513 results about "Model validation" patented technology

The invention relates to an intelligent industrial equipment state monitoring device and method, and the method comprises the steps: installing a vibration sensor, an acoustic sensor and an image sensor at key parts of industrial equipment, and comprehensively collecting the operation data of the equipment. In the data preprocessing stage, vibration and acoustic signals are filtered and denoised, and image data are denoised and enhanced. Extracting multi-dimensional characteristic parameters from three aspects of vibration, acoustics and images; a random forest algorithm is adopted for model training, and the method comprises the steps of data preparation, segmentation, decision tree construction, voting mechanism, majority voting, model verification and optimization, testing and the like. In the model identification stage, the real-time features are input into the trained model, and the equipment state is determined through decision tree prediction and voting summarization. And when an abnormal state is detected, setting a multi-level alarm response according to the probability, and generating a maintenance suggestion. According to the method, the whole-process intelligent monitoring of the industrial equipment is realized, and the fault identification accuracy and the maintenance efficiency are improved.

The invention provides a numerical control machining model verification method and system combined with digital twinning, and the method comprises the steps: firstly obtaining a numerical control machining twinning data association set which is correspondingly formed by a physical machining process actual measurement data sequence and a virtual twinning model simulation data sequence according to a machining stage identifier; the actual measurement data sequence and the simulation data sequence both comprise processing action and material response feature sequences, and then carrying out feature space unification processing on the twin data association set to generate a verification feature corresponding set comprising actual measurement comprehensive features and simulation comprehensive features; performing deviation analysis on the verification feature corresponding set by using a pre-trained model deviation analysis model to obtain a feature matching and association influence relationship, and deducing and determining a specific deviation position of the virtual twin model in a processing action and material response modeling link based on an analysis result; and model optimization guidance information for defining the parameter adjustment direction and the structure correction content is generated, so that the precision and the reliability of the virtual twin model are effectively improved.

The invention discloses a coal rock fracture intelligent extraction method based on improved U-Net. The method comprises the following steps: S1, constructing a coal rock fracture CT image data set; s2, constructing an improved U-Net segmentation model, specifically comprising the following steps: S2.1, taking VGG16 as a backbone network, and introducing a depth separable convolution module; s2.2, a PPA attention module is added after each layer of depth separable convolution of the decoder, the PPA attention module is introduced after each up-sampling stage of the decoder, and the output of the PPA attention module is subjected to batch normalization and Dropout layer processing; s2.3, defining a composite loss function; s3, training and optimizing a segmentation model, wherein the specific steps comprise: S3.1, setting hyper-parameters; and S3.2, training the model by using the training set, adjusting hyper-parameters by using the verification set, and evaluating the performance by using the test set, wherein the evaluation indexes comprise MIoU, MAcc and FWIoU. According to the method, the problems of difficult identification of small fractures, large model calculation amount, poor multi-scale information fusion and class imbalance in the coal rock fracture image can be solved, and the robustness, segmentation precision and practicability of the model are improved.

The invention relates to a gradient aggregation federated learning method based on combination of zero knowledge proof and a block chain technology, and belongs to the field of distributed machine learning. Through combination of zero knowledge proof (zk-SNARK) and an extensible block chain technology, limitations of a traditional method in aspects of data privacy protection and model verification are broken through. According to the method, the correctness of a global model is verified by using zero-knowledge proof, the transparency and data privacy of an aggregation process are ensured, the Chinese remainder theorem is introduced to compress the proof, and the storage burden of block chain nodes is reduced. And the hash value updated by the encryption model is recorded through the block chain, verification is carried out based on a block chain consensus node, and the data integrity and the system transparency are further improved. Besides, a dynamic client selection mechanism is introduced in the method, participants are optimized based on training performance scores, and the training efficiency and the model quality are improved. As a whole, the invention provides a safe, efficient and transparent distributed learning solution.

The invention relates to the field of milling, in particular to a modeling method and system for a morphology model of a milling surface, and the method comprises the steps of data collection, data preprocessing, feature extraction, model construction and model verification and optimization. According to the modeling method and system, various actual factors in milling are fully considered, including tool abrasion, cutting force vibration, workpiece material non-uniformity and the like, the fitting degree of the model and the actual milling surface appearance is improved, and the microscopic geometrical characteristics of the machining surface can be reflected more accurately; a machine learning algorithm is adopted to construct a model, so that a complex milling process parameter combination relationship can be flexibly processed, the applicability and accuracy of the model under different milling process parameters are improved, and accurate evaluation of part performance and optimization of a machining process are facilitated; the system is complete in structure, all the modules are clear in division of labor, and the construction, verification and optimization process of the morphology model of the milling surface can be efficiently achieved.

