698 results about "Machine models" patented technology

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 provides a digital twinborn simulation method for an automatic verification system of an electric energy meter, and belongs to the technical field of electric energy meters, and the method comprises the steps: S1, collecting the multi-modal data of the electric energy meter in real time; s2, based on a multi-scale convolutional neural network, deep features of the multi-modal signal data are extracted, and a digital twinborn model is constructed; s3, operating the digital twin model in the virtual environment, simulating the verification process of the electric energy meter, and monitoring the equipment state in real time; and S4, inputting the implicit state representation into the graph convolutional network, constructing a fault relation network of the electric energy meter verification system, analyzing fault causes through the graph convolutional network, obtaining a comprehensive analysis report based on output of fault prediction and diagnosis, and optimizing an electric energy meter verification process by using a multi-arm tiger machine model. The digital twinning technology is fully utilized, the actual operation state of the electric energy meter is simulated in the virtual environment, real-time synchronization of the physical entity and the virtual model is achieved, and the intelligent level and the management efficiency of the system are effectively improved.

The invention discloses a multi-modal wind turbine generator electromechanical transient modeling method based on artificial intelligence, and relates to the technical field of new energy power generation modeling, and the method comprises the steps: carrying out the causal association mining and dependence path recognition of a standardized spatio-temporal data cube through a causal discovery algorithm, constructing a causal topological graph, and carrying out the modeling of the new energy power generation. Performing cross-modal feature fusion through a space-time diagram attention network to generate a high-order feature tensor; dividing the high-order feature tensor into meta-learning task pools according to different models and environmental conditions, and training a cross-model general parameterization framework by adopting a double-layer optimization strategy; constructing a composite working condition generator based on the trained cross-model general parameterization framework, and performing constraint through a causal regularization loss function to form an extended test working condition set; and performing control parameter optimization on the extended test working condition set by adopting a multi-modal deep reinforcement learning algorithm to obtain optimized control parameters. According to the method, a foundation is laid for realizing electromechanical transient modeling with high robustness and high generalization ability through accurate causal modeling and cross-modal fusion.

The invention provides a prognosis risk prediction model construction method based on coexistence of acute myocardial infarction and atrial fibrillation and application. The method comprises the following steps: S1, acquiring historical patient clinical information of a target patient and death time after coexistence of diseases; s2, preprocessing clinical information of historical patients; s3, using an LASSO method and a ten-fold cross validation method to identify related clinical features related to death time after coexistence of diseases; s4, dividing a training set and a verification set; s5, performing training optimization on the four machine models by using the training set, evaluating the prediction performance of the models by using the verification set, and determining a Glmnet model with the optimal prediction performance; and S6, performing model interpretation on the Glmnet model by using an SHAP value, and determining an optimal prediction factor of which the model prediction contribution ranks the first three. The prognosis risk of coexistence of acute myocardial infarction and atrial fibrillation can be accurately predicted, and reference is provided for clinical diagnosis and treatment of patients with coexistence of acute myocardial infarction and atrial fibrillation.

The invention provides a machine learning-based marine chlorophyll concentration inversion method, which comprises the following steps of: clustering remote sensing reflectivity data to obtain clusters corresponding to different water body types, and applying training sets to various machine learning models for training according to the water body types to obtain a plurality of machine learning models; and performing performance verification on different optimization machine models under different water body types by using the verification set to obtain optimal machine learning models under different water body types, and finally forming a chlorophyll concentration dynamic inversion model. And carrying out chlorophyll concentration inversion by adopting the optimal machine learning model of the corresponding water body type, so that the model has a wide application scene. The chlorophyll concentration dynamic inversion model provided by the invention has very strong universality, and the global sea area water color information monitoring capability is effectively improved.

