426 results about "Scale model" patented technology

The invention discloses a knowledge-based visual question-answering method and device based on big and small model collaboration and a medium, belongs to the technical field of visual question-answering, and solves the problem of how to improve the accuracy of complex questions faced by a visual question-answering technology. In the image description extraction step, an image description and key object label set which is highly associated with a natural language problem is generated, and in the entity enhancement processing step, key entities are extracted and a clarity problem and an entity example which are used for resolving semantic ambiguity are generated. In the candidate answer generation step, a plurality of semantically complementary answers are generated under different reasoning dimensions on the basis of a multi-round generation strategy, optimized candidate answers are screened on the basis of a model built-in scoring mechanism, in the context example retrieval step, examples most related to current input are retrieved, and finally, the candidate answers are obtained. And the large language model receives a unified input prompt formed by splicing output results in the steps, and inference is performed in an autoregression mode to generate answers, so that the accuracy of the visual question-answering technology facing complex questions is effectively improved.

The invention discloses a method and a system for predicting the lumpiness of open-air throwing blasting, and relates to the technical field of rock blasting engineering. The invention discloses a new calculation relation about a lumpiness similarity proportion, relates to the technical field of open-air loose blasting mining, and can predict blasting lumpiness of projects such as mines, tunnels and the like by scaling a lumpiness distribution proportion. The method comprises the following steps: firstly, acquiring a rock sample from a blasting site, measuring parameters such as rock density and fracture toughness, and acquiring blasting parameter information of a to-be-blasted area; and then, a numerical simulation model under an open-air throwing blasting similar material is constructed by using a numerical simulation method, the change rule of blasting fragmentation lumpiness along with explosive unit consumption in a scale model test is studied, and the blasting lumpiness in a field blasting area is predicted according to the blasting lumpiness similarity ratio. According to the method, the change rule along with the unit consumption of the explosive is analyzed, the utilization rate of crushing energy of the explosive in surface blasting engineering is improved, reference is provided for blasting lumpiness control, and prediction of field blasting lumpiness before blasting is achieved.

The invention relates to the technical field of wind tunnel tests, in particular to a large-scale model wind tunnel test device and a debugging method thereof. The scale model wind tunnel test device comprises a supporting device which comprises an upper supporting truss, a lower supporting truss and a plurality of supporting stand columns, the upper supporting truss and the lower supporting truss are composed of main beams and anchoring structures, the supporting stand columns are connected with the upper supporting truss and the lower supporting truss, and sliding rails are symmetrically arranged on the upper supporting truss and the lower supporting truss. The large-scale model is connected between the two sliding rails through a line spacing adjusting device and an inclination angle adjusting device, large-scale model assemblies are fixed to the upper end and the lower end of the large-scale model through detachable force transmission plates, and the force transmission plates are connected with a force measuring balance; the large-scale model is provided with a pressure measuring hole, and the scale ratio of the large-scale model is greater than 1: 20; a wind pressure sensor is arranged in the data acquisition device, the data acquisition device is connected with the pressure measuring hole of the large-scale model through a pressure measuring pipe, and wind pressure is transmitted to the wind pressure sensor of the data acquisition device through the pressure measuring pipe. The large-scale model wind tunnel test device and the debugging method thereof are convenient and fast to install and flexible to adjust.

The invention discloses a fluid distribution dynamic regulation and control method and device based on a shale reservoir microstructure, and relates to the technical field of oil and gas exploitation. The method comprises the steps that microstructure parameters of a target shale reservoir are obtained through a core experiment, and a multi-scale model is constructed based on the microstructure parameters; determining control equations of different physical fields of the multi-scale model; coupling the control equations of different physical fields, and resolving through a finite element method; performing a numerical simulation experiment based on the multi-scale model and the resolving result to determine regulation and control parameters; the regulation and control parameters are input into the multi-scale optimization model to optimize the regulation and control parameters, and a regulation and control strategy is obtained. The problems that an existing displacement experiment is single, the complex interaction process under the actual mining environment is not comprehensively considered, and the guiding effect on mining work is limited are solved. Business personnel can be guided to formulate a development scheme more scientifically and accurately, the mining efficiency and the success rate are improved, the development cost can be reduced, and meanwhile economic benefits are improved.

