1032 results about "Molecular dynamics" patented technology

The invention discloses an asphalt pavement fatigue damage model calibration method based on AI and digital twinning, and relates to the technical field of damage detection. Compared with the prior art, the problems that traditional asphalt pavement design depends on empirical formulas and static parameters, material aging, environmental coupling and load uncertainty are difficult to dynamically reflect, and cross-scale correlation between microscopic interface behaviors and macroscopic structure performance is lacked are solved; the method comprises the following steps: collecting and preprocessing multi-source heterogeneous data in real time through a multi-modal data fusion and dynamic sensing system, simulating and accurately quantifying asphalt-aggregate interface binding energy and adhesion work in combination with molecular dynamics, and constructing a cross-scale damage evolution model; a physical information neural network is used for embedding an improved Paris formula, actually measured data and a physical rule are deeply fused, and the locality hypothesis of a traditional model is effectively corrected.

The invention provides a self-adaptive high-temperature damage model construction method and system. Belongs to the technical field of material science and engineering calculation. The method comprises the following steps: acquiring experimental data of a material in a high-temperature environment, preprocessing the collected data through a machine learning algorithm, and extracting key damage features; constructing a basic damage prediction model based on a deep learning framework, training the model by using the preprocessed data, and enabling the basic damage prediction model to adaptively adjust internal parameters according to prediction errors through a reinforcement learning mechanism; and carrying out global search on thermodynamic parameters in the model by utilizing a genetic algorithm, searching an optimal parameter combination, and dynamically adjusting model parameters in combination with real-time temperature monitoring data. Through integration of deep learning, reinforcement learning, a genetic algorithm and a molecular dynamics simulation technology, the damage evolution process of the material in a high-temperature environment can be predicted more accurately and comprehensively.

To provide a test method for mechanical characteristics of combined electrical, thermal and mechanical deterioration of insulating oil-paper.SOLUTION: The present invention comprises: constructing an AC and DC / thermal / mechanical stress combined deterioration experimental platform; preparing insulating oil-paper samples with different deterioration states; measuring a degree of polymerization and tensile strength test of the insulating oil-paper samples with different deterioration states; acquiring change rules of mechanical characteristics after deterioration; observing microscopic morphology diagrams and XRD spectra of the insulating oil-paper samples with different deterioration states; constructing an amorphous unit cell of a cellulose molecular chain; optimizing a structure; acquiring a cellulose model; constructing an oil-paper mixed model; performing molecular dynamics simulation on the oil-paper samples with different deterioration states based on the cellulose model and the oil-paper mixed model; and constructing the relation between the deterioration of macroscopic mechanical characteristics of insulating oil-paper and changes in microscopic physical and chemical characteristics, where a data basis and theoretical support for prediction of a life of insulating paper are provided.SELECTED DRAWING: Figure 19

The invention provides a gradient crosslinking process of photosensitive resin for photocuring 3D printing, and relates to the technical field of photocuring 3D printing materials. The gradient crosslinking process of the photosensitive resin for photocuring 3D printing comprises the following steps: S1, based on double-initiator system design, adopting molecular dynamics simulation screening, respectively adding a 405nm sensitive type TPO-L initiator and a 365nm sensitive type I TX initiator into an epoxy acrylate prepolymer, and verifying initiation energy barrier matching through quantum chemistry calculation, and generating a pre-initiation gradient resin formula. Through molecular dynamics simulation, initiator combinations are screened, energy barrier matching is verified, the ratio of dual-wavelength sensitive initiators is optimized, and accurate triggering of surface layer and deep layer cross-linking reaction is ensured. And a three-roller grinding and dispersing process is combined with ultrasonic oscillation to eliminate nanoparticle aggregation, so that the mechanical uniformity and light scattering effect of a resin system are improved.

