603 results about "Industrial yard" patented technology

The invention discloses an industrial scene-oriented data acquisition system and an industrial scene-oriented data acquisition method. According to the invention, through the multi-level dynamic optimization design, the data acquisition efficiency and the system reliability in a complex environment are significantly improved. The system dynamically allocates thread resources based on the real-time communication state of the equipment, realizes stable throughput under a high-concurrency scene in combination with core binding and polling scheduling strategies, and ensures that millisecond-level response is still maintained when 10000-level equipment is accessed. The memory preloading and protocol template technology eliminates jitter during operation, the hierarchical resource isolation mechanism provides deterministic guarantee for key control instructions, and interruption of the production process due to data delay or resource competition is avoided. The data flow delay is further reduced through multi-protocol efficient analysis and intelligent cache management, seamless compatibility of heterogeneous equipment in a hybrid networking scene is supported, and the strict requirements of continuous production industries such as steel and chemical engineering for real-time performance and stability are met.

The invention discloses a multi-modal collaborative decision-making method and device for a humanoid robot in an industrial scene, and relates to the technical field of robot control, and the method comprises the steps: obtaining a multi-frame monitoring image, force touch sensor data and equipment operation sensor data of a visual camera of the humanoid robot in the industrial scene; extracting feature vectors of the multi-frame monitoring image, the force touch sensor data and the equipment operation sensor data as multi-modal feature vectors; taking the multi-modal feature vector as a training sample to train a cross-modal model, so that the cross-modal model learns an association relationship among vision, haptic and equipment data; obtaining dynamic industrial scene data, extracting feature vectors, and inputting the feature vectors into the trained cross-modal model to generate scene description information; and outputting an operation decision instruction according to the scene description information so as to control the humanoid robot. Through cross-modal feature fusion and dynamic knowledge reasoning, the task execution precision and environmental adaptability of the humanoid robot in a complex industrial environment can be improved.

The invention discloses an industrial equipment intelligent operation and maintenance method based on multi-source heterogeneous data dynamic collection and LSTM optimization, and relates to the technical field of industrial Internet of Things and industrial equipment intelligent operation and maintenance, and the method comprises the steps: collecting multi-source heterogeneous data, transmitting the multi-source heterogeneous data to an edge node, and carrying out the data preprocessing through a data preprocessing module; constructing a lightweight multi-modal LSTM model, and identifying and predicting the fault of the industrial equipment; through a self-adaptive threshold algorithm, differential weighted sampling and dynamic balance of energy consumption and precision, edge nodes realize real-time fault detection, and an operation and maintenance decision of local industrial equipment is generated; moreover, cross-factory cooperative training is carried out through a federal learning platform, and the generalization ability of the model is improved. Therefore, by the adoption of the industrial equipment intelligent operation and maintenance method based on multi-source heterogeneous data dynamic collection and LSTM optimization, the problem that response to hidden faults is lagged in a traditional method can be solved, optimal resource configuration in an industrial scene is achieved, and the operation and maintenance cost of an industrial Internet of Things terminal is reduced.

The invention provides an intelligent production scheduling system and method for a coal industry scene, and the method comprises the steps: fusing multi-source production information (including equipment state information, coal quality index information and safety detection information) through a server, constructing a fault prediction model, and carrying out the fault prediction of the real-time production information; and generating a task list based on the fault prediction result, the real-time production information and the historical production information, matching a workflow and an optimal executor for each task in the task list, then sending the task to the PC terminal for execution, monitoring the execution progress of each task in real time, and urging the overdue task. And generating a corresponding report for each executed task based on the fused information, the fault prediction result, the real-time production information, the historical production information and the execution process information of each task, and sending the report to a display device for display. By adopting the method, the efficiency and the accuracy of production scheduling in a coal industry scene can be improved, the real-time performance of production scheduling can be ensured, and the statistics and the checking of the whole process link can be facilitated.