The invention discloses a diversified recommendation method based on a graph neural network and reinforcement learning. The method comprises the following steps of: preprocessing collected data containing users and things to form a data set, and dividing the data set into a training set, a test set and a verification set: mapping the users and things in the data of the training set to a dense vector space through a lookup table of an embedded layer, and selecting the data of the users and things through a facility site selection method; iteratively screening an object with the highest dependency from the vector representation embedded by the embedding layer, and constructing a diversified neighborhood subset of each user; on the basis of the constructed neighborhood subset, performing secondary neighbor selection by using an A3C algorithm, dynamically adjusting a recommendation strategy through continuous interaction between the user and the environment, capturing and adapting to the change of user interest, and performing secondary neighbor selection; inputting a selection result of the secondary neighbor selection module into a graph neural network model for processing, and training the model; and verifying the trained model by using the verification set, and performing model performance evaluation through the test set. The diversity and adaptability of recommendation can be improved.

The invention provides a ViT distillation training method, system and device and a readable storage medium, and the method comprises the steps: selecting a long-tail data set, and carrying out the preprocessing of the long-tail data set; training the convolutional neural network to generate a teacher model; generating a data sample based on the long-tail data set, inputting the data sample into a teacher model, and generating a soft label; constructing a student model based on a visual Transform, and configuring a knowledge distillation function and a loss function for the student model; generating a data sample based on the long-tail data set, inputting the data sample into a student model, generating a classification result, and optimizing student model parameters by using a loss function based on the classification result and the soft label to train the student model; and after training is completed, performing model verification and output on the student model. According to the method, the technologies of long-tail data set preprocessing, teacher network training, knowledge distillation, loss reweighting and the like are combined, so that the classification performance and generalization ability of the ViT model on the long-tail data set are effectively improved.

The invention relates to a power system digital twin model generation method and device, computer equipment, a readable storage medium and a program product. The method comprises the steps of obtaining multi-source heterogeneous data of a transformer substation, preprocessing the multi-source heterogeneous data to obtain preprocessed data, performing fuzzification processing based on the preprocessed data, extracting a fuzzy logic rule, constructing a to-be-trained adversarial network model, and training the to-be-trained adversarial network model based on the fuzzy logic rule. And when it is determined that the model verification conditions are met, training is stopped, and the digital twin model of the power system is obtained. In the modeling process, a model combining fuzzy logic and a generative adversarial network is introduced, and through dynamic rule base management and self-adaptive updating, it is ensured that the system can adapt to the complex operation environment of a power system in real time, so that the accuracy of automatic generation of the substation operation order is greatly improved, and the automation degree of the substation operation order is improved. And meanwhile, the rule compliance and the compatibility of the power system standard are ensured.

The invention relates to a method for constructing a high-resolution atmosphere carbon dioxide concentration data set based on XGBoost-BO, and belongs to the technical field of environment monitoring and artificial intelligence modeling. The method comprises the following steps: preprocessing OCO-2 satellite data and multi-source auxiliary data, and fusing the preprocessed OCO-2 satellite data and multi-source auxiliary data to obtain a new data set; a Bayesian optimization method is adopted to search for an optimal hyper-parameter, a target function is optimized through second-order Taylor expansion, a regular term is introduced to control the complexity of the model, and ten-fold cross validation is used to evaluate the performance of the model; quantizing the contribution degree of each feature to model prediction through a tree SHAP method, and analyzing global feature importance ranking and feature contribution distribution of individual samples; and performing model verification by using the test set and the site actual measurement data. According to the method, the problems that an existing model-based reconstruction method is insufficient in interpretation and prone to falling into local optimum are solved, and the temporal-spatial resolution of CO2 concentration monitoring can be improved.