The invention discloses an optimized molecular dynamics simulation method for a monocrystalline silicon cutting process. Comprising the following steps: initializing and setting parameters, creating a workpiece area, creating an abrasive particle area, creating an atomic box, setting atomic mass, fixing a boundary layer, selecting a potential function, carrying out energy minimization processing and relaxation processing, setting cutting parameters, and carrying out operation simulation and result visualization processing. According to the method, interaction between silicon atoms and interaction between silicon and carbon can be described more accurately by using Tersoft potential; the simulation stability is improved by setting time step length, temperature control and energy minimization; by defining different temperature control layers such as a constant temperature layer and a Newton layer, complex dynamic behaviors in the material cutting process can be better simulated; by optimizing a calculation model and an algorithm, the speed and the precision of atomic motion trail and stress distribution in the process of simulating the cutting of the monocrystalline silicon are remarkably improved, and the stability of the simulation process is ensured.

The invention discloses a chalcogenide phase change storage material potential model construction method, a material characteristic calculation method and electronic equipment, and belongs to the field of semiconductor materials. On the basis of a potential model trained by a first training set collected through molecular dynamics simulation based on a first principle calculation method, a current potential model is fully utilized, molecular dynamics simulation is carried out based on the current potential model, training samples are further collected, representative training samples are screened out, and a second training set is formed; according to the method, the training efficiency is high, the generalization ability is high, and a large amount of training data can be obtained with low cost. Meanwhile, verification of physical properties is introduced into convergence conditions of model training, so that the physical consistency and interpretability of the potential model are improved; on the basis, the training set which is good in diversity and sufficient in data volume can be obtained with low cost, and meanwhile the accuracy of the potential model in an actual application scene is further improved.

The invention provides a machine learning potential function design method for UO2 and a fission product thereof, and the method comprises the steps: S1, constructing a UO2-Xe / I unit cell with the fission product, and carrying out the optimization of the UO2-Xe / I unit cell; s2, the optimized UO2-Xe / I unit cell structure is disturbed and simulated, and a training data set is generated; s3, establishing a machine learning potential function; s4, performing molecular dynamics simulation on the machine learning potential function; s5, performing density functional theory calculation on the candidate configuration to obtain accurate structure-energy-force data, and repeating the steps S3 to S5 to perform iterative calculation; s6, verifying the trained machine learning potential function to obtain an accurate machine learning potential function; and S7, performing molecular dynamics simulation by using an accurate machine learning potential function. The precise DP model is obtained through machine learning, and a theoretical basis is provided for research of a diffusion mechanism of fission products in UO2 and molecular dynamics simulation of other mechanical properties.

The invention discloses a simulation method for abrasive particle vibration machining based on reaction molecular dynamics, and relates to the technical field of reaction molecular dynamics, a vibration auxiliary model of a Si surface of 4H-SiC is established, the process of vibration auxiliary chemical mechanical polishing of diamond abrasive particles in the Z-axis direction is simulated, the Si surface model of the 4H-SiC is consistent with an actual machining surface of silicon carbide, and the abrasive particle vibration machining simulation method is suitable for the actual machining surface of silicon carbide. The vibration direction of the vibration auxiliary simulation is consistent with the motion direction of the abrasive particles in the actual chemical mechanical polishing process, so that the acting force and motion trail simulation of the diamond abrasive particle model in the polishing process are more real, and the simulation process is closer to the actual machining process; the atom removal mechanism of the Si surface of 4H-SiC under the conditions of different vibration amplitudes and frequencies and different scratching depths can be researched, so that a chemical mechanical polishing technology is conveniently optimized by ultrasonic vibration, and the polishing quality of silicon carbide is further improved; the technical problem that an existing vibration auxiliary model based on reaction molecular dynamics simulation cannot effectively optimize the chemical mechanical polishing process of silicon carbide is solved.