The invention belongs to the technical field of a computer system based on a specific calculation model, relates to a virtual and real dynamic interaction-based digital twin bearing fault diagnosis method, and aims to solve the problem that a bearing system in large rotary mechanical equipment is large in fault hidden danger and avoid serious consequences caused by faults. A generally used bearing is in a high-precision standard, so that system signal data under bearing fault operation is not easy to collect in a factory, and the unbalanced data sample distribution directly leads to finiteness of fault diagnosis in a real scene only based on a big data driving mode classification method, so that the system signal data cannot be easily collected in the factory. The method has good scene working condition self-adaption, can be applied to fault diagnosis of a bearing system in different industrial scenes, fully excavates limited industrial data information and rich physical priori knowledge, and ensures safe and reliable operation of an important rotating mechanical system through a digital twinning technology.

The invention discloses a strip steel surface defect detection method based on a multi-branch parallel attention model, and belongs to the technical field of industrial defect target detection. On the basis of a YOLOv8 network, space depth conversion convolution is used for replacing all down-sampling convolution in a backbone network CSPDarkNet, a multi-branch parallel attention module is used for replacing a C2f module, and an internal feature interaction module is added behind the backbone network, so that the strip steel surface defect detection precision of the model is improved. The strip steel surface defect detection precision is effectively improved while model parameters are slightly increased, and compared with an existing strip steel surface defect model, the problem that the image detection effect is poor due to the fact that background interference is strong, various defects are large in difference, the number of small defects is large, and defect targets are likely to be confused in an industrial scene can be better solved.

The invention relates to a cooling tower device for recovering heat from waste steam, which adopts three layers of transversely arranged heat exchange tube groups, realizes cascade recovery of heat energy of waste steam through communication of an air inlet and an air outlet, and is additionally provided with fins on the surfaces of heat exchange tubes to enhance the gas-liquid mass transfer efficiency. The core innovation lies in that a built-in mechanical cleaning mechanism is arranged, a driving assembly is in linkage with multiple sets of bidirectional adapters through a rotating shaft, brush rods distributed in the circumferential direction are driven to conduct high-frequency physical scraping on heat exchange pipes and fins, scale deposition is effectively restrained, and compared with traditional chemical cleaning, the shutdown maintenance time is shortened; the steam latent heat recovery rate can be increased, meanwhile, secondary pollution is avoided through a full-mechanical cleaning scheme, modular layout is adopted in structural design, interlayer fluid distribution of the heat exchange pipe set is achieved through a U-shaped pipe and a straight pipe, it is ensured that the resistance coefficient of the system is lower than that of similar equipment, and the device has remarkable energy-saving benefits in industrial scenes such as chemical engineering and metallurgy.

The invention relates to an edge computing migration system for an intelligent factory digital twin system, and the system comprises a scene obtaining module which is used for obtaining the real-time data of automation equipment in a factory; wherein the real-time data comprises a running state and task information; the digital twin module is used for virtually mapping the real-time data of the automation equipment and synchronizing the state between a factory physical system and a virtual system; the model construction module is used for constructing an edge computing network time delay and energy consumption model according to the real-time data of the automation equipment; and the optimization algorithm module is used for carrying out real-time optimization on allocation of calculation tasks and resources by adopting a multi-agent deep reinforcement learning algorithm based on the edge calculation network time delay and energy consumption model. The system provided by the invention has the characteristics of low time delay and high energy efficiency, is suitable for highly dynamic industrial scenes, can optimize the scheduling of computing resources, and improves the overall operation efficiency of factories.

