60 results about "Iterative design" patented technology

Digital model platform that enables the streamlined creation and management of digital twins and physical twins by leveraging external feedback and artificial intelligence (AI) is disclosed. Methods and systems for a model collaboration platform that facilitate the integration of external feedback, whether from physical, virtual, or human sources, into the streamlined design, validation, verification, certification, assembly, operations, and maintenance processes of complex systems. Updated results are output to those external sources, including physical twins, other digital twins or models and simulations, and / or human users. External feedback includes feedback data from physical prototypes and their environment, virtual prototypes, simulations, and subject-matter experts. Embodiments are directed to integrating external feedback into the assembly and system-level assessment of digital twins, physical twins, digital threads, and the iterative design of constituting digital engineering models, including constructing, maintaining, and improving digital engineering models for the design, validation, verification, certification, operations, and maintenance of complex systems.

The invention belongs to the technical field of composite material design, and discloses a polyimide-based composite material design method and system based on experiment-machine learning collaborative optimization. The method comprises the following steps: S1, experimental database construction and machine learning performance modeling; S2, machine learning model construction and training; S3, model evaluation and performance index output; and S4, intelligent design of the polyimide-based composite material. The multi-objective performance collaborative optimization design and preparation of the polyimide-based ternary carbon heterostructure composite material are carried out by taking experimental data as a main material and machine learning as an auxiliary material. According to the method, an experiment-model-optimization closed-loop iterative design system is constructed based on an experiment-machine learning collaborative optimization method, the method has the advantages of high prediction precision, high optimization efficiency, good multi-target adaptability and the like, the development efficiency of the polyimide-based composite material is remarkably improved, and the development cost of the polyimide-based composite material is reduced. The method is suitable for intelligent design and large-scale application and popularization of the high-performance heat-conducting electromagnetic shielding material.

The invention provides an integrated circuit chip electromagnetic interference intelligent suppression and shielding method and system, and relates to the technical field of integrated circuits, and the method comprises the steps: collecting chip electromagnetic interference data, and carrying out the time-frequency domain decomposition and feature extraction, so as to obtain an initial electromagnetic interference feature vector; calculating an electromagnetic interference threat index based on state space mapping and action space search, and further evaluating the electromagnetic interference situation and determining the minimum shielding strength; carrying out optimization design on the electromagnetic shielding structure by adopting a gradient-guided genetic algorithm to obtain an optimal shielding structure parameter; real-time electromagnetic interference data are adjusted according to the parameters, the suppression ratio is calculated, and iterative design is carried out by combining the suppression ratio optimization genetic algorithm. According to the invention, intelligent evaluation and dynamic suppression of electromagnetic interference are realized, and the accuracy and adaptability of shielding structure design are improved.

The invention discloses a truss type load-bearing structure time domain dynamics topological optimization method and system based on an intrinsic orthogonal decomposition method, and relates to the technical field of truss type load-bearing structure topological optimization. The method is provided for solving the problems of high calculation power and the like caused by large-scale space-time response iteration of original transient problems and intensive calculation of dual problem sensitivity analysis in the prior art. According to the method, a local geometric control strategy for the cross interference problem of rod piece units is introduced, and a transient dynamics full-order topological optimization model of the truss structure is established through an equal geometric stiffness diffusion method. Based on an intrinsic orthogonal decomposition method, a transient dynamics reduced-order model of a truss structure is constructed, a reduced-order model base is updated in real time through an incremental singular value decomposition method, and then efficient solving of a transient dynamics equation and an adjoint equation in sensitivity analysis is achieved. And updating an iterative design variable by adopting a penalty function method, and seeking the optimal layout design of the truss structure. The invention provides a time-domain dynamics topological optimization method of the truss type load-bearing structure based on an intrinsic orthogonal decomposition method, and the method can be used for efficiently solving the dynamics layout optimization problem of the truss structure under the action of a transient load.

