553 results about "Materials design" patented technology

The invention belongs to the technical field of steel and iron material design, and discloses a stainless steel strength and toughness collaborative optimization method and system based on heterogeneous integration, and the method comprises the steps: constructing a database of stainless steel components, process parameters and mechanical properties; according to the database, establishing a stacked heterogeneous integration model; quantizing contribution weights of input variables of the stacked heterogeneous integrated model to mechanical properties based on an SHAP method, identifying key factors, and setting a multi-target strength and toughness collaborative optimization index to guide an optimization direction; optimal components and processes are screened according to SHAP analysis, a sample is prepared through vacuum melting, hot rolling and heat treatment, the performance is verified according to the ASTM standard, and a final optimization scheme is determined; and a cross-scale digital twinborn verification system is constructed, and collaborative optimization of alloy components, process and macroscopic performance is realized. According to the method, the problems of low efficiency and insufficient generalization ability of a single model of a traditional trial and error method are solved, and an efficient and explainable intelligent optimization scheme is provided for development of high-performance stainless steel.

The invention discloses a steel fiber reinforced concrete material design method based on multiple performance requirements, which comprises the following steps: acquiring original data of parameters and performance of steel fiber reinforced concrete, and determining a training data set; training the initial convolutional neural network model according to the training data set to obtain a convolutional neural network performance prediction model; using a convolutional neural network performance prediction module to construct a virtual function of the steel fiber reinforced concrete performance as a target function; obtaining constraint conditions of the basic performance parameters corresponding to the target function; based on a genetic algorithm, performing concrete mix proportion optimization on the target function under each constraint condition, screening an optimal scheme meeting a preset performance index, and determining an optimal solution set; an optimal solution set is screened through a TOPSIS method, and an optimal scheme of steel fiber concrete material design is obtained; various properties of the steel fiber reinforced concrete are improved, waste of raw materials is avoided, and sustainable development of building materials is achieved.

The invention belongs to the technical field of high polymer material design and intelligent manufacturing, and discloses a machine learning driven epoxy resin based composite material thermal-mechanical property aided design method, which comprises the following steps: S1, data acquisition and feature construction; s2, performing feature screening; s3, constructing and training an interpretable prediction model; s4, carrying out reverse design and optimization; and S5, performing closed-loop verification and updating. According to the method, the quantitative relation of structure-process-performance is constructed through an interpretable machine learning model, and the contribution mechanism of each factor is revealed by means of SHAP analysis. And finally, reversely designing an optimal epoxy resin monomer structure and a matched curing process according to the performance target. The limitation of a traditional trial and error method is broken through, collaborative optimization of the material structure and the forming process can be achieved, and the development efficiency of the epoxy resin-based carbon fiber composite material is remarkably improved.

The invention discloses a special large language model for a solid waste cementing material and an innovative hypothesis generation method thereof, which realize accurate understanding and reasoning of information such as material composition, process parameters, mechanical properties and the like by constructing a special knowledge graph in the field of materials, combining experimental data vector retrieval and fusing a mixed retrieval enhanced generation technology, so that the innovative hypothesis generation of the solid waste cementing material is realized. And a scientific reasoning module is used for deducing a material design rule to generate a potential innovation hypothesis. The method effectively breaks through the problems of long development period and low innovation efficiency of traditional materials, and is suitable for the fields of low-carbon building material development and solid waste high-valued utilization.

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 discloses a micro proportional valve gradient composite coating and a preparation method thereof, and belongs to the technical field of micro proportional valve surface strengthening manufacturing. Aiming at the corrosion-resistant and wear-resistant requirements of the micro proportional valve under the working conditions of strong corrosion, multiple impurities and high pressure difference, the interface strengthening and corrosion-resistant and wear-resistant performance optimization of a metal matrix and a functional coating are combined, and metal / ceramic / polymer gradient material design, spraying parameter suitability research and a coating porosity / bonding strength control method are covered; the valve core and valve seat protection device is suitable for high-efficiency protection technical systems of valve cores and valve seats of precise instruments such as gas chromatographs and mass spectrometers.