The invention discloses an intelligent detection and dynamic supplement regulation and control system for electroplating bath solution components, and belongs to the technical field of electroplating. The system comprises an electroplating bath body, a detection module, a data processing and control module and a regulation and control module. The detection module is used for detecting the metal ion concentration, the pH value, the temperature and the additive concentration of the bath solution on line in real time through a spectrum sensor, an electrochemical sensor and a physical parameter sensor; the data processing and control module adopts a PID and machine learning fused intelligent regulation and control model, predicts the component change trend according to the detection data and the process parameters, and generates a dynamic regulation and control instruction; the regulation and control module quantitatively supplements target components through a high-precision metering pump, and the closed-loop feedback correction module is combined to ensure that the components of the bath solution are stabilized within a preset threshold range. Multi-parameter synchronous detection and accurate regulation and control are achieved, the quality stability of the plating layer is improved, raw material consumption and labor cost are reduced, and the method can be widely applied to industrial scenes such as metal surface treatment.

The invention discloses a multi-parameter cooperative temperature control system of an energy-saving industrial oven, and relates to the technical field of temperature control of industrial ovens, load data in the oven are collected in real time through a high-precision sensor, and a Kalman filter is used for cleaning, calibrating and filtering environmental noise and drift to obtain smooth and stable data; analyzing a real-time load based on a support vector regression model, capturing a nonlinear relation in combination with a radial basis function kernel, and predicting temperature recovery time and expected energy consumption; a reinforcement learning algorithm is adopted, a high-dimensional state space is analyzed through a deep Q network, the heating power and the airflow speed are dynamically optimized, and optimal control parameters are output; and the control module executes the adjusted setting, monitors the temperature and the energy consumption in real time, feeds back data to a prediction model and a learning strategy, and periodically updates parameters to adapt to load and environment changes. The adaptive capacity and long-term stability are remarkably improved, and the method is suitable for industrial scenes with load change, equipment aging or environment fluctuation.

The invention belongs to the technical field of industrial robot inspection, and discloses an instrument identification method for industrial robot inspection, an instrument identification system comprises a pose adjustment module, a lightweight detection module, an image double enhancement processing module and a double-branch instrument reading identification module, and the instrument identification method comprises the following steps: obtaining an instrument image, inputting the instrument image into an image dual-enhancement processing module to obtain a preprocessed instrument image; the preprocessed instrument image is input into a lightweight detection module, an instrument target detection result is output, the instrument type is judged according to the result, and an instrument reading result is output and recorded. According to the method, the improved lightweight target detection model and the adaptive image optimization processing algorithm are combined, the real-time performance and the high efficiency of instrument reading in an industrial scene are effectively improved, more intelligent and accurate instrument reading and industrial inspection can be provided, and powerful support is provided for information acquisition in a complex industrial environment.

The invention discloses a park multi-source heterogeneous data analysis method and system based on the industrial Internet of Things, and relates to the technical field of data analysis. The park multi-source heterogeneous data analysis method based on the industrial Internet of Things comprises the following steps: determining a suspected target according to image information of a target area; according to the moving trend of the suspected target, predicting a moving path of the suspected target, and obtaining feature information of the suspected target through supervision equipment on the moving path; according to the feature information and in combination with working data of the suspected target in a past preset time period, predicting an abnormal probability of an abnormal condition of the suspected target, and judging whether the abnormal probability exceeds a preset threshold value or not; and if the abnormal probability exceeds a preset threshold value, tracking the abnormal target. The technical problems that in the prior art, due to data islands and response mechanism lagging, accurate risk identification and dynamic management and control in a complex industrial scene are difficult to achieve, and false alarm or missing alarm is likely to occur are solved.

The invention provides a cutting device for valve pipeline machining, and relates to the technical field of metal cutting. The cutting device for valve pipeline machining comprises a machine cabinet, two roller shaft conveyors are symmetrically arranged at the top of the machine cabinet, and angle adjusting assemblies are jointly installed between the two roller shaft conveyors and the machine cabinet; a support matched with the cabinet is arranged on one side of the outer surface of the cabinet, and three mounting frames are arranged at the bottom of the support. Through the integrated lifting type cutting assembly and the groove milling cutter on the telescopic machine box, pipeline cutting and groove forming are synchronously completed in one-time clamping, and the problem of repeated positioning caused by step-by-step machining in a traditional technology is solved. Especially for a thick-wall pipe or a high-alloy steel pipe, the coaxiality of the cutting end face and the groove machining face is ensured through cooperative clamping of the fixed roller and the wingspan type auxiliary roller, the precision of the valve pipeline butt joint face is remarkably improved, and the industrial scene with the high sealing performance requirement is met.