The invention relates to the technical field of suspended sediment monitoring, in particular to a suspended sediment monitoring method and system based on a remote sensing technology. Comprising a concentration inversion module, a model establishment module, a data processing module, a remote sensing data acquisition module, an alarm module and a control platform, the concentration inversion module comprises an inversion calculation unit, a result output unit and a visual display unit, and the model establishment module comprises a model training unit, a model verification unit and a model updating unit. The data processing module comprises a radiometric calibration unit, a correction unit and a feature extraction unit, the remote sensing data acquisition module comprises a satellite remote sensing data receiving unit and an unmanned aerial vehicle remote sensing data acquisition unit, a large amount of data can be acquired in a short time through a satellite and an unmanned aerial vehicle, and the remote sensing technology can cover a wide water area; and finally, a model is established to invert a remote sensing image to obtain a suspended sediment concentration distribution diagram so as to judge a monitoring result.

The invention belongs to the field of artificial intelligence, finance and medical treatment, and relates to an algorithm model verification and precision evaluation method, which comprises the steps of calling a pre-constructed original algorithm model to process an original sample file set to obtain a to-be-evaluated model result, and associating an original sample file with the to-be-evaluated model result to obtain a to-be-evaluated model result; performing annotation task allocation according to the generated annotation task allocation scheme, receiving a truth value result submitted by the annotation personnel, comparing a to-be-evaluated model result with the corresponding truth value result to obtain an initial model precision evaluation result, optimizing the model according to the initial model precision evaluation result, and evaluating the optimization algorithm model to obtain an evaluation result. And generating a model performance comparison report. The invention further provides an algorithm model verification and precision evaluation device, equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the original sample file can be stored in a block chain. According to the method, the model iteration efficiency can be greatly improved, and the precision and performance of the model are improved.

The invention belongs to the technical field of water supply network water quality monitoring, and provides a water supply network trihalomethane prediction method based on a fusion model. Comprising the steps of original water quality data set acquisition, data preprocessing, CNN-BiLSTM-MultiHead Attention fusion prediction model construction, hyper-parameter optimization space and model evaluation function definition, model prediction and output evaluation, model parameter iteration and verification evaluation, model verification, sample importance display, to-be-detected water quality data set collection and trihalomethane prediction. According to the method, the convolutional neural network, the bidirectional long-short-term memory network and the multi-head attention mechanism are fused, so that the change characteristics of a plurality of conventional water quality indexes in the water supply network are efficiently learned and extracted, and better prediction precision can still be kept under the condition of less training data; and the prediction performance and generalization ability of the model in the aspect of predicting a plurality of target variables by using a plurality of input variables are remarkably improved.

The invention provides a landslide disaster dynamic monitoring method based on a time sequence and a hybrid model, and belongs to the technical field of intelligent monitoring, and the method comprises the steps: collecting multi-source heterogeneous data of historical landslide, carrying out the preprocessing of the multi-source heterogeneous data, obtaining first data, carrying out the type division of the first data, and carrying out the time sequence coding of each type of data, obtaining single samples under the same time sequence to obtain a sample set, and training the neural network model according to the sample set to obtain an initial model; performing model verification on the initial model, and optimizing to obtain a time sequence and a hybrid model in combination with the constructed mapping relationship between the landslide deformation and the monitoring dimension under the corresponding type; and monitoring and acquiring current heterogeneous data of the target monitoring point, inputting the current heterogeneous data into the time sequence and the hybrid model, predicting to obtain a current disaster result of the target monitoring point, and outputting a prompt. The accuracy of the model is ensured through model verification and mapping relation construction, and a convenient basis is provided for landslide disaster prediction.

The invention relates to an optimization method for intelligent ISO drawing output based on an external platform. The optimization method comprises the following steps: S1, importing a model and judging a model type; importing a model, and judging whether the model is a two-dimensional model or a three-dimensional model; s2, verifying the three-dimensional model: verifying the three-dimensional model; s3, model data splitting: splitting the verified three-dimensional model; s4, generating a pipeline component file; s5, processing the generated PCF file through an ISO # algorithm; s6, generating an ISO map of the pipeline according to the data processed by the ISO # algorithm; s7, generating a unique reference number and coordinates; S8, establishing data version management, and establishing a data version management mechanism; s9, when the three-dimensional model is modified, automatically updating the two-dimensional model data and the ISO map; and S10, auditing and publishing: auditing the generated ISO map. By efficiently processing two-dimensional and three-dimensional model data in an engineering project, automatic generation of the ISO drawing is achieved, the method is widely applied to the field of CAD design and the like, and the working efficiency and the drawing accuracy are improved.

