18 results about "Computational design" patented technology

The invention relates to a heat supply prediction method and system based on spatial-temporal feature fusion deep learning, and the method comprises the following steps: S1, carrying out the collection and fusion of multi-source heterogeneous data, and constructing an integrated data set; s2, preprocessing the data; s3, constructing a graph structure model of the heat supply system, and constructing a weighted undirected graph; s4, constructing and executing forward calculation of the space-time double-flow deep network; s5, designing a composite loss function including mean square error loss and physical constraint loss, and performing joint optimization training on the space-time double-flow deep network; and S6, performing multi-step heat supply load prediction by using the trained model, outputting a heat supply load curve of each heat exchange station in a specified time period in the future, and integrating a prediction result with a heat supply scheduling system. The method has the advantages that the prediction precision is improved compared with that of a traditional machine learning model by capturing the spatial-temporal characteristics at the same time, and the advantages are more remarkable in extreme weather.

This invention belongs to the field of enzyme engineering technology, specifically relating to an enzyme engineering method and its application in biocatalysis. Based on the excellent performance optimization capabilities of the deep learning-guided protein sequence design model ProteinMPNN, this invention developed a computational design framework called DeepPCD. This framework integrates deep learning-guided sequence design, physical energy calculation, and molecular dynamics simulation, constructing a three-level intelligent screening process from "massive generation" to "high-precision prediction." Using this strategy, nitrile hydrolase (EC 3.5.5.1) was mutated, resulting in a nitrile hydrolase mutant with improved stability, specificity, and enzyme activity, capable of efficiently and specifically catalyzing the hydrolysis of nitrile compounds to carboxylic acids.

The application discloses a kind of novel photovoltaic device transient dynamics calculation design system and method, system includes: user parameter input module is used to receive and manage the input parameter required by simulation;Device structure construction module is used to construct the layered structure model of target device based on input parameter, and define the space interval, physical property and interface boundary condition of each layer;Physical model selection and coupling module is used to construct corresponding coupled partial differential equation set according to the device type of target device;Space grid division module is used to construct the space discrete grid of layered structure model, and the calculation precision of interface and thin layer area is enhanced using non-uniform grid division mode;Core numerical solution module is used to solve coupled partial differential equation set, and obtain simulation result;Data export module is used to output simulation result as general data format.

The application provides a kind of klystron high-dimensional parameter optimization method and system, comprising: using klystron one-dimensional large signal simulation software KlyH, the input design parameter is simulated and calculated, and initial data set containing design parameter and corresponding output parameter is generated;Regression prediction model of design parameter to output parameter is constructed, the normalized output change rate of design parameter is calculated based on regression prediction model, and the sensitivity of each design parameter to output parameter is determined according to the normalized output change rate;According to the sensitivity, the range of each design parameter is dynamically adjusted, the optimization search interval of each design parameter is obtained, and multi-objective optimization algorithm is used to optimize and solve in the optimization search interval, and the optimal solution set is obtained.The dimensionality reduction and search space compression of klystron design parameter are realized, the calculation efficiency and search quality are further improved, and reliable support can be provided for intelligent optimization design of high-performance klystron.

The invention relates to the technical field of intelligent manufacturing, and provides an intelligent lightweight method and device for an additive manufacturing support structure based on a virtual test. According to the method, a design area is formed according to the expansion of an original model structure, the material distribution of the design area is calculated according to the load, constraint and optimization target of a scaffold structure, and a scaffold structure topological optimization Pareto optimal solution set is formed based on interaction between a reinforcement learning agent and a virtual topological optimization environment by means of an artificial intelligence technology; according to stress simulation analysis of the optimal solution set of the support topology, the lattice gradient is calculated, and based on reinforcement learning and virtual lattice structure reinforcement environment interaction, a lightweight Pareto optimal solution set of the support structure is formed. According to the method, based on the mode that the topological optimization agent and the lattice strengthening agent carry out reinforcement learning in the virtual simulation environment, on the premise that frequent manual debugging and material object printing are not needed, the lightweight degree and structural strength of the support structure are improved, and efficient and intelligent lightweight design is achieved.

