116 results about "Material Design" patented technology

The invention belongs to the technical field of high-performance composite materials, and discloses a carbon fiber reinforced thermoplastic composite material performance database, a construction method and application thereof, and the method comprises the following steps: S1, database structure construction; s2, experimental sample collection and data standardization; s3, feature engineering and variable reduction; s4, training a machine learning model; s5, constructing and verifying an adaptive model; and S6, data expansion and feedback optimization. According to the method, material performance prediction and formula parameter reverse design under target performance are realized through systematic acquisition and normalization processing of three types of data of material components, preparation process and performance characterization and building of a nonlinear mapping model among a material structure, a process and performance through a machine learning method. The database can be used for intelligently recommending a high-performance composite material combination scheme, is suitable for rapid screening and customized development of various thermoplastic composite materials, effectively reduces the research and development cost and development cycle, and improves the material design efficiency.

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 belongs to the technical field of concrete material design, and particularly relates to a data-driven concrete mix proportion multi-objective collaborative optimization method and system.The method comprises the steps that firstly, a concrete test data set is obtained, and the concrete test data set comprises concrete components, the curing age and the compressive strength; then, a BP neural network model is trained by utilizing the concrete test data set, and a multi-objective optimization model is constructed by taking cost minimization and carbon emission as objectives on the premise of preset compressive strength based on the trained BP neural network model; and finally, solving the multi-objective optimization model to obtain a Pareto optimal solution set, and outputting an optimal concrete mix proportion scheme under preset compressive strength. According to the method, concrete compressive strength constraint is set, only double-objective optimization needs to be considered, the calculation efficiency can be improved, meanwhile, the curing age of the concrete is taken into consideration during compressive strength prediction, and the accuracy of a compressive strength prediction result can be improved.

The invention relates to an intelligent design method of a radiation shielding material based on cross-scale error feedback lock step, which comprises the following steps: determining a material component set and acquiring an atomic-scale graph structure of the material component set, and extracting intrinsic performance parameters such as heat conductivity and attenuation coefficient through an atomic-scale prediction module; and then, constructing a design variable vector in combination with a multi-physical field condition, calculating equivalent performance parameters of the composite material, establishing a cross-scale lock step mechanism, and triggering a molecular dynamics and Monte Carlo recalculation module to carry out correction when the deviation between a predicted value and a mesoscopic recalculation result exceeds a limit. Based on the correction parameters, a candidate material scheme is generated by using a multi-objective optimization algorithm; and performing gamma-ray and neutron shielding performance simulation on the candidate schemes through a Monte Carlo radiation transfer model accelerated by a deep neural network, and comparing with an experimental result to realize self-adaptive material design driven by cross-scale errors. According to the method, the design precision and efficiency of the radiation shielding material are remarkably improved.

This invention discloses a rapid modeling method for large-size composite structures with variable thickness solid meshes based on a yarn model, belonging to the field of finite element modeling of fiber-reinforced composite materials. Its core process includes: for a large-size component S to be analyzed, generating yarn models for each ply partition using composite material design software and batch-dividing triangular meshes; similarly, extracting smooth surface profiles from the three-dimensional geometry of the overall component S and generating a structured shell mesh as the base carrier; then, using a voxel hash-accelerated spatial Boolean intersection algorithm to automatically identify the element sets of each ply partition between each yarn mesh and the overall shell mesh, generating a stepped solid mesh through normal offset, ensuring interface compatibility through node merging, and finally assigning material properties and generating an analysis model that can be directly submitted for solution. This invention significantly reduces manual workload and error risk, providing an efficient and reliable preprocessing solution for the curing deformation and strength analysis of composite material structures.

