65 results about "Potential energy surface" patented technology

The invention discloses a construction method of a TiH binary system machine learning potential. The construction method comprises the following steps: constructing a reference electronic structure data set by adopting first principle calculation software VASP; training and testing an artificial neural network potential-ANN potential model on the reference data set by using the artificial neural network model; vASP and ANN potential obtained through training are used for calculating and comparing a Dimer curve, a lattice constant, an elastic modulus and the like for performance testing; and performing targeted improvement on data with large comparison error between the ANN model and the DFT result in model test and performance test results by increasing related configuration weights until an ANN potential model conforming to the precision is obtained. The machine learning potential model constructed by the invention can better fit the interatomic interaction potential energy surface of the TiH binary system, solves the problems of small time-space scale and low precision of the traditional empirical potential in the calculation of the first principle, and provides a technical basis for the high-precision and large-size simulation and research of the TiH binary system.

The invention belongs to the technical field of computational chemistry, and particularly discloses a mechanism research and analysis method for catalyzing oxidation of 2, 4-tert-butylphenol by using a double-copper biomimetic oxygen copper intermediate [Cu (II) 2O2TMP32] < 2 + >, which is based on a density functional theory (DFT), adopts a gas phase model to calculate a QM reaction mechanism, and performs structure optimization on the intermediate and a transition state; a PCM continuous medium solvation model is adopted, single-point energy correction is carried out, heat and enthalpy correction is obtained by calculating frequency analysis, the whole catalytic reaction potential energy surface is calculated by considering the Van der Waals effect, so that a possible reaction channel is obtained, and on the basis of QM calculation, possible intermediates and transition states are searched again under a QM / MM solvent model by adopting a QM / MM method, so that the calculation efficiency is improved. And determining the reaction speed step and the reaction mechanism. A complete theoretical method for simulating the system is established, a basis is provided for treating the system to develop a new solvent model, and meanwhile, an important theoretical basis and a technical reference are provided for design and development of efficient novel copper biomimetic catalytic phenol.

The invention discloses a method for exploring a heterogeneous catalytic reaction network based on a deep potential energy surface model, and the method comprises the steps: carrying out the accurate prediction of the free energy change of all possible element reactions on a catalyst through the combination of transfer learning and a density functional theory, and constructing a reaction network diagram based on a graph theory method; an improved Dijkstra method is used for searching a reaction network diagram to determine a reaction mechanism, and the selectivity of the catalyst is explored based on a Markov chain method. According to the technical scheme provided by the invention, when the CO2 reduction reaction mechanism on the monatomic alloy is explored, the prediction error MAE of the electron energy of each intermediate is only 0.16 eV, the calculated amount is reduced by 90%, the dominant path of the CO2 reduction reaction is visually displayed, and a new normal form is provided for complex mechanism exploration and catalyst screening.

The invention relates to the technical field of machine learning, and discloses a doped cluster ground state structure optimization method and system based on machine learning, and the method comprises the steps: collecting and optimizing original doped cluster data as a doped cluster standard data set, and dividing the doped cluster standard data set into a training set, a verification set and a test set; constructing a doped cluster potential energy surface fitting machine learning network by adding an interatomic interaction attention mechanism in an original SchNet, and training by using a training set and a verification set; inputting the test set into the trained doping cluster potential energy surface fitting machine learning network, and obtaining and outputting a final doping cluster potential energy surface; and performing structure search and optimization on the final doped cluster potential energy surface by using an artificial bee colony algorithm, and continuously updating the structure until a ground state structure with the lowest energy is found. According to the method, the fitting accuracy of the potential energy surface is improved, the calculation benefit is improved, and good transportability is achieved.