The invention provides a large model evaluation method, a large model optimization method and device, electronic equipment, a storage medium, an intelligent agent and a program product, and relates to the technical field of artificial intelligence, in particular to the technical field of large models, the technical field of evaluation analysis, the technical field of optimization and the like. According to the specific implementation scheme, a dialogue log is obtained, wherein the dialogue log comprises dialogue content and an intermediate result; based on the dialogue content features of the dialogue content, determining evaluation nodes and a plurality of evaluation indexes belonging to the evaluation nodes, the evaluation nodes being used for evaluating sub-processes executed by the large model; based on the dialogue log, performing evaluation analysis on the large model, and determining respective evaluation results of the plurality of evaluation indexes; and based on the respective evaluation results of the plurality of evaluation indexes, determining a target evaluation result for the large model.

The invention provides an intelligent ore blending method and system based on multi-modal feature fusion. The method comprises the following steps: collecting multi-source data; extracting each modal feature from the multi-source data, and performing weighting processing on each modal feature to obtain a first ore blending scheme; extracting mineral attribute features, semantic features and spatial features of different granularities from the first ore blending scheme by adopting depth separable cavity convolution; fusing the semantic features and the spatial features through a dual-path collaborative enhancement mechanism to generate a candidate ore blending proportion combination; carrying out constraint processing on the candidate ore blending proportion combination, optimizing the candidate ore blending proportion combination by adopting a mixed meta-heuristic optimization algorithm, and outputting an optimal ore blending proportion based on a multi-objective optimization function; and generating a target picture based on the optimal ore blending proportion. And technologies such as a multi-modal feature fusion large model are introduced, so that the reasoning capability is improved, complex ore blending requirements are processed, and the problems of insufficient feature expression and weak dynamic adaptation capability in a traditional ore blending process are solved.

The invention discloses a dynamic active learning and knowledge graph agent-based airworthiness document review method, which comprises the following steps of: collecting and processing a multi-modal heterogeneous data source to obtain a standardized knowledge base; based on the standardized knowledge base, constructing an aviation domain knowledge system by using dynamic active learning and a man-machine cooperation mechanism; constructing a knowledge graph and performing knowledge enhancement; and dynamically constructing a review context based on a retrieval enhancement generation method in combination with the knowledge graph, and injecting an intelligent agent to perform intelligent data review and report generation. According to the method, automatic review of airworthiness documents is realized through a dynamic active learning-agent review method, and the manual review efficiency is remarkably improved; domain knowledge is injected into an intelligent agent by utilizing an RAG technology, so that the accuracy of a general large language model in an airworthiness review task is improved; through knowledge semantic driving and human-in-the-loop knowledge enhancement, the problem of scarcity of high-quality data in the field is relieved; models of different parameter scales are cooperatively utilized, and computing power resources are saved.

The invention discloses a robot dog target following method based on computer vision. The robot dog target following method comprises the following steps: S10, preparing human body data, human body weight identification data and a single target tracking data set; s20, designing a lightweight human body detection network architecture and a detection human body frame, and performing model training based on the human body data; s30, constructing a lightweight single-target tracking model, selecting a detection frame of a to-be-tracked target as initialization input, receiving an initial frame transmitted by a robot dog camera as a template image, and performing specified template tracking and following; s40, constructing a lightweight full-scale model, starting a relocation mechanism after a lost target is tracked by a single target, and controlling the robot dog to turn around in situ, globally search a specified target and relocate a disappearing target; and S50, based on the tracking result of the single target, converting the target position on the image to an actual three-dimensional coordinate, and controlling the motion displacement of the robot dog to complete the following operation.