The invention provides a multi-objective optimization method for material performance, and belongs to the technical field of material science and artificial intelligence, and the process of the method provided by the invention takes a small sample learning model as a core, combines an active learning optimization strategy, and realizes quantitative optimization of multi-objective performance indexes in material research and development in an extreme service environment. According to the method, limited test data are fully utilized for learning, and the number of physical tests is remarkably reduced; through intelligent optimization search, the efficiency and the success rate of searching for the material design scheme meeting the multi-target performance requirement are improved, and the method has important significance in accelerating development of new materials in a severe environment.

The invention discloses a composite material four-nail connection structure strength prediction and bolt layout optimization method based on a physical information neural network, and belongs to the technical field of composite material design. The method comprises the following steps: carrying out simulation modeling and verification on the composite material four-nail connection structure; generating and expanding a basic data set; constructing and training a physical information neural network model; performing system calibration and verification on the prediction precision and generalization ability of the physical information neural network model by using experimental data; and constructing a composite material four-nail connection structure bolt layout automatic optimization framework, and outputting optimal bolt layout parameters. According to the method, the problem of physical unreasonable prediction of a pure data driving model in a data sparse region is solved, efficient collaborative optimization under geometric constraints of bolt spacing, edge distance and the like is realized, a complete closed loop from rapid strength evaluation to automatic layout optimization is realized, and the design efficiency and reliability of a composite material four-nail connection structure are improved.

The invention relates to the field of environment-friendly packaging boxes, and discloses a multi-modal data fusion environment-friendly packaging box intelligent design auxiliary system which comprises a packaging full-life-cycle heterogeneous atlas database module, a design constraint parameter analysis module, a topological variation index engine module, a compliance and multi-objective optimization module and a parameterization scheme generation module. According to the method, a time dimension is introduced through a topological variation index engine, instantaneous stress in a folding process is calculated in combination with a nonlinear viscoelastic model, physical evolution of a structure is simulated in a virtual design stage, and the fracture risk is predicted; meanwhile, multi-objective optimization is carried out by utilizing a Hash mask mechanism based on laws and regulations and a pruning algorithm, and a compliance design scheme containing production process parameters is output, so that the problems of lack of physical simulation and low compliance verification efficiency in environmental protection material design are solved, and the physical feasibility and the production yield of the design scheme are improved.

The present invention discloses a smart bio-inspired material design platform to satisfy multi-objective material design featuring complex microstructure for the future. the platform sets mechanical properties of a simulative material element via establishing a reduced model. A distribution of the simulative material element is simulated so as to output a material simulative parameter. A deep learning framework is combined in the platform for computing and evaluating an optimal material design that meets a target material parameter. Specifically, the reduced model can be based on data provided by any test of material mechanical properties, and the deep learning framework evaluates whether a biomimetic material design meets demand of the optimal target material parameter according to a standardized reward function model. The platform is applicable to multi-objective simulative material design, and is greatly potential for futuristic applications.

The invention discloses a multilayer wave-absorbing material design method, system, medium and equipment, and the method comprises the steps: building a multilayer wave-absorbing material model through electromagnetic simulation software, taking a radar cross-sectional area RCS as an optimization target, and controlling FEKO to be within a specified target frequency band; sampling electromagnetic parameters in a value range by adopting a Latin hypercube sampling algorithm, performing parameterized simulation on the multilayer wave-absorbing material model, extracting radar cross-sectional area (RCS) values to form a parameter-RCS data set, generating an electromagnetic parameter-RCS data set, training a convolutional neural network, and obtaining a multi-layer wave-absorbing material model; establishing a nonlinear mapping model from the electromagnetic parameters to a radar cross-sectional area (RCS); embedding a proxy model obtained by training into a Bayesian optimization framework, applying an expected improved function to guide a search space, automatically optimizing an electromagnetic parameter combination, and performing FEKO full-wave simulation verification; if the RCS value of the optimization result is lower than the preset threshold value, iteration continues until the performance requirement is met, and the optimal electromagnetic parameter combination is output.