The invention relates to an intelligent state monitoring method and system for a high-voltage isolation switch operating mechanism, and relates to the technical field of power equipment fault diagnosis, and the method comprises the steps: enabling a collected real-time sequence to update a standard operation response potential energy surface, obtaining a real-time operation response potential energy surface, generating a phase response difference tensor through data projection, and obtaining a real-time operation response potential energy surface; and depicting deviation characteristics of actual and standard operation states. And then, in the constructed graph attention network, on the basis of a real-time sequence, monitoring parameters and video motion characteristics, constructing a multi-modal sequence state graph, and determining a state typing result through fine-grained recognition and interpretable analysis of a fault. And finally, introducing a cyclic fingerprint residual model, performing clustering optimization based on a real-time sequence, determining an abnormal deviation index, and combining the abnormal deviation index with a state typing result to determine a fault diagnosis result. Therefore, the accuracy of intelligent state monitoring of the high-voltage isolation switch operating mechanism can be effectively improved, and the method can be suitable for non-ideal environments, low dominant anomalies and other conditions.

The invention discloses a method for predicting the coverage degree of an H ion negative electrode in a Zn aqueous battery, and relates to the technical field of surface catalysis. In order to solve the defect that in the prior art, it is difficult to accurately predict the coverage degree of H ions on the surface of a Zn negative electrode on a multi-scale level, the technical scheme provided by the invention comprises the steps that a three-dimensional atom structure model of H atoms and a Zn electrode adsorption surface is constructed, formation energy and adsorption energy of the H ions and water molecules are calculated, and a reaction potential energy surface is established; constructing a reaction path and an electron transfer behavior, defining potential related parameters, and outputting reaction rate, current density and coverage data; establishing a phase field dilute material transfer model containing temperature, pH and pressure parameters, and completing material migration and charge distribution calculation; interface physical field parameters are fed back to the microdynamics model to form microcosmic-macroscopic bidirectional data interaction and realize self-consistent convergence; and outputting a coupling model result to obtain multi-scale prediction data. The method is suitable for active site identification and performance prediction in electro-catalytic reaction.

This application provides a method and apparatus for training a molecular multiconformation prediction model. The method includes: acquiring training data, which includes molecular structure representation samples and molecular conformation samples; processing the molecular structure representation samples and molecular conformation samples using the molecular multiconformation prediction model to be trained to obtain a training output; constructing a loss function value based on the training output and the molecular conformation samples; and, if the loss function value or the number of training rounds is within a preset range, using the trained molecular multiconformation prediction model as the molecular multiconformation prediction model. This application can achieve fast and accurate prediction of multiple three-dimensional conformations of molecules without analyzing their potential energy surfaces, reducing the computational resources and time consumed in resolving multiple three-dimensional conformations of molecules.

The invention provides an artificial neural network potential energy function development method for simulating a dynamic process of a molecular sieve packaged platinum cluster in an oxygen environment, which comprises the following steps of: performing potential energy surface sampling on a system of a Silicalites molecular sieve packaged platinum nanocluster and O2 and Pt-O structures by using a random surface walking global optimization method of LASP software; a part of structures are randomly extracted from a data set obtained through sampling, VASP software is used for structural optimization, and the obtained structures and data such as energy and force of the structures are added into a DFT training set. Neural network training is carried out on the DFT data set by means of machine learning, and an artificial neural network potential energy function G-NN is obtained; the artificial neural potential energy function obtained by training not only meets the expectation in calculation precision, but also has the advantage of magnitude order in calculation speed, and overcomes the defects of traditional molecular dynamics in calculation systems and calculation speed.

The invention belongs to the technical field of computational chemistry and artificial intelligence crossing, and provides a molecular potential energy surface prediction method based on deep learning. The method comprises the following steps: inputting a structure file of an unoptimized molecule, and reading and predicting energy and force of a current molecular structure by utilizing a machine learning potential model; and then, judging whether the structure is converged or not according to a prediction result by adopting a GeomeTRIC algorithm, and if not, adjusting coordinates to generate a new structure and performing circular prediction until the structure is converged. According to the method, the quantum chemistry and the deep learning technology are combined, the calculation efficiency can be greatly improved, complex inter-atomic interaction in molecules can be fully captured, and the prediction accuracy is ensured; and meanwhile, batch processing and automatic generation of a quantum chemistry software interface are supported, and the method is particularly suitable for high-throughput molecular structure optimization in the fields of drug discovery, material science and chemical product design.