The invention provides a PCELL layout design optimization method and device, a medium and equipment, and is applied to the technical field of chip design. Flexible layout drawing is carried out by acquiring the PCELL containing the process parameters and the graph adjustable parameters, so that the layout structure parameters of the current PCELL are obtained. A three-dimensional device simulation model is constructed by using the parameters, and a simulation compact model is created by using an artificial neural network algorithm to describe the electrical behavior of the device. And verifying the electrical performance trend of the three-dimensional device simulation model by using the PCELL and the simulation compact model. And when the verification is passed, further verifying whether the module test circuit meets a preset PPA index. And if yes, fixing the structural parameters of the current PCELL layout. According to the method, process and design requirements are integrated through a construction and parameterization method, and simulation and verification of closed-loop feedback are utilized, so that the design precision and the process maturity are improved, the development period is shortened, and the reliability and efficiency of the process are enhanced.

The invention discloses a logistic regression enterprise credit assessment method and system based on an additive model, belongs to the technical field of big data processing, and aims to solve the technical problem of how to realize robust enterprise credit assessment based on the additive model. Comprising the following steps: analyzing and fusing multi-source heterogeneous data of a user to construct a multi-source data standard library; selecting index data based on the multi-source data standard library, and constructing an index system for enterprise credit assessment based on the selected index data; preprocessing index data in the index system; constructing an evaluation model and a loss function of the evaluation model based on logistic regression and an additive model, performing model optimization on the evaluation model through loss function minimization, and performing model verification on the optimized evaluation model; and evaluating the to-be-evaluated enterprise through the trained evaluation model to obtain an evaluation result including the predicted label and the probability value, and judging the credit risk level of the enterprise based on the evaluation result.

The invention discloses a turnout switch machine fault diagnosis and prediction model method based on artificial intelligence. The method comprises the following steps: step 1, data acquisition; step 2, data preprocessing; step 3, feature extraction; step 4, model training; 5, verifying the model; 6, deploying the model; step 7, fault diagnosis and prediction; an artificial intelligence algorithm is introduced to automatically analyze data and identify faults, safe operation of equipment is ensured, instant fault response is realized through real-time monitoring and rapid data processing, the equipment safety is improved, an automatic modeling tool is adopted to simplify the construction process, non-professional personnel operation is facilitated, system deployment is accelerated, and the system reliability is improved. The method combines expert experience and data driving to form a hybrid model, improves the adaptability and accuracy of the model, integrates multi-sensor data to form a unified monitoring platform, enhances the comprehensiveness and accuracy of fault diagnosis, and provides powerful guarantee for the safety and efficiency of railway transportation.

The invention relates to the technical field of ship energy consumption prediction, and discloses a ship energy consumption interval prediction method and system based on a Gaussian quantile regression model.The method comprises the steps that firstly, a ship navigation historical data set is preprocessed, a model input feature set is screened, a Gaussian process quantile regression model with a radial basis function as a kernel is constructed, and hyper-parameters are optimized; and after the prediction performance of the subset evaluation point is verified through the model, an upper quantile prediction model and a lower quantile prediction model are respectively established according to a target confidence level, and finally a prediction interval is synchronously output and an evaluation report is generated. According to the method, through combination of Gaussian process processing nonlinear relation and quantile regression estimation condition distribution, high-precision point prediction is provided, meanwhile, prediction uncertainty can be quantized, an energy consumption prediction interval corresponding to a target confidence level is output, and more comprehensive and reliable information support is provided for ship energy efficiency management and operation decision making.

The invention discloses a verifiable privacy protection federated learning method based on sensitive samples, and relates to the field of fault diagnosis. According to the method, the Poisson sampling process is introduced, the sampling probability is generated based on the privacy budget, it is ensured that all recorded privacy budgets are synchronously exhausted, data disastrous forgetting is effectively prevented, and the model effectiveness is improved. In the model verification module, a sensitive sample set is generated by means of a gradient maximization algorithm, a model integrity attack is detected, a user side only needs to submit a small number of sensitive samples for prediction through an inference service API provided by a private cloud client side, and if a returned result and a real result have significant deviation, it can be judged that the model is possibly tampered. According to the method, diversified privacy requirements of users can be met, black box verification on the integrity of the model is realized, and the precision of the model is improved.

