43 results about "Materials design" patented technology

The application discloses a kind of composite cemented filling material design method, and the application relates to the technical field of mine filling, comprising the following steps: determining optimization component and its optimization domain, and randomly generating multiple groups of design combinations, preparing filling material and filling to be filled sample to form composite filling body test piece;Sample test body is cured under simulated environment, with the degree of hydration heat reaction as index, dynamically adjust sampling interval and determine multiple sampling time;Coupling monitoring test is carried out using the detection method of pulse velocity and low-frequency dielectric spectrum combination, interface coupling degree parameter is extracted, and cementation coupling degree is calculated, and the termination time is determined based on its change rate;The structural strength at this time is obtained, and the preset strength is used as constraint, the cementation coupling degree maximization and the experimental time minimization are used as optimization goal, the double objective optimization function is set, and the optimal design combination is determined by optimization algorithm, which can significantly reduce engineering risk and prolong the service life of structure.

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).

This invention provides a method, system, and equipment for optimizing the mix proportions of rubber concrete, belonging to the interdisciplinary field of building materials design and artificial intelligence. The method includes: constructing a high-precision prediction model for compressive strength and relative dynamic elastic modulus using Bi-LSTM, which serves as the fitness function during the optimization process. Furthermore, three optimization objectives are introduced. NSGA-III is enhanced by introducing chaotic perturbations and an adaptive evolution mechanism, thereby improving the convergence and diversity of the solution set in the high-dimensional objective space. Based on this, a three-objective optimization framework involving compressive strength, cost, and relative dynamic elastic modulus is established, enabling a coordinated balance among these three objectives in the mix proportion design of rubber concrete. This method solves the problem of insufficient optimization of rubber concrete mix proportions.

This invention provides an intelligent experimental decision-making method and device for foamed lightweight soil mix proportions, relating to the field of building material design technology. The method includes: acquiring experimental data of multi-source foamed lightweight soil and preprocessing it to obtain a standardized tabular dataset; using the standardized tabular dataset as context input to a pre-trained tabular prior data fitting network model to obtain performance prediction values; employing the SHAP value analysis method to calculate the contribution value of input features to the performance prediction values, thus obtaining the contribution relationship between input features and performance prediction values; using the tabular prior data fitting network model as the performance prediction model, establishing a multi-objective optimization model by combining material cost and material density, and setting constraints based on the contribution relationship; and using a non-dominated sorting genetic algorithm to solve the multi-objective optimization model, searching for a set of Pareto optimal mix proportion schemes. This invention can automatically search for Pareto optimal mix proportion schemes, improving the efficiency of mix proportion design.

The application belongs to the technical field of fuel cells, and specifically discloses a method for improving the high-temperature operation life and the number of cold and hot cycles of an SOFC stack. In the structural design, the single cell adopts an anode-supported structure and a barrier layer is additionally arranged, a reforming and temperature equalizing integrated cooling channel is introduced between adjacent single cells, and a structure in which cross-flow channels and reverse-flow channels are alternately stacked is adopted in the stack. In the material design, the anode of the single cell is of a gradient pore structure, a composite spinel coating layer is introduced on the surface of the bipolar plate, and a material with a smaller creep strength than the bipolar plate is used for the sealing layer. In the manufacturing process, a multiple progressive continuous stamping method is used to prepare a flexible connector, and the structure of the flexible connector is a fin type with a fin angle of 60° and a fillet radius of 10 μm. In the operation method, the sealing property and the insulation property of the stack are detected, and three-step continuous cooling is used in the cooling stage. The application comprehensively reduces the stress in the manufacturing and service processes, and improves the service life of the SOFC stack.

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 application discloses a ship plate high-strength steel material composition design method based on multi-target black box optimization, relates to the field of metal material design, and collects ship plate high-strength steel historical data to obtain a standard semi-structured data set through alignment and cleaning treatment; based on the data set, optimization targets, decision variables and constraint conditions are determined, and a multi-target optimization model is constructed; a mechanical property prediction model integrating multiple performances is obtained through machine learning algorithm training; an optimal solution set is obtained through iterative calculation of a reference vector guided multi-target optimization algorithm, and a final composition design scheme is selected by combining target steel grade service scenarios and assigning weights, so that the complex mapping relationship of composition-process-performance is accurately quantified, the strength, toughness, weldability and corrosion resistance are simultaneously optimized to match service requirements, the optimization algorithm considers global exploration and local development, the optimal solution under multiple constraints is efficiently obtained, manual experience derivation is not needed, and the composition design can be popularized to other high-strength steels or special steels.