The present invention relates to the field of machine learning technology, and discloses a method and system for optimizing the ground state structure of a doped cluster based on machine learning. The method comprises: collecting original doped cluster data and optimizing it as a standard doped cluster data set, and dividing the standard doped cluster data set into a training set, a validation set, and a test set; constructing a doped cluster potential energy surface fitting machine learning network by adding an interatomic interaction attention mechanism to the original SchNet, and training it using the training set and the validation set; inputting the test set into the trained doped cluster potential energy surface fitting machine learning network to obtain and output the final doped cluster potential energy surface; and using an artificial bee colony algorithm to perform structure search and optimization on the final doped cluster potential energy surface, continuously updating the structure until the lowest energy ground state structure is found. The present invention improves the accuracy of potential energy surface fitting, enhances computational efficiency, and has good portability.

The invention relates to the technical field of computational chemistry and drug screening, and discloses a fluorinated derivative screening method based on computer-aided design, which comprises the following steps: acquiring an initial binding conformation of fluorine-containing molecules and a target system, and constructing a follow-up local orthogonal coordinate system by taking the axial direction of a fluorocarbon bond as a reference; projection coordinates of the environmental particles relative to the fluorocarbon bonds are calculated and mapped as a spherical coordinate index, a preset anisotropic potential energy surface grid is called, and a potential energy value is calculated through interpolation; the method comprises the following steps: generating an anisotropic correction term, monitoring the modulus length of the energy gradient in real time, and when the modulus length of the energy gradient exceeds a sensitive threshold value, adaptively and nonlinearly reducing a sampling step length and executing high-frequency local sampling in a sensitive area. The problem of false negative activity prediction caused by insufficient sampling when a traditional equal-step algorithm is used for processing anisotropic distribution of fluorine atom electron clouds is solved, and the recognition precision and screening efficiency for weak directional interaction such as halogen bonds are improved.

This invention discloses a multi-objective adaptive control method for a power generation, grid, load, and storage system in an industrial park, relating to the field of energy management technology. The method first constructs a generalized state space of physical equipment and virtualized production tasks, mapping the production tasks to a virtual energy storage model and constructing a congestion risk potential surface function. Then, it calculates and decomposes the total regret value of the strategy, dynamically updates the objective function weights based on external regrets, and corrects the virtual model parameters online based on internal regrets. Subsequently, it constructs a collaborative optimization proposition using the updated weights and parameters, incorporating congestion risk into the optimization objective, and solves for the optimal control sequence. Finally, it decouples the control sequence into physical charging / discharging commands and production operation commands. This invention achieves compatibility between discrete production and continuous energy control through virtualization mapping and utilizes a two-layer regret mechanism to achieve adaptive adjustment of strategies and parameters, improving the system's economy and robustness.

The application discloses a calculation method of a reaction mechanism of cyanamide prepared in an alkaline environment and application thereof in byproduct control, and the calculation method comprises the following steps: step 1, constructing a molecular initial model of a reaction system containing a hydroxyl water molecular cluster, performing structural optimization and vibration analysis tasks on the model by using a density functional theory method, and calculating the molecular configuration to obtain a reasonable configuration without virtual frequency; step 2, searching for a reaction transition state based on the reasonable configuration of step 1, and verifying the reasonableness of the transition state; step 3, calculating the free energy in an alkaline aqueous solution environment, and drawing a potential energy surface diagram to determine the reaction rate control step; and step 4, selecting the reaction calculation hydrogen dissociation energy and hydrogen combination energy values of the reaction rate control step containing an intramolecular hydrogen migration process. The calculation method can simulate and calculate phenomena that are difficult to observe by experimental means, obtain reaction information of each elementary reaction process in an actual reaction, obtain the essential law of the reaction mechanism in the alkaline environment, and provide a theoretical reference for process improvement to reduce byproduct generation and promote the selectivity of the main reaction.

The invention discloses a tug system maintenance operation risk supervision method and system based on the Internet of Things, and relates to the technical field of the Internet of Things, and the method comprises the steps: collecting multi-physical-quantity data, accessing the Internet of Things, carrying out the preprocessing of original data, and generating standard input; inputting the preprocessed data to a coupling resolver, capturing characteristics among physical quantities, and dividing a coupling state; generating risk factors based on abnormal coupling, and constructing a first safety potential energy surface and a second safety potential energy surface; comparing the two types of potential energy surface data, and outputting execution admission judgment of the maintenance step; and collecting the track of the maintenance personnel, comparing with the path template, and triggering the behavior lock if deviation occurs. According to the invention, through a cooperation mechanism of multi-physical quantity coupling analysis, potential energy surface admission determination and personnel trajectory supervision, real-time risk identification and safe controllable execution of the whole tug maintenance operation process are realized.

