279 results about "Si model" patented technology

The invention relates to a method and a device for optimizing a digital twin model of power equipment. The method comprises the following steps: acquiring operation monitoring data and a digital twinborn simulation result of target power equipment to perform difference analysis, and determining a deviation between a digital twinborn model of the target power equipment and an actual operation state of the equipment; a prediction error matrix updated in real time is obtained based on the deviation, parameters of the digital twin model are dynamically adjusted according to the prediction error matrix, and a model after parameter correction is obtained; simulating dynamic characteristics of the target power equipment under different fault conditions by adopting the model after parameter correction, and correcting according to the dynamic characteristics to obtain a fault scene adaptation model; and performing parameter distribution optimization and model uncertainty correction on the fault scene adaptation model through model iteration processing to obtain an optimized digital twin model of the target power equipment. By adopting the method, dynamic correction and optimization of the digital twinborn body of the power equipment under complex working conditions can be realized, and the precision and reliability of the digital twinborn model are effectively improved.

The invention relates to the technical field of dredge pump performance analysis, and discloses a numerical simulation and model test-based dredge pump performance analysis method, which comprises the following steps of: planning an analysis process, and determining numerical simulation (dredge pump internal flow field simulation) and model test contents (actually measured performance data under different working conditions); determining working condition types according to design parameters and working conditions; generating a performance analysis process set and determining an execution sequence; generating a simulation parameter setting list and a test scheme list of each working condition; and associating the data to generate an overall scheme. The method further relates to working condition analysis boundary determination, working condition type subdivision, dynamic adjustment of the process, test rule optimization, database construction and the like. According to the method, comprehensive and accurate analysis of the dredge pump performance is achieved through multi-dimensional data integration and a dynamic mechanism, the analysis efficiency and reliability are improved, and the method is suitable for evaluation and optimization of the dredge pump performance.

The invention relates to the technical field of artificial intelligence, in particular to a cue word optimization method, an intelligent agent and a storage medium. According to the cue word optimization method provided by the invention, a plurality of cue word templates are generated, different cue word templates and different task sample combinations are input into different models, and through continuous evaluation and feedback optimization, a first cue word template adaptive to each task and model type is finally screened out; and setting a first label representing a corresponding task type and a second label representing a corresponding model type for each first cue word template to obtain a label cue word template and storing the label cue word template, so that searching in a task dimension and a model dimension is facilitated, rapid and accurate matching of the cue word templates can be realized, the adaptability of the cue word templates is improved, and the user experience is improved. Efficient operation of the intelligent agent in dynamic scenes of different tasks and models is supported, so that the intelligent agent can adapt to the cue word template with the most appropriate task and model type, and the generalization ability and execution effect of the intelligent agent in a multi-task scene and a multi-model are improved.

The invention relates to the technical field of digital twinning, and discloses a digital twinning modeling method, device and equipment, a storage medium and a product, and the method comprises the steps: building a static environment model through selecting a corresponding processing technology based on the characteristics of a fixed facility and the characteristics of an operation machine, obtaining the point cloud data of a material pile through a multi-source sensor and a two-dimensional laser radar, and obtaining the point cloud data of the material pile; obtaining a virtual material pile irregular triangulation network model through a point-by-point insertion algorithm based on the material pile point cloud data, extracting material pile surface data from the virtual material pile irregular triangulation network model, and constructing a dynamic scene model based on the material pile surface data according to the material pile boundary and the material pile surface data; and a digital twin bulk cargo model is obtained by integrating the static environment model and the dynamic scene model. According to the invention, based on the fixed facility features, the operation machinery features and the two-dimensional laser radar, the static environment model and the dynamic scene model are integrated, so that the bulk cargo modeling data precision and the model real-time mapping stability are improved.