The invention discloses a monitoring and early warning method and system based on active load prediction of a power distribution network, which breaks through the limitation of purely depending on historical data and simple statistical analysis, fully considers the complexity and uncertainty of load change influenced by various factors, and achieves the early warning of the load change through the combination of multiple models. The method can accurately classify and analyze the operation active load of the power distribution network through an active power analysis model, a decision tree model and the like, thereby improving the prediction precision. In the aspect of data processing, mass operation data generated by intelligent equipment in the power distribution network can be effectively integrated and mined by utilizing a vector machine model and a cloud large model server, an early warning mechanism is flexible, the method can adapt to different operation scenes and load characteristics, false alarm and missing alarm are avoided, and the method is suitable for popularization and application. According to the method, the power distribution network fault identification efficiency of the power distribution network power factors in different time periods is remarkably improved, and effective operation of the power distribution network is ensured.

The invention discloses a regression test case determination method and device, a storage medium and electronic equipment, and relates to the field of artificial intelligence. The method comprises the steps of obtaining a target change code of a target program; the target change code is input into a vector machine model, code features of the target change code are extracted through the vector machine model, a potential defect score of the target change code is determined according to the code features, and the potential defect score is used for representing the probability that the target program is abnormal due to the target change code; and determining at least one regression test case for testing the target change code from the M test cases according to the potential defect score of the target change code, the code feature of the target change code and the case feature of each test case in the M test cases. The technical problem that in the prior art, the efficiency of compiling the regression test case is low is solved.

The invention provides a driving training method and system for a robot vehicle by an intelligent agent based on auxiliary driving, and relates to the technical field of intelligent driving, and the method comprises the steps: obtaining the multi-sensor fusion sensing data of the robot vehicle, inputting the multi-sensor fusion sensing data into a preset deep reinforcement learning model, according to a driving decision output by the deep reinforcement learning model, in combination with a preset safe driving rule base, generating driving guidance subtasks in three dimensions of transverse control driving guidance, longitudinal control driving guidance and traffic rule driving guidance; and sensing the execution state and the environment of the robot vehicle in real time, inputting a sensing result into the hierarchical finite-state machine model so as to trigger a corresponding state transition condition, and outputting a corresponding driving guidance action sequence according to a current state node until a corresponding driving guidance sub-task is completed. And converting the driving guidance action sequence into a specific vehicle control instruction.

The invention provides an Alzheimer disease auxiliary accurate identification method and system based on a multi-omics marker network and an adaptive support vector machine. Accurate identification of Alzheimer's disease and other types of dementia is realized through a marker network based on five modal data and an adaptive support vector machine model. According to the method, multi-source heterogeneous data such as blood, urine, neuroimaging, electrophysiology and clinical evaluation are fused, specific markers are analyzed and screened by adopting a weighted gene co-expression network, and cross-modal feature interactive learning is realized through a self-attention mechanism. An online learning mechanism is introduced to enable the model to adapt to new data distribution, and the contribution degree of each marker to diagnosis is output in combination with an interpretability module. Finally, multi-center data synchronization and model optimization are realized by means of a cloud platform, the accuracy, specificity and early diagnosis capability of AD diagnosis and identification and the adaptability of the model are remarkably improved, the limitation of the prior art is overcome, and doctors are assisted to diagnose and treat the Alzheimer's disease.

A machine learning model, such as a Gradient Boosting Machine model, is trained using historical data associated with different types of operations. The machine learning model extracts features from the historical data and learns which features result in a predefined outcome, such as approval by a predefined entity. After the machine learning model is trained and validated as being accurate, it is used to predict the likelihood of a prospective operation achieving the predefined outcome when submitted right away versus a future date. If the likelihood of achieving the predefined outcome is low if submitted right away, the submission of the prospective operation is temporarily suspended. The machine learning model calculates a future time during which to submit the prospective operation for approval, where the future time has a greater likelihood of achieving the predefined outcome. This reduces waste of electronic resources including computer processing power and network communication bandwidth.

The invention relates to a wireless federated learning scheduling method based on multi-arm long machine optimization, a wireless federated learning model and a multi-arm long machine model, a wireless federated learning algorithm based on a multi-arm long machine can be given, and a super pull rod combination (or each action) is selected in each turn as an integral feedback. The algorithm describes the process of carrying out efficient wireless federal learning training under the assistance of the dobby machine provided by the invention.