A multi-modal large model illusion detection and inhibition method based on attention time sequence difference comprises the following steps: inputting text lexical elements of cue words and visual lexical elements of images into a multi-modal large model, and obtaining an internal attention graph of the decoding stage of the multi-modal large model; then calculating the attention proportion of the visual lexical units at the current generation moment, and making a difference between the attention proportion and the proportion at the previous moment; and if the difference value exceeds a set threshold value, determining that the lexical elements are visual related lexical elements. When the visual related lexical elements are recognized, performing secondary forward propagation of primary visual enhancement to obtain more accurate output; and if not, directly entering the next step of generation. According to the method, visual related lexical elements in text generation are recognized and refined through attention time sequence difference, two-time forward propagation is adopted, the visual attention of second-time forward propagation is enhanced based on a visual attention graph of first-time forward propagation, and illusion can be recognized and corrected on the premise that the language expression ability is not reduced.

The invention discloses a split type three-box girder nonlinear vortex vibration steady-state amplitude intelligent prediction method, belongs to the field of bridge vortex-induced vibration control, and aims to solve the problem of low accuracy of three-box girder vortex vibration nonlinear modeling and amplitude prediction. The method comprises the following steps: acquiring displacement time sequence data through a reduced scale model wind tunnel test, preprocessing to obtain displacement, speed and acceleration dimensionless data, and dividing a data set; constructing a candidate function library containing high-order polynomial terms of the primary function; performing nonlinear system sparse recognition by taking acceleration data as a target item and combining an improved algorithm to obtain a preliminary feature set; a final feature set is obtained through energy-statistics-self-adaption three-stage screening; and finally, constructing a control equation to predict the steady-state amplitude. The method can accurately predict amplitude, coincide test and real bridge observation results, and is less in computing resource occupation and high in numerical value precision.

The invention belongs to the technical field of artificial intelligence, and particularly relates to a general agent reflection system based on large model multi-path fusion and a gating mechanism. The system comprises an input module which is used for receiving an input information set after the intelligent agent completes a single-step subtask; the task routing module is used for performing task type classification on the current action and outputting a classification result; the large-model multi-path fusion reflection module is used for performing multi-dimensional evaluation and reflection on the current action and the corresponding execution result by adopting a reflection strategy combination adaptive to the task type according to the classification result; the reflection result gating module is used for integrating the output reflection sub-results in multiple dimensions and generating and outputting a final reflection conclusion and a comprehensive evaluation score; the security and timeout control module is used for performing security risk monitoring and resource consumption control on the reflection process; and the output module is used for outputting the final reflection conclusion and the comprehensive evaluation score so as to determine the subsequent execution process of the intelligent agent.

According to the title level identification large model training method, the title identification method and system and the program product provided by the invention, the first title information covering all texts of the original file is constructed through the multi-modal semantic model, and the limitation of plain text identification is made up in combination with the element matching page picture; second title information with semantic and visual features is generated through multi-modal fusion, so that the title judgment accuracy is improved; in the training process, effective title objects are screened in combination with original title objects to optimize pre-training data, and a large model which is high in precision and adapts to complex scenes is cultivated; in the identification process, the title information to be identified is constructed based on the valid title object. And performing dynamic branch processing according to a calling condition, if not, directly outputting an answer, if yes, generating accurate final title information by means of a trained large model, and finally constructing and outputting the answer, thereby realizing training and identification full-link coordination, considering complex scene adaptability and efficient and accurate identification, and comprehensively improving the structuralization and practicability of document title identification.