The invention discloses an intelligent recommendation method and system for an industrial process monitoring model, and the method comprises the steps: firstly, solving a problem that industrial time series data lacks visual features; extracting data set features of each case from four aspects of general statistical features, distribution shape features, task related features and exogenous knowledge embedding by adopting a data set feature engineering method; secondly, designing a mapping relation learning strategy based on width learning, mapping the data set feature of each case with the corresponding model score vector, and thus endowing the width learning network with the capability of predicting the model performance; and finally, providing a triple increment strategy for driving multiple increment demands of an industrial scene, and designing an updating strategy of a wide learning network for monitoring case increment, candidate model increment and recommendation node increment respectively, thereby continuously expanding and enhancing the recommendation capability of the method. According to the method, the detection model with the optimal performance can be recommended for the industrial process.

The invention discloses an industrial robot predictive maintenance system based on machine learning, and relates to the technical field of industrial robot maintenance. Comprising a data acquisition module, a preprocessing module, a feature engineering module, a hybrid prediction model unit, a meta-learning and domain adaptive module, a federated learning coordination module, a digital twin sample generation module and a dynamic decision engine unit. A model agnostic meta-learning algorithm is utilized to train a cross-brand universal feature extractor, distribution of different brand data is confused in combination with an adversarial field adaptive network, a'data gap 'caused by sensor parameter definition and sampling frequency difference in traditional modeling is broken through, model cooperative training is achieved on the premise that data of all brands are not out of the local, and the modeling efficiency is improved. A global model containing cross-brand fault generality is generated, and the problem of data islands caused by commercial secrecy requirements in an industrial scene is solved.

The invention relates to the technical field of intelligent manufacturing and industrial Internet of Things, in particular to an intelligent factory equipment safety management system and method, and the system comprises an identity authentication module, a dynamic safety interaction module, an intelligent monitoring response module and a self-adaptive optimization module. An identity authentication module; through fusion of multi-dimensional information authentication, block chain decentralized storage, intelligent algorithm behavior analysis, encrypted communication and fine-grained authority control, multi-source data threat detection and reinforcement learning driven strategy optimization, a whole-process security system is constructed. The method comprises the steps of identity authentication, security interaction, monitoring response and adaptive optimization. The problems that in a traditional industrial scene, equipment identity authentication is fragile, data transmission is not safe, threat response lags and strategies are staticized are solved, high-safety authentication, dynamic encryption communication, real-time threat response and strategy self-optimization are achieved, and the equipment safety protection capacity and the system intelligence level are improved.

A method, system, device, and medium for generating 3D model of industrial scene are disclosed. The method comprises: acquiring point cloud data for an industrial scene; determining a domain of the industrial scene; acquiring a trained semantic segmentation model associated with the domain from a model library, wherein the model library comprises multiple trained semantic segmentation models associated with respective domains; performing semantic segmentation on the point cloud data to obtain multiple segmented objects, based on the trained semantic segmentation model associated with the domain; meshing the multiple segmented objects; and generating a 3D model of the industrial scene based on the meshed multiple segmented objects. A flexible domain-specific model library is provided to meet the needs from different industrial scenes, thus improving modeling efficiency.

The invention discloses an anomaly detection method based on a hybrid expert field adaptive industrial large model. According to the method, a hybrid expert model and a field adaptive technology are introduced, and an efficient industrial anomaly detection scheme is provided for the problems of training efficiency and adaptability of an industrial large model in multi-field tasks. Comprising the steps of data preprocessing, field division and self-adaption, industrial knowledge and data fusion, hybrid expert model construction, model training and reasoning adaptation and the like. The hybrid expert model can automatically select a proper expert for reasoning according to input data, and the domain adaptive module effectively reduces the distribution difference of data in different domains, so that the migration ability and generalization performance of the model are improved. The method is based on data driving, can adapt to multi-modal data of different industrial scenes, and has high universality. Compared with the prior art, the method has higher training efficiency and better model adaptability in industrial application, and both theoretical property and practicability are enhanced.