The invention relates to the technical field of computer-aided material design, in particular to a material chemical formula generation method based on performance sensitivity self-adaptive stratified sampling, which comprises the following steps: inputting an element list; querying a performance sensitivity knowledge base to obtain a sensitivity level and an adjustment factor; analyzing the composite elements, extracting multi-dimensional element features, and quantitatively calculating element combination complexity; based on the element number, the sensitivity and the complexity, a corresponding sampling strategy is adaptively selected, and the sampling amount is dynamically allocated; generating a chemical formula and de-weighting; and outputting a chemical formula list and full-process metadata. Through innovation of resource allocation driven by performance sensitivity, composite element atomic-scale analysis, feature space clustering and the like, on the premise that sampling representativeness and chemical rationality are guaranteed, the calculation efficiency is improved by dozens of times to hundreds of times, the response time is reduced to the second level or the minute level, and the method has the advantages of being traceable, extensible and high in universality and has wide application prospects. And the material screening and discovery process is effectively accelerated.

The invention discloses a microstructure mapping modeling and mechanical simulation method suitable for a two-phase structure alloy, and the method comprises the steps: carrying out the self-adaptive median filtering denoising and Retinex enhancement of a metallographic diagram, so as to improve the gray scale comparison of a matrix and a second phase; training a U-Net + + segmentation model by using the enhanced image to complete pixel-level phase region extraction; a two-phase geometric model is established according to the segmentation result, a finite element feature data set is obtained through multi-physics field coupling calculation, lossless fusion and topological consistency verification are conducted on the finite element feature data set and a prior model, and a fusion model is obtained; simulation parameters are set based on actual working conditions, mechanical simulation is executed, and mechanical property parameters and response curves are output. The method can accurately reflect the mechanical behaviors of the two-phase structure alloy under different working conditions, provides a scientific basis for material design and performance optimization, has high universality, and can be widely applied to performance analysis and evaluation of various types of alloys.

The invention discloses a material design method, device and equipment based on positive and negative interaction and a medium, and the method comprises the steps: collecting and sorting the formula process, structural characteristics, property indexes, performance expressions and other data of a material, training a positive prediction model through the data, and enabling the data to predict the property of the material according to the formula process parameters; a reverse optimization algorithm is introduced, possible formula process combinations are reversely deduced or generated according to target properties, the performance of the combinations is evaluated through a forward prediction model, and iterative optimization is performed until the target properties are achieved or a preset threshold value is met, so that the problem that a traditional experimental method needs to be subjected to multi-batch design, test inspection and repeated adjustment is solved; the technical problems of time and labor consumption, low efficiency, difficulty in quickly responding to market and application requirements, extremely high calculation cost for multi-factor strong correlation analysis, and difficulty in realizing quantitative, precise and high-efficiency optimization design in the prior art are solved.

The invention discloses a large model collaborative material multi-objective interactive design and decision-making method, relates to the field of alloy material design optimization, and aims to realize efficient design and multi-objective decision-making of a complex system through a closed-loop process of knowledge graph construction, dynamic agent model optimization, evolutionary algorithm search and large model real-time feedback. The method comprises the steps of constructing a knowledge graph from cross-domain knowledge and interacting with a large model, automatically adapting to a machine learning model and constructing a proxy model library, performing multi-objective optimization by using an evolutionary algorithm, and recommending an optimal design scheme through large model fine tuning and a feedback mechanism. Through the method, the limitation of traditional optimization is broken through, the design efficiency, precision and optimization efficiency are improved, the effectiveness of the design scheme in engineering feasibility and multi-target balance is ensured, and the method has remarkable application value.

The invention discloses a twin crystal nucleation position and variant selection prediction method based on machine learning, and belongs to the crossing field of material science and machine learning. The method comprises the following steps: acquiring microscopic structure data of a deformation material through electron back scattering diffraction, and constructing a multi-dimensional data set containing crystal grain parameters, crystal boundary parameters and deformation mechanism parameters by taking crystal grains and a certain crystal boundary combination as an analysis unit; and then modeling and predicting the twin crystal nucleation position and variant selection respectively by adopting a hierarchical machine learning modeling strategy. According to the method, the twinning behavior in the polycrystalline material can be efficiently and accurately predicted, and theoretical support and a technical path are provided for high-performance metal material design and plastic deformation mechanism research.