The invention discloses an icing wind tunnel cloud spray nozzle design method, device and equipment and a medium, and the method comprises the steps: S1, preliminarily determining the layout of a spray rake and the number of spray nozzles according to the section size of the position of the spray rake in an icing wind tunnel; s2, according to existing super-cooled large water drop frozen hairy rain conditions, the cloud and mist requirements are determined; s3, according to the liquid water content LWC and the speed requirement of the wind tunnel test section, the nozzle water supply demand quantity and the single-nozzle water supply demand quantity are analyzed; s4, preliminarily designing a nozzle combination mode of the spraying system according to the water supply flow and the water supply parameters; s5, performing analog simulation of cloud-air bidirectional coupling heat transfer in the icing wind tunnel on the nozzle combination mode; and S6, analyzing a simulation result, evaluating whether the particle size requirement of the frozen hairy rain cloud is met, if so, completing the cloud nozzle design, and if not, returning to the step S4, optimizing the distance and combination of the nozzles, and carrying out iterative design. According to the method, the design iteration period is shortened, and the test cost is reduced.

One embodiment of a computer-implemented method includes receiving the plurality of design constraints defining properties of a machine assembly, receiving a first selection of a first part in a user interface, the first part selected from a virtual parts inventory, identifying, using a generative machine learning model, a second part from the virtual parts inventory connectable to the first part based on the plurality of design constraints and a second selection of a first location within the first part, and displaying the first part and the second part in a user interface, wherein the first part and the second part comprise a first portion of the machine assembly.

An optimization method for a fuel control device structure based on additive manufacturing includes: performing a basic arrangement analysis and a selection of the fuel control device structure; performing an arrangement design of a basic component / interface feature structure according to the basic configuration structure; performing an optimization design for a flow channel structure on the basis of determining structural features of all cores, components and interfaces; performing the optimization design for an outer envelope structure on the basis of the flow channel structure; and checking a calculation and optimizing an iterative design of the fuel control device structure through a finite element tool, and determining a structural scheme of the optimal fuel control device. The optimization method gives full play to the technological advantages of additive manufacturing and determines the optimal structural arrangement and flow channel design scheme to meet the product requirements through pure forward design ideas.

The invention provides an efficient parameterization co-simulation method which comprises the following steps: S1, parameterization design: in circuit design software, performing parameterization design on a target circuit, and defining adjustable parameters in the target circuit; s2, data transmission interaction design: defining a data transmission channel and a data transmission format between the circuit design software and the graphical programming software, and then writing a test program in the graphical programming software according to the requirement of the data transmission format; and S3, co-simulation is carried out. According to the method, rapid iteration design can be achieved, potential problems can be rapidly found and solved through an automatic testing process, time and energy of designers are saved, product marketing time is shortened, design accuracy and reliability are improved, production cost is further reduced, product competitiveness is improved, and remarkable economic benefits are brought to enterprises.

The application discloses a kind of uncertainty quantification driven MEMS sensor intelligent design method and system, the method is first obtained by finite element simulation MEMS sensor experimental data;Then construct and train uncertainty quantification model, obtain the positive mapping relationship from sensor physical structure to performance parameter, and output corresponding uncertainty quantification result;Then construct and train generative model CDDPM, for realizing by expected performance and expected variance to structure parameter inverse design;Finally, construct multi-solution generative model, and efficiently generate multiple sets of structure parameters that meet performance requirements and variance constraints simultaneously.The application does not need to carry out time-consuming multi-physical field simulation and artificial parameter adjustment, with the characteristics of fast speed, high precision and intelligence, which helps to shorten the design cycle and realize rapid iterative design;The application realizes the efficient output of diversified design scheme while giving quantifiable confidence information, significantly improves the reliability of MEMS sensor intelligent design method.

The invention provides a train airtightness iterative design method, system and equipment based on a simulation model and a medium. The train airtightness iterative design method comprises the following steps that an initial empirical relational expression and an initial simulation model are obtained according to a first train of airtight trains; according to the related theoretical relational expression and the initial simulation model, obtaining a whole vehicle air tightness index; according to the initial empirical relational expression and a related theoretical formula, the whole vehicle air tightness index is converted into a part air tightness index; according to the airtightness indexes of the parts, the whole newly-manufactured train is installed and manufactured, and the newly-manufactured train is used as the first airtight train of the next airtightness iteration; according to the method, the static sealing index of each key airtight component is obtained through decomposition based on a simulation analysis method, the problems and defects existing in existing train air tightness optimization design can be solved, and train air tightness meeting the requirements is obtained according to simulation and test data of an existing train combination line and used for guiding and optimizing subsequent product air tightness design. The system also has the same beneficial effects.