A natural language test case for an application is automatically converted into a test script by a test script generator. During the generation of the test script, the test script generator may access a blueprint of the application. The blueprint may include a time-evolving model of the application, which may include a set of translations and a state machine model of the application. The state machine model may include a state space and a set of state transitions. During the test script generation process, the blueprint may be continually updated to include new knowledge of the application. The test script generator may communicate with an artificial intelligence (AI) engine in order to determine the semantic similarity between two phrases, convert images into textual description, and perform tasks requiring the use of a large language model (LLM).

The invention provides a numerical control machining control method and device, a numerical control machine tool, a medium and a program product, and relates to the technical field of numerical control machining. The numerical control machining control method comprises the steps that in response to a received first setting instruction of a self-adaptive learning state, a main shaft of a numerical control machine tool is controlled to machine a part based on a fixed feeding rate under a preset machining condition, and a corresponding main shaft power curve is generated; performing adaptive learning based on the main shaft power curve and the configured power range to obtain a processing model; and in response to a received second setting instruction of the self-adaptive control state, in the machining process of the part, the sensed load of the main shaft is input into the machining model, so that the machining model outputs the feeding rate of the main shaft based on the self-adaptive adjustment operation, and the main shaft operates based on the changing feeding rate. According to the technical scheme, the machining model is used for adjusting the feeding rate of the machine tool spindle in real time based on the detected real-time load, and the machining efficiency is higher.

The invention discloses an aggregate loading size identification and detection control system based on radar identification, and particularly relates to the field of constructional engineering, which comprises a multi-source sensing module, a feature extraction module, an index calculation module, a threshold judgment module, a logic decision module and a control execution module. Characteristic parameters such as phase difference and coordinate deviation are extracted through multi-modal processing, four kinds of comprehensive indexes such as volume uniformity and overload risk are generated, risk grading early warning is achieved through a three-level threshold system, a control instruction is generated in combination with a state machine model and a logic gate strategy, and the system is provided with an electro-hydraulic proportional valve and a redundant braking mechanism. The system supports multi-stage response from rate adjustment to emergency braking, has the characteristics of multi-dimensional dynamic monitoring, intelligent decision making and environment self-adaption, effectively improves the safety and automation level of bulk cargo loading operation, and is suitable for continuous operation requirements of complex industrial scenes.

The invention discloses a location social network service recommendation method based on trajectory collaborative filtering and Mama. The method comprises the following steps: firstly, collecting service interaction data of a user in a location social network; carrying out representation modeling on the service interaction behavior based on static and dynamic joint representation learning, and generating a point-of-interest static representation embedding vector and a user interest signal embedding vector; constructing a service interaction behavior sequence modeling network based on a state space machine model Mamba, embedding and inputting a user interest signal into the network, modeling a user long and short term interest state transition mode field through the state space model, and outputting a prediction interest point matching embedding vector; and finally, optimizing the model through a minimized cross entropy loss function, generating a user interaction service recommendation list based on the normalized score matrix, and taking the first K interest points with the highest score as recommendation results. According to the method, a unified user long-term interest transfer mode field and a short-term interest response mode are constructed, and the problem of popularity bias of a recommendation system is relieved.

The invention discloses an English writing grammar error detection system based on deep learning. The system comprises an original data acquisition module, a data preliminary processing module, a grammar error positioning model construction module, a grammar error classification model construction module and a grammar error detection module. The invention relates to the technical field of text grammar error detection, in particular to an English writing grammar error detection system based on deep learning. A data preliminary processing method of text data trimming, text vectorization, data standardization and data set segmentation is adopted; a lightweight gradient elevator model is adopted as a grammar error positioning model, and the error positioning precision is improved through adaptive fusion of rule conflicts and statistical mode anomalies; a transformer model is adopted as a grammar error classification model, and classification accuracy is improved by modeling dependency relationships among words and introducing graph structure constraints.