The invention provides a copper-based composite material performance prediction method based on a space-time attention mechanism, and the method comprises the steps: obtaining a microstructure diagram and stress-strain data through molecular dynamics simulation, extracting topological features through a diagram attention network, and dynamically adjusting the parameters of a time sequence convolution network; a cross-space-time attention module is constructed, and bidirectional feedback fusion of space feature screening and time sequence feature optimization is realized; and finally, carrying out dimensionality reduction and nonlinear transformation on the fused features through a full-connection layer, and outputting performance prediction values such as yield strength and Young modulus. According to the method, the precision and reliability of performance prediction of the copper-based composite material can be improved, and efficient and accurate theoretical support is provided for material design and performance optimization.

This material designing device is provided with: a search unit (121) that sets a generation condition (21) for generating a three-dimensional structure (23) of a material, the generation condition (21) including information indicating at least one of the characteristic and structure of the material; a cross-sectional image generation unit (123) that generates a cross-sectional image (22) of the material on the basis of the generation condition (21) set by the search unit (121); and a three-dimensional structure generation unit (124) that generates the three-dimensional structure (23) of the material on the basis of the cross-sectional image (22) generated by the cross-sectional image generation unit (123).

1. The name of the design product: the graphic user interface of the interface design software for electronic equipment. 2. The use of the design product: an electronic equipment. 3. The design points of the design product: the interface content of the graphic user interface in the screen. 4. The picture or photo that best indicates the design points: the front view. 5. The use of the graphic user interface: for measurement and observation after data import in the intelligent material design system. The front view is the initial interface of the software.

This invention relates to the field of printer nozzle technology, and more particularly to a high-precision FDM 4D printing nozzle for metal-plastic functional graded structures. The nozzle includes a first feeding device, two second feeding devices, a feeding connector, a water cooling device, a melting and stirring device, a feeding conduit shell, and multiple filament guides. This invention solves the problems of poor material mixing uniformity in existing technologies. In the design and fabrication of plastic functional graded structures, the composite precision and segregation of the plastic directly affect the performance and interface quality of the functional graded structure. Current plastic functional graded structure designs mainly focus on different material content ratios, requiring material design to be completed before molding. This results in a small range of material variability and poor flexibility. Furthermore, uneven plastic mixing directly causes inconsistencies between the functional graded structure performance and the design, severely leading to interface cracking and molding failure.

The invention provides a material microstructure digital design method based on a non-local model. The material microstructure digital design method can be used for controlling the microstructure and performance of a material. The method comprises the following steps: establishing a fractional order Cahn-Hilliard equation model for describing diffusion and phase separation processes of components in a material; selecting non-local parameters to control the phase distribution characteristics of the material; the fractional order equation is solved through numerical values, and material component space distribution under different non-local parameter values is obtained; constructing a material atom model based on the obtained component distribution; and analyzing the performance of the constructed model in combination with molecular dynamics simulation. By regulating and controlling non-local parameters, materials with different microstructures can be obtained under the same component proportion, accurate control of the microstructures and collaborative optimization of multiple properties such as strength, toughness and conductivity are achieved, and the method is suitable for material design in the fields of electronic packaging, high-performance conductors, aerospace and the like.