The invention discloses a method for predicting corrosion resistance of a magnesium-lithium alloy based on machine learning, and belongs to the technical field of metal material design. Metal elements participating in prediction comprise Mg, Li, Al, Zn, Si, Ca, Sn, Y, Nd, Gd, Ce, Zr, La, Mn and Er, and the prediction method comprises the following steps: training model parameters by using a training set in an established database based on a machine learning algorithm; and evaluating the model by using a test set, and predicting Ecorr and icorr values of different alloys formed by elements with different contents in the magnesium-lithium alloy. According to the method, the electrochemical corrosion behavior of the alloy with different components formed by multiple different element contents of the magnesium-lithium alloy is predicted through a machine learning algorithm, so that the corrosion resistance of the alloy is effectively judged; and meanwhile, the method plays an important auxiliary role in research on the corrosion resistance of the magnesium-lithium alloy and design of the corrosion-resistant magnesium-lithium alloy in the future, and the problem that the corrosion resistance of the material is rapidly and accurately evaluated at present is effectively solved.

The invention discloses a building composite phase change material intelligent matching and optimizing method based on a large language model, and belongs to the technical field of building energy saving and intelligent material design. Basic thermophysical property data, building environment parameter data and user demand data are collected; a deep reinforcement learning technology is utilized to construct an intelligent model based on a deep Q network strategy, and generated data samples are integrated into a thermophysical property database; outputting a candidate material combination recommendation scheme by adopting a large language model; evaluating the candidate material combination recommendation scheme by using the semantic tag vector and a sorting engine to obtain a performance evaluation result; generating a performance evaluation report according to the simulation model; a multi-agent negotiation algorithm is adopted, cross-regional thermal control performance is optimized, a multi-dimensional performance comparison diagram and tuning suggestions are generated, correction information of designers is recorded, optimization is carried out, and feedback is provided in a self-adaptive mode. According to the method, the building composite phase change material combination is screened, cross-regional thermal control is optimized, adaptive schemes and suggestions are output, and the self-adaptive optimization capability of the system is improved.

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 relates to a data-driven deformation nickel-based superalloy multi-objective performance reverse design optimization method, which belongs to the technical field of metal material design and development, and comprises the following steps: calculating a stable high-strength deformation nickel-based superalloy system based on a first principle, and on this basis, calculating a deformation nickel-based superalloy system; constructing a deformed nickel-based superalloy component design space based on the knowledge of the nickel-based superalloy field; based on a deformed nickel-based superalloy component design space, the deformed nickel-based superalloy component design space is reduced by adopting an empirical formula in combination with thermodynamic high-throughput calculation to obtain the reduced deformed nickel-based superalloy component design space, and based on the reduced deformed nickel-based superalloy component design space, based on machine learning and a genetic algorithm, the deformation nickel-based superalloy component design space is obtained. And a deformed nickel-based high-temperature alloy reverse design model is established, and the deformed nickel-based high-temperature alloy with the target performance is screened. Compared with the prior art, the oriented development method for the high-strength and high-toughness nickel-based high-temperature alloy is achieved by fusing cross-scale calculation, domain knowledge constraint and machine learning reverse design.

The invention discloses a material performance prediction method and device based on a multi-machine learning regression model and a high-throughput experiment, a medium, a product and application thereof, and relates to the technical field of material design and optimization, and the method comprises the steps: obtaining preset material parameters; any performance is determined as the current performance; based on material components in the preset material parameters, determining target key features of the current performance under the preset material parameters; respectively inputting the process in the preset material parameters and the target key features of the current performance under the preset material parameters into a plurality of optimal performance prediction regression models corresponding to the current performance to obtain a plurality of sub-prediction values of the current performance under the preset material parameters; and based on the plurality of sub-predicted values of the current performance under the preset material parameters, determining a total predicted value of the current performance under the preset material parameters. The material performance prediction precision and the research and development efficiency are improved, and the research and development cost is reduced.

