211 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 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 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 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.

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 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 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 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 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 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.

The invention discloses a MaaS platform construction method and system based on evaluation-driven closed-loop optimization, and the method comprises the steps: enabling a model square to serve as a unified entrance of a model, and providing rich model resources for a user to select; the computing platform provides model development, training and deployment for a user; evaluating the performance of the model; through feedback, close cooperation among the model square, the calculation platform and the model evaluation is realized, and an automatic optimization closed loop is formed. According to the closed-loop optimization mechanism based on evaluation driving, close cooperation among the model square, the calculation platform and the model evaluation module is achieved through feedback of the model evaluation module, an automatic optimization closed loop is formed, and the problem that an existing platform cannot achieve the automatic process from model selection, evaluation to retraining is solved.

The invention discloses a web end power grid model data general maintenance method and system, and the method comprises the following steps: 1, extracting and expanding power grid model metadata, and storing the expanded metadata in a database in the form of a table information table and a column information table; 2, configuring the types of the models needing to be maintained and the dependency relationship between the models; and 3, reading and analyzing the metadata and the configuration file in the step 1 and the step 2, and displaying and maintaining the model data. The system comprises a metadata extraction module which extracts metadata in a database where a power grid model is located and expands the metadata into more comprehensive information required by system maintenance; the configuration module is used for configuring power grid models needing to be maintained in different regions and dependency relationships thereof; and the analysis module is used for reading the metadata of the power grid model and analyzing the configuration file to obtain the power grid model needing to be maintained, and displaying and maintaining the power grid model in an interface. According to the method, by modifying configuration, the maintenance requirements of models in different regions are met, codes do not need to be modified, reusability and expandability are high, and the maintenance cost is reduced; metadata is automatically extracted, and power grid model data under different service systems are adapted.

The invention relates to a profile drifting buoy heterogeneous digital twinborn model construction method, which belongs to the technical field of model construction, and comprises the following steps: constructing a mechanical motion model of a profile drifting buoy, acquiring actual operation data, defining an error function according to the mechanical motion model, and calculating an error value between the mechanical motion model and the actual operation data according to the error function. Calculating a mean value and a standard deviation of the error values through a neural network, and performing error correction on the error values according to the mean value to obtain a heterogeneous digital twinborn model; a model error result is calculated according to the predicted operation state and actual operation data; an error threshold value is defined according to the standard deviation; a loss function is calculated according to the error threshold value and the model error result; and parameters of the heterogeneous digital twin model are updated according to the loss function. A deviation quantification mechanism between a physical model and a real system can be established, and high-precision modeling and prediction of the running state of the profile drifting buoy are achieved.

The invention provides a CAD-based multi-model building object data conversion method and a related device, and belongs to the technical field of super-huge building object data conversion. Geometric parameters of a CAD model are modified according to actual operation and maintenance requirements of a building object; performing incremental synchronization on the BIM model and the CAE analysis model according to a mapping relationship among geometric parameters of the CAD model, attribute parameters of the BIM model and characteristic parameters of the CAE model in a pre-constructed topological feature library to obtain the synchronously converted attribute parameters of the BIM model and the characteristic parameters of the CAE model; and according to the synchronously converted attribute parameters of the BIM model and the characteristic parameters of the CAE model, respectively updating and generating the BIM model and the CAE analysis network in real time. According to the method and the device, the problem that when the CAD drawing is changed, BIM software needs to be modified manually, so that the working efficiency is reduced is solved.

The present invention discloses a three-dimensional registration and reconstruction method based on multi-domain multi-dimensional feature maps. First, a specified number of key points are randomly selected from the scene point cloud and the model point cloud. Then, each key point is traversed, and the corresponding multi-domain multi-dimensional feature maps are calculated as local feature descriptors. Based on the multi-domain multi-dimensional feature maps, the correspondence between key points is obtained, and the key point pairs are sorted according to the matching degree. In each iteration, a compatible triple is selected in order to generate a hypothesis, and it is checked whether the hypothesis can correctly register the model into the scene. The present invention has a short calculation time and a low time cost.

The invention provides a model training method and device, a three-dimensional generation method and device, equipment and a storage medium, and relates to the technical field of computer vision. The method comprises the following steps: according to a two-dimensional reference image of a sample three-dimensional model under each view angle, generating a prediction rendering image under each view angle and a prediction SDF parameter of a sampling point by adopting an initial three-dimensional generation model; calculating a first loss parameter according to the real rendered image and the predicted rendered image under the plurality of visual angles; and determining a winding number SDF parameter of the sampling point as a real SDF parameter of the sampling point, calculating a second loss parameter according to the predicted SDF parameter and the real SDF parameter of the sampling point, and performing parameter adjustment on the initial three-dimensional generation model according to the first loss parameter and the second loss parameter to obtain a target three-dimensional generation model. According to the embodiment of the invention, the supervised training precision and spatial resolution of the model can be improved, and the geometric precision and details of the model are improved.

The invention relates to the technical field of intelligent driving, in particular to a data closed-loop system, a data closed-loop method, a controller and a readable storage medium, and aims to solve the technical problem of how to carry out effective data closed-loop to realize high-efficiency model iteration. In order to achieve the purpose, the data closed-loop system comprises a data mining module, a data processing module and a model iteration training module. And the data mining module is used for performing data mining based on the mining model according to a preset data mining requirement to obtain mining data. And the data processing model is configured to perform data processing according to the mining data to obtain first training data. The model iteration training module is configured to perform model iteration training on the to-be-iterated model according to the first training data to obtain a model iteration training result, so that the model performance of the to-be-iterated model can be effectively improved, the iteration efficiency of the model is improved, better expansibility is achieved, and the iteration requirements of multiple to-be-iterated models with different functions can be met.

The present disclosure provides a method, apparatus, electronic device, storage medium, and computer program product for assisting model training, which relates to the field of computer technologies, specifically artificial intelligence and deep learning technologies, and can be used in model training and application scenarios. The specific implementation solution is as follows: obtaining a training sample set, where the training samples include training data and label information; during the process of training an initial model with the training sample set, determining intermediate data in the forward propagation process of the initial model to obtain an output result based on the input training data, and loss information between the output result and the corresponding label information; obtaining an interpretation result according to the intermediate data and the output result through a model interpreter; and adjusting the initial model according to the loss information and the interpretation result to obtain a trained target model. The present disclosure not only makes the model learning stage interpretable, but also trains the model in combination with the interpretation result, improving the model training speed and model accuracy.

The invention belongs to the technical field of federated learning, and discloses a federated edge learning model training method, system and device and a medium, and the method comprises the steps: enabling a plurality of clients to train a local model and generate a pseudo vector, and enabling the local model to be a lightweight model; transmitting the pseudo vector generated by each client and the model parameter of the local model to an edge server; and constructing and training a global model in the edge server based on the pseudo vector and the model parameter of each client, and distributing partial parameters of the trained global model to each client based on a preset division rule. According to the technical scheme, the energy cost and the model performance of the mobile equipment can be balanced.

One embodiment of the technology of the present disclosure provides a model learning method, a program, and a model learning device for efficiently learning a model built by neural network. The model learning method includes: a first learning step in which a plurality of layers of a neural network for a model constitute a preceding stage layer and a subsequent stage layer that outputs a final result by using the output from the preceding stage layer as input, and the weight of the preceding stage layer of the neural network and the weight of the subsequent stage layer are updated using a first learning data set; and a second learning step in which, after the first learning step, a second learning data set is used to update only the weight of the preceding stage layer without updating the weight of the subsequent stage layer of the neural network.