The invention relates to the technical field of blockchain data management, and discloses a blockchain-based cleaning and spraying data management system, which comprises a cleaning parameter acquisition module, a data fragment encryption module, a cross-chain feature verification module, a dynamic decision reconstruction module and an execution instruction generation module. The system obtains the operation state data flow of the spraying equipment through distributed nodes, generates a data verification feature matrix set through space-time dimension division and feature fragmentation encryption, obtains an optimized verification feature matrix set through consensus mechanism screening and feature relevance verification, generates a data chain type decision feature map based on Hash time lock fusion, and obtains a data chain type decision feature map. And finally, an equipment control instruction set is generated. The system realizes data security storage, cross-chain verification and dynamic decision by means of a block chain technology, improves the cleaning and spraying data management efficiency and decision accuracy, is suitable for intelligent data management and equipment control in an industrial scene, and solves the problems of weak data security, decision lag and the like of a traditional system.

The invention relates to an intelligent industrial fault prediction and maintenance method and system based on a large model. The method comprises the following steps: 1) collecting equipment data; 2) preprocessing and equipment feature extraction; 3) fault prediction driven by a large model; 4) generating a dynamic maintenance plan; and 5) user feedback and model optimization. By using the strong generalization ability of the pre-training large model and the fine tuning of the industrial scene data, the system can realize higher-precision equipment state prediction and dynamic maintenance optimization, so that the equipment operation risk is reduced, and the industrial production efficiency is improved. By using the strong generalization ability of the pre-training large model and the fine tuning of the industrial scene data, the system can realize higher-precision equipment state prediction and dynamic maintenance optimization, so that the equipment operation risk is reduced, and the industrial production efficiency is improved.

The invention discloses a laser point cloud-based industrial equipment digital twin model rapid reconstruction method and system, and the method combines a model matching mode and a point cloud reconstruction mode, and effectively solves the problem of twin model reconstruction in different scenes. According to the first mode, on the basis of an existing three-dimensional model, through shape matching, feature extraction and model retrieval methods, registration of point cloud data and the three-dimensional model is combined, and rapid reconstruction of the equipment twinborn model is successfully achieved. The mode is suitable for equipment with an existing standard three-dimensional model, the repeated utilization rate of the model can be improved, and the reconstruction time and cost are reduced. In the second mode, the reverse grid model construction method based on the point cloud data is provided for equipment which cannot be retrieved through an existing model. Through an improved greedy projection triangulation algorithm, point cloud data is converted into a grid model, and the precision and authenticity of the model are improved in combination with a grid optimization algorithm and a surface texture mapping technology. According to the method, the digital twinborn model of the industrial equipment can be efficiently and accurately reconstructed, the modeling difficulty in an industrial scene is relieved, the actual demand of field modeling is met, and the method has high application value and practicability.

The invention discloses a multi-modal data fusion-based steel wire rope detection and real-time transmission method and system, and the method comprises the steps: starting a detection system, collecting a steel wire rope damage detection signal, collecting equipment position and operation state data, constructing an original data set, carrying out the preprocessing, building an incidence matrix, dividing a processing unit, and then extracting features, and forming an initial feature data set. And extracting damage features through a multi-branch network, strengthening the weight of a key region, fusing position and equipment state features through a multi-modal fusion module, generating fusion vectors, classifying and identifying, and outputting a structured detection result. And the acquisition equipment end performs grading processing on the data, distributes transmission channels according to priorities, dynamically adjusts parameters, adds integrity and time sequence identifiers, and the upper computer verifies the data integrity and triggers abnormal supplementary transmission. And the upper computer decodes the data, reconstructs the waveform, gives an alarm in real time in combination with preset parameters, and generates details of damage key information. Reliable technical support is provided for safe operation and maintenance of the steel wire rope in industrial scenes.