The invention discloses a method for searching a minimum energy path from a discrete potential energy surface and a related product, the method is applied to a discrete potential path optimizer, and the method comprises the steps that an energy coordinate data set in an input file is read, and each energy coordinate data in the energy coordinate data set comprises a three-dimensional coordinate and an energy value corresponding to the three-dimensional coordinate; the energy coordinate data set is simplified based on a preset energy cutoff value, a simplified energy coordinate data set is obtained, and the energy value corresponding to each three-dimensional coordinate in the simplified energy coordinate data set is smaller than or equal to the energy cutoff value; searching energy coordinate data corresponding to a minimum energy path from the simplified energy coordinate data set based on a path connection condition between a preset starting point coordinate and a preset end point coordinate; and sorting the energy coordinate data corresponding to the minimum energy path based on preset grid precision to obtain the minimum energy path corresponding to the discrete potential energy surface. Therefore, the minimum energy path can be searched from the discrete potential energy surface.

A machine learning potential energy surface model construction method comprises the following steps: collecting data for training a model, the data comprising data of one or more systems, the data of each system comprising atomic coordinates of the system and corresponding properties of the system; performing data inspection and data storage on the collected data; constructing a machine learning potential energy surface model, comprising: establishing a feature engineering; obtaining a final data set for training the model through the feature engineering; constructing a machine learning model; and training the machine learning model using the final data set to obtain the machine learning potential energy surface model. By using a data-driven method, the present application avoids manual feature extraction, and the model autonomously iterates learning from the data set, thereby avoiding the introduction of human bias. The model of the present application has very strong scalability, can be scaled to larger systems, and is not limited by the properties of the target system, and simultaneously supports multi-phase systems and periodic / non-periodic systems.

The present invention proposes an outlier-aware adaptive mixed-precision quantization method and system for an interatomic potential energy surface model. By using mixed-precision quantization with different data widths for coefficients of different-order terms, the outlier-aware quantization method proposed in the present invention can effectively improve the efficiency of quantization representation. The present invention also proposes a mechanism and method for systematically controlling the errors in polynomial representation caused by quantization, and proposes a method for adaptively selecting the optimal quantization precision for mixed-precision quantization of coefficients of different-order terms under the constraints of error control. By analyzing the data of the polynomial coefficient table of the interatomic potential energy model, the present invention adaptively provides an optimal mixed-precision quantization scheme and performs outlier-aware mixed-precision quantization operations on the polynomial coefficient table based on this scheme, thereby improving the inference scale and speed of the interatomic potential energy model.

The application discloses a kind of optimization method and device for identifying Cu-Zn alloy cluster structure potential energy surface, comprising: randomly generating several Cu-Zn alloy clusters, constitute population structure library n pop ; develop shell script that can efficiently call Gaussian16 quantum chemistry software, carry out first local structure optimization to n pop ; innovative surface atom self-adapting reorganization strategy is proposed, iteratively move cluster surface atoms to self-adapting generated empty space sites, execute second stage structure optimization;Through crossover, variation operation, in combination with similarity detection and potential energy comparison, extract the optimal structure of binary Cu x Zn y Cluster.Using the technical scheme of the application, the local and global spatial search capability of genetic algorithm is optimized and improved, and the stability and electronic structure of Cu-Zn alloy cluster can be efficiently analyzed by calling quantum chemistry software.

A computing system including one or more processing devices configured to compute a simulation of a chemical system. Computing the simulation includes, at a machine learning force fields (MLFF) model, computing local label sets of respective local regions. Each local label set includes MLFF labels. Computing the simulation further includes computing local uncertainty values and identifying local regions based on the uncertainty values. For each identified local region, computing the simulation further includes computing a substructure that surrounds that region. The substructure is selected by computing a substructure boundary that approximately minimizes a substructure uncertainty. Computing the simulation further includes selecting atomic positions within the substructure that approximately minimize the substructure uncertainty. Computing the simulation further includes computing substructure labels via quantum chemical simulation, training the MLFF model using the substructure labels, and outputting a potential energy surface (PES) specified by the MLFF labels and the substructure labels.

