, and the designed acoustic metamaterial has the frequency-doubling filtering characteristic, and can effectively filter the inevitable system nonlinearity in nonlinear ultrasonic Lamb wave detection.

The present application relates to the technical field of power system high-voltage equipment design and optimization, and specifically provides a GIS disconnector contact shape optimization method based on multi-physical field coupling simulation, which solves the problems of rebound, discharge, ablation and the like in the contact action process. Specifically, the method comprises the following steps: S1: constructing a geometric model of the GIS disconnector; S2: importing the constructed geometric model into finite element simulation software; S3: constructing a multi-physical field coupling simulation model of the GIS disconnector based on the finite element simulation software, and performing preliminary multi-physical field coupling simulation calculation; S4: optimizing the GIS disconnector contact shape using an IPOPT algorithm. The contact shape optimized by the method can effectively reduce the rebound and discharge phenomena generated in the disconnector action process, improve the temperature rise, improve the efficiency, and reduce the probability of occurrence of major dangerous accidents.

This invention belongs to the field of rotor optimization technology and discloses a rotor aerodynamic shape optimization method and system based on airfoil geometric feasibility constraints. It transforms the high-dimensional, complex three-dimensional rotor shape into low-dimensional mathematical vectors using CST and SVD parameterization methods; constructs a large-scale aerodynamic database using the low-fidelity but extremely fast XROTOR tool; utilizes a deep neural network MLP to learn the nonlinear mapping relationship between design variables and aerodynamic performance, constructing a high-precision surrogate model to replace expensive CFD simulations; and finally introduces airfoil geometric feasibility constraints based on modal space Euclidean distance into the SLSQP gradient optimization algorithm, rapidly searching for the global optimal solution within the surrogate model space while ensuring the geometric rationality and manufacturability of the optimization results.

The invention relates to a shape optimization method for helicopter fairing assembly, and belongs to the field of helicopter assembling.The method comprises the steps that deviation distribution of actual manufacturing and theoretical shape of the shape of a helicopter fairing is analyzed; constitutive parameters of fairing composition materials are obtained; establishing a finite element deformation reconstruction model based on a skin theory molded surface; establishing a helicopter fairing assembly finite element model; establishing a helicopter fairing proxy model based on numerical simulation; according to the method, not only can the profile optimization of the weak-rigidity large-span fairing be realized, but also the loading prediction limitation of the fairing under different working conditions can be made up, and theoretical support is provided for the shape optimization design and engineering application of the helicopter fairing.

The application provides a pose reconstruction method, device and system, and relates to the technical field of medicine. The method comprises the following steps: obtaining target information collected by an OFDR system when performing shape sensing on a target; the target information is used to reflect optical signal information of the target at different positions; positioning the target based on the target information to obtain an end position; performing reverse pose reconstruction on the target by taking the end position as a starting point to obtain initial pose information; the initial pose information comprises a plurality of shape points of the target; performing shape optimization on the target based on each shape point in the initial pose information to obtain optimized target pose information; and the target pose information is used to describe the spatial pose of the target. The application solves the problem that the accuracy of pose reconstruction in related technologies is not high.

This invention belongs to the field of structural dynamics technology, specifically relating to a multi-objective shape optimization method and system for non-uniform material blades of rotating machinery. The method includes: obtaining initial geometric and material parameters of the blade; initializing blade geometric control point parameters according to the range of design variables; constructing a blade material model and geometric model based on the blade geometric control point parameters, node vectors, and basis function orders; establishing a strength analysis model to obtain Von Mises equivalent stress; establishing a vibration analysis model to obtain the blade's vibration frequency; obtaining the blade mass; and inputting the Von Mises equivalent stress, blade vibration frequency, and blade mass into an optimization algorithm for multi-objective optimization to obtain the optimal solution set and optimal individual set. This invention effectively overcomes the limitation of traditional gradient-based methods that easily get trapped in local optima, providing an efficient optimization tool for the complex design of high-performance blade structures made of novel materials.

Techniques for level-set based shape optimization with shape constraints include simulating a state of a current shape of a component, calculating a sensitivity of an objective function to with respect to modification to the current shape based on the simulated shape based on the simulated state, generating a source function for an optimization equation based on the sensitivity, adding one or more constraint terms to the optimization equation based on one or more constraints on an interface of the shape to generate a constrained optimization equation, solving the constrained optimization equation to generate a solution to the constrained optimization equation, updating a velocity field based on the solution to the constrained optimization equation, solving a transport function based on the updated velocity field to generate a solution of the transport equation, and updating the current shape based on the solution to the transport equation to generate an updated shape.