The invention discloses a multi-modal fusion material design method and system based on material mechanism constraints, and relates to the technical field of material science and artificial intelligence crossing. According to the system, vertical domain data such as a two-dimensional / three-dimensional structure, a performance index, a cost index, a mass production requirement, an environmental adaptability requirement and a service life requirement of a product are integrated through a multi-modal data input module, and domain rules are converted into quantitative constraints through a material mechanism constraint engine; and then cross-modal feature accurate association is realized through a multi-modal feature fusion module driven by an attention mechanism, and finally, a physical feasible complete design scheme is output by a generative design unit in combination with a multi-objective optimization algorithm. According to the method, the problems of mechanism mismatch and poor process adaptability of a traditional multi-modal model are solved, the development cycle is obviously shortened, the design precision is greatly improved, the development cost and risk of new materials are remarkably reduced in the fields of powder metallurgy and additive manufacturing, and the method is suitable for efficient and innovative design of a complex material system.

The application provides a kind of anti-hydrogen embrittlement material design method and system based on deep generative model, belongs to material design field.The method first collects the material composition of anti-hydrogen embrittlement material, hydrogen charging process parameters and corresponding hydrogen embrittlement sensitivity index obtained by experiment, constructs experimental data set, and is preprocessed to obtain training data set;Again, based on deep generative model, a component and hydrogen charging process-performance bidirectional mapping model is constructed, including a component and hydrogen charging process to performance bidirectional mapping network and a generation network acting on performance space, and a loss function is constructed, and the component and hydrogen charging process-performance bidirectional mapping model is trained and verified;Preset target performance, based on the component and hydrogen charging process-performance bidirectional mapping model after training, the composition and hydrogen charging process parameters of anti-hydrogen embrittlement material are designed reversely.The application realizes the composition reverse design of anti-hydrogen embrittlement material from target performance, shortens the material development cycle, and improves the anti-hydrogen embrittlement performance of material.

The invention discloses a composite material for enhancing the electrocaloric effect and a construction method and application thereof, and belongs to the technical field of refrigeration devices. The invention provides a composite material for enhancing an electrocaloric effect, which comprises a ferroelectric material and a relaxation material which are periodically and alternately arranged to form a superlattice structure along a crystal orientation. The effective Hamiltonian method based on the first principle is adopted to construct the structure and quantitatively calculate the electrocaloric effect, the calculation method is high in precision and low in cost, theoretical guidance can be provided for experiments, resources and time are saved, and the material design efficiency is improved. The scheme provided by the invention has a solid physical background, can effectively enhance the electrocaloric effect, is suitable for various material systems, and is beneficial to development of electrocaloric materials, improvement of the efficiency of electrocaloric refrigeration devices and promotion of application of efficient and environment-friendly refrigeration technologies.

The invention discloses a fiber reinforced composite material variable stiffness reliability multi-scale optimization design method, and belongs to the technical field of composite material structure reliability optimization design. The method comprises the following steps: constructing a composite material multi-scale reliability topological optimization model considering material and load uncertainty; an improved single-cycle single-vector chaos control (SLSV-MCC) method is provided, and probability constraints are efficiently and accurately processed by adopting a current design point gradient and a stable factor; and in combination with a normal distribution fiber optimization (NDFO) model, parameterizing a discrete fiber angle to realize synchronous optimization of a macroscopic topology and a microcosmic fiber path. According to the method, the problems of low calculation efficiency and unstable convergence when the existing method is faced with multi-scale and strong-nonlinearity problems are effectively solved, and a lightweight composite material design scheme with high reliability in an uncertain environment can be obtained.

The invention relates to the technical field of cement-based material design, and discloses a machine learning-based cement-based material multi-scale intelligent design method, which comprises the following steps of: constructing a system element database of a cement-based material under nano-scale, micro-scale, meso-scale and macro-scale; based on a machine learning algorithm, training the system element database to construct a machine learning model so as to establish mapping and association among different scales; designing parameters under any scale are input into the machine learning model, forward prediction is executed, and performance and structural features of the target object under the scale are output and obtained; and inputting the performance or structural characteristics of the target object under any scale into the machine learning model, executing reverse derivation, and outputting design elements required for realizing the performance or the structure. The method has the characteristics of intelligence, automation and high efficiency, the labor cost is remarkably reduced, the limitation that a traditional fitting method is long in period and low in efficiency is overcome, and the technical blank of multi-scale information transmission and performance mapping is filled.