The invention discloses a power grid transient process deduction method based on digital twinning, electronic equipment and a medium, and the method comprises the steps: building a digital twinning simulation model based on a new energy single-machine simulation model and a three-dimensional field station virtual model, and outputting a virtual value by the digital twinning simulation model; collecting core parameters in a monitoring period; calculating the deviation ratio of the physical value and the virtual value of the physical station based on the core parameter; and adjusting the transient process control strategy based on an adjustment object and the deviation rate, wherein the adjustment object comprises a virtual value, a core parameter, a scene parameter and a model control mode. The digital twinborn model can be calibrated in real time through deviation ratio closed-loop correction of a physical value and a virtual value, it can be ensured that simulation of the transient process of the power grid is highly consistent with the physical reality, and the precision and reliability guarantee of a deduction result is improved.

The invention provides a prediction method for the remaining service life of a rolling bearing based on transfer learning, and belongs to the technical field of artificial intelligence and mechanical engineering. Rolling bearing vibration signals are obtained, and a data set is constructed and divided into a source domain and a target domain; constructing a prediction model of the remaining service life of the rolling bearing; the model comprises the following steps: obtaining low-dimensional features and model weights by using a coding layer; the coding layer comprises a multi-head self-attention sub-layer used for obtaining a relationship between features and a model weight; the feedforward mechanism is used for obtaining low-dimensional mapping; predicting the residual life of the bearing by using the feature representation output by the last coding layer through the full connection layer; training the prediction model of the remaining service life of the rolling bearing: calculating the difference between a source domain and a target domain by using the data set, and constructing a loss item; weight parameters are added to the loss item, the weight parameters and the root-mean-square error loss item are added for back propagation, and the model weight is updated. And the generalization ability of predicting the bearing life by the model is improved.

The invention relates to the technical field of geological analysis, and discloses a method for fusing a three-dimensional geological model and a WebGIS (Web Geographic Information System), aiming at solving the problems of poor data intercommunity, limited spatial analysis capability, difficulty in real-time updating and low model loading efficiency of the existing method, and the scheme mainly comprises the following steps: extracting geological model data, and carrying out standardized format processing; lightweight processing is carried out, and geological attributes and model nodes are bound one by one; the format is converted into a binary format embedded with a metadata label, and data integrity verification and automatic error correction are carried out in the conversion process; constructing a non-uniform adaptive octree spatial index, a multi-level attribute data architecture and a real-time updating mechanism of attribute data; after the geological model and the terrain are precisely registered and fused, a dynamic loading mechanism, a high-performance rendering mechanism and a geological model real-time updating mechanism are constructed, and a three-dimensional geological analysis tool is integrated. According to the method, efficient loading, real-time rendering, dynamic updating and spatial analysis of the three-dimensional geologic model in the WebGIS are realized.

The invention discloses a building BIM data exchange process geometric defect automatic identification and repair method based on an AI technology. The method comprises a model training stage and a model using stage. The logic process of the model training stage comprises data collection, data analysis, data conversion, data annotation, data set division, model selection, model architecture design, model training, model evaluation, model deployment and model use; and the flow of the model use stage comprises data input, geometric defect identification, only feedback, geometric repair and data output. The invention belongs to the technical field of BIM data conversion, and particularly provides a building BIM data exchange process geometric defect automatic identification and repair method based on an AI technology, and the method can achieve intelligent geometric defect detection and identification, intelligent geometric repair, and high efficiency. The problems that in the prior art, manual repairing consumes time, the repairing efficiency is low, precision is insufficient, and the automation degree is low are solved.

The invention discloses a model selection method and device. The method comprises the steps that a to-be-recognized data set is received, feature extraction is conducted on the to-be-recognized data set, element features of the to-be-recognized data set are obtained, and the element features comprise at least one of the data scale, the feature type, target variable information and the data sparsity; determining a to-be-executed target task type according to the meta-features; selecting a plurality of candidate models from a preset model database according to the target task type; a target model is selected from the multiple candidate models according to a predetermined reward function, and the reward function is determined according to the performance index of the model and the training efficiency index of the model. The technical problem of low model selection efficiency in related technologies is solved.