The invention discloses an engine multi-mode operation identification method and device based on a multi-dimensional internet of things, and a medium, and aims to solve the problem that the driving state cannot be obtained in time due to inaccurate engine monitoring data. According to the method, multiple key parameters in operation of the engine can be comprehensively covered through different types of sensors, rich information basis is provided for multi-modal operation identification of the engine through multi-dimensional data collection, rich feature data is extracted from the multiple sensors, time domain, frequency domain and time frequency features are covered, and the method is suitable for multi-modal operation identification of the engine. Through construction of a multi-modal operation identification model, data of a plurality of sensors can be comprehensively considered, a neural network model is used for training, and a cross validation method is used for model verification, so that the stability and generalization ability of the model are ensured; and the state of the engine is quickly judged according to the multi-mode operation identification model, so that real-time monitoring and early warning of the state of the engine are realized.

A complex system uncertainty digital model simulation verification method based on data feature measurement comprises the following steps: under the condition of considering uncertainty, extracting feature vectors of simulation output and real installation test output parameter data from multiple angles to construct a feature matrix; and the statistical similarity between the corresponding digital model and the real installation data feature vector is measured through the probability distribution difference, so that the consistency degree between the digital model and the real installation test data is obtained. According to the method, the problem of multivariable digital model verification complexity can be effectively solved, and the confidence coefficient of complex system digital model verification is improved.

A method for verifying system behavior and correcting design flaws in a finite state machine (FSM)-modeled system or any other representational method that includes receiving from a user device via a model verification platform, data associated with the system design. The data describes states, state transitions, events, and outputs of the FSM-modeled system. The method includes searching the data for predetermined behavior of the FSM-modeled system, including predetermined state(s) and / or mode changes. The method includes flagging the predetermined behavior as a verified behavior and performing a control action in response to the verified behavior, including transmitting a notification to the user device that is indicative of the verified behavior, and a design recommendation where applicable. Instructions for the method may be recorded in a computer readable storage medium and executed by a processor to cause the model verification platform to perform the method.

The invention discloses an anti-money laundering risk rule generation method and system based on a multi-modal large language model, and the method comprises the following steps: obtaining an initial training set composed of transaction data, adding a money laundering label based on a rule model, extracting transaction features through a multi-modal large language feature extraction model, and carrying out the expansion, forming a modeling training set by the initial training set and the expanded data set; fitting the multi-modal large language learning prediction model through the modeling training set to obtain a money laundering risk value of the transaction data, and calculating an actual contribution value of the structured features; and inputting the verification set into the multi-modal large language learning prediction model, verifying to obtain a money laundering label re-determination result, updating the money laundering label re-determination result to the initial training set, and then generating an updated rule model according to the verification result and the contribution value of the structured feature to the money laundering risk value. According to the invention, multi-mode transaction data can be integrated, a risk prediction model of money laundering transaction is formed, real-time adjustment and updating are carried out, and money laundering transaction behaviors can be accurately identified.

The invention provides an integrated circuit model verification method and system, computer equipment and a storage medium. The method comprises the steps that parameters in a model library are analyzed through a script, and model parameters needed by verification are automatically extracted; a standard configuration file format is obtained, the model parameters are loaded into a standard configuration file, and a simulation configuration file is generated; obtaining netlist file formats required by different simulators, and generating netlist files which comprise output instructions and are adaptive to different simulators in batches according to the simulation configuration file; calling each simulator to execute the corresponding netlist file for simulation, and outputting an intermediate file; analyzing the numerical data in the intermediate file, and generating a standard format file; and comparing the standard format files generated by different simulators to obtain a verification result. According to the scheme, batch parameter configuration, netlist generation, simulation execution and result processing of the integrated circuit model can be realized, so that the model verification efficiency is improved.