To improve efficiency in design of material that is required to satisfy a plurality of characteristics.SOLUTION: A method according to an embodiment of the present invention is a method executed by a prediction system, and the method includes acquiring the composition of and a manufacturing condition for the material; and inputting the acquired composition of and the manufacturing condition for the material to a machine learning model that predicts a plurality of characteristics of the material from the composition of and the manufacturing condition for the material, to predict the plurality of characteristics of the material. The machine learning model is on the basis of the mixture of continuous probability distribution.SELECTED DRAWING: Figure 1

Embodiments relate to system and methods involving use of a technique for managing a database for producing a material composition having a thermodynamic phase. The technique can include: receiving a binary phase diagram for each material to be used as a component of a high-entropy alloy (HEA); using one or more active learning machine learning techniques for generating a feature, the feature including: a primary feature that is representative of a probability that an HEA will exhibit a solid solution phase and / or an intermetallic phase, and a physics-based feature that is representative of a factor related to formation of a desired intermetallic HEA phase; encoding the primary feature and the physics-based feature; generating an output representation of a HEA alloy composition and phase of a predicted materials composition; and selecting a HEA composition and phase that will meet a material design criterion.

The invention relates to an ultra-high-purity silver target material and a preparation method thereof, and belongs to the field of target materials, and the ultra-high-purity silver target material comprises the following raw materials in percentage by weight: 99.99% of high-purity silver, 0.05%-0.15% of palladium, 0.025%-0.075% of iridium, 0.1%-0.3% of neodymium and 0.1%-0.3% of praseodymium. According to the ultra-high-purity silver target material and the preparation method thereof, 5N-grade high-purity silver is adopted as a base material, trace palladium, iridium, neodymium, praseodymium and other elements are accurately added, the purity of the target material is remarkably improved and exceeds the purity range in the prior art, the hardness, strength and abrasion resistance of the target material are optimized through the innovative material design, and the service life of the target material is prolonged. The compact uniformity of the material is effectively improved and the internal stress is eliminated through grain refinement and multi-stage heat treatment, in addition, the isotropy of the target material is enhanced through the multi-directional forging process, the consistency of the performance in different directions is ensured, the mechanical performance of the target material is remarkably improved through the improvements, the target material can better adapt to the application environment with the high wear resistance requirement, and the service life of the target material is prolonged. And meanwhile, the conductivity, the reflectivity and the uniformity of a thin film prepared by using the target material are improved.

The present invention relates to the technical field of concrete. Disclosed is a toughening design method for fiber-reinforced concrete. The method of the present invention changes the passive control characteristics of fibers on a concrete crack propagation process in conventional fiber-reinforced concrete. Starting from the origin of composite material design, firstly, an ultrahigh-ductility composite cementitious matrix is designed; and secondly, an aggregate is incorporated. On the basis of a specific combination of matrix and aggregate parameters, a composite material develops meso-scale multiple cracking and strain-hardening behaviors between aggregate particles during external loading. The fiber-reinforced concrete prepared by this method actively disperses brittle damage and failure within the material, and avoids unstable crack propagation caused by weak interfacial bonding between the aggregate and the matrix. Compared to conventional fiber-reinforced concrete design methods, the present invention more accurately establishes relationships between material compositions, microstructures and macroscopic mechanical response, and more efficiently enhances the toughness of the material.

The invention belongs to the technical field of composite material design, and discloses a polymer composite material design method based on LLM knowledge database construction and reasoning optimization, and the method comprises the following steps: S1, target performance setting; s2, constructing a knowledge database; s3, constructing a reverse design model; s4, constructing a performance verification module; and S5, performing multi-round test-verification design loop optimization. According to the method, an intelligent design method integrating target setting, semantic knowledge database construction, a design assistant, a performance verifier, a prompt engineering module and a language model material knowledge system is provided, closed-loop reasoning and feedback of structure-mechanism-performance are achieved through multiple rounds of DA-VM collaborative optimization, and the design efficiency is improved. The method has the advantages of high design efficiency, strong structure generation rationality, accurate performance prediction, knowledge evolvable and the like, and is suitable for intelligent rapid development of the high thermal conductivity-wave absorbing-shielding-mechanical integrated functional polymer composite material.

The invention discloses a metal material design method based on deep learning, and the method comprises the steps: S1, collecting real chemical component data, forming training samples, carrying out the data preprocessing of the training samples, increasing the number of the training samples through a data enhancement technology, and improving the expression capability of features through a self-attention mechanism; s2, designing a model architecture, wherein the model architecture comprises two basic elements, namely a generator and a discriminator; s3, in the model architecture, generating data similar to real chemical components through a generator, and measuring the similarity between the generated data and actual data by using an objective function; and S4, training the confrontation generation network to balance the generator and the discriminator. The metal material design method based on deep learning has the advantages of convenient operation in the material design process, low cost and convenient use.

