564 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 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 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.

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 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 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.

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 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 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.

The invention provides a heterogeneous database structure dynamic synchronization and fault-tolerant migration method, system and device, and belongs to the technical field of database migration. The method comprises the following steps: detecting a structural difference through combination of active detection and passive triggering; realizing DDL statement conversion of different databases by utilizing AST analysis through a cross-platform DDL converter; defining a migration process by adopting a migration state machine model so as to ensure orderly migration; and a breakpoint resume and consistency guarantee mechanism is utilized to ensure that migration fault tolerance is consistent with data by means of a vernier triple, an intelligent recovery strategy and a bidirectional check protocol. According to the method, the problems of structure synchronization and migration fault tolerance of the heterogeneous database in an environment without native change log support are effectively solved, the automation, high efficiency, stability and reliability of database migration are improved, and the method has wide application value.

The invention relates to the field of impact failure full-process prediction of complex-structure die castings, and discloses a data-driven impact failure full-process prediction method for complex-structure die castings, which comprises the following steps: step 1, performing mold flow simulation on a target part to obtain the solidification time and porosity of any position of the target part; 2, the solidification time and porosity of any position of the target part are input into a multi-layer perceptron model, and the multi-layer perceptron model outputs mechanical parameters of any position of the target part; the multi-layer perceptron model is trained based on data of actually measured mechanical properties; 3, acquiring a collision simulation grid model of the part, mapping the mechanical parameters to each grid unit of the collision simulation grid model, and generating an input file for collision simulation; and 4, performing collision simulation based on the input file in the step 3.

The invention relates to a wind power transmission fault early warning method and device based on single machine-cluster model interaction. The method comprises the steps that historical operation data of wind turbine generators of the same type in the same wind power plant are collected; aggregating to obtain a first data set corresponding to a single wind turbine generator set and aggregating to obtain a second data set of the same type of wind turbine generator sets; performing model training according to the first data set to obtain a single-machine early warning model, and performing model training according to the second data set to obtain a cluster early warning model; interactively correcting an output result by using the single-machine early warning model and the cluster early warning model; and adopting a voting fusion strategy to obtain a final prediction result. Through interaction and fusion of the single machine-cluster model, personalized features of the single machine model and a common rule of the cluster model are fully utilized, result misjudgment and missed judgment are avoided, and the accuracy of fault prediction of the wind turbine generator transmission system is remarkably improved. The method can better adapt to complex and changeable operation conditions of the wind turbine generator, and the reliability of fault early warning is enhanced.

The invention discloses a hydrogen fuel cell ship electric propulsion inertia self-adaptive optimization control method, which relates to the technical field of hydrogen fuel cell ship electric propulsion control, and comprises the following steps of: acquiring ship operation state data and ship internal power network fluctuation data in real time, preprocessing, extracting features, calculating a virtual inertia coefficient and a virtual damping coefficient, and calculating an inertia coefficient and a damping coefficient; generating a virtual torque instruction; obtaining a total power demand of the ship by using a torque rotating speed calculation method, and dividing the total power demand into high-frequency, intermediate-frequency and low-frequency ship power distribution instructions; through a virtual synchronous machine model, the actual power of the ship is output, the voltage of a direct-current bus and the power of a hydrogen fuel cell are monitored in real time, a dynamic compensation power fluctuation method is utilized, the operation state of the ship is regulated and controlled, and a voltage stability index is obtained; the ship propulsion inertia is adaptively optimized through a power regulation algorithm, so that the ship can better adapt to different working conditions, and the stability and safety of the ship are enhanced.

The invention provides a cooperative control method and device for low-voltage power consumption of a whole vehicle and electronic equipment, and relates to the technical field of automotive electronics, and the method comprises the steps: obtaining multi-modal original data (including vehicle state information, environment information and user behavior information), and carrying out the preprocessing; performing feature extraction and fusion processing on the preprocessed multi-modal original data to generate a high-level semantic event used for representing the vehicle leaving intention of the user or the parking scene; matching a global power consumption management strategy of a high-level semantic event through a hierarchical finite-state machine model; and according to the global power consumption management strategy, executing hierarchical power supply control on the low-voltage electricity load of the whole vehicle, and in the hierarchical power supply control process, dynamically adjusting control parameters in the global power consumption management strategy based on a comparison result of the actual power consumption monitoring data and a preset baseline model. Depth power shortage of the storage battery caused by redundant power consumption is effectively avoided, the risks that the vehicle cannot be started and equipment is abnormal are reduced, and the reliability of the whole vehicle and the user experience are improved.

Aspects of the present disclosure relate to an apparatus for predicting an olfactory profile of a molecule, the apparatus comprising memory circuitry, machine-readable instructions, and processor circuitry to execute the machine-readable instructions to obtain a first representation of the molecule and a second representation of the molecule, process the first representation using at least one first machine-learning model to obtain a first predicted olfactory profile of the molecule, process the second representation using at least one second machine-learning model to obtain a second predicted olfactory profile of the molecule, process the first predicted olfactory profile and the second predicted olfactory profile, or a combined version of the first predicted olfactory profile and the second predicted olfactory profile, using a third machine-learning model, the third machine-learning model being trained to output a third predicted olfactory profile of the molecule.