The invention relates to a two-dimensional slicing method and device for a three-dimensional model, and the method comprises the steps: carrying out the coordinate system conversion and bounding box calculation of the three-dimensional model constructed by a triangle, and obtaining a target bounding box; according to the size of the target bounding box, the direction with the small cutting number is determined as the cutting direction, and orthogonal cutting is conducted on the target bounding box; performing intersection judgment on all triangular patches in the three-dimensional model according to the target bounding box and the cutting direction; cutting and comparing triangles in the intersecting triangle set with planes in the cutting plane array to obtain a plurality of sequence points, and connecting all the sequence points to obtain a two-dimensional slicing result; the optimal cutting direction is determined through coordinate system conversion and bounding box calculation, orthogonal cutting and triangular patch intersection judgment are combined, the slicing efficiency of the large-scale three-dimensional model is remarkably improved, manual intervention is reduced, the real-time processing requirement is met, and the method has the advantages that the optimal cutting direction is automatically determined, and the processing efficiency of the large-scale model is improved.

The invention discloses a large model dynamic optimization method and system for edge-cloud collaborative reasoning, relates to the technical field of large model dynamic optimization, and solves the technical problems that the prior art lacks flexibility and adaptivity and is difficult to effectively deal with complex and changeable edge application scenes. The method comprises the following steps: S1, collecting and analyzing various key information of edge equipment, a cloud end, a large model to be reasoned and a reasoning task in real time; s2, hierarchically dividing the large model to be reasoned, identifying a plurality of layers or sub-modules which can be used as model unloading points, and dynamically determining an optimal unloading point and an edge-cloud collaborative execution strategy of the large model by utilizing an intelligent optimization algorithm based on the information collected in the step S1; s3, executing a reasoning task according to the dynamic unloading and cooperation strategy generated in the step S2, and converging a final result; through the decision module based on deep multi-agent reinforcement learning (DMARL), the optimal unloading point and the cooperation strategy of the large model can be intelligently selected in real time.

The invention discloses a hybrid architecture large model system for resume screening, the hybrid architecture large model system comprises a structured analysis large model, an unstructured analysis large model and a weight distribution large model, the structured analysis large model is obtained by training a first type of general large model based on structured data in a resume, and the unstructured analysis large model is obtained by training a second type of general large model based on structured data in the resume. The large structured analysis model can output the matching degree of the structured data of the resume and the post information according to the input resume and the structured data in the post information; the unstructured analysis large model is obtained by training a second type of general large model based on unstructured data in the resume, and the unstructured analysis large model can output the matching degree between the resume and the unstructured data of the post information according to the input resume and the unstructured data in the post information. By utilizing the hybrid architecture large model system provided by the embodiment of the invention, the resume screening accuracy can be improved.

The invention discloses a large model memory management method and device and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining a new knowledge unit and a partition parameter corresponding to the new knowledge unit; according to the partition parameter, determining a storage partition corresponding to the new knowledge unit in the knowledge base; calculating the similarity between the new knowledge unit and each existing knowledge unit, and taking the existing knowledge unit of which the similarity is greater than a preset similarity threshold as a candidate conflict object; calculating the conflict degree between each candidate conflict object and the new knowledge unit, and processing the new knowledge unit according to the conflict degree to obtain a first processing result; and injecting the first processing result into the corresponding storage partition. According to the management method, catastrophic forgetting can be effectively prevented and controlled, long-term retention and safety compliance of key knowledge are guaranteed, and technical support is provided for application of a large model in a complex and continuous evolution scene.

The invention discloses a data center machine room temperature field equalization method based on a multi-scale model learning strategy. Fusing the equipment tolerance, the refrigeration system performance and the environmental thermodynamic boundary to construct a dynamic safe operation boundary; a machine room-cabinet-equipment multi-scale reverse model is constructed based on a physical guidance neural operator, and backstepping from observation of a temperature field to an optimal control strategy is realized; the method comprises the following steps: dynamically dividing a machine room into a plurality of logic control areas, deploying a reinforcement learning agent for each area, deciding and adjusting the air supply speed under the constraint of a safety boundary, and meanwhile, learning the minimum feasible air speed on line to optimize energy conservation; and when temperature abnormity which cannot be processed by local control is detected, generating and executing a global coordinated regulation and control instruction according to the global temperature field data and an analysis result of the multi-scale model. According to the method, on the premise of guaranteeing the safety of equipment, the temperature field of the data center is subjected to refined and self-adaptive balanced regulation and control, and the energy efficiency and the operation reliability of a refrigeration system are remarkably improved.