This invention discloses a product packaging iterative design system and method based on data analysis, relating to the field of product packaging technology. The invention acquires a simulated packaging process of the product being placed into a packaging shell, marks primary damage risk points, generates a static matching degree map in the static state after simulated packaging, applies environmental load parameters simulating the transportation environment to the static matching degree map, analyzes the relative displacement and internal stress redistribution between the product and the packaging shell, assesses their impact on the deterioration of primary damage risk and static matching degree, identifies points that exacerbate damage risk, adjusts the design scheme of the packaging shell, conducts iterative simulation analysis, and selects the packaging shell with the best overall performance as the final design scheme. This solves common quality problems in cross-regional transportation of cold chain food, such as high-altitude bag swelling and extrusion, and high-temperature softening providing space for extrusion, improving the accuracy and efficiency of packaging scheme determination.

The application provides a heavy-duty gas turbine compressor design method, system and medium suitable for multiple working conditions. The method comprises the following steps: in the two-dimensional through-flow inverse problem design stage, through a plurality of set blade profile geometric parameters and a preset artificial neural network proxy model, through-flow loss and lag angle are calculated; based on a positive problem analysis file generated by a positive and inverse problem coupling design, two-dimensional through-flow positive problem analysis is carried out, including judging whether the compressor working margin meets the requirements by calculating a stall factor; for the deviation between the matching parameters of each stage of the compressor and the expected values of the through-flow design, the adjustment amount of the blade profile geometric parameters corresponding to the deviation is predicted through through-flow analysis; and the VGVs control law of the compressor under variable load working conditions is optimized and designed by using the positive problem analysis file and a particle swarm optimization algorithm. The method fully utilizes the positive problem analysis file generated in the positive and inverse problem coupling mode, can reduce the number of iterative designs, and improves the aerodynamic design efficiency.

The invention discloses a process control method and device for rear-end design of a digital chip and EDA tool software, and the method comprises the steps: firstly, carrying out RC automatic calibration on a pre-wiring database according to a design database, a reference database, a reference parasitic parameter information file and / or a preset time sequence calibration target, and then obtaining a parameter configuration file, the parameter configuration file comprises calibration configuration parameters for parasitic parameter extraction and / or time sequence values; and then loading the parameter configuration file in a logic synthesis stage, a layout stage, a clock tree synthesis stage, a wiring stage and / or an ECO stage of physical perception in a digital chip back-end design for RC extraction. According to the calibration configuration parameters, RC extraction or a time sequence value of a certain stage is used as a reference value to guide an RC engine of another stage, and then an optimized RC estimation model is used for iterative design again, so that a calibrated RC estimation or extraction model can be applied in different stages, the RC estimation and extraction precision is improved, and the design process efficiency is further improved.

The application relates to a dynamic response analysis method of a gas turbine cylinder elastic support structure, wherein the method comprises the following steps: generating a finite element simulation result of the gas turbine cylinder elastic support structure based on at least one of an isotropic loss factor, a structure size, an elastic modulus and an acting load of the gas turbine cylinder elastic support structure; constructing a firefly optimization algorithm-back propagation FA-BP neural network model; training the FA-BP neural network model by using a training set; evaluating the trained FA-BP neural network model, and generating a dynamic response result of the gas turbine cylinder elastic support structure after the evaluation result meets a preset condition. The embodiment of the application can realize training and prediction of a dynamic analysis model of an elastic support structure, provide a fast iteration method for design optimization, improve the calculation efficiency of elastic support dynamic simulation in the iteration design process, and realize a dynamic simulation method with high efficiency and precision.

