10 results about "Crystal properties" patented technology

The application relates to a training method and device of a crystal property prediction model and a computer device. The method comprises the following steps: obtaining a sample crystal and a property label corresponding to the sample crystal; the sample crystal comprises a plurality of sample atoms; determining respective atomic coordinates of each sample atom, and determining orbital characteristics of the sample atoms according to the atomic coordinates; determining respective atomic potential energies of the sample atoms according to the orbital characteristics, and determining a predicted property corresponding to the sample crystal according to the atomic potential energies; training the crystal property prediction model according to the difference between the predicted property and the property label, stopping when a first training stop condition is reached, and obtaining a trained crystal property prediction model; and the trained crystal property prediction model is used to determine the property of the crystal. The method can improve the accuracy of predicting the property of the crystal.

The application discloses a device for micro in-situ characterization of hydrate crystal characteristics of a solid-liquid interface, which comprises a visual reaction kettle, a test sample, a simulated disturbance system, a confocal Raman spectrometer and a constant-temperature control system. The test sample comprises solid wafers arranged oppositely and liquid bridges between the solid wafers. The test sample is placed into the visual reaction kettle, and the temperature and pressure in the visual reaction kettle are adjusted to a low-temperature and high-pressure state. According to different test requirements, a three-axis moving force arm of the simulated disturbance system can drive the solid wafers to move in different directions, so that different degrees of disturbance can be simulated. Meanwhile, the disturbance of fluid injection / extraction, a magnetic field, an electric field and pH value change can also be simulated. In the state of disturbance, micro-analysis information of hydrate structure, components, pore occupancy, hydration number and the like in a natural gas hydrate generation / dissolution dynamic process on the solid-liquid interface can be obtained, so as to provide a theoretical basis for natural gas hydrate accumulation and exploitation.

The application discloses a driving-containing micro light emitting diode (Micro-LED) structure and a preparation method thereof. The structure comprises a gallium nitride (GaN) layer with a non-polar upward crystal face, a mask layer containing micropores, a GaN three-dimensional triangular island, and a high electron mobility transistor (HEMT) structure arranged on one side of the triangular island and a Micro-LED structure arranged on the other side of the triangular island. The GaN island with a three-dimensional structure is obtained by using selective epitaxy combined with lateral epitaxy. The GaN island naturally forms a left-right symmetrical structure due to its crystal properties. The HEMT and the Micro-LED structure are arranged on the two sides, respectively. The HEMT on one side can directly drive the Micro-LED on the other side. The problems of additional driving of the traditional Micro-LED are solved. The micropores are not bound to the current during the traditional selective epitaxy Micro-LED structure. In addition, the Micro-LED with an independent structure is grown on the inclined surface of the triangular island. The adverse effects caused by etching damage of the quantum well and the P-type layer in the traditional micro-processing technology can be avoided. The edge effect of each light emitting unit is effectively inhibited. The light emitting efficiency is improved. The light emitting units are arranged on the basis of close packing. The area of the epitaxial wafer can be effectively utilized to the maximum extent. The economic benefits are maximized.

The application discloses a symmetrical gallium nitride (GaN) based high electron mobility transistor (HEMT) structure and a preparation method thereof. x Ga 1‑x The HEMT structure comprises a GaN layer with a non-polar face as an upward crystal face, a mask layer, a GaN stereoscopic triangular island, an Al The application utilizes selected area epitaxy and combines lateral epitaxy to obtain a GaN island with a stereoscopic structure, the GaN island naturally forms a left-right symmetrical structure due to its crystal properties, and the HEMT prepared based on the feature has atom level consistency, and the left-right symmetrical semi-polar face AlGaN / GaN heterojunction can generate a two-dimensional electron gas (2DEG) with a convenient control concentration, realizes high-quality, high-performance and high-consistency paired GaN based HEMT, and can be applied to mirror current sources, differential amplification and other circuits, and has better consistency and stability compared with traditional devices.