The invention provides a large model training method and device, a function recommendation method and device, equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical fields of natural language processing, deep learning, large language models, information recommendation, intelligent agents, intelligent agents and the like. According to the implementation scheme, first sample data are obtained, the first sample data comprise sample dialogue information and corresponding positive sample labels and negative sample labels, and the positive sample labels indicate target function recommendation results determined according to the sample dialogue information; the negative sample label is a function recommendation result which is inconsistent with the positive sample label and is obtained by inputting sample dialogue information into an initial large model to execute sampling operation; and training the initial large model based on the first sample data to obtain a target large model.

The invention provides a bridge deck reduced scale model design method and experiment system in a plateau environment, and the design method comprises the steps: building a multi-factor coupling similarity criterion based on a similarity principle, physical parameters affecting the prototype structure performance of a bridge deck, and plateau environment parameters; determining a dynamic stress similarity ratio model based on a multi-factor coupling similarity criterion and the plateau environment parameters; based on the dynamic stress similarity ratio model and the section shape and size of the bridge deck prototype structure, performing scale design on the bridge deck prototype structure to obtain an initial scale model; and performing simulation experiment and simulation verification on the initial scale model based on a preset numerical simulation strategy and a preset plateau environment simulation strategy, and performing parameter optimization of the dynamic stress ratio similar model to design a target scale model. According to the scheme provided by the invention, experimental simulation of the bridge deck in the plateau environment can be efficiently and accurately carried out, and the experimental simulation cost is reduced.

The invention discloses a reduced scale model pile body test structure which comprises a test box, a model pile and a laser scanner, a test soil body is laid in the test box, the model pile is vertically inserted into the test soil body, a reaction wall is installed on one side of the test box, a jack is installed on the reaction wall, and a thrust plate is installed at the front end of the jack; a target is installed on the model pile, and the laser scanner is located above one side of the target. According to the hollow nylon pipe model pile, it is guaranteed that lateral mechanical behaviors are similar, and the material cost and the machining difficulty are greatly reduced; the nylon pipe can also be used as an inclinometer pipe, so that the sensor is convenient to arrange; meanwhile, a grooving pipe inertia moment correction formula is introduced to accurately calculate the actual inertia moment of the grooved pipe, and similar errors are reduced; meanwhile, a strain gauge and a target are matched to comprehensively monitor the model pile from internal deformation, surface strain to top displacement; the surface of the model pile is roughened, so that the surface roughness of the model pile is equivalent to that of a concrete pile, slurry is injected into a pile-soil gap, and the simulation authenticity of the interface friction characteristic is improved.

The invention discloses an interactive naked-eye 3D scene dynamic adaptive construction method of a cross-scale model, and relates to the technical field of civil engineering BIM + GIS. According to the method, a dynamic three-dimensional scene is constructed based on multi-source BIM + GIS data; adjusting the position and attitude parameters of the main camera according to the observer position; calculating the position and attitude parameters of the slave camera according to the interpupillary distance of the observer; according to the dynamically changing scene, calculating visual cone parameters of the master and slave cameras in real time; then, a viewport picture of the main camera is calculated based on forward perspective projection, a viewport picture of the slave camera is calculated based on oblique perspective projection, self-adaption is carried out on display equipment, a multi-viewport image is synthesized, picture interweaving is carried out, the picture is input into a naked eye 3D display screen, and real-time and multi-angle picture three-dimensional presentation is carried out through a real and three-dimensional BIM + GIS three-dimensional scene. Interactive camera operation and scene modification and re-rendering are supported, and the effect of intelligent design and intelligent construction result visualization is remarkably improved.