One embodiment of a computer-implemented method includes receiving the plurality of design constraints defining properties of a machine assembly, receiving a first selection of a first part in a user interface, the first part selected from a virtual parts inventory, identifying, using a generative machine learning model, a second part from the virtual parts inventory connectable to the first part based on the plurality of design constraints and a second selection of a first location within the first part, and displaying the first part and the second part in a user interface, wherein the first part and the second part comprise a first portion of the machine assembly.

This application discloses an improved iterative design method for multi-channel cosine-modulated filter banks. The aim is to improve the performance of the prototype filter in terms of aliasing error control and system response by introducing constraints on the amplitude-frequency characteristics of the passband and transition band of the prototype filter into the optimization objective. Compared with traditional iterative design methods, the method proposed in this application shows superior performance in these performance indicators. Furthermore, based on the closed-form expression of the objective function given in this application, an iterative solution method can be used to obtain the optimization results, further effectively reducing the computational complexity and implementation difficulty of the proposed method.

The application discloses a symbolic controller design method based on chino polyhedron under linear temporal logic specification, belongs to the technical field of nonlinear system control, and solves the linear temporal logic (LTL) task controller synthesis problem of a nonlinear control system. First, an accepted path is generated for a preset LTL task. Second, a chino polyhedron and a constrained chino polyhedron are used to divide a state space, the divided regions are defined as 'units', adjacent units are allowed to intersect, a unit topology graph is constructed based on the unit intersection relationship, and the realizability of the LTL accepted path is verified. Finally, if the accepted path is realizable, the global LTL task is decomposed into a plurality of local subtasks, a local symbolic model is constructed for each unit, a local symbolic controller is iteratively designed through a 'local to global' control strategy, and combination is completed, so that a symbolic controller satisfying the global LTL specification is obtained. The application supports different units to adopt a differentiated local equivalence relationship, reduces the conservativeness of a single equivalence relationship, reduces the calculation complexity of global approximation, and improves the efficiency and practicability of controller synthesis.

A single pilot mode under the scene multiple task coordination iterative design method constructs single pilot mode scene operation task coordination architecture; through scene modeling software Prepar3D, nominal process of the scene is modeled, and after exporting the nominal task and time information of key points required to be executed in the single pilot mode scene operation process, multiple non-nominal tasks are set, the final single pilot mode scene operation scene is formed, and system model construction is carried out on the scene operation scene through system modeling software MagicDraw; then, time interval data of the nominal flight process and non-nominal flight process in the single pilot mode scene operation process are extracted, a fault tree is constructed, and DiCluster algorithm is used to carry out time interval sequence mining and analysis on the above data, iterative design is carried out based on the mining and analysis results, and the above process is repeated; finally, safety index comparison and analysis of the front and back designs are carried out. The simulation verification platform is built to carry out iterative design on the single pilot mode scene operation architecture and process, and finally the safety is improved.

The application provides a full-compass iterative design method and system of a special heavy ice area door-type tower applied to a digital power grid, and relates to the technical field of digital power grids.In the application, first, basic parameter information of the door-type tower is acquired.Then, the minimum value of the height difference of the sub-tower is determined based on the maximum slope of the terrain, and the height of the sub-tower is configured.Next, the vertical length value range of the tower leg of the sub-tower is determined according to the angle threshold value between the sub-tower inclined material and the horizontal plane and the main material, and the self-adaptive terrain slope value of the sub-tower is calculated, and the tower leg length meeting the requirements is selected for configuration.Further, based on the principle that any tower leg may be the longest or shortest tower leg, the tower leg lengths are randomly combined to obtain multiple configuration schemes.Finally, the internal force of the main material of the door-type tower under each scheme is calculated, and the most unfavorable internal force is selected for bearing capacity judgment.The application improves the design precision, enhances the safety of the power grid, improves the design efficiency, adapts to complex terrain, and promotes the transformation of the power grid to digitization and intelligentization.