The invention discloses a dynamic optimization system and method for a compound essential oil ratio, and aims to solve the problems that the traditional technology depends on artificial experience, the optimization efficiency is low and the quality tracing is insufficient. According to the method, raw material molecular fingerprint data are collected in real time through a high-precision spectrum sensor array and a micro-fluidic chip, a production environment field domain is constructed in combination with a computational fluid mechanics model, a formula optimization problem is encoded into an Ising model by using a quantum annealing algorithm, and global search is realized through a quantum tunneling effect. The system integrates digital twin bodies, covers molecular dynamics simulation, phase equilibrium prediction and olfactory receptor activation probability simulation, and accurately maps a physical system state; a multi-modal data fusion network and a reinforcement learning framework are adopted to dynamically adjust formula parameters, and an NSGA-III algorithm is combined to optimize efficacy collaboration degree, cost and stability indexes. And the execution control module realizes nanoscale flow regulation through the piezoelectric micro-injection valve array, and realizes non-tampering evidence storage of formula parameters and quality data based on a block chain technology. Dynamic closed-loop optimization of the compound essential oil ratio is achieved, the production efficiency, the product consistency and the supply chain transparency are remarkably improved, and the method is suitable for the field of intelligent manufacturing of high-end essential oil.

The invention relates to the technical field of chemical engineering and machine learning, and provides a Fischer-Tropsch reactor strengthening method based on microsystem catalyst screening and kinetic research. The method comprises four main steps of catalyst screening, kinetic model establishment, reactor size optimization and performance verification. The method comprises the following steps: firstly, screening Fe9Cr3 as an optimal bimetallic catalyst through molecular dynamics simulation; then, establishing a kinetic model by utilizing an Arrhenius equation, and calculating a reaction rate constant and activation energy; secondly, optimizing the length-diameter ratio L / D of the reactor through macroscopic simulation and computational fluid dynamics (CFD) simulation; finally, the performance of the optimized reactor is verified through experiments, it is ensured that the activity and the synthesis rate of the catalyst reach expected targets, and CO2 emission reduction is achieved. According to the method, microscopic simulation and macroscopic simulation are combined, so that the overall efficiency and performance of F-T synthesis are improved, and meanwhile, the research and development cost is reduced, and the research and development time is shortened.

The invention discloses a cross-scale rock elastic mechanical parameter measurement method and system, and relates to the technical field of rock measurement, and the method comprises the following steps: obtaining nano-scale rock elastic mechanical parameters and micro elastic-plastic deformation of rock through a nanoindentation experiment, so as to construct a molecular dynamics model of the rock; according to the molecular dynamics model of the rock, using an inclusion homogenization theory to upgrade the rock elastic mechanics parameters of the nanoscale to the rock elastic mechanics parameters of the centimeter scale, so as to construct a rock elastic mechanics parameter conversion model, and using environmental data in an in-situ environment for correction; and inputting the nano-scale rock elastic mechanical parameters into the corrected rock elastic mechanical parameter conversion model to obtain centimeter-scale rock elastic mechanical parameters. According to the invention, centimeter-scale rock elastic mechanical parameters in a deep stratum in-situ environment can be accurately measured.

The invention provides a method and a system for evaluating the luminescence performance of a near-infrared two-region molecular fluorescent probe, and relates to the technical field of fluorescent probes, the method comprises the following steps: obtaining the initial configuration of the near-infrared two-region molecular fluorescent probe in an aqueous solution, and carrying out molecular dynamics simulation on the initial configuration to obtain a plurality of representative conformations of the probe in the aqueous solution; performing quantum chemical calculation on each representative conformation to obtain first system energy of each representative conformation in a stable state and second system energy and intensity parameters of each representative conformation in a lowest singlet excitation state; generating a comprehensive evaluation factor based on the first system energy, the second system energy and the intensity parameter; and sorting the luminescence properties of the probes based on the comprehensive evaluation factor, and screening out the probe with the optimal performance. According to the method provided by the invention, quantitative evaluation on the luminescence property of the near-infrared two-region molecular fluorescent probe is realized, and technical support is provided for optimal design and clinical application of the probe.