The application discloses a ceramic capacitor microstructure regulation and control method and system based on cross-scale modeling and fuzzy neural network, and belongs to the technical field of ceramic material design and performance optimization. The method comprises the following steps: constructing a cross-scale digital twin model of a target ceramic dielectric system; constructing an initial data set based on sample data; constructing and training a fuzzy neural network reverse design engine based on the cross-scale digital twin model and the initial data set; inputting target macroscopic performance indicators of a ceramic capacitor to be prepared into the fuzzy neural network reverse design engine to obtain a microstructure target and process parameters; and regulating and controlling the microstructure of the ceramic capacitor to be prepared according to the microstructure target and the process parameters. The implementation of the application is beneficial to breaking through the key technical bottleneck of high-performance ceramic capacitors, shortening the exploration period of new material formula from several years to several months or even several weeks, and greatly reducing the research and development cost.

The present application relates to a kind of method for determining carbon fiber strength based on molecular dynamics, belong to aerospace lightweight composite material design technical field.The present application constructs the method for meeting the interlayer spacing and interlayer crosslinking fragment of actual carbon fiber using molecular dynamics method, and the tensile and compression strength of normal temperature 300K-high temperature 2000K are calculated.Meanwhile, the change trend of experimental and simulation results is extremely high, and it provides strong theoretical basis for the preparation process development and service strength calculation of high-performance carbon fiber.

This invention discloses a heavy-duty gearbox shell based on gradient-optimized composite materials and its manufacturing process, relating to the fields of material design and equipment manufacturing technology. The shell body is an integrally formed gradient heterogeneous composite structure with the following gradient design: a core load-bearing layer located in the gear meshing area, bearing housing, and flange connection surface of the shell body, made of a composite powder of high-carbon chromium-molybdenum steel powder and nano-ceramic particles; a transition buffer layer connecting the core load-bearing layer and the lightweight support layer, made of a composite powder of medium-carbon alloy steel powder and short carbon fibers; and a lightweight support layer located on the sidewalls and non-stressed areas of the shell body, made of a composite powder of aluminum alloy powder and hollow ceramic microspheres. The thickness ratio of the core load-bearing layer, transition buffer layer, and lightweight support layer in the radial section is 1:1.4:1.6. This invention, based on a three-dimensional gradient heterogeneous composite structure, achieves precise matching of material properties and load distribution, optimizing and improving load-bearing capacity while maximizing lightweight design.

This invention relates to the fields of materials science and parts forming and manufacturing technology, and discloses a method and system for cross-scale prediction of material mechanical properties. The method includes: acquiring EBSD data of the modeling material; extracting first-class microscale features (crystal orientation, phase distribution) and second-class microscale features (SF, TF, grain size, texture); constructing an RVE model based on the first-class features; embedding the crystal plastic constitutive model for finite element calculation to obtain the macroscopic mechanical response and grain-scale stress-strain distribution; combining the calculated data, selecting at least one feature from the two classes as input to establish a quantitative prediction model for macroscopic mechanical properties; for the target material, acquiring its EBSD data and extracting corresponding features, and applying the model to predict macroscopic mechanical properties. This invention achieves direct quantitative prediction from microscopic mechanisms to macroscopic properties, reducing reliance on large-scale experiments and providing an efficient and reliable tool for materials design and process optimization.

This invention provides a low-density wear-resistant high-chromium cast iron and its preparation method, relating to the technical field of metal material design and heat treatment. The chemical composition of the low-density wear-resistant high-chromium cast iron, by mass percentage, is: C 3.16-3.22%, Si 0.4-0.6%, Mn 12.7-13.3%, Cr 19.0-20.0%, Cu 0.8-1.1%, Mo 0.9-1.0%, V 0.10-0.14%, Ti 0.04-0.07%, Al 5.7-6.3%, with the remainder being Fe and other unavoidable impurities. The preparation method of the low-density wear-resistant high-chromium cast iron includes quenching treatment, cryogenic treatment, and tempering treatment. This invention reduces the density of cast iron from the high density of traditional high-chromium cast iron to a low density by introducing Al and Mn elements, thus achieving the low-density characteristics of wear-resistant cast iron. It also creatively introduces deep cryogenic treatment between the quenching and tempering processes, synergistically optimizing the precipitation morphology and distribution of carbides in the microstructure, significantly improving the material's hardness. This method is stable, easy to operate, and suitable for applications such as mining machinery and engineering machinery where both material weight and wear resistance are critical.