The invention relates to the technical field of education, in particular to a medical defense fusion skill evaluation method based on a causal-machine model, and the method comprises the steps: 1, generating question feature vectors and knowledge point semantic vectors through employing a natural language processing technology in combination with a deep learning model, and calculating the correlation between the feature vectors through employing cosine similarity; 2, generating a question difficulty coefficient based on a causal-machine model; step 3, generating a student knowledge mastering feature vector according to the answering accuracy and answering speed of the student; 4, recommending the most suitable homework questions to the students based on a deep learning model; and 5, quantitatively analyzing the answering performance of the students through a causal-machine model, and providing feedback suggestions and learning suggestions. According to the invention, weak links of students can be identified, the efficiency of preventive medicine major learning is effectively improved, the teaching decision of teachers is assisted, and personalized cultivation of medical defense fusion and medical defense collaboration talents is promoted.

The invention discloses a transient response calculation method for a complete machine model with a gap support. The method comprises the following steps that SS1, whole machine nonlinear modeling of a rotor-bearing-casing system is carried out, linear component modeling of a whole machine structure and nonlinear modeling of a gap bearing are included, linear component modeling of the whole machine structure comprises rotor modeling, casing modeling, linear bearing modeling and installation section modeling, and linear component modeling of the whole machine structure comprises linear component modeling of the rotor-bearing-casing system and linear component modeling of the gap bearing; the non-linear modeling of the gap support comprises non-linear modeling considering friction influence and contact influence, and a whole machine non-linear rotor dynamic model is constructed; step SS2, response calculation of a Newmark method based on variable step size control is carried out; and step SS3, extracting transient responses of each node of the rotor, the support and the casing. According to the method provided by the invention, the fit clearance between the rotor journal and the bearing inner ring and the influence of the casing are considered at the same time, the transient response of the rotor-bearing-casing system is calculated, the vibration characteristics of the whole machine with the clearance bearing are analyzed, and support is provided for the structural design of an engine.

The invention discloses a psychological counseling intelligent recommendation method and system based on artificial intelligence, and relates to the field of psychological counseling cross technology, and the method comprises the steps: calculating a three-dimensional emotion vector according to an emotion axis space and a syntactic structure, constructing a psychological semantic tensor by using a tensor outer product, generating a user intention tensor by using a prototype weight, and carrying out a flattening operation. Obtaining a final intention vector; combining the structural potential energy deviation and the spectral distance to construct a matching factor tensor; constructing a factorization machine model, predicting a matching score, generating a prediction score matrix, screening by using a Top-K selection method, generating recommended content, and constructing a visual interface to display the recommended content. According to the method, the fine granularity and accuracy of emotional representation are improved through emotional axis space and syntactic dependency analysis, the matching precision of intention and resources is improved through comprehensive calculation of semantic gravitation intensity and spectral distance, and the expression ability of matching factor tensor is enhanced through fusion of structural potential energy deviation and spectral distance.

The invention relates to the technical field of data processing, and relates to an automobile supply chain risk identification method based on a knowledge graph, and the method comprises the steps: obtaining the entity type of an automobile supply chain, and dividing the levels of the automobile supply chain based on the entity type; each entity type comprises a plurality of entities, each two entities comprise one or more relationships, the entities are used as nodes, the relationships between the entities are used as edges, and a knowledge graph of the automobile supply chain is constructed; aiming at node risk change, calculating the influence of the node risk change on the overall risk of the supply chain, quantifying the node risk through the edge weight, the initial risk variation and the hierarchy of the node, and dividing the risk level; and finally, inputting the initial risk variable quantity and the risk level into a machine model for training so as to predict the risk level of the to-be-detected node in the supply chain. According to the invention, the problem of inaccurate risk identification of the automobile supply chain is solved.