The invention discloses a method, a system, equipment and a medium for constructing an integrated digital model of a full-motion analog machine, and belongs to the field of analog machines. The method is suitable for constructing the digital model based on the unstructured heterogeneous data, and obtains the structured text information set from the document through the named entity recognition and relation extraction technology by obtaining the three-dimensional geometric model and the unstructured technical document of the full-motion simulator. And a three-dimensional model is combined to jointly construct a heterogeneous knowledge graph containing two types of nodes representing technical entities and three-dimensional parts. And link prediction is performed on the graph by using a graph neural network, so that a target edge representing deep implicit association between the text information and the three-dimensional part can be inferred. The target edges are updated to the atlas, and all complete technical information associated with the parts is bound to the corresponding three-dimensional geometric model, so that an all-moving simulator integrated digital model with complete information is generated, and the digital model construction efficiency and the model information association degree can be improved.

The invention discloses a building engineering drawing and model integrated interaction system and method, and the method comprises the steps: carrying out the semantic association of a drawing and a model, generating a dynamic index, enabling a constructor to input a natural language instruction, and enabling the constructor to synchronously locate an index region and an index component corresponding to the natural language instruction in the drawing and the model, the drawing and the model of the corresponding index area are subjected to holographic projection synchronously, and the corresponding index component is highlighted, so that the information acquisition efficiency and accuracy are improved, the time cost of switching between the drawing and the model is reduced, and the construction efficiency is improved; furthermore, through comparative analysis of the drawings and the models, collision conflicts can be detected, an optimization scheme can be generated, construction errors of the drawings and the models are effectively reduced, meanwhile, change records and communication information of the drawings and the models are synchronously stored and updated, the accuracy of obtained information can be ensured, and therefore the interaction reliability of the drawings and the models is improved.

In order to improve the accuracy and fineness of three-dimensional scene interactive display in a three-dimensional reconstruction model, the invention provides a data processing method for 3DGS and BIM model space matching, the method comprises three-dimensional reconstruction based on a 3DGS technology, the process comprises data acquisition, data generation and data splicing, then BIM model generation is carried out, and the BIM model space matching is carried out. And then, the obtained 3DGS data and the BIM data are imported into a Unity 3D engine, and 3DGS model space matching and BIM model space matching are carried out in the Unity 3D engine. According to the method, the 3D GS technology and the BIM model are dynamically fused, multi-source data can be subjected to superposition processing, a physical space is accurately restored, and fine three-dimensional scene interactive display is achieved.

The invention discloses a deformed workpiece twin modeling method based on measurement point cloud and three-dimensional CAD model matching. The deformed workpiece twin modeling method comprises the steps that an improved GFO-ICP registration algorithm is adopted to solve the initial coarse registration problem of the measurement point cloud and a CAD model in combination with geometric feature constraint and self-adaptive step length optimization; extracting a key geometric curved surface of the point cloud by adopting a clustering-based plane segmentation algorithm, and extracting a semantic feature vector of a segmented region in combination with a Pointnet + + network; a cosine similarity matching mechanism is constructed by integrating mixed descriptors of geometric features (areas and normal vectors) and semantic features, and accurate binding of a point cloud curved surface and a curved surface of a CAD model is achieved. According to the method, the problem of assembly geometric deviation caused by workpiece deformation due to manufacturing errors in compressor and fan rotor assembly is solved, multi-link error accumulation is effectively processed, digital twin modeling of high-precision deformed workpieces is achieved, and the assembly simulation effect and intelligent manufacturing application are improved.

The invention discloses a federal space-time attention adaptive graph learning method and system, and the method comprises the steps: constructing a traffic prediction problem, constructing a space-time attention enhancement dynamic graph convolutional network model composed of a feature enhancement layer, a dynamic graph convolutional recursive network, a multi-head time attention module, a graph attention module and a space-time attention fusion module according to the traffic prediction problem; placing a traffic prediction problem in a federated learning scene, and setting privacy constraints of the model; on the basis of privacy constraints, an activation decomposition strategy is implemented on the model, and the activation decomposition strategy is that a transfer function is applied to a dynamic graph convolutional recursive network in the model; and performing traffic prediction on the traffic data acquired by the sensor by using the model which implements the activation decomposition strategy in a federated learning scene. According to the method, the problems of privacy leakage risk, high communication cost, limited model flexibility and the like in a traditional federal space-time attention adaptive graph learning framework are solved.