The invention discloses a boiler heating surface three-dimensional digital twin construction method and system based on multi-source data fusion, and relates to the field of boiler monitoring. Comprising the following steps: carrying out multi-source data space-time alignment and structured processing, and unifying CAD design coordinates, installation welding seam GPS positioning, DCS operation measuring points and ultrasonic detection point positions to a boiler absolute coordinate system by adopting a space-time reference conversion technology; analyzing the unstructured data through a data cleaning engine, generating a welded junction level equipment ledger, and forming a time-space aligned standardized database; carrying out multi-scale point cloud fusion and three-dimensional model reconstruction, fusing laser scanning point cloud, BIM parametric modeling and welding seam ray imaging data, and constructing a multi-scale model by adopting an octree spatial index; cT scanning point cloud is introduced into the key area to enhance the precision. Compared with traditional BIM modeling, the geometric accuracy is improved, the creep damage simulation error of the high-temperature pipeline is reduced, and a real geometric base is provided for life evaluation.

The invention discloses a coal ash roadbed permanent deformation prediction method and a prediction model thereof. The method comprises the following steps: firstly, obtaining the optimal water content and the maximum dry density of fly ash through a fly ash compaction test; filling the fly ash in the state into a full-scale model according to a core-spun method, and applying dynamic loads simulating different vehicle speeds and axle loads to carry out a test to obtain permanent deformation values under different working conditions; and establishing a prediction model based on a time hardening power law criterion and a nonlinear viscoplastic constitutive theory, fitting test values to determine model parameters, and constructing the prediction model. Based on the prediction model, equivalent standard axle load action times allowed by a road structure are predicted according to a specified critical threshold, quantitative evaluation of road durability is realized, and a scientific early warning mechanism is provided for road maintenance decision. According to the technical scheme, the settling volume of the fly ash roadbed can be accurately predicted, and the road durability is effectively evaluated.

The invention provides a large model backdoor attack detection and automatic tracing method, and aims to solve the problems of poor accuracy, high false alarm rate and difficulty in hidden backdoor recognition in large-scale pre-training model backdoor attack detection in the prior art. The method comprises the following steps: firstly, extracting parameter distribution characteristics and reasoning behavior characteristics of a target large model, and identifying potential abnormal clusters by utilizing clustering analysis; then, whether the model is affected by backdoor attacks or not is verified by analyzing deviation output by the model and generating an adversarial sample, and through a feature inversion backtracking technology, a mapping relation between input and output is tracked, and backdoor trigger features are positioned; and finally, identifying a backdoor attack source and a propagation path thereof through traceability analysis, and eliminating the backdoor influence by correcting abnormal parameters and retraining. The method has the advantages of high efficiency, low false alarm, automatic traceability and the like, the safety of a large-scale model can be effectively improved, and the credibility and reliability of the model in practical application are ensured.

The invention discloses an operation and maintenance data management system and method based on a large model, and relates to the technical field of data management. The system comprises a data acquisition module, a data processing module, a rule mining module, a dynamic adaptation module and a feedback optimization module. The data acquisition module acquires environment sensitive parameters and operation threshold data and performs calibration verification, the data processing module constructs an environment-threshold association data set, the rule mining module generates a dynamic anchoring rule base through a pre-training large model, and the dynamic adaptation module matches rules to generate an adjustment instruction and an operation and maintenance suggestion. And the feedback optimization module records the evaluation adjustment effect and supports the updating of the rule base. According to the method, the dynamic anchoring adaptation of the operation and maintenance threshold value and the environment change is realized, and the operation stability and the operation and maintenance accuracy of equipment are improved.