The invention belongs to the technical field of functional ceramic materials, and provides a lead-free high-entropy relaxor ferroelectric material and a preparation method thereof.The raw materials of the lead-free high-entropy relaxor ferroelectric material comprise ceramic powder and oxide; the chemical general formula of the ceramic powder is (1-x) (Bi < 0.2 > Na < 0.2 > Ba < 0.2 > Sr < 0.2 > Ca < 0.2 >) TiO < 3-x > La (Mg < 1 / 2 > Zr < 1 / 2 >) O3. The ceramic powder is prepared through a high-entropy strategy, a slender ferroelectric hysteresis loop is obtained at the room temperature, the breakdown field strength of the material is obviously improved, meanwhile, high energy storage density and energy storage efficiency are obtained, the energy storage density reaches 13.5 J cm <-3 >, the energy storage efficiency is 94.6%, and the breakdown electric field reaches up to 750 kV cm <-1 >. According to the material design based on the high-entropy strategy, the relaxation characteristic of the material is remarkably improved, the dielectric loss of the ceramic is effectively reduced, and the practical application potential is shown.

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 discloses an interface enhancement gradient design method of an anti-impact aviation glass laminated structure, and relates to the technical field of composite material design, the method comprises the steps of glass material preparation, interface enhancement gradient design, lamination compounding, quality detection and performance testing, the glass material comprises a glass layer material, a middle layer material and a transition layer material, the laminated composite process comprises the steps of pre-strain treatment, pre-pressing treatment, hot-pressing combination and cooling demolding, and has the advantages that by arranging the transition layers with components and performance in gradient change, the content of reinforcing materials such as nanometer titanium dioxide particles and graphene nanosheets in each transition layer is gradually increased; and compared with a traditional uniform or simple layered structure, the gradient design has the advantage that the phenomenon of interface stress concentration caused by performance difference between the glass layer and the polymer intermediate layer is remarkably reduced.

The present invention belongs to the technical field of metal material design and preparation, and specifically relates to a double heterogeneous structure high-strength plasticity low-density steel and a preparation method thereof. The double heterogeneous structure high-strength plasticity low-density steel proposed in the present invention includes the addition of a large amount of Al elements, which can greatly reduce the material density, and introduces the non-shearable NiAl type B2 phase through Ni alloying, and forms a double heterogeneous structure through multiple rolling and annealing processes. The double heterogeneous structure low-density steel can have higher strength, greater plasticity and higher work hardening rate at a lower density. And the addition of Al and Ni elements can greatly improve the corrosion resistance of steel materials, and the preparation method is simple and economical, and can realize large-scale industrial production. The research and development and application of the finished steel have important economic value and social significance for promoting lightweight material design, improving strength and plasticity, reducing energy consumption, and reducing greenhouse gas emissions.

The invention discloses an information acquisition method and device of an alloy material, electronic equipment and a medium. The method comprises the following steps: acquiring an information query instruction of the alloy material; analyzing the information query instruction through a specified large model to determine a current information query task; the information query task comprises at least one of a general information query task, an alloy performance prediction task and an alloy reverse design task; according to the information query task, calling a target model from a pre-constructed alloy field model library; and executing the information query task through the target model to obtain a target query result. Therefore, the general understanding, reasoning and interaction capabilities of the specified large model and the professional prediction precision and reverse optimization capability of the alloy field model are effectively combined, so that the efficiency, accuracy and intelligent level of alloy material design and discovery are improved, and the rich knowledge requirements of users on alloy material design are met.