A model deployment tuning system (MDTS) receives a trained ML model, specified constraints, and model evaluation data and applies a plurality of model utilization techniques to the trained ML model to produce a plurality of useable model versions of the trained ML model. The MDTS executes each of the plurality of useable model versions of the trained ML models on a plurality of different compute instance types using the model evaluation data to produce model evaluation results for a plurality of different combinations. The MDTS filters the model evaluation results based on the specified constraints to indicate one or more of the different combinations satisfying the specified constraints. The MDTS deploys one of the plurality of useable model versions of the trained ML model to a compute instance types according to a selected combination satisfying the specified constraints.

The invention provides a federal learning dynamic cutting method and device based on gradient correlation, and the method comprises the steps: receiving a global model issued by a server; training the global model according to the target local data to obtain a local model; determining an update of each level of the local model and an update of each level of the global model; determining a correlation value for each level between the local model and the global model; determining hierarchies of which the correlation values are smaller than a preset correlation threshold value in the local model as cutting hierarchies of the local model; determining hierarchies of which the correlation values are greater than a preset correlation threshold value in the local model as reserved hierarchies of the local model; cutting the invalid update corresponding to the cutting hierarchy of the local model, and returning the valid update corresponding to the reserved hierarchy of the local model to the server; according to the invention, federal learning efficiency and model performance can be improved.

The invention discloses a surface wave frequency dispersion curve intelligent inversion method based on parameter normalization, and relates to the technical field of deep learning. The method comprises the following steps: firstly, generating a plurality of groups of training data pairs in a reference underground model space, then pre-training the training data pairs by using an improved Transform-based PADIT model, mapping an actually measured Rayleigh wave frequency dispersion curve into the reference underground model space, predicting the actually measured Rayleigh wave frequency dispersion curve by using the pre-trained PADIT model, and finally selecting a better inversion result by using a mismatch value. According to the method, the defect that in the prior art, a deep learning method depends on a specific scale sample is overcome, and the efficiency of seismic data Rayleigh wave frequency dispersion curve inversion work and the universality of the model are greatly improved; meanwhile, the deep learning model adopted by the invention can directly process frequency dispersion curve data with variable length, does not need to carry out preprocessing such as interpolation or truncation on input data, is more in line with the condition that the data length is variable in practical application, and has better flexibility and robustness.

Techniques for selecting a learning model defined in particular by parameters and hyperparameters from among a plurality of learning models, implemented by a computing device and provided. A computing device may be provided includes a model selection module and a model repository including a plurality of series of instructions each corresponding to a learning model and each including hyperparameter values. The method may be provided that includes a step of selecting a model when the prediction performance value and the classification value are greater than a predetermined second threshold and the hyperparameter value is greater than a predefined threshold value.

The invention discloses a communication efficient distributed reasoning method based on model pruning, and relates to the technical field of distributed reasoning, and the method comprises the steps: S1, constructing a delay prediction model, S2, determining an initial break point in a heuristic manner, S3, carrying out model pruning, S4, determining the break point through a dynamic planning method, and S5, carrying out model pruning. The method comprises the following steps: firstly, designing a neural network delay prediction model, selecting according to importance by using the obtained delay, the accuracy of the model and the communication overhead of a segmentation point, removing a part which has great influence on the delay and has small influence on the delay in the model, and then finely adjusting the model to adjust the accuracy of the model; regularization items for communication overhead are added, the communication overhead brought in the reasoning process is further reduced, meanwhile, in order to determine optimal segmentation points of delay and communication, a dynamic planning method can be utilized according to the prediction result of the model, finally, the pruning process and model segmentation are optimized in a cross iteration mode, and the delay and communication overhead are optimized.