The invention discloses a model shrinking method for a ship and bridge collision experiment. The method comprises the following steps: simplifying a ship and bridge collision model; establishing a ship-bridge collision dynamics similarity model; based on the established mechanical similarity model, carrying out ship and bridge collision model shrinkage verification; on the basis of a model shrinkage verification result, performing model shrinkage model optimization iteration; and an optimized shrinkage model is obtained. The invention provides a systematic model shrinkage design method based on geometric similarity, material invariance and dynamic similarity principles. According to the method, a system verification system of an energy consumption path, a force-displacement curve and a failure mode is constructed, and the consistency of a mold shrinkage result and a full-size prototype in multiple dimensions is ensured. According to the optimization iteration design method of the shrinkage model, accurate reduction of complex plastic deformation and energy dissipation characteristics of the ship bow in collision can be achieved.

Digital model platform that enables the streamlined creation and management of digital twins and physical twins by leveraging external feedback and artificial intelligence (AI) is disclosed. Methods and systems for a model collaboration platform that facilitate the integration of external feedback, whether from physical, virtual, or human sources, into the streamlined design, validation, verification, certification, assembly, operations, and maintenance processes of complex systems. Updated results are output to those external sources, including physical twins, other digital twins or models and simulations, and / or human users. External feedback includes feedback data from physical prototypes and their environment, virtual prototypes, simulations, and subject-matter experts. Embodiments are directed to integrating external feedback into the assembly and system-level assessment of digital twins, physical twins, digital threads, and the iterative design of constituting digital engineering models, including constructing, maintaining, and improving digital engineering models for the design, validation, verification, certification, operations, and maintenance of complex systems.

The present application relates to a kind of equivalent modeling method of acoustic baffle, comprising the following steps, step 1, the finite element model of baffle comprising several periodic units is constructed, according to the conventional simulation process of baffle sound performance, the frequency response table of sound absorption coefficient, reflection coefficient, transmission coefficient is obtained by solving model;Step 2, the finite element model of homogeneous material of same size with the above-mentioned baffle finite element model is constructed, and three parameters a, b, c are set as the Young's modulus, Poisson's ratio and density of homogeneous material.The present application reduces the structural complexity of baffle model, the resources and time required for calculation, is conducive to the rapid iterative design of relevant acoustic structure.

This invention discloses a Python-based parametric modeling method for wind turbine blades, relating to the field of finite element analysis technology. By combining Python with an Abaqus scripting interface, this invention automates the entire process of geometric modeling, model segmentation, mesh generation, material property assignment, assembly arraying, and contact and boundary condition setting for the blade root segment, blade root bolts, flanges, bearings, hub, and hub bolts. The final result is the generation of a semi-model (CAE and INP) file of the blade root. This invention significantly reduces the finite element modeling time for blade roots, decreasing the modeling efficiency from tens of hours using traditional manual methods to minutes. It effectively reduces human error and provides a simple and intuitive interactive interface, offering a reliable technical means for the rapid iterative design and analysis of blade root structures.

The invention discloses a structure response rapid prediction method based on a physical coding graph network. The method comprises the following steps: constructing the physical coding graph network; inputting the physical parameters of the target structure into a physical coding graph network for coding; message passing is carried out on the coded physical parameters, message passing comprises node mapping and edge mapping which are carried out in sequence, and data flow of message passing conforms to mathematical logic; and decoding results of node mapping and edge mapping to obtain a displacement prediction result and an internal force prediction result. According to the invention, through constructing the physical coding graph network, multi-working-condition structure response rapid prediction is realized; the encoding, message passing and decoding processes are matched with complex structure parameters, accurate prediction of displacement and internal force is completed through node mapping and edge mapping in a labor division mode, the problem of repeated calculation of a traditional method is solved, the digital twinning real-time interaction requirement is met, rapid iterative design and real-time performance evaluation are efficiently supported, and a better solution is provided for structural engineering calculation.

The invention relates to the technical field of antenna design automation, and discloses a filtering PI FA antenna parasitic element design method based on a generative adversarial network, and the method comprises the following steps: obtaining a training data set comprising geometric parameter vectors, electromagnetic performance data and geometric rationality labels; constructing a generative adversarial network model which comprises a generator, a performance discriminator for judging the performance matching degree and a geometric rationality discriminator for judging the physical effectiveness; through a total loss function formed by weighting performance loss and geometric loss, performing dual-constraint antagonism training on the generator; and directly generating a parasitic element geometric parameter vector meeting requirements according to an input target performance condition by using the trained generator. Through a unique double-discriminator architecture, the physical realizability and process feasibility of the generation scheme are fundamentally ensured, traditional iterative design is converted into nearly instant model calculation, and the efficiency and accuracy of on-demand design are remarkably improved.