The utility model relates to the technical field of detection equipment, and provides multi-spectral detection equipment for defects in industrial places, which comprises a three-axis cradle head bracket, the detector outer shell is rotationally connected with the three-axis holder bracket, and the position adjustment of the detector outer shell is controlled by the three-axis holder bracket; the visible light lens I, the visible light lens II, the infrared lens and the ultraviolet lens are mounted on the detector outer shell, and lenses of the four lenses are positioned on the same side surface of the detector outer shell; and the visible light lens I, the visible light lens II, the infrared lens and the ultraviolet lens are distributed in a crossed manner. According to the technical scheme, visible light pictures and infrared or ultraviolet pictures under the same field angle can be collected, the four lenses are distributed in a crossed mode, coordinate transformation of the pictures can be achieved conveniently, information result fusion of visible light detection and infrared or ultraviolet detection is achieved, and the detection accuracy is improved. And the detection accuracy and reliability of industrial place defects and the like can be improved.

The invention discloses a coal mill unbalanced data fault diagnosis method based on a Bayesian network, and belongs to the field of generalized zero sample fault diagnosis of a thermal power generation feed pump set. Aiming at the problems of unbalanced fault data distribution, difficult minority class fault diagnosis and poor result interpretability in an industrial scene, sample distribution is collaboratively optimized through SMOTE data enhancement and Dirichlet prior smoothing, a three-layer causal topology network of'fault layer-attribute layer-observation layer 'is constructed, expert knowledge constraint and data-driven learning are combined, and the fault layer-attribute layer-observation layer-based fault diagnosis method is established. High-precision fault classification is realized; a dual-mode diagnosis mechanism is designed, fault node direct inference and attribute node indirect inference are synchronously supported, and explainable physical-level diagnosis guidance is provided while the fault diagnosis accuracy is guaranteed. The method is successfully applied to a coal mill system of a coal-fired unit, and can be expanded to transparent intelligent operation and maintenance of complex industrial equipment.

The invention discloses a lightweight industrial device surface defect detection method, system and equipment and a medium, and the method comprises the steps: obtaining any one of or a combination of two of an image and point cloud data of a normal sample in an industrial scene, and training a pre-established teacher model; constructing a student model, generating knowledge distillation through masking, migrating teacher features to a student network, and training the student model; performing channel sorting pruning on the trained student model to obtain a pruning model; and inputting a to-be-detected sample collected in real time into the pruning model, and judging whether the to-be-detected sample has defects or not. According to the method, the knowledge distillation technology and the model pruning technology are combined, through iterative optimization, the complexity of the model is greatly reduced while high precision is kept, and the limitation of a single lightweight method on a multi-modal defect detection task is effectively solved. According to the invention, the target of deploying a high-performance multi-modal defect detection model on edge equipment can be realized, and meanwhile, relatively high detection precision and modal loss robustness are kept.

The invention belongs to the technical field of three-dimensional scanning path planning and industrial automatic detection, and particularly relates to a full-coverage scanning path planning method for a large complex structural part. The revolutionary optimization of the three-dimensional scanning path of the large structural member is realized by constructing a comprehensive technical system of curvature self-adaptive sampling, pose collaborative optimization, a three-stage Weibull motion strategy, real-time collision detection and whole-process efficiency improvement. According to the scheme, geometric feature perception, motion continuity guarantee, algorithm adaptability enhancement and operation safety control are creatively integrated, a technical breakthrough is formed in three dimensions of non-blind area coverage, high motion efficiency and zero collision risk, and meanwhile, through parameterization design and a cross-platform compatible framework, the operation safety is improved. Deployment flexibility and system robustness in an industrial scene are remarkably improved, and a complete solution with high precision, high efficiency and high reliability is provided for automatic detection of a complex curved surface.