The present application relates to the technical field of geological prediction, in particular to a tunnel rock mass quality identification method and system based on multi-scale drilling model fusion, specifically comprising the following steps: S1, collecting and preprocessing the field drilling data to obtain a test set; S2, inputting the test set into a multi-scale fusion model to obtain a tunnel rock mass quality identification result, the tunnel rock mass quality identification result being one of the prediction labels, and the prediction labels including relatively complete, relatively broken, broken and fissure; in the training process of the multi-scale fusion model, the field drilling data is collected, preprocessed and segmented in multiple scales, and the multi-scale model fusion is performed by using the error reciprocal weighted average method in the training process. The effect of weakening the shortcomings of each scale model, optimizing the prediction effect and enhancing the practicality of the technology is achieved.

The invention relates to a method and device for duplicating a real character based on a large model, electronic equipment and a computer readable medium. The method for duplicating the real figure based on the large model comprises the following steps: receiving input information; determining whether knowledge base retrieval is needed or not according to the content of the input information; when it is determined that knowledge base retrieval needs to be carried out, an enhancement prompt is formed based on the input information and the content retrieved from the knowledge base, and the enhancement prompt is input into the role large model to generate a response; and when it is determined that knowledge base retrieval does not need to be performed, directly inputting the input information into the role large model to generate a response.

The invention discloses an adjusting device for a traction cable tensioning process in a cable structure reduced scale model test, which comprises a hydraulic lifting platform, a shear type supporting arm of the hydraulic lifting platform is connected with a base and a top frame, and a sliding groove and two hydraulic rods are arranged in the base; the hand-cranking capstan is borne on a top frame of the hydraulic lifting platform and is provided with two parallel capstan bodies connected through a telescopic sleeve, the two parallel capstan bodies are fixed to the two flat plates respectively, the telescopic sleeve is wound with a steel wire rope with a lifting hook, and the capstan body on one side is provided with a self-locking type manual rotating mechanism; the length telescoping mechanism is installed between the two flat plates of the hand-cranking capstan and is provided with two gear boxes and a transmission mechanism, and a transmission rod is arranged between the gear boxes. The device has the function of bidirectional adjustment of height and span, can meet the tensioning requirements of cable bodies at different spatial positions in a cable structure reduced scale model test, and is high in flexibility, time-saving and labor-saving.

The invention relates to the technical field of information, in particular to a comprehensive AI large model base construction method and system based on multi-data fusion. The method comprises the following steps: constructing a multi-source heterogeneous data acquisition layer, and acquiring operation and maintenance related data from a plurality of preset devices through a standardized protocol; preprocessing the collected multi-source data to generate a fusion data set; based on the fusion data set, an AI large model base is constructed, and the AI large model base comprises a plurality of basic perception models, a cross-domain correlation analysis model and an intelligent decision generation model; obtaining an operation and maintenance target, and selecting a plurality of basic sensing models and configuring fusion weights according to the matching degree and implicit dependency relationship between the operation and maintenance target and a plurality of preset reference operation and maintenance objects; and fusing the plurality of selected basic perception models according to the fusion weight, and docking the fused basic perception models with an intelligent decision generation model to obtain an operation and maintenance auxiliary model of the operation and maintenance target.

The invention belongs to the field of wind power equipment intelligent structure health monitoring, and particularly discloses an offshore wind turbine blade damage quantitative monitoring method based on transfer learning, which comprises the following steps of guided wave data acquisition, coarse graining feature extraction, cross-domain feature alignment, damage quantitative model construction and damage size output. Target domain labeling information is not needed, coarse graining features are combined, the sample labeling and detection calculation cost is greatly reduced, and the method is adaptive to an existing guided wave collection system; the generalization ability is enhanced through cross-domain feature alignment and multi-scale model fusion, complex marine environment interference can be resisted, and cross-regional stable monitoring is achieved; damage can be accurately quantified, scientific operation and maintenance are supported, fault loss and excessive maintenance are reduced, the operation reliability of the wind turbine generator is improved, and remarkable engineering value and economic benefits are achieved.