The application discloses a method for improving the strength and toughness of duplex stainless steel based on alternating powder laying in additive manufacturing, and belongs to the field of metal additive manufacturing and advanced material design. In the method, duplex stainless steel powder and austenitic stainless steel powder are respectively laid on different layers for forming through an alternating powder laying strategy. After laser melting and solidification, a composite structural material with alternating arrangement of ferrite and austenite is directly obtained. Meanwhile, the method retains the characteristics of laser powder bed fusion forming materials, i.e. fine grain structure and high density dislocation, and can realize the synergistic improvement of strength and elongation without subsequent heat treatment, with the yield strength being greater than or equal to 700 MPa and the elongation being greater than or equal to 25%, which is significantly higher than the standard value of ASTM 240.

This invention relates to a method for surface modification of key friction pairs in internal combustion engines based on laser cladding and diamond-like carbon (DLC) composite coatings, belonging to the field of surface strengthening and remanufacturing technology for key internal combustion engine components. Two functional transition layers are sequentially prepared on the substrate of the key friction pair using laser cladding technology: first, a Ni60-Cu alloy layer is clad as a toughness buffer layer to alleviate thermal stress and improve the bonding strength with the substrate; then, a WC particle-reinforced Ni-based alloy layer is clad as a reinforcing support layer to provide a high-hardness substrate; after polishing the cladding layers, a DLC coating is prepared on the polished surface using cathodic arc deposition. This invention solves the problems of weak adhesion and easy peeling of DLC coatings on gray cast iron through a gradient material design and sequential process of toughness buffering, reinforcing support, and ultra-hard friction reduction. The prepared friction pair possesses high interfacial bonding strength, excellent fatigue resistance, and friction-reducing and wear-resistant properties, extending the service life of the friction pair under harsh operating conditions.

This invention relates to a method for determining the strength of amorphous carbon interfacial layers based on molecular dynamics, belonging to the field of aerospace lightweight composite material design technology. This invention utilizes molecular dynamics to construct a method that satisfies the interlayer spacing and interlayer crosslinking segments of actual amorphous carbon interfacial layers, and calculates the tensile, compressive, and shear strengths at room temperature (300K) to high temperature (2000K). Furthermore, the experimental and simulation results show extremely high agreement, providing a strong theoretical basis for the development of interfacial layer preparation processes and the calculation of service strength in high-performance composite materials.

This invention discloses a design method and apparatus for refractory high-entropy alloys based on a large model, relating to the field of alloy material design technology. The method includes: First, by generating and collecting data, pre-trained surrogate models for thermodynamics (covering phase diagrams, solidification processes, etc.) and mechanical properties are constructed, and calculation models for physical parameters such as valence electron concentration and density are established. Then, these models are integrated into a single ensemble model, and a large language model is introduced as the core of intelligent scheduling. The large model is responsible for parsing the design task, intelligently planning and calling the interfaces of each model based on a knowledge base and rule base. Finally, based on the set design objectives, a multi-objective genetic algorithm is initiated for iterative optimization and adaptive adjustment, efficiently outputting a final alloy design scheme that meets multiple performance requirements. This invention enables intelligent multi-objective design of refractory high-entropy alloys, solving the problem of high dependence on manual intervention.

The application provides a kind of corrosion-resistant water-cooled plate and its preparation method and application, it is related to water-cooled material technical field. Specifically, the corrosion-resistant water-cooled plate includes upper layer plate and lower layer plate, and at least one of (a) or (b) is satisfied: (a) the upper layer plate is double-layer composite structure, and the material of the upper layer plate includes 1 pure aluminum and 3 aluminum-manganese alloy; (b) the lower layer plate is three-layer composite structure, and the material of the lower layer plate includes 4 silicon-aluminum alloy, 3 aluminum-manganese alloy and 1 pure aluminum. The corrosion-resistant water-cooled plate of the application effectively enhances the corrosion resistance of the water-cooled plate by specific material design and structure design, and takes into account mechanical strength, is suitable for extreme application scenarios such as high temperature and high salt, the preparation process is simple and easy to popularize, and has good application prospect.

The application discloses a kind of fiber concrete toughening design methods, belong to concrete technical field.The method of the present application changes the passive control characteristics of fiber to the crack propagation process in traditional fiber concrete, from the source of composite material design, first design the composite cementitious material matrix with super-high ductility, secondly, in the specific matrix and aggregate parameter combination, make the composite material develop mesoscopic multi-crack cracking and strain hardening behavior between aggregate particles during external loading process.The fiber concrete prepared by this method actively disperses the brittle damage of the material inside, and avoids the crack instability propagation caused by the weak interface bonding between aggregate and matrix.Compared with the traditional fiber concrete design method, the present application more accurately constructs the correlation between material composition, microstructure and macroscopic mechanical response, and more efficiently improves the toughness of the material.