The present application relates to the technical field of crystal material property prediction, and in particular to a crystal property prediction method and model based on graph convolution and attention mechanism, which first one-hot encodes and projects atomic key physical properties as node features, then calculates local and global potential edge features and fuses them, combines atomic geometric information to generate directional edge features through a directional message passing network, inputs the multi-source edge features and node features into a graph convolution network to complete feature iterative updating, dynamically filters the features through element-by-element gating attention mechanism, obtains a crystal-level global representation through global pooling, and inputs the crystal-level global representation into a fully connected network to output a prediction result. The model corresponds to three major modules of input, interaction and output, can accurately model atomic multi-scale interactions, explicitly represent directional interactions, dynamically adjust feature weights, has excellent prediction accuracy and generalization ability, and is suitable for property prediction of various crystal systems.

The invention relates to the technical field of artificial intelligence, and discloses a crystal structure screening method and system, a terminal and a storage medium. The method comprises the following steps: generating a plurality of first candidate crystal structures through a crystal structure generation model according to input target crystal property parameters; performing physicochemical property prediction on the plurality of first candidate crystal structures to obtain a plurality of candidate crystal property parameters; screening out a second candidate crystal structure meeting a preset condition from the plurality of first candidate crystal structures according to the difference between the plurality of candidate crystal property parameters and the target crystal property parameter; and taking the second candidate crystal structure and the target crystal property parameters as training data, updating model parameters of the crystal structure generation model, repeatedly executing the generation, prediction and screening steps, and carrying out iterative optimization until a preset termination condition is met, thereby obtaining a plurality of target crystal structures. According to the method, the candidate structure related to the target property can be automatically generated, and the design efficiency is improved.

The invention relates to the technical field of artificial intelligence, and discloses a multi-graph crystal property prediction method based on geometry and state driving, and the method comprises the steps: S1, reconstructing crystal structure information: reconstructing the crystal structure information into a local crystal graph and a global crystal graph which share a node set, connecting edges of the local crystal diagram are constructed through a neighborhood truncation strategy based on the Euclidean distance; the global crystal diagram is fully connected; s2, extracting local features to obtain the local features; s3, extracting global features to obtain the global features; s4, updating and residual connection through iterative interaction between local features and global features, and completing feature extraction of the crystal structure; and carrying out global average pooling operation convergence to obtain graph-level feature representation, and carrying out full connection layer mapping to obtain final target property prediction. According to the method, geometric drive enhanced local feature extraction and state drive enhanced global feature extraction are introduced, and the limitation of an existing GNN method in the aspects of complex geometric interaction and long-range dependence modeling is overcome.

This invention relates to the field of crystal property prediction technology, and proposes a method for predicting the properties of crystal materials. The method includes: acquiring a crystal informatics file of a target crystal; mapping the atoms in the target crystal to a three-dimensional grid with adjustable resolution based on the atomic structure information in the crystal informatics file, and filling each grid cell with the feature values ​​of the atoms at corresponding positions to obtain the three-dimensional distribution features of each atom; inputting the three-dimensional distribution features of each atom into a neural network to obtain the property prediction result of the target crystal, wherein the neural network is trained with the three-dimensional distribution features of all atoms in the known crystal as input and property labels as supervision. This invention achieves end-to-end direct prediction of crystal properties from a crystal informatics file by reconstructing the crystal structure into three-dimensional distribution features, possessing the advantages of high computational efficiency, complete preservation of spatial information, and flexible and adjustable representation granularity.

The application discloses a crystal property prediction method based on a graph neural network, and relates to the field of material science. The method comprises the following steps: taking atoms of a crystal to be predicted as nodes, taking atomic bonds as edges, and encoding the nodes and the edges to obtain node feature vectors and edge feature vectors, so as to form a crystal graph; based on a graph neural network architecture, introducing an edge convolution operator and a related self-attention mechanism, and constructing a crystal property prediction model; and inputting the crystal graph into the crystal property prediction model to obtain a crystal property prediction result. The application can grasp long-range information between atoms, and then realize high-precision prediction of crystal properties.

A method is provided for manufacturing a crystalline, preferably monocrystalline SiC-based device. The method includes combining: the use of a specific buffer layer, through its aspects which are refractory and inert to temperature and through its crystalline properties close to those of SiC, to grow the device, and the laser lift-off of the device by sacrificing the buffer layer, the latter having a thickness enabling a functional absorption of a laser lift-off radiation, while remaining sufficiently low to not have dislocations which can propagate to the device during its growth. The thermal balance is reduced, with respect to the known methods and the integrity of the device is best preserved, at least relative to what would be observed, if a thermal annealing, for example at a temperature greater than 400° C., had to be applied to lift off the device.