The invention relates to the technical field of artificial intelligence, and discloses a large language model access method, system and device and a storage medium. The access method of the large language model comprises the steps that a first target parameter capable of being used for indicating the model type of a target model to be accessed is extracted from an obtained user access request, and the first target parameter comprises at least one of an access protocol, a model identifier of the target model to be accessed and a model source; distributing the user access request to a target actuator matched with the first target parameter; and executing the target operation process by using the target executor to perform dialogue interaction with the target model. By setting the actuators corresponding to different models, API interfaces of numerous large language models can be rapidly and efficiently compatible, the access request of a user to any model can be processed, the problems of incompatibility of different model interfaces and interface differences are solved, and the access efficiency of various large language models is improved.

The invention provides a big language model merging method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a density hyper-parameter and a model merging coefficient hyper-parameter used for model merging based on a task target of a merging model in a downstream task; generating a mask matrix based on the density hyper-parameter, and determining task vectors of the two to-be-merged models based on the mask matrix, the respective model parameters of the two to-be-merged models and the model parameters of the basic model; based on the parameter vector angle of the corresponding neuron between the two to-be-merged models, the task vectors of the two to-be-merged models and the model merging coefficient hyper-parameter, determining the task vector of the merged model; and obtaining the merging model based on the task vector of the merging model and the model parameters of the basic model. By adopting the technical scheme, the problem that the performance of a merging model obtained by an existing model merging method is poor is solved.

The invention discloses a development, operation and maintenance platform of a large language model and a model development and deployment method, and the development, operation and maintenance platform adopts a front-end and rear-end separation architecture design, and comprises a front end part and a rear end part, wherein the front end comprises a data set uploading interface, a model training interface, a model evaluation interface, a model deployment interface, a model-adapter merging interface and a model tracing interface; and the rear end comprises a data set management function module, a data set uploading function module, a model training function module, a model evaluation function module, a model deployment function module, a model-adapter merging function module and a model management function module. The data set uploading interface is used for uploading the data set for training and evaluation, the model training interface is used for model training to improve the model performance, the model evaluation interface is used for evaluating the capabilities of the model in different aspects, the model deployment interface is used for providing services for model deployment, and the model development and deployment work is completed.

The invention discloses a two-way traffic flow dynamic modeling method based on a deep space-time diagram neural network, and belongs to the field of intelligent traffic and data mining, and the method comprises the following steps: S1, constructing a traffic flow dynamic diagram, and capturing the local space-time dependence of a traffic flow; s2, after the local space-time dependency is obtained, extracting time features by using a time convolutional layer; s3, after the time features are obtained, a selection gate is used for screening the effective information obtained in the step S2, and final output is obtained; s4, after a result in S3 is obtained, using a composite graph convolution module to extract spatial features; s5, fusing the two-way traffic, and obtaining a final prediction result through a prediction layer; s6, the loss of the model is calculated, and whether the model meets the requirement is determined, the problems that in the prior art, in traffic flow prediction, bidirectional flow modeling is insufficient, dynamic dependency capture is insufficient, and adaptability to complex traffic scenes is poor are solved, and therefore the traffic flow prediction precision and the model applicability are improved.

The invention discloses an interactive multi-model aircraft filtering algorithm and system driven by reinforcement learning, and the algorithm comprises the steps: firstly constructing a multi-model state prediction set composed of a Singer model, a current statistical model and a Jerk model, and presetting a state transition probability matrix according to the state evolution correlation between the models, so as to define the interaction relation between the models; in the filtering stage, state estimation preliminary fusion of the three maneuvering models is achieved according to a traditional interactive multi-model algorithm, the fusion proportion of each model is adjusted in real time in combination with a weight correction vector output by a reinforcement learning strategy function, and strategy iteration optimization is conducted through a reward function containing an error improvement item, a matching item and a balance item. The method can significantly improve the filtering precision and fusion stability of the aircraft maneuvering target.

A system enables agile model development to speed up innovation by data scientists. Model training and deployment are coordinated and standardized to reduce redundancy. Data is obtained for feature generation and reformatted and de-sensitized for storage. The features are stored in locations available to all models and training modules of a system so data does not need to be adjusted for new models. To generate a machine learning model, the system establishes a cohort for evaluation by the model. A model template and features for use by the model are identified. The selected template and features are used for experimentation and evaluation. Model training artifacts, such as model weights are subsequently recorded in a model store and the model scripts and settings can then be registered in a centralized database where it can be accessed for execution.