This invention belongs to the field of polymer material design technology, specifically a high-performance multi-objective reverse design method for polymers based on Graph Attention Network (GAT) and Non-Dominated Sorting Genetic Algorithm II (NSGA-II). The method includes: performing self-supervised comparative pre-training on the GAT encoder, and fine-tuning it through supervised learning to adapt it to the polymer property prediction task; calculating the dielectric constant (k) or glass transition temperature (k) of the substituent by comparing the predicted values ​​before and after deletion. T g The contribution value of ) is obtained to obtain a robust contribution law; the target performance of polymer materials is optimized through substituent modification, thereby meeting the needs of high-performance electronic applications; this invention can simultaneously optimize low-k and high-k values. T g It improves the accuracy and generalization ability of property prediction; generates candidate structures superior to baseline molecules in different systems; and the optimized candidate molecules maintain improved overall performance while having reasonable synthetic accessibility scores, making them valuable for further experimental synthesis and screening.

This invention provides a design method for high-entropy ceramic carbide coatings for laser protection, belonging to the field of laser protection ceramic material design technology. The method includes: constructing a high-entropy ceramic carbide atomic model using a special quasi-random structure method; performing relaxation optimization on the structure based on DFT; generating a neural network potential energy training database based on multi-condition AIMD calculations; constructing a neural network model and training energy-force data using DeepMD-kit; performing LAMMPS simulations using DeepMD, setting upper and lower thresholds based on model deviations to filter high-deviation configurations; performing high-precision calculations on the high-deviation configurations to generate a high-entropy carbide potential function with acceptable accuracy; and optimizing the coating composition ratio to obtain the optimal laser protection high-entropy ceramic carbide coating design scheme. This invention combines first-principles calculations and deep learning to construct a high-precision potential function suitable for laser protection scenarios, efficiently completing the precise design of high-performance laser protection coatings.

This invention discloses a design method for steel fiber reinforced concrete (SFR) materials based on multiple performance requirements, comprising: acquiring raw data of SFR parameters and performance, and determining a training dataset; training an initial convolutional neural network (CNN) model based on the training dataset to obtain a CNN performance prediction model; constructing a virtual function of SFR performance as the objective function using the CNN performance prediction module; obtaining the constraints of the basic performance parameters corresponding to the objective function; optimizing the concrete mix proportion for the objective function under each constraint using a genetic algorithm, selecting the optimal solution that meets the preset performance indicators, and determining the optimal solution set; and using the TOPSIS method to select the optimal solution set to obtain the optimal design scheme for SFR materials. This invention is beneficial for improving the various performance characteristics of SFRs, avoiding raw material waste, and achieving sustainable development of building materials.

The utility model provides a kind of fibre composite material reinforcing frame forming device, belong to fibre composite material design technical field.The problem of continuous fiber integrated winding forming thick-wall narrow frame is solved.It includes mould, two first shaping toolings, two second shaping toolings and flange, mould is ladder shaft with small diameter at both ends and large diameter in middle, two first shaping toolings and two second shaping toolings are respectively installed from outside to inside at both ends of mould, flange is arranged between first shaping tooling and second shaping tooling at one side.The utility model can integrally wind forming thick-wall narrow frame by shaping tooling, realizes the one-off forming of thick-wall narrow frame, avoids the waste of raw material and the instability of size when open forming reinforcing frame, and one forming guarantees the continuity of fibre, avoids the damage caused by secondary processing, improves the quality and production efficiency of pipeline product.

The distinguishing feature of this design is that it is a decorative surface composite material, and it is used as a material for counter surfaces, bench surfaces, washbasins, wall panels, etc. For Design 1, the distinguishing features of the design lie in its pattern and color. 1) Plan view

The application provides a wear-resistant injection head assembly for a semiconductor package, which comprises a main body guiding structure and an end working structure coaxially arranged and fixedly connected, the main body guiding structure is a cylinder, and the outer surface of the cylinder is a double guiding structure formed by a front guiding surface and a rear guiding surface, the front guiding surface is located on one side close to the end working structure, and the rear guiding surface is located on one side away from the end working structure; the main body guiding structure is made of a first material, and the end working structure is made of a second material, and the hardness, wear resistance and chemical corrosion resistance of the second material are higher than those of the first material. In the scheme, the high wear-resistant and corrosion-resistant material is used as the working end surface, so that the adhesion tendency of the plastic sealing material is reduced, and the end surface is prevented from being adhered with the plastic sealing material in the service life cycle of the assembly; in addition, the double-material design optimizes the performance and cost, the main body guiding structure guarantees the toughness, the end working structure provides extreme wear resistance, and the overall service life is much longer than that of a single-material injection head.