Disclosed is a method of operating a computing system. The method performed in the computing system having one or more processors and a memory storing one or more programs executed by the one or more processors, includes receiving one of a plurality of artificial neural network architectures as a backbone architecture, determining a structure of a DCIM (Digital Computing-in-Memory) macro based on the backbone architecture, generating an approximate addition candidate group of the DCIM macro based on a first algorithm, generating a heterogeneous approximate DCIM based on the structure of the DCIM macro and the approximate addition candidate group, and mapping channel-specific weights with respect to the heterogeneous approximate DCIM based on a second algorithm.

The invention relates to the field of computational chemistry, in particular to design accuracy and efficiency optimization in a transition metal chromophore computational design process. The invention aims to provide a complex design method based on a full historical data retention strategy, which not only retains failure data in an iteration process, but also classifies and differentiates the failure data. The situation of information overload and noise interference under a full historical data retention strategy is changed, and the learning efficiency and reasoning quality of LLM are improved.

Organic field-effect transistors (OFETs) have some advantages over inorganic transistors, for example, due to being physically flexible and lightweight. Additionally, OFETs can cover large-areas and can potentially be mass-produced at a low cost. It is recognized herein, however, that a technical challenge related to OFET design is evaluating effects at multiple length scales during the design process.

This invention relates to the field of computer-aided design and discloses a computational design method for negative thermal conductivity metamaterials based on topology optimization algorithms. The method includes the following steps: defining the material's relative density field and the active heat source's power density field as dual design variables; performing active-passive collaborative optimization iteration using the adjoint variable method and the moving asymptote method; introducing a hyperbolic tangent function to quantize the continuous power field, extracting the coordinates away from the heat source and applying repulsive constraints; performing cross-scale mechanical-thermal decoupling reconstruction, replacing stress concentration regions with microscopic metalattices; calculating the Jacobian matrix to generate a feedforward compensation network and performing engineering-level derivation. This invention breaks the theoretical limit of thermal conductivity in passive metamaterials, achieves interference-free physical mapping of standard hardware in topological space, eliminates destructive thermal stress through lattice reconstruction, generates a physical system with extremely low computational latency, and realizes a dynamic adaptive negative thermal conductivity representation under complex perturbations.

The invention relates to the field of research and development assistance systems, in particular to a research and development system based on multi-objective optimization and knowledge mining, which is characterized in that a demand task generation module matches an objective function and a constraint condition according to a design demand to form an initial task book; the case retrieval module retrieves a plurality of historical cases with high similarity in the knowledge base to generate a historical case set; the sensitivity analysis module calculates the sensitivity of each adjustment value under the constraint of the constraint condition of the design demand, and generates a sensitivity report; the multi-algorithm fusion optimization module uses multiple algorithms to carry out parallel iterative analysis and fusion communication according to the initial task book, the historical case set and the sensitivity report to obtain an optimal scheme set, and then the digital twinborn verification module carries out multi-physics field simulation analysis to generate a simulation report; the final review module performs comprehensive review on the initial task book, the optimal scheme set and the simulation report, and outputs a review scheme and a modification suggestion; the problem of low research and development efficiency caused by multi-person cooperation in the research and development process is solved.

The application provides a control surface structure flutter margin optimization method based on a Kriging surrogate model, comprising the following steps: establishing a control surface structure reference model; performing quality discrete processing on the reference model, updating the quality of each point of the control surface structure reference model according to the perturbation method, performing control surface structure flutter analysis, performing sensitivity analysis on each quality point of the control surface, obtaining the positions of a plurality of quality points with the greatest influence on the quality point discrete flutter speed, and marking the plurality of quality points as flutter significant points; updating the quality data of the plurality of flutter significant points in batches, establishing a flutter speed surrogate model based on the Kriging method; testing the flutter speed surrogate model by using a test data set; and performing rudder surface flutter optimization analysis based on the control surface flutter speed surrogate model and a genetic algorithm. The technical scheme of the application is used to solve the technical problem that the traditional design method usually depends on experience, experiments or a large amount of calculation, and the design cycle is long and the cost is high.