This invention discloses a method for optimizing the shape of irregular plate structures based on modal frequency modulation, comprising: determining the shape optimization variables and variable ranges of the irregular plate structure and initializing the shape optimization variables; obtaining other geometric dimensions and material property parameters of the irregular plate structure; extracting modeling information for constructing a geometric model from the other geometric dimensions and material property parameters; constructing deformation displacement vectors in three directions of the irregular plate structure based on the modeling information and obtaining the stress-strain relationship of the structure; deriving the potential energy and kinetic energy of the irregular plate structure based on the stress-strain relationship; performing variational processing on the potential energy and kinetic energy to obtain the vibration control equation of the irregular plate structure; calculating the vibration control equation and obtaining the frequency result of the irregular plate structure; determining whether the frequency result meets the preset convergence condition; if it meets the condition, outputting the variable values ​​and frequency result; if it does not meet the condition, re-initializing the shape optimization variables until the preset convergence condition is met.

The invention discloses an aerodynamic configuration optimization method and system based on a two-stage particle swarm optimization algorithm, and solves the technical problem of poor aerodynamic configuration optimization effect caused by the fact that a fixed inertia weight coefficient of a traditional single-stage PSO algorithm is difficult to give consideration to global exploration and local convergence capabilities at the same time in the aerodynamic optimization problem. The method comprises the steps that when aerodynamic configuration optimization needs to be carried out, a first-stage particle swarm is initialized based on a predefined class shape transformation variable value range, and a global optimal value sequence is constructed and output through a random inertia weight strategy in combination with predefined learning factors, particle historical individual optimization and population global optimization; second-stage particles are obtained through three times of B-spline screening, the second-stage particles are iteratively updated by adopting a predefined fixed inertia weight and a learning factor to determine target global optimal particles, finally, the geometric shape coordinates of the airfoil profile are calculated based on the class shape transformation variables corresponding to the particles, and aerodynamic shape optimization is achieved.

A coaxial loudspeaker with a horn and a shape optimization method therefor are provided. The coaxial loudspeaker includes: a woofer unit; a tweeter unit; and a horn having an inner cavity, an open upper end and an open lower end. The tweeter unit comprises a high-pitch cone, the horn surrounds the high-pitch cone, a lower end portion of the horn is connected to the tweeter unit, and an upper end portion of the horn has the largest inner diameter.

The invention relates to the technical field of data processing, and provides a retaining wall shape optimization method and device based on an atomic search optimization algorithm, and the method comprises the steps: building a target function through the volume of a retaining wall with the minimum unit width based on the standard proportion of the retaining wall according to the predetermined key shape parameters of a plurality of retaining walls; randomly generating a plurality of groups of key body shape parameters under the same working condition to obtain initial body shape parameters, calculating corresponding mechanical indexes based on each group of initial body shape parameters and corresponding loads, obtaining preset constraints according to design specifications, and generating fitness function values according to the mechanical indexes, the preset constraints and a target function; and carrying out iterative optimization on the fitness function value by adopting an atomic search optimization algorithm to obtain an optimized body type parameter. According to the method, a standardized and reproducible technical path is provided for optimizing the shape of the retaining wall, the dependence on personal experience is reduced, and the design quality and the efficiency stability are guaranteed.

The invention discloses a water delivery system air tank body type optimization method based on self-adaptive sampling, and belongs to the technical field of water hammer protection of long-distance water delivery (regulation) engineering. According to the method, in a preset interval of main body shape parameters of an air tank, Latin hypercube sampling is adopted to generate a small number of initial samples, a water delivery system pressure extreme value and in-tank water level changes are obtained through hydraulic transient simulation, a target function is calculated, an initial training data set is constructed, and a deep neural network agent model is trained to replace high-cost simulation. And then, performing global optimization on the DNN proxy model by using a particle swarm algorithm, selecting a current optimal point and a farthest point relative to an existing sample according to an optimization result, performing adaptive incremental sampling to expand a training set, and iteratively updating the DNN model until convergence. According to the method, the simulation frequency is greatly reduced while the optimization precision is guaranteed, the calculation cost is remarkably reduced, and an efficient and reliable design approach is provided for optimization of the air tank type of the long-distance water conveyance project.

The invention provides a gas compressor non-axisymmetric end wall modeling method based on adjoint shape optimization, and belongs to the technical field of aero-engine gas compressor design. Specifically, an axisymmetric end wall gas compressor serves as an optimization object, and cascade single-channel original geometric model establishment and structured grid division are sequentially completed; the method comprises the steps of obtaining isentropic efficiency of a gas compressor designed by adopting an axisymmetric end wall through flow field simulation, establishing an optimization target and constraint conditions, solving design variable sensitivity based on an adjoint shape optimization method, arranging control points on the outer surface of the end wall, calculating the total displacement of the control points in combination with the sensitivity, and achieving end wall grid deformation through a radial basis function. And carrying out simulation verification on the performance of the geometric configuration of the current end wall, and then carrying out iterative optimization until the end wall accords with an optimization target and constraint conditions. The optimization efficiency and the modeling precision of the end wall of the gas compressor are improved, the isentropic efficiency of the gas compressor is improved, and it is guaranteed that performance parameters of the optimized gas compressor are stable.