The present invention discloses a method for identifying the path of ligand-gated ion channels based on molecular dynamics simulation. The path identification method includes releasing the ligand-gated ion channel from the constrained state by using conventional molecular dynamics simulation, simulating the random process of ligand binding to the ligand-gated ion channel, and then performing targeted molecular dynamics simulation. After the targeted molecular dynamics simulation, conventional molecular dynamics simulation is performed again to further optimize the structure of the ligand-gated ion channel so that it is in a relaxed state. Gaussian accelerated molecular dynamics simulation is used to smooth the potential energy surface of the ligand-gated ion channel and reduce the energy barrier. Further combined with methods such as dynamic network analysis, the binding sites and allosteric paths of the ligand-gated ion channel and the ligand are analyzed, which is of great significance for studying the mechanism of action of ligand-gated ion channels and ligands binding and developing new allosteric regulators.

The invention discloses a diacetylene topological chemical reaction method which comprises the following steps: spin-coating a diacetylene solution on a substrate to form a coating film; and irradiating the coating film by adopting an infrared light source, and reacting to generate polydiacetylene. Compared with side reaction and degradation caused by the fact that high-energy rays enable the material to enter an electron excitation state and material fragmentation caused by severe spatial change of molecules under high polymerization, mid-infrared light vibration excitation in the method serves as a means capable of triggering molecular vibration under an electron ground state, and under the mild condition, the mid-infrared light can be used as a means capable of triggering molecular vibration under the electron ground state. Therefore, various bad effects generated in the electron excitation state can be avoided.

The present invention discloses a method for accelerating the search of material structures, including: searching for potential energy surface structures through a global potential energy surface search method; calculating the potential energy and atomic forces corresponding to the extracted potential energy surface structures by using first-principles calculations and collecting them as an initial training data set; training a machine learning potential energy model representing the potential energy surface of the system through a machine learning model; combining the global potential energy surface search method to perform screening sampling on the potential energy surface of the system, updating the training data set and the machine learning potential energy model; performing high-throughput search on the target system structure through the global potential energy surface search method, predicting the structure potential energy and performing structure screening; performing first-principles calculations on the screened structures to obtain the corresponding potential energy and atomic forces, using the potential energy and atomic forces as a test data set to test the prediction performance of the machine learning potential energy model, and calculating the formation energy of the structure through the potential energy. The present invention also discloses a device, an electronic device and a medium for accelerating the search of material structures.

The invention discloses a potential energy surface acquisition method based on global feature physical constraint and machine learning, and the method comprises the steps: constructing a general radial function and an angular basis function based on a material structure, and determining a basis function for the expansion of a two-body interaction function based on the general radial function and the angular basis function; constructing a potential energy surface model based on the primary function; obtaining a training set, and pre-training the potential energy surface model based on the training set; and obtaining a material structure corresponding to a target material, and determining the potential energy surface according to the material structure and the pre-trained potential energy surface model. According to the method, the general radial function and the angular basis function are constructed based on physical constraints, so that the potential energy surface model with physical expansibility is finally constructed based on the general radial function and the angular basis function, and the problems that the physical characteristics of a material system are neglected when an existing machine learning potential function is predicted through statistical analysis of big data, and the prediction efficiency is low are effectively solved. And dynamic simulation may be lack of reliability.

This invention provides a method for the controllable synthesis of high-quality quantum dots based on pre-nucleated clusters that reach a minimum potential energy surface through chemical self-assembly, belonging to the field of semiconductor nanomaterials technology. The quantum dots of this invention are prepared by reacting a pre-nucleated sample of semiconductor material with pre-prepared quantum dots to obtain high-quality quantum dots grown heterogeneously (core-shell structure) or homogeneously. This method, based on the pre-nucleated clusters, allows for the control of quantum dot size growth, narrowing the quantum dot distribution and avoiding the need to control the bonding temperature of the semiconductor material. This method improves the accuracy of quantum dot size control, and the quantum dots prepared by this method also exhibit significant luminescent properties, effectively expanding the applications of quantum dots and showing great promise.