This invention provides a method for automatic generation and energy-saving optimization of three-dimensional building functional layout, belonging to the field of automatic generation and optimization of building models in computational design. The method includes: acquiring basic modeling data of the target building; inputting the basic modeling data into model generation software; determining fixed parameters for the layout scheme and generating rule parameters; using a three-dimensional spatial layout algorithm to perform three-dimensional spatial layout on the mesh model; calculating the annual load per unit building area and the applicability score of the building functional layout of the basic building model; setting the running parameters of a multi-objective evolutionary algorithm; optimizing the basic building model using the multi-objective evolutionary algorithm; and performing cluster analysis and visualization processing. This invention provides an automatic three-dimensional modeling method for energy-saving buildings, simultaneously utilizing a three-dimensional spatial layout algorithm and a multi-objective evolutionary algorithm to increase the efficiency of modeling and optimization, and resulting in a model with better applicability.

The invention discloses an intelligent auxiliary review method and system for a power distribution network project. The method comprises the following steps: collecting multi-source heterogeneous data, preprocessing, constructing a space-time reference, and forming an equipment space topology database and a typical cost case feature library; thirdly, extracting engineering entity characteristics based on the preprocessed data by adopting a detection model, establishing a three-dimensional space mapping model, calculating design layout offset, and generating a resource scheduling signal when the design layout offset exceeds a threshold value; meanwhile, an abnormal diagnosis result and a high calculation demand signal are obtained through analysis of an event influence quantitative model by using historical cost data and an event graph. And formulating a hierarchical scheduling strategy according to the signals to optimize computing power resource allocation. And finally, under the resource constraint, integrating the three-dimensional evidence chain to output a review report, determining an actual deviation and a correction suggestion, and realizing intelligent review and dynamic resource management. By implementing the method provided by the invention, efficient integration of spatial topology verification, cost anomaly prediction and resource scheduling and closed-loop feedback optimization can be realized.

The application relates to the technical field of intelligent manufacturing, and provides an intelligent lightweight method and device for a support structure of additive manufacturing based on virtual testing. The method forms a design region according to original model structure expansion, calculates material distribution of the design region according to load, constraint and optimization target of the support structure, interacts with a virtual topology optimization environment based on reinforcement learning intelligent agents and artificial intelligence technology, and forms a support structure topology optimization Pareto optimal solution set. Stress simulation analysis is performed on the support topology optimal solution set, a lattice gradient is calculated, and interaction is performed between reinforcement learning and a virtual lattice structure reinforcement environment to form a lightweight Pareto optimal solution set of the support structure. The method is based on the reinforcement learning mode of the topology optimization intelligent agents and the lattice reinforcement intelligent agents in the virtual simulation environment, and the lightweight degree and the structural strength of the support structure are improved without frequent manual debugging and physical printing, so that efficient and intelligent lightweight design is realized.

The application discloses a method and system for supporting brain-like simulation model learning, and the method comprises the following steps: managing all parameters in the brain-like simulation model, and classifying the parameters into fixed parameters, variable parameters, non-differentiable parameters and learnable parameters according to calculation characteristics; designing an approximate function operator library for the non-differentiable parameters, and integrating the library into the system; designing usage rules of the approximate functions, so that the original calculation function of the non-differentiable parameters is used in the forward calculation process of the model, and the approximate function of the non-differentiable parameters is called to perform differential calculation in the gradient solving stage of the back propagation; designing an approximate function calling interface of the brain-like simulation model, replacing the non-differentiable calculation part in the model; and constructing a learnable brain-like simulation model network to perform task learning and training. Through the fine parameter management and the approximate function simulation gradient calculation, the application realizes efficient learning and training of the brain-like simulation model, and is successfully applied to complex classification tasks.

This invention discloses a computational design method, system, device, and storage medium for broad-spectrum antibacterial compounds, relating to the fields of computational chemistry and drug discovery. The method includes: virtual screening of an initial compound library to identify a preliminary set of active compounds; extracting pre-defined chemical skeletons from the preliminary set of active compounds to identify a group of dominant chemical skeletons; filtering the identified dominant chemical skeletons based on pre-defined medicinal chemistry indicators to select a group of high-potential skeletons; selecting one or more representative molecules from the original cluster members corresponding to the selected high-potential skeletons, and generating a derivative library through virtual chemical derivatization; and virtual screening of the derivative library to identify a final set of candidate compounds. This invention can transform narrow-spectrum compounds that exhibit activity only against Gram-positive bacteria into broad-spectrum antibacterial compounds that are also active against Gram-negative bacteria through systematic computational design.

Alpha(v) beta (6) integrin (avb6) binding polypeptides are disclosed herein, and their use in treating and detecting tumors, and their use in treating pulmonary fibrosis.