The invention provides an isogeometric topology optimization method and device based on thermoelastic metamaterial design, and relates to the field of isogeometric topology optimization. The method comprises the following steps: constructing a multi-material interpolation model corresponding to a thermoelastic metamaterial, and obtaining multiple groups of density distributions corresponding to multiple solid materials and one density distribution corresponding to one solid material in a thermoelastic metamaterial design domain according to the multi-material interpolation model; obtaining a relation interpolation among the multiple groups of density distributions, and obtaining an elastic modulus and a thermal expansion coefficient according to the relation interpolation; calculating an equivalent elastic matrix corresponding to the thermoelastic metamaterial according to the elastic modulus, and calculating a thermal expansion coefficient matrix corresponding to the thermoelastic metamaterial according to the thermal expansion coefficient; performing discretization form processing on the calculation equations of the equivalent elastic matrix and the thermal expansion coefficient matrix through an isogeometric grid, constructing a constraint function according to the equivalent elastic matrix, constructing a target function according to the thermal expansion coefficient matrix, and calculating sensitivity information corresponding to the first design variable through the target function and the constraint function; updating the first design variable according to the sensitivity information until the thermal expansion coefficient meets a convergence condition, and acquiring a second design variable meeting the convergence condition through geometric topology design models such as a negative thermal expansion metamaterial; and performing optimization design on the thermoelastic metamaterial according to the second design variable. The problem that when a complex geometric structure is processed, a finite element method is difficult to guarantee efficient and high-precision design of the thermoelastic metamaterial is solved.

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.

The invention discloses a design method for improving the thermal performance of a composite material by regulating and controlling the cluster type and number. The composite material designed by the method consists of an inorganic filler and an organic polymer material matrix, wherein the inorganic filler is a high-thermal-conductivity material and is in a cluster form; and orderly construction of a heat conduction path in the system is realized by regulating and controlling the type and the number of the filler clusters, so that the composite thermal interface material with ultrahigh heat conductivity is obtained under the condition of lower filling volume fraction. The heat-conducting interface material prepared by the method has excellent ductility, can adapt to various thermal interface applications, effectively improves the thermal management efficiency of the device by virtue of the characteristics of ultrahigh heat-conducting property and low filling volume fraction, realizes energy consumption reduction and material saving, further improves the performance release of the device and prolongs the service life of the device.

The invention discloses a multilayer heat-conducting wave-absorbing material design method based on a genetic algorithm. The method comprises the following steps: establishing a powder parameter database; the design of the multi-layer wave-absorbing material is completed based on a genetic algorithm, specifically, electromagnetic parameters and heat conductivity coefficients are calculated, the fitness of the material is evaluated, and a better design is generated through iteration by adopting crossover, variation and elite selection strategies; the formula meeting the expected heat-conducting and wave-absorbing performance can be output according to the designed method. According to the method, by introducing calculation of the heat conductivity coefficient and the equivalent medium theory, the sorting of the gaskets on all layers, the selection materials of all layers and the proportion of the filling materials of all layers can be adjusted, and the limitation that the traditional design of the multi-layer wave-absorbing material only depends on thickness adjustment is broken through. Compared with a traditional design method of the multi-layer heat-conducting wave-absorbing material, the design scheme meeting the requirements can be obtained without repeated tests, the consumed time is short, the cost is low, and the accuracy rate is high.

The invention discloses a fracture toughness prediction method for a non-continuous bionic Brini-gang structure, and belongs to the field of bionic composite material design. The prediction method comprises the following steps: S1, acquiring geometric and material parameters of a discontinuous bionic Belii Vagina structure; s2, constructing a fracture mechanics theoretical model of the structure; s3, solving the opening displacement of the fracture tip of the bionic Belii gang structure by adopting a numerical method; and S4, calculating parameters such as a crack propagation resistance curve and fracture toughness according to the crack tip opening displacement. According to the fracture toughness prediction method of the non-continuous bionic Beliolian structure provided by the invention, fracture parameters such as crack tip opening displacement and a crack propagation resistance curve can be obtained by taking microscopic sizes and material parameters of fibers and a matrix of the structure as input, and the prediction method not only can reveal fracture characteristics and a toughening mechanism of the bionic Beliolian structure, but also can obtain fracture parameters such as fracture toughness of the bionic Beliolian structure. And the method can also be used for optimal design of a bionic Brini spine structure.

The invention discloses a machining method for a hollow blade of an aero-engine. The machining method comprises the steps of hollow blade blank designing, forging, parting surface and profile groove machining, hollow blade profile contour welding and hollow blade profile contour machining. The finished blade is split along the middle of the front edge and the rear edge, and then blanks are designed for the split blade basin and the blade back respectively. The subsequent welding and flaw detection requirements are considered when the hollow blade blank is designed, the allowance of each part of the blank is adjusted, and finally the shape and the size of the blank are obtained. Through reasonable blank design, the blade can be smoothly combined, welded and machined, and the size and quality of the cavity and the surface of the hollow blade are guaranteed.

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.