The invention provides a metal matrix composite microstructure strengthening simulation method and system, and relates to the technical field of composite mechanical property simulation, and the method comprises the following steps: establishing a polycrystalline aluminum matrix atomic model and a spherical silicon nitride particle strengthening phase atomic model unit; embedding the spherical silicon nitride particles into the polycrystalline aluminum matrix according to the target embedding position coordinates, and integrating to generate an atomic scale structure model; according to the method, an embedded atom potential function is adopted to describe interaction among atoms in a polycrystalline aluminum matrix, a Tersoft potential function is adopted to describe covalent bond interaction among atoms in spherical silicon nitride particles, and a Lennard-Jones potential function is adopted to describe interaction among heteroatoms at a Si3N4 / Al interface; based on the interaction potential between atoms, molecular dynamics simulation is adopted for conducting uniaxial stretching simulation on the atomic scale structure model, mechanical property parameters of the particle reinforced metal matrix composite are obtained through calculation, and a visualization method is combined for analyzing the microcosmic strengthening mechanism of the particle reinforced metal matrix composite.

The invention discloses a nano twin copper rough surface direct bonding atomic-scale simulation method, which comprises the following steps: determining an inter-atomic interaction potential function in molecular dynamics through a first principle, constructing a polycrystalline nano twin copper supercell model based on experimental parameters, and generating a rough surface with fractal characteristics; molecular dynamics simulation is adopted to simulate bonding and annealing processes, a bonded polycrystalline nano twin copper model is obtained, and the performance of the interconnection structure is calculated based on the bonded polycrystalline nano twin copper model. The result feedback is used for optimizing the copper-copper direct bonding material and process parameters. According to the method, the atomic-scale polycrystal nano twin copper model is established through simulation, the optimal performance parameter combination of the interconnection structure is obtained, the trial and error cost in tests and production is reduced, the quality of a copper-copper direct bonding interface is improved, and guidance is provided for design and process optimization of high-density packaging.

A federated distributed computational system enables secure drug discovery and resistance tracking through hybrid simulation capabilities. The system implements a hybrid simulation orchestrator that coordinates molecular dynamics simulations with machine learning models for drug discovery analysis, while maintaining secure cross-institutional data exchange. The architecture coordinates multi-scale spatiotemporal synchronization across computational nodes, with each node containing local processing capabilities for molecular dynamics simulation and resistance pattern detection. Through a distributed graph architecture, the system enables real-world clinical data integration, resistance evolution tracking, and multi-scale tensor-based analysis with adaptive dimensionality control. The system implements real-time drug response prediction through multi-modal data analysis, enabling pharmaceutical companies and research institutions to collaborate on complex drug discovery projects while maintaining strict data privacy controls.

A system and method are provided for a machine-learning drive framework for predicting ionic conductivity of solid-state electrolytes. In use, the method and / or system may include receiving, at a machine learning system, two or more molecular structures from at least one structural dataset, where the two or more molecular structures relate to ionic mobility. Additionally, atomic weights are calculated for the two or more molecular structures, and the machine learning system is trained based on the two or more molecular structures, where the training relies on at least one intrinsic atomic feature and the calculated atomic weights for the two or more molecular structures. Further, a bias-correction is applied for the two or more molecular structures to improve the training of the machine learning system. Further, one or more molecular dynamics (MD) simulations are outputted, using the machine learning system, for the two or more molecular structures.

The invention discloses a method for realizing metallurgical slag viscosity prediction by using molecular dynamics simulation, and belongs to the technical field of metallurgical slag viscosity prediction. The method comprises the following steps: carrying out molecular dynamics simulation by adopting Lammps software according to specific components of a slag system, and obtaining the oxygen bond type and the oxygen bond molar content of the slag by using Matlab software; creatively adopting a radial basis function interpolation method to establish an oxygen bond molar content database of continuous component change in the slag system range; and inputting the oxygen bond molar content of the to-be-predicted slag obtained from the database into the deduced and modified slag viscosity prediction equation to obtain a predicted value of the viscosity of the to-be-measured slag. According to the method, interference of external environmental factors is avoided through a molecular dynamics simulation method, and meanwhile, the flow mechanism of a slag network structure is considered, so that the data precision and efficiency are improved, and the cost is greatly reduced.