The application provides a 3D printing cement-based material design method based on artificial intelligence. The intelligent design method comprises the following steps: determining a mix proportion of component raw materials in the 3D printing cement-based material according to a required performance index and a mix proportion constraint range, wherein the component raw materials comprise cementitious materials, sand, water and admixtures, and the mix proportion constraint range is a preset value range of the amount of each raw material in the component raw materials; determining printing parameters, and a target printing parameter is a printing parameter that meets the printability under the constraint range of the printing parameters and rheological parameters, wherein the constraint range of the printing parameters and rheological parameters is a value range of each printing parameter; and printing the material and testing the performance of the material based on the mix proportion and the target printing parameter. The intelligent design method provided by the application can save design time and cost.

The application provides a multi-target optimization method for material performance, and belongs to the technical field of material science and artificial intelligence. The method process provided by the application takes a small sample learning model as a core, combines an active learning optimization strategy, and realizes quantitative optimization of multi-target performance indexes in material research and development in an extreme service environment. The method fully utilizes limited test data for learning, significantly reduces the number of physical tests, improves the efficiency and success rate of searching for a material design scheme meeting multi-target performance requirements through intelligent optimization search, and has important significance for accelerating development of new materials in harsh environments.

The invention relates to the field of material design, and discloses an aluminum-based material intelligent design method and equipment based on 5G communication and machine learning, and the method comprises the steps: receiving collected data, such as locally preprocessed components and technological parameters, in real time through an edge computing system and a 5G mobile network base station of an aluminum-based material production line; components and process parameters are obtained through a 5G mobile network base station, phase diagram and thermodynamic property calculation is conducted through a thermodynamic database by means of a phase diagram calculation method, and a comprehensive database is established; inputting the components and the process parameters into a plurality of performance index independent prediction models based on a comprehensive database and machine learning; when the predicted value is abnormal, a comprehensive performance prediction model and a non-dominated sorting genetic algorithm are adopted to carry out collaborative optimization on the multiple performance indexes and the comprehensive performance to obtain a Pareto optimal design scheme, and the Pareto optimal design scheme is issued to a production line for trial production and is fed back to a comprehensive database to enable the model to learn and update online. 5G, phase diagram calculation and machine learning are fused, and the design efficiency of the aluminum-based material is improved.

The invention relates to the technical field of material informatics and artificial intelligence, in particular to a method for training and calculating a high-entropy material structure descriptor based on a large language model, and the method is used for a machine learning task of high-entropy material design and performance prediction. According to the 3D chemical structure model of the high-entropy material or the element information in the chemical structural formula, the corresponding information is extracted through the large language model, and the structure descriptor for the high-entropy material machine learning task is automatically calculated according to the element information with the highest utilization rate in the literature and the knowledge base, so that the method has the characteristics of simple operation, reliable data, high speed and the like; and the structure descriptor with the highest literature recognition degree can be obtained through calculation.

The invention relates to the technical field of material design, in particular to an automatic material optimization method, device and equipment based on an integration algorithm, and the method comprises the steps: carrying out the weighted summation of prediction results of a plurality of machine learning fitting models through the integration algorithm on the basis of an automatic material optimization mode, and obtaining a final prediction result. And an optimization result is obtained through an optimization algorithm. Therefore, the problem that the optimization result is inaccurate due to the fact that only one algorithm is used for material optimization at present is solved. The method has an automatic optimization workflow, cleaning, data division, integrated calculation model training and component and process multi-objective automatic optimization of a material design data set can be fully automatically carried out, an optimization scheme report is generated, programming and personnel operation are not needed in the process, the material design efficiency can be greatly improved, and the method is suitable for large-scale popularization and application. And an efficient intelligent tool is provided for material designers.