The invention provides an industrial scene automatic monitoring method, system and product based on multi-modal data, and relates to the technical field of industrial scene monitoring, and the method comprises the steps: obtaining environment multi-modal data in an industrial scene, carrying out the anomaly detection of each device in the industrial scene based on the environment multi-modal data, and obtaining the abnormal data of each device in the industrial scene; outputting an environment perception result in a natural language form; obtaining operation data corresponding to each device based on the environment perception result, obtaining a real-time correlation coefficient between different operation parameters of each device during operation, and outputting a parameter correlation result during device operation in a natural language form; and aligning time information of the environment multi-modal data and the operation data, describing an industrial scene state based on an environment perception result and a parameter association result, and outputting an industrial scene monitoring result including an environment state, an equipment state and an overall trend in a natural language form. According to the invention, the problems of low efficiency, easy omission and the like caused by dependence on workers in industrial scene monitoring are solved.

The invention discloses a multi-agent resource scheduling method based on a large language model in an industrial scene, and the method comprises the following steps: 1, setting initial scheduling parameters and user input of a multi-agent scheduling system; 2, the planning agent performs intention recognition, feature value extraction and coding; and 3, the scheduling agent receives the scheduling coding information, selects a scheduling algorithm tool and generates a scheduling scheme. And 4, the fault detection agent receives the initial scheduling scheme and receives key parameters of the working agent. And 5, the fault detection agent judges that a fault exists and optimization exists, if yes, the scheduling agent is fed back, and the step 3 is executed again, and if not, an optimal scheduling result is output. According to the method, a multi-agent architecture driven by a large language model is adopted, and a dynamic algorithm tool selection mechanism and a prompt project are introduced. Minimization of task total time consumption and maximization of fault detection accuracy are taken as optimization objectives, and adaptivity of industrial scene resource scheduling and system reliability are remarkably improved.

The invention provides a task processing method and device based on an industrial large model, a medium and a product, and relates to the technical field of industrial automation. The method comprises the following steps: constructing a multi-source data set based on an industrial scene, and training a plurality of adapters corresponding to the multi-source data set by adopting an adaptive low-rank adaptation algorithm; according to the learnable weight, fusing the plurality of adapters to obtain a fine-tuned industrial large model; and inputting an operation and maintenance task of the intelligent equipment in the industrial scene into the fine-tuned industrial large model, outputting an operation and maintenance strategy of the intelligent equipment, and controlling the intelligent equipment in the industrial scene to execute the operation and maintenance strategy. According to the method, efficient fine tuning and capability integration of an industrial large model in a multi-source heterogeneous data scene are achieved by introducing a self-adaptive low-rank adaptation algorithm and a multi-task adapter fusion framework, the fusion conflict problem of multi-source heterogeneous data is solved, efficient reasoning of full-process intelligent interaction of the air compressor is achieved, and the intelligent interaction of the air compressor is achieved. And the stability and the precision of the large industrial model in a complex industrial task are improved.

The invention relates to an industrial safety health risk prediction method and device based on machine learning, and a medium. The method comprises the following steps: obtaining industrial scene description, generating structured data through a large language model, inputting the structured data into a trained industrial safety health risk prediction model, and outputting a predicted potential risk level. Wherein the industrial safety health risk prediction model comprises a feature extraction module, a feature enhancement module and a feature fusion module, and the feature extraction module is used for extracting text features and attribute features; the feature enhancement module comprises an attribute feature enhancement network based on a Transform architecture, a text feature enhancement network based on a Bi-LSTM architecture and a cross attention mechanism, and an accident level embedded network, and is used for performing feature enhancement; and the feature fusion module is used for splicing the output of the feature enhancement module to obtain a comprehensive feature vector. Compared with the prior art, the method can further improve the prevention and coping capacity of safety production accidents.