The invention discloses a molecular dynamics-macroscopic multi-scale coupling calculation method, which relates to the field of material damage numerical simulation analysis, and comprises the following steps: respectively establishing a microcosmic plate model and a macroscopic plate model; young modulus and Poisson's ratio parameters are calculated through microscale pneumatic simulation in the microcosmic plate model and are transmitted into the macroscopic plate model, a stress value I and a strain value I are obtained through macroscopic pneumatic simulation calculation and are transmitted into the microcosmic plate model, and the stress value I and the strain value I are obtained through microcosmic-macroscopic continuous coupling iteration. And obtaining the mechanical property indexes of the silicon thin plate in each stage from stress starting, crack generation, crack propagation to failure and fracture. The invention provides a molecular dynamics-macroscopic multi-scale coupling calculation method. A new analysis method is provided for researching structural failure and damage in an aerodynamic hot extreme environment through coupling calculation of macroscopic and microscopic scale models.

The invention provides a high-entropy alloy tensile property prediction method and system based on molecular dynamics simulation, and belongs to the technical field of high-entropy alloy tensile property prediction. Molecular dynamics data are combined into a data set, and the data set is divided into a training set and an evaluation set; training and evaluating the dense connection neural network based on the training set and the evaluation set; calculating a potential function by using the evaluated dense connection neural network; based on an LAMMPS simulator, simulating the inter-atomic motion trail in the tensile fracture process of the high-entropy alloy; and predicting the tensile property of the high-entropy alloy according to the motion trail simulation result. According to the method, the tensile property of the high-entropy alloy can be accurately predicted on the basis of enhancing the generalization ability of the model.

The invention relates to multi-scale modeling and mechanical and thermodynamic property simulation of a particle reinforced biological composite material, and belongs to the crossing field of biology, material science and computer simulation. The method specifically comprises the following steps: constructing a polyether-ether-ketone (PEEK) high-molecular polymer and a graphene reinforced composite material model thereof through a cross-linking algorithm under a microscopic scale, and simulating and calculating the mechanical and thermodynamic properties of the model by adopting molecular dynamics; in the microscopic scale, constructing a representative volume element model of the microstructure artificial skeleton, inputting property parameters calculated by molecular dynamics into a microscopic model, and calculating microscopic mechanical and thermodynamic properties of the model by adopting a substance point method; and inputting the property parameters obtained under the microscale into the macroscopic model, and calculating the overall macromechanical and thermodynamic behavior response of the material by adopting a finite element method. According to the method, mechanical and thermodynamic responses of the biological composite material are finally simulated through transmission of property parameters of different scales, and theoretical support is provided for research and formula design of the particle reinforced biological composite material.

In a small molecule drug discovery method, a transition state for a specific enzyme is modelled using quantum mechanics and molecular dynamics based simulation of the enzyme and substrate reaction; data defining the transition state (a ‘quantum pharmacophore’) is fed to a machine learning engine configured to generate transition state analogues, such as enzyme inhibitors.

The invention provides a classroom simulation method for virtual reality, and relates to the technical field of data processing, and the method comprises the steps: obtaining a high-dimensional data matrix with a time-space correlation characteristic; constructing an electrical connection relation graph; obtaining a quantum state evolution result of the transient process of the power system; calculating to obtain a multi-physical field distribution parameter corresponding to the equipment; based on the multi-physics field distribution parameters, combining molecular dynamics simulation and a fluid mechanics model to obtain arc dynamic characteristic data; collecting an electromyographic signal of an operator, and generating a force feedback control instruction through a neural network mapping model in combination with mechanical parameters of equipment; and according to the eye movement tracking data, the arc dynamic characteristic data and the force feedback control instruction, generating a virtual reality scene adaptive to the visual response and the operation state of the operator by using a dynamic rendering engine. According to the embodiment of the invention, the authenticity and interactivity of virtual reality classroom simulation can be improved.