This invention discloses a method for optimizing the shape of a spatial reticulated shell structure based on a genetic algorithm, relating to the field of data processing technology. The method includes: generating a topological knowledge graph of structural force paths based on node force characteristic data to extract feature vectors representing the integrity and coherence of the main load-bearing paths; using the feature vectors as input and the integrity and coherence of the main load-bearing paths as a reward function to determine the perturbation sequence of key nodes, and encoding the node coordinates using a genetic algorithm; obtaining the optimized positions of structural nodes through population iteration and fitness evaluation; identifying regions of missing non-functional force paths in the structure and updating the digital twin model until the integrity and coherence of the main load-bearing paths meet the optimization threshold, and outputting the optimized geometric shape of the reticulated shell structure. This invention achieves accurate identification and perturbation optimization of key nodes in spatial reticulated shell structures, thereby significantly improving the integrity and coherence of the main load-bearing paths.

Techniques for level-set based shape optimization with shape constraints include simulating a state of a current shape of a component, calculating a sensitivity of an objective function to with respect to modification to the current shape based on the simulated shape based on the simulated state, generating a source function for an optimization equation based on the sensitivity, adding one or more constraint terms to the optimization equation based on one or more constraints on an interface of the shape to generate a constrained optimization equation, solving the constrained optimization equation to generate a solution to the constrained optimization equation, updating a velocity field based on the solution to the constrained optimization equation, solving a transport function based on the updated velocity field to generate a solution of the transport equation, and updating the current shape based on the solution to the transport equation to generate an updated shape.

This invention relates to the field of crane welded structure analysis technology, specifically a method for simulating and evaluating stress distribution in crane welded structures. The method includes: collecting design parameters and service load data such as weld geometry, material properties, and working load spectrum; constructing a parametric finite element model containing a refined mesh of the weld region based on this data; performing nonlinear stress analysis on the model using a stress distribution solver to obtain stress distribution characteristics including stress concentration factors, stress gradients in the heat-affected zone, and overall stress cloud diagrams; performing multi-criteria strength evaluation on the stress distribution characteristics to generate a strength safety factor and identify potential failure areas; and automatically generating a set of structural optimization suggestions, including weld shape optimization and stiffener layout adjustment schemes, based on the evaluation results. This invention achieves accurate quantification and evaluation optimization of the stress state of welded structures in a closed loop, improving the reliability and efficiency of crane structural design.

The invention discloses a pumped storage power station diversion shaft and surge shaft combined arrangement structure finite element calculation method and system, and the method comprises the following steps: a pumped storage power station diversion system shaft and surge shaft combined arrangement model and a pumped storage power station diversion system shaft and surge shaft non-combined arrangement model are established, and the models comprise a turning pipe, a surge shaft shaft, an overlying rock mass and the like; selecting a proper material for the model, dividing model grids and determining calculation coordinates, and then determining calculation boundary conditions according to the working condition of the surge shaft; the stress conditions of linings of the diversion shaft and the surge shaft in different arrangement forms are researched by adopting an elastic theory and combining a finite element analysis method, and the stress rule of the joint of the turning section and the connecting pipe is disclosed. And according to a calculation result, carrying out surge shaft lining shape optimization design. The finite element calculation and optimization analysis method of the diversion shaft and surge shaft combined arrangement structure serves as a reference for optimization design of the surge shaft body type of the pumped storage power station diversion shaft and surge shaft combined arrangement.

This invention belongs to the field of road traffic noise reduction technology, and relates to a sound barrier shape optimization method based on the singular boundary method of isogeometric geometry. This method combines isogeometric analysis with the singular boundary method to optimize the sound barrier shape more simply and accurately, improving optimization efficiency. Specifically, it includes the following steps: establishing a geometric model of the sound barrier based on its geometric parameters; extracting information from the established geometric model and importing it into the program to obtain the interpolation points of the geometric model boundary, which are then used as the boundary points of the singular boundary method; establishing a sound barrier shape optimization model using known acoustic control equations; calculating the set objective function and constraints using the optimization model, and iterating the results using the moving asymptote method to obtain the optimal value; and outputting the final optimized shape of the sound barrier. This method avoids repetitive modeling processes during optimization, eliminates the need for mesh generation and numerical integration, and boasts high overall speed, high efficiency, and reliable principles.

The invention discloses a lightweight design method for an integrated structure of an attitude control power system, which comprises the following steps of: firstly, according to design input, carrying out strength analysis on a loading load of the attitude control power system structure, defining a design domain and a non-design domain of the attitude control power system structure, and designing a target function and a constraint condition; the method comprises the following steps: carrying out lightweight design on a structural design domain by adopting an optimization mode of integrating topological optimization, size optimization, shape optimization and morphology optimization, designing an optimal force transmission path according to an optimization result, reconstructing an attitude control power system structural model according to the optimal force transmission path, and carrying out strength check on the reconstructed model. High performance, low weight and low production energy consumption of the attitude control power system are organically combined, and the overall rigidity of the attitude control power system is improved.