The invention relates to the technical field of federal learning, in particular to an incremental data-oriented personalized federal learning method and device, which can solve the problem that the traditional federal learning is insufficient in the aspects of incremental data processing and personalized ability to a certain extent. The method comprises the following steps: introducing a weight attenuation regular term in a model training process, applying regularization constraint to model parameters, preventing model overfitting, improving the generalization ability of the model, fusing the thought of meta learning, carrying out model training by utilizing an internal and external loop mechanism, and carrying out iteration of a personalized algorithm in an external loop. The model can adapt to new incremental data more quickly, the training efficiency and the model performance are improved, the real-time performance and the adaptability of the model are improved, the model of each client can be optimized according to own characteristics through personalized algorithm iteration, and the adaptability and the accuracy of the model on different clients are improved.

The invention discloses a sample automatic collection and model iteration method for electrical equipment defect identification, belongs to the technical field of electrical equipment defect identification, and aims to solve the problems that a difficult sample discovery and collection mechanism is missing, model short plates are difficult to supplement and a model performance evaluation and feedback mechanism is imperfect. The method comprises the following steps: collecting multi-source power equipment inspection data, carrying out standardization processing, automatically discovering and collecting difficult samples, identifying the difficult samples from preprocessed samples based on a preset rule, establishing a difficult sample library, carrying out model iteration training, constructing a training set based on the difficult sample library and a basic sample library, and carrying out model training by adopting a weighted sampling strategy. Generating an iterative model; according to the method, key samples for model optimization are accurately screened through a difficult sample automatic discovery mechanism, storage and computing resources are prevented from being occupied by invalid samples without defects, with simple backgrounds and the like, and limited sample resources serve for model performance improvement in a centralized manner.

The invention provides an unbalanced data classification task optimization method driven by reinforcement learning, and mainly aims to solve the problems that when minority class samples are few or complex in distribution, synthetic samples may not completely and accurately reflect real distribution and key information is lost. According to the scheme, a confrontation scene is designed and a reinforcement learning model is introduced to assist training, so that the classification precision and the generalization ability of the model can be remarkably improved; the reinforcement learning model is responsible for selecting a proper training sample and adjusting parameters based on a prediction result of the classifier; and meanwhile, the classifier model receives the samples for prediction, and updates the model according to a prediction result. The algorithm provided by the invention has excellent classification precision in the unbalanced cifar-10 data set, is obviously superior to the similar algorithm, and is not limited to any specific model type, so that extremely high flexibility and expandability are provided, and the algorithm has strong application potential.

The invention discloses an environmental noise classification method based on adaptive joint parameter space optimization, and the method comprises the steps: collecting a plurality of noise signals, enabling each type of signals to correspond to a specific environmental noise type, and constructing a data set; defining a joint parameter space comprising a plurality of optimization variables, wherein the joint parameter space comprises a data enhancement parameter subspace, a model network parameter subspace and a model training hyper-parameter subspace; according to training data characteristics, environmental noise classification task complexity and model deployment constraint, adaptively calculating each parameter range space; and constructing an objective function, and searching a multi-parameter optimal collaborative combination by using Bayesian optimization. According to the method, a joint parameter space is constructed, and Bayesian optimization is utilized to adaptively search a multi-parameter optimal collaborative combination of a data enhancement parameter, a model network parameter and a training hyper-parameter in a multi-model training process, so that synchronous dynamic optimization of data enhancement, a model structure and model training is realized; and finally, the performance of the neural network model in environmental noise classification is improved.

One or more embodiments of the invention provide a three-dimensional model generation method, apparatus and device, a medium and a program product. The method is applied to CAD software and comprises the following steps: acquiring a plane image and a model thickness of a modeling object; generating a plane grid for the modeling object according to the plane image; generating a front grid, a back grid and a side grid for the modeling object according to the plane grid and the model thickness; and combining the front grid, the back grid and the side grid into a three-dimensional grid, and mapping the texture of the plane image to the three-dimensional grid to obtain a three-dimensional model of the modeling object.