The invention relates to the technical field of carbon dioxide sequestration and shale gas development, and particularly discloses a shale micro-nano pore multiphase multicomponent competitive adsorption data determination method and device, and the method comprises the steps: obtaining a shale core sample of a target area, and determining the type and relative content change characteristics of surface functional groups of the shale core sample; key structures and force field parameters of shale clay minerals in a target block are collected, and a shale clay mineral molecular model is established; establishing a plurality of fluid molecular models; establishing slit models, and establishing a multiphase fluid system model between the slit models to obtain a stable configuration; applying an external electric field to the stable configuration, and performing molecular dynamics calculation to obtain molecular trajectory coordinates and dynamics information of the multi-phase multi-component fluid; and calculating competitive adsorption data of the shale micro-nano pore multi-phase multi-component fluid under the action of the electric field. According to the scheme, the occurrence state and the competitive adsorption behavior of the shale micro-nano pore multi-phase multi-component fluid under the action of the electric field can be disclosed from the molecular scale.

The invention relates to the technical field of data processing, in particular to a liquid disperse dye for polyester fabrics and a use method thereof, and the dye comprises an azo or anthraquinone disperse dye main agent subjected to superfine grinding, a nonionic and anionic compound dispersant system, a fiber plasticizer and a stabilizer. According to the preparation method, molecular dynamics simulation and mesoscale dissipative particle dynamics simulation are combined, the synergistic effect of a dispersant adsorption configuration and double electric layer potential is quantified, and a nonlinear association rule of dynamic particle size control and dispersion stability is established; a multi-physics field coupling model is adopted to integrate fiber humidity, temperature gradient and pressure distribution parameters, and cross-scale collaborative optimization of microscopic interface action and macroscopic process parameters is achieved. According to the method, repetitive experiment iteration is replaced by digital design, the formula development period is remarkably shortened, the dyeing uniformity and the batch-to-batch reproducibility are improved, and the method is suitable for continuous dyeing production of high-density and superfine polyester fabrics.

The invention relates to the technical field of researching or analyzing materials by testing chemical or physical properties of materials, in particular to an intelligent analysis method for corrosivity of sulfide molecules in transformer oil. The influence of the oil environment on the adsorption energy is simulated and corrected in combination with molecular dynamics, a microscopic parameter database is constructed, and a corrosion risk grade classification rule and a generation rate prediction model are established. Oil data are collected in real time and input into the model to output a dynamic risk level, and a circulation rate adjusting or corrosion inhibitor adding instruction is triggered. Model parameters are regularly corrected by combining a closed-loop feedback mechanism, and a microscopic database is expanded, so that transfer learning prediction of unknown sulfide corrosion behaviors is realized. According to the method, the limitation of an existing single experiment condition is broken through, the relevance between a microcosmic molecular mechanism and a macroscopic corrosion behavior is dynamically analyzed, and the prediction precision under the multi-factor coupling effect is improved.

The invention discloses an AIREBO potential optimization method and system suitable for a multi-core processor, and relates to the technical field of molecular dynamics simulation. The method comprises the steps that atomic information is acquired, and a layered adjacency list is constructed according to the truncation radius characteristic of the AIREBO potential and the atomic information; a key sequence network is pre-constructed according to connectivity information between atoms in the adjacency list, and the pre-constructed key sequence network is utilized when the FLJ function is calculated; classifying and grouping according to different types of interactions among atoms, calculating FREBO functions in batches according to a classifying and grouping result, splitting calculation tasks, and processing the split tasks by using a multi-core processor; and integrating the calculation results of the FLJ function and the FREBO function, and combining the calculation result of the FORRSION function to obtain the final AIREBO potential. According to the method, AIREBO potential efficient parallel computing is realized on the basis of a multi-core processor architecture, and the overall molecular dynamics simulation efficiency is improved.