The invention relates to the technical field of data processing, and discloses an intelligent arrangement, storage, tracking, management and control method and system for sulfur hexafluoride gas cylinders. The method comprises the following steps: performing leakage risk assessment through a sulfur hexafluoride concentration sensor and a gas cylinder pressure monitoring device to obtain an environmental risk data set; performing multi-dimensional state sensing on the gas cylinder according to the intelligent label and the inclination angle sensor to obtain a dynamic state information set of the gas cylinder; performing path optimization through a multi-target search algorithm to obtain a multi-target path cost matrix; performing Pareto optimal solution screening through a leading edge set maintenance mechanism to obtain an optimal scheduling path set; and tracking the life cycle of the gas cylinder based on the state machine model to obtain full life cycle tracking data. The problems of intelligent scheduling optimization and full-life-cycle tracking management and control under the multi-target constraint condition in sulfur hexafluoride gas cylinder storage management are solved.

The invention discloses a vehicle control method and device, a vehicle, a processor and a program product. The method comprises the following steps: determining location information of a target area where a vehicle is located; target state machine models corresponding to the attribution information are determined from at least one state machine model, and different attribution information corresponds to different target state machine models; based on the target state machine model, a target emission control strategy corresponding to the vehicle when the vehicle travels to the target area is determined, the target emission strategy is used for determining the exhaust emission condition of the vehicle, and different target areas correspond to different target emission control strategies; on the basis of the target emission control strategy, control data of the vehicle are determined, and the control data are used for controlling emission of tail gas of the vehicle; and according to the control data, a sensor in the vehicle is controlled to discharge tail gas of the vehicle. The technical problem that the tail gas emission control efficiency is low is solved.

The invention discloses a pouring planning method and device of a material distributing machine, electronic equipment and a storage medium, and the method comprises the steps: obtaining a BIM model of a pouring site, a material distributing machine model and obstacle information of the pouring site, and obtaining a feasible region of the material distributing machine corresponding to the material distributing machine model in the pouring site according to the BIM model, the material distributing machine model and the obstacle information; according to the pouring attributes of the components contained in the BIM model, the components contained in the pouring site are divided into pouring components and poured components, communication processing is conducted according to the adjacency of the pouring components, and the area where all the pouring components are located is determined as a pouring area; according to the BIM model of the pouring area and the feasible region, based on concrete flow collapse and component connectivity, a collapse statistical algorithm is used for calculation, and a pouring planning result of the material distributing machine is generated; and according to the pouring planning result, a material distributing machine is controlled to move in the pouring site so as to conduct pouring treatment on all the areas in the pouring area. And the pouring safety and the pouring efficiency are improved.

The invention relates to a multi-Agent-based hierarchical progressive RFC state machine model extraction method, belongs to the technical field of network protocol extraction, and solves the problems that RFC document information is difficult to refine when a state machine model is extracted at present, the large model used for extraction is easily influenced by illusion due to the limitation of the large model, and the accuracy and recall rate are difficult to guarantee. Comprising the steps of obtaining an RFC document of a to-be-extracted state machine model and performing structured processing to obtain each RFC document block taking a title as a demarcation point; based on a preset protocol state machine term, recalling a core document block, a supplementary document block and a long tail document block from each RFC document block; extracting an initial state machine model from the core document block, performing review, and optimizing the initial state machine model based on a review result to obtain a reviewed state machine model; and on the basis of the supplementary document block and the long tail document block, performing supplementary optimization on the reviewed state machine model to obtain an RFC state machine model.

The invention discloses a spherical roller bearing entity simulation method, device and equipment and a medium, and relates to the technical field of wind power generation. According to the scheme, when the finite element mesh model of the spherical roller bearing is constructed, the rollers are connected to the bearing inner ring and the bearing outer ring through the spring units, that is, traditional finite element constraint is replaced with the mode that the rollers are constrained through the spring units, and the conventional constraint limitation in finite element simulation is broken through; accurate analysis of bearing roller contact in a complete machine model is realized; after a complete machine finite element mesh model is generated based on a model of the spherical roller bearing, simulation parameters and loading parameters of the complete machine finite element mesh model are set, the simulation parameters at least comprise a working clearance between a roller and a raceway, that is, contact offset is added to simulate the existence of the radial clearance of the bearing, and the loading parameters of the complete machine finite element mesh model are set. The problem of simulation of play contact of the SRB main bearing under the working condition of high axial force is solved, and three-dimensional balance of physical authenticity, calculation efficiency and engineering applicability is achieved.

A method for designing proteins using multi-objective reinforcement learning can include generating, by one or more processors using a machine model, based on an initial protein sequence data structure, a plurality of protein sequences, the machine learning model configured based on reinforcement learning from a plurality of reward metrics including at least one reward metric associated with experimental data regarding example sequence data, scoring, by the one or more processors, using a plurality of scoring functions, the plurality of protein sequences, to select a subset of protein sequences of the plurality of protein sequences, and outputting one or more selected protein sequences of the subset of selected protein sequences.

The invention discloses an additive manufacturing method of a part, relates to the technical field of additive manufacturing, and aims to solve the problem that a substrate and the part deform when a large-format part is printed. The additive manufacturing method comprises the steps that a part three-dimensional model is obtained; determining a part forming direction; a margin cutting part is constructed close to the bottom face of the base plate, a supporting structure is constructed on the bottom face, close to the base plate, of the margin cutting part, a machining model is obtained, the supporting structure comprises a contour supporting piece and a plurality of internal supporting pieces, the contour supporting piece is connected with the edge area on the bottom face of the margin cutting part, and the thickness of each internal supporting piece is smaller than that of the contour supporting piece; the multiple internal supporting pieces are distributed in the area defined by the contour supporting pieces on the bottom face of the allowance cutting part at intervals. Printing based on the processing model to obtain a printed piece; and treating the printed piece to obtain the part. The supporting structure is used for supporting the bottom face of the part and used for forming the part in large-area contact with the base plate, and deformation caused by direct contact between the base plate and the bottom face of the part is avoided.