The embodiment of the invention relates to a processing method and device for relation extraction based on a large language model. The method comprises the steps that the large language model is selected as a first model; constructing a first data set through a data acquisition / cleaning / labeling mode of a manual / machine model to pre-train a relationship extraction / verification function of the first model; constructing a second data set based on the text generation function of the first model after the pre-training is finished, performing data cleaning on the second data set based on the relationship verification function of the first model, and performing fine adjustment on the relationship extraction function of the first model based on the cleaned second data set; and after the fine tuning is finished, substituting the queried text input by the user, the limited relation sequence and the output format into the first instruction template to perform large-model input text assembly, and inputting the assembled text into the first model to perform relation triple recognition and screening processing to obtain an output text to be fed back to the user. According to the invention, the model generalization can be enhanced, and the prediction accuracy is improved.

The invention provides a construction method and system of a settlement landscape evolution database based on multivariate spatial-temporal characteristics. According to the method, historical literatures, aerial photography, satellite images and landscape data are integrated to form a multivariate data set; constructing a dynamically updated database by using MySQL, and realizing data source associated storage by using a relational model; establishing a settlement landscape state machine model, and extracting spatio-temporal data to identify typical states and conversion conditions; constructing a state transition matrix, and analyzing the influence of social economic and environmental changes on evolution; the database is updated through field investigation, and a visual tool is developed to display the evolution process. According to the method, full-process dynamic analysis of settlement landscape evolution is realized, and efficient and accurate support is provided for decision making.

In order to improve the accuracy and reliability of impact damage identification based on machine learning, the invention provides impact damage identification based on multi-modal data fusion and ensemble learning. According to the method, multi-modal data including discrete impact damage characteristics, a time-domain impact signal sequence and a time-frequency image of an impact signal are adopted as input of a machine model, and impact damage information contained in an impact stress wave signal is fully mined; and the artificial neural network, the long-short-term memory network and the convolutional neural network are integrated by using a weight average technology, and impact damage is identified by fusing three distances including a cosine distance, a Manhattan distance and an Euclidean distance. The method is verified on a 400mm * 400mm composite material platy structure, and the result shows that the method can perform high-precision identification on the impact damage in the structure under the condition of using a small number of sensors.

The invention relates to a flexible combined machine tool control system. The system comprises a multi-channel user interface module, a servo parameter monitoring module, a workpiece coordinate system management module and the like. The multi-channel user interface module is associated with a work station by means of a dynamic binding technology, automatically generates an interactive interface according to configuration parameters and visually configures an enabling state. And the servo parameter monitoring module displays and adjusts the shaft motion parameters in real time and adjusts the shaft motion parameters on line, the deviation is corrected through a self-adaptive algorithm, coordinate synchronization of multiple workstations is achieved through the algorithm and a batch writing function, and mixed analysis of an NC program and a user-defined instruction is supported. The hardware abstraction layer module encapsulates a heterogeneous control card interface, dynamically allocates hardware resources, and coordinates time sequence linkage of each part by using a state machine model. The system also combines visual inspection to correct cutter compensation parameters, and double safety protection is set. According to the invention, the problem of low equipment cooperation efficiency in multi-station flexible processing is effectively solved, and the system compatibility and the processing precision are improved.

The invention provides a Web page testing method and system, and the method comprises the following steps: requesting and analyzing a URL (Uniform Resource Locator) address of a target webpage, and extracting different types of element positioning feature information in the target webpage; performing data labeling on the extracted element positioning feature information to obtain a training data set; the training data set is input into a machine model for training, an element positioning prediction model is obtained, and the element positioning prediction model is used for predicting element positioning information in the webpage; the method comprises the steps that a base class is constructed, a browser and a calling function method of page elements are packaged in the base class, an independent subclass is created for each page, all subclasses inherit the base class, and testing methods and private attributes of the corresponding pages are defined in the subclasses; according to the method, the element positioning prediction model is constructed based on the neural network, the element positioning feature information in the target webpage can be accurately and automatically extracted, the manual element positioning work caused by frequent page change is reduced, and the test efficiency is improved.