The invention discloses a lubricant adsorption and friction regulation and control method based on molecular dynamics simulation, which comprises the following steps: S1, constructing a lubricant molecule and friction pair metal unit cell model, generating topological structure information based on a minimum structure unit, and constructing a lubrication system model with a sandwich structure; s2, giving force field parameters to the lubrication system model, and performing geometric structure optimization and dynamic relaxation; s3, giving surface charges to the upper and lower friction pairs for targeted adsorption simulation of the lubricant; and S4, applying uniformly distributed contact pressure and constant sliding speed to the upper friction pair to perform friction simulation of the lubrication system. According to the lubricant adsorption and friction regulation and control method based on molecular dynamics simulation, a targeted adsorption strategy of a solid-liquid interface is established, the microcosmic adsorption process of the lubricant is reproduced, controllable regulation of friction characteristics is achieved, the human resource cost in actual experiments is reduced, and manual operation errors are reduced.

The invention provides a drinking water pipeline anti-corrosion powder coating multi-component proportioning intelligent batching method and system, and relates to the technical field of intelligent manufacturing, and the method comprises the following steps: obtaining drinking water pipeline anti-corrosion powder coating raw material parameters and formula information; constructing a quantitative characteristic volume element numerical simulation unit, and performing multi-scale bridging calculation in combination with microscopic molecular dynamics and a macroscopic discrete element method; inputting parameters, calculating, correcting a formula, and converting into control parameters; dynamically adjusting parameters through a regression network self-learning feedback compensation algorithm; starting mixing equipment for batching, calculating the uniformity in real time, stopping mixing after the uniformity reaches the standard, detecting a finished product, and generating a report. According to the invention, through a self-learning feedback compensation algorithm based on a regression network, in combination with real-time weight detection and a material blockage identification result, intelligent dynamic adjustment of quantitative feeding control parameters is realized.

The invention discloses a method for obtaining hydrogen solubility in slag based on microstructure analysis, and belongs to the field of high-temperature melt physical property characterization. The method comprises the following steps: determining initial components of a simulation system; establishing an initial structure model of the water molecule-containing slag system; determining a potential function for describing the simulation system; simulation calculation parameters are set, LAMMPS software is operated for simulation calculation, and simulation result data such as an atomic coordinate file and free energy of a simulation system are obtained; the atomic coordinate file is imported into visual software for statistical analysis and visual processing, and microstructure information of the slag is obtained; and calculating the hydrogen solubility of the slag according to simulation result data such as free energy. According to the method, the microstructure information of the atomic scale of the slag and the hydrogen solubility of the slag are calculated by adopting a molecular dynamics simulation method, so that the blank of experimental data can be filled, theoretical guidance is provided for controlling the hydrogen content of the slag, and a theoretical foundation is laid for controlling the hydrogen content of the molten steel.

The invention discloses a microemulsion interfacial tension efficient prediction method and system based on active learning and molecular dynamics. According to the method, 217 molecular descriptors corresponding to each molecular structure are calculated by adopting an RDKit software package, and the descriptors are used for representing molecular structure characteristics and serve as input variables of a machine learning model, so that key structure information including molecular branching degree, polarity and the like is transmitted. For an oil-water-surfactant ternary interface system, the oil-water interfacial tension in the presence of a surfactant is simulated and calculated through molecular dynamics, and an IFT value is set as a model prediction target. An active learning mechanism is introduced, and iterative sample labeling in the molecular dynamics simulation process is guided; and integrating the obtained IFT data with the molecular descriptor features, constructing a machine learning data set, and training a random forest model. According to the method, the problem of screening a high-performance surfactant layer by a middle-phase microemulsion system can be solved, and the ultra-low oil-water interfacial tension can be rapidly and efficiently screened.