This invention discloses a low-cost, low-weight test carrier manufacturing method for stealth testing of large-size radomes. The method includes the following steps: designing a carrier structure consisting of a skeleton, surface skin, and surface metal layer; designing the shape; disassembling the structure; manufacturing composite material sandwich skeleton parts; assembling the skeleton; applying and curing the surface skin; and preparing the surface metal layer. This invention replaces the traditional metal skeleton welded skin structure with a composite material design and integrated molding process, reducing the carrier weight by more than 50% within the same size, while ensuring structural rigidity and surface accuracy, and significantly reducing manufacturing costs. It effectively solves the problems of excessive turntable weight and insufficient testing accuracy in RCS testing of large-size radomes.

The present application relates to the technical field of computer-aided material design, in particular to a material chemical formula generation method based on performance sensitivity adaptive hierarchical sampling, which comprises the following steps: inputting an element list; querying a performance sensitivity knowledge base to obtain sensitivity levels and adjustment factors; analyzing a composite element and extracting multi-dimensional element features, and quantitatively calculating element combination complexity; based on the number of elements, sensitivity and complexity, adaptively selecting a corresponding sampling strategy and dynamically allocating a sampling amount; generating a chemical formula and removing duplicates; and outputting a chemical formula list and full-process metadata. Through the performance sensitivity driven resource allocation, composite element atomic level analysis, feature space clustering and other innovations, the present application improves the computing efficiency by tens to hundreds of times, reduces the response time to seconds or minutes, and has the characteristics of traceability, scalability and strong universality, effectively accelerating the material screening and discovery process.

This invention discloses a method for discovering the core structure of high-entropy alloys based on multi-view characterization, belonging to the field of high-entropy alloy material design and characterization technology. The method includes data alignment enhancement; collaborative candidate mining; joint optimization discovery; physical verification and refinement; and iterative solidification output. This invention collects and preprocesses multi-modal data on the chemical composition, microstructure, crystal structure, and process parameters of high-entropy alloys. It utilizes anchoring processing to establish a unified cross-modal representation, achieving efficient fusion and structured encoding of multi-view data. This enables the construction of a performance prediction model, significantly improving the accuracy of predictions for mechanical properties and other indicators, while reducing data noise and feature redundancy. This method is applicable to different high-entropy alloy systems and multi-modal data types, providing a scalable and practical technical means for the intelligent design and optimization of high-entropy alloys. It has significant scientific research value and promising industrial application prospects.

The application belongs to the technical field of high-end biomedical metal material preparation, and particularly relates to a high-uniformity large-size Ti-6Al-7Nb medical titanium alloy ingot and a preparation method thereof. Through synergistic control of "high-purity sponge titanium pretreatment + Ti-Al-Nb ternary intermediate alloy design + trace boron addition grain refinement + three-time VAR melting precise segregation control", the application realizes the deep integration of material design of pre-alloying and micro-alloying and three-time VAR + EMS melting process, simultaneously starts from two aspects of thermodynamics and dynamics, ensures that niobium element is fully dissolved in the melting stage and uniformly distributed in the solidification stage, and realizes the requirements of high uniformity of ingot composition, small and compact structure and excellent batch stability. The whole-process high-cleanliness control of the application ensures that the oxygen content is less than or equal to 0.10wt%, and there is no harmful inclusion larger than 15 microns, thereby meeting the most stringent medical standards.

This invention provides an intelligent design and manufacturing method for mosaic-type electromagnetic frequency-selective laminated composite materials, relating to the field of electromagnetic frequency-selective composite material design and manufacturing technology. By establishing a mapping relationship database, training a deep neural network model, and invoking optimization algorithms for automatic optimization design, combined with pixelated manufacturing processes, it efficiently covers the global design domain, reduces iteration cycles, lowers trial-and-error costs, and solves the problem of low manufacturing reliability.

The application discloses a kind of based on heat dissipation's ultra-high cycle fatigue stress life curve evaluation method.This method is loaded by stepwise increment fatigue stress amplitude to single sample, until the sample breaks;Real-time monitoring test sample surface temperature rise under different stress amplitude and corresponding cycle loading cycle;By analyzing the heat dissipation of single sample under different stress amplitude, the fatigue life limit under each stress amplitude is calculated, and the complete stress life curve is constructed.The number of fatigue test samples is greatly reduced, the ultra-high cycle fatigue stress life curve of the material is quickly obtained, the experimental cost is effectively reduced, and reliable data support is provided for material design and service safety evaluation.