The invention discloses an optimal power flow solving method and device based on a graph neural network and an extreme learning machine, and relates to the field of power grid power flow calculation, and the method comprises the steps: obtaining the node topology of a to-be-solved power system and the historical operation data of each power node, and constructing a system topological graph according to the node topology and the historical operation data; extracting features of a system topological graph based on a multilayer graph convolutional neural network to obtain first node features; taking the minimum total output of the system as a target, screening first node features based on regularization, and fusing the first node features to obtain second node features; performing multiple times of iterative training on the initial extreme learning machine model according to the second node features, optimizing model parameters based on mean square error loss during iteration, completing training until the model parameters meet preset values, and obtaining a first extreme learning machine model; and obtaining real-time operation data of the to-be-solved power system, and obtaining an optimal power flow solving result of the to-be-solved power system according to the real-time operation data and the first extreme learning machine model.

The invention relates to the technical field of electronic noses, in particular to a double-center intuitionistic fuzzy large-interval classification method with unified marble loss, which comprises the following steps: defining and optimizing a large-interval distributor model, and introducing a marginal mean value and a marginal variance to describe marginal distribution characteristics; replacing a hinge loss function with a marble loss function, and defining a hyper-parameter of a control quantile; calculating a membership degree and a non-membership degree, verifying the rationality of the new intuitionistic fuzzy strategy through a theorem, and calculating the confidence coefficient of the sample; constructing a double-center intuitionistic fuzzy large-interval classifier model of unified marble loss, deducing a dual problem, solving an optimization problem to obtain model parameters, and calculating a decision function to classify new examples; a classifier model is used, the performance of the model is evaluated through a verification set, the classifier model is deployed in practical application, and a data classification task is carried out, so that the anti-drift performance of the electronic nose system is effectively improved, the mean value and the variance are taken as optimization targets, and the relatively strong anti-interference capability is realized.

The invention provides an industrial ray radiation dose visual simulation method and system based on FLUKA. The method comprises the following steps: creating and optimizing an X-ray machine model, setting radiation parameters, establishing an optimized radiation propagation model, carrying out simulation calculation, establishing the radiation intensity of a freely selected detection point or focus point according to a calculation result, and generating two-dimensional and three-dimensional dose and energy distribution diagrams. And establishing a dynamic radiation intensity calculation model and carrying out mistaken radiation accident simulation and evaluation. The system can accurately simulate and predict the dose of industrial ray radiation in real time, outputs a visual dose distribution diagram, provides a convenient and visual operation interface for workers, and is beneficial to improving the efficiency and safety of ray protection work. The method has wide application value in the aspects of industrial ray protection, mistaken irradiation accident early warning, ray device design optimization and the like.

The invention discloses a precise air conditioner energy-saving control optimization method based on reinforcement learning, which comprises the following steps of: acquiring environmental parameters such as temperature, humidity, thermal load, electric energy consumption and running state of an air conditioner system, generating a vector reflecting the current environmental condition, scoring a plurality of control actions through an improved Banditron perceptron model, and calculating the control parameters of the air conditioner system according to the scored control actions. Selecting an optimal control action through a Thompson sampling mechanism, executing the selected control action, collecting environment feedback information after execution, forming a feedback parameter set, dynamically adjusting parameter values of exploration behaviors through data analysis of a continuous control period, and finally jointly inputting a current environment state and the control action into a decision model. And generating a parameter set for setting operation of the air conditioner. Intelligent optimization and energy-saving regulation and control of the air conditioner control process are achieved.

This machining surface estimation device comprises: an acquisition unit that acquires tool position data indicating the position of a tool, tool shape data indicating the shape of the tool, workpiece shape data indicating the shape of a workpiece, and factor data indicating factors affecting the control of a control axis; an association unit that associates the tool position data with the factor data; a simulation unit that generates a machining model on the basis of the tool position data, tool shape data, and workpiece shape data acquired by the acquisition unit; and a display unit that displays factor information, indicating the factor data, on the machining model generated by the simulation unit, on the basis of the tool position data and the factor data associated by the association unit.