The invention discloses a compound structure identification database construction method, system and device and a medium, and the method comprises the steps: inputting a model training data set into a plurality of retention time prediction models for training, and obtaining a plurality of trained retention time prediction models; verifying the plurality of trained retention time prediction models by adopting a model verification data set, and selecting an optimal retention time prediction model; inputting the migration training data set and the migration verification data set into the optimal retention time prediction model for migration learning to obtain a target retention time prediction model; inputting to-be-predicted compound structure data into the target retention time prediction model for prediction to obtain predicted retention time; and constructing a compound structure identification database according to the predicted retention time. The data in the compound structure identification database can be perfected, and the accuracy of the compound structure identification database is improved, so that the database performance is improved.

The invention discloses a behavior analysis and anomaly detection method and system based on Internet of Things equipment, and relates to the technical field of power Internet of Things, and the method comprises the steps: obtaining behavior data of power grid Internet of Things equipment, carrying out the preprocessing of the obtained behavior data, and carrying out the feature extraction of the preprocessed behavior data; analyzing the extracted features, and establishing an Internet of Things equipment behavior model; and identifying a device state based on the Internet of Things device behavior model, and outputting a corresponding defense means. According to the equipment behavior analysis and anomaly detection method based on the Internet of Things, the accuracy of abnormal behavior detection is improved, the reliability of a classification result and the comprehensiveness of detection are ensured through fusion and comprehensive analysis of various data sources and a multi-model verification method, various conditions of equipment faults, data anomalies and operation anomalies are covered, and the accuracy of abnormal behavior detection is improved. And a flexible protection means is provided, and efficient maintenance and stable operation of a power grid system are realized.

The invention relates to a new energy GCI dq impedance acquisition method based on a BKA-BiLSTM model, and the method comprises the following steps: firstly, carrying out the mechanism modeling of a new energy grid-connected inverter based on the Norton's theorem, and analyzing the nonlinear mapping relation between the equivalent dq impedance of the new energy GCI and the port characteristics; secondly, establishing a new energy unit grid-connected system simulation model by utilizing MATLAB / Simulink software, and acquiring a data set required by BiLSTM neural network training under various working conditions; secondly, training a BiLSTM neural network by utilizing simulation data, and optimizing hyper-parameters of the BiLSTM by adopting a black-wing optimization algorithm (BKA); and finally, an RT-LAB hardware-in-loop test technology is combined with a small perturbation method to scan impedance characteristics of the GCI, and an actual impedance value required by model verification is obtained. Through example simulation analysis, the correctness of the GCI dq impedance identification method provided by the invention is verified.

Disclosed herein are systems and methods for cross-domain training of sensing-system-model instances. In an embodiment, a system receives, via a first application programming interface (API), an input-dataset selection identifying an input dataset, which includes a plurality of dataframes that are in a first dataframe format and that have annotations corresponding to one or more sensing tasks performed with respect to the dataframes. The system executes a plurality of dataframe-transformation functions to convert the plurality of dataframes of the input dataset into a predetermined dataframe format. The system trains an instance of a first machine-learning model using the converted dataframes of the input dataset to perform at least a subset of the one or more sensing tasks. The system outputs, via the first API, one or more model-validation metrics pertaining to the training of the instance of the first machine-learning model.

The invention relates to the technical field of formalized analysis and verification of a complex software system, and particularly provides a multi-modal cross-language multilayer verification formalized integration method. According to the method, a multi-dimensional analysis and verification process from codes to models is realized through a code or model self verifier layer, a code or model plug-in verifier layer, a multi-language or multi-model conversion verification layer and a code and model bidirectional cross verification layer. The multi-level verification framework covers code static analysis, model dynamic simulation and cross-language and cross-model conversion, various formalized tools are systematically integrated, verification results of different languages and models are deeply integrated while automatic and efficient verification is achieved, on one hand, system compatibility and consistency are kept, and on the other hand, the verification efficiency is improved; on the other hand, the sufficiency and reliability of system analysis and verification are remarkably improved.

The invention belongs to the technical field of prognosis models, and particularly relates to a diffuse large B-cell lymphoma risk prognosis model based on lactic acid metabolism related genes. The model construction comprises the following steps: S1, data acquisition and processing; s2, constructing a prognosis model; s3, verifying and evaluating the prognosis model; and S4, application of a prognosis model. GSE10846 and GSE87371 data sets are used for screening lactic acid metabolism related genes (LMRGs), a prognosis risk model is constructed and verified, and association of the prognosis risk model with clinical pathological characteristics, immune characteristics and treatment response is disclosed.