The invention provides an instruction set design method for matrix online parallel general calculation, which analyzes several common large-scale matrix calculation operators in a deep learning algorithm and extracts a general calculation mode. And configuring an instruction type demand model and a behavior model according to a general calculation mode by taking universality and calculation performance as optimization targets. And performing iterative design on the deep learning instruction set according to the constructed instruction type demand model and behavior model, so that the deep learning processor gives consideration to calculation performance and universality.

The embodiment of the invention provides a visualization method for multi-model stress comparative analysis and related equipment, and belongs to the field of stress analysis and the field of data visualization. The method comprises the steps of obtaining a design scheme; converting the node stress data into stress body data; automatically grouping voxels with similar stress modes in different design schemes according to stress body data; performing tree view display: adopting hierarchical tree layout, organizing a plurality of schemes generated in an iterative design process, and providing volume rendering based on a stress value or a stress difference value; and performing comparison view display: arranging voxel groups obtained by segmentation according to rows by adopting matrix layout, arranging different design schemes according to columns, and simultaneously realizing stress comparison analysis among multiple schemes and local stress analysis in a single scheme through visual comparison among rows and columns. According to the method, the stress mode or the stress difference mode in the design scheme is extracted, the overall stress mode and the local stress mode are considered, and engineers are helped to better execute decisions.

The invention provides a drug design digital twinning method and platform based on a pre-training knowledge graph, and the method comprises the steps: constructing the pre-training knowledge graph focusing on drugs, target spots and mechanism paths, and generating a drug structure embedding vector and a mechanism path embedding vector through a graph neural network; a mechanism path is utilized to embed and guide a conditional graph to generate a network, and candidate molecules matched with a target mechanism are generated from a public skeleton; performing conditional graph attention propagation on the candidate molecules in combination with mechanism semantics in the mechanism sub-graph, and simulating multi-dimensional behavior performance of the candidate molecules under a mechanism path; and performing comprehensive scoring based on behavior performance, screening an optimal structure, generating a standardized execution object which can be directly issued to an experimental platform, and extracting a mechanism-structure optimization mode for subsequent iterative design. Closed-loop cooperation of knowledge representation, structure generation, mechanism simulation and experiment execution in drug design is realized, and research and development efficiency, prediction interpretability and result feasibility are improved.

This disclosure relates to the field of aerospace materials technology, and in particular to a rapid vibration fatigue specimen design method and apparatus. It addresses the problems in existing vibration fatigue specimen design technologies, such as long design cycles, high costs, component frequencies exceeding the excitation frequency range of the vibration test bench, or the need for multiple rounds of optimization and iterative design. This disclosure first designs a reference specimen, and then uses the principle of dynamic similarity to rapidly design a vibration fatigue specimen that is simultaneously applicable to the geometric characteristics of the component and the excitation frequency range of the vibration test bench, i.e., determining the specific scaling factor required for the reference specimen. This disclosure only requires the pre-designed reference specimen to rapidly design a vibration fatigue specimen that is simultaneously applicable to the geometric characteristics of the component and the excitation frequency range of the vibration test bench, making better use of existing resources. Compared to the best existing technologies, it improves specimen design efficiency and has the advantages of high speed and strong applicability.

A plurality of design iterations are performed for a flow to design a circuit. The design flow includes a sequence of at least two stages. Each stage generates an output design of the circuit from an input design of the circuit according to a parameter for that stage. The design iteration selects parameter values for slices of one or more stages of the design flow. In a design iteration for at least one slice, a parameter value for a non-final stage of the design flow is selected based on a final result quality (QoR) of the design flow. The design iteration for the slice is adjusted based on the final QoR generated by the design iteration.