A method for training and subsequently executing a machine learning network of both an autoencoder and a machine learning model in the context of machine learning inter-atomic potential is disclosed. The systems described herein are configured to embed atomic locations and categories of a given atomic system, and apply them to an autoencoder to learn auxiliary attributes, and to a machine learning model to learn local energy. The auxiliary attributes are then used to generate an auxiliary Hamiltonian description. Attributes, such as the total energy of the atomic system, are determined by combining both the auxiliary Hamiltonian description and the local energy. By processing machine learning via both an autoencoder and a machine learning model, such methods ensure that both long range and short range effects are considered while also appropriately achieving realistic discontinuities and / or transitions within potential energy surfaces.

The invention relates to the cross field of computational chemistry and artificial intelligence, in particular to a multiphase chemical reaction transition state certainty generation method and system based on physical constraint and adaptive optimization and a storage medium. The method is executed by a computer system and comprises the following steps: acquiring initial structure data of reactants and products; calling a nonlinear initial guess module to execute path search based on the coarse-grained potential energy surface so as to generate a nonlinear initial guess path; a constraint optimal transmission module is called to generate a candidate transition state TS structure; the invention provides a multiphase chemical reaction transition state certainty generation method and system based on physical constraint and adaptive optimization and a storage medium, which not only keep high efficiency of a machine learning method, but also realize accurate, robust and reliable simulation of complex and real chemical scenes.

The invention belongs to the field of molecular simulation, and particularly relates to a method for constructing a reactive force field based on a multi-pole moment model. Comprising the following contents: a charge penetration effect, a polarization effect, a charge transfer effect, Van der Waals interaction and a three-body potential energy form suitable for a chemical reaction; a dynamic electric multi-pole moment method suitable for chemical reaction; the invention relates to a method for constructing a potential energy surface data set with six degrees of freedom. The invention provides a simple and effective force field model for researching chemical reaction and a parameter optimization method for users. According to the method, a potential energy surface data set composed of a large number of conformations with six degrees of freedom can be generated, and a data basis is provided for model development and parameter optimization. The method is mainly used for researching the chemical reaction process and the mechanism thereof, and has a wide application prospect in the research fields of chemistry, material science and the like.

This invention relates to the field of engineering machinery safety technology, specifically disclosing a load stability prediction system for telescopic boom forklifts based on the force exerted by the boom. The system collects motion sensing data and stress wave sensing data at the boom hinge; calculates a cross-spectral coherence function based on the motion data to generate a hinge coherence disorder index; performs time-frequency transformation on the stress wave data and automatically identifies energy impact patches, extracting their peak energy, center frequency, and duration; and generates a transient collision intensity spectrum index based on sensitive frequency band mapping and aggregation; constructs a time-series comprehensive feature vector from the two indices, inputs it into a pre-trained multi-layer gated recurrent unit structure for nonlinear dynamic system identification, and outputs a fused stability assessment state quantity; maps this state quantity to a virtual potential energy surface for multi-step forward extrapolation, calculates the dynamic stability margin value, and issues an early warning when the margin is lower than an adaptive threshold; this invention achieves early and accurate prediction of nonlinear jump instability.

The invention provides a method for calculating and evaluating the safety of an explosive through neural network potential. The method comprises the following steps: S1, obtaining a microstructure image of a binder explosive through an in-situ transmission electron microscope (TEM); s2, establishing a molecular model of an energetic material and a molecular model of a binder according to the obtained microstructure image, and modifying the microstructure image; s3, performing neural network training on data obtained by analogue simulation, and fitting potential energy surfaces of the molecular model of the energetic material and the molecular model of the binder; s4, simulating the evolution of the explosive along with time under the load effect; and S5, analyzing a simulation result. According to the method for calculating and evaluating the safety of the explosive through the neural network potential, all explosives which have been applied and have application potential at present can be evaluated by adopting the established method for calculating the safety of the real microstructure of the binder explosive based on the neural network potential, so that the application of novel explosives is greatly promoted; and great convenience is brought to ammunition safety engineering personnel.