190results about "Registering/indicating during manufacturing process" patented technology

The invention relates to the technical field of press monitoring, in particular to a digital twinning-based three-dimensional monitoring system for a precision servo press, which comprises a physical layer sensing module for acquiring real-time operating parameters, environment variables and workpiece processing data of the press; the dynamic twin construction module constructs a total-factor digital twin, and simulates a force-heat-deformation coupling effect by using finite element analysis and a multi-body dynamics algorithm based on physical attributes and process parameters; the intelligent analysis center identifies a potential fault mode of the press machine and locates an abnormal source through multi-physics field simulation data in combination with an improved CNN-LSTM model; the three-dimensional visual interaction unit constructs an interactive immersive three-dimensional virtual scene, renders a running state and a processing process in real time, and generates a maintenance strategy; and the self-adaptive regulation and control unit predicts the residual life of the key component and dynamically adjusts parameters according to a maintenance strategy and real-time monitoring data. Therefore, the problems of single monitoring dimension, disjunction of maintenance strategies and the like in the prior art are solved.

The invention discloses a scraper conveyor middle trough production line operation state monitoring method based on digital twinning, and belongs to the technical field of industrial intelligent manufacturing. The method comprises the following steps: constructing digital twin bodies in one-to-one correspondence with physical production line elements; establishing a real-time data driving channel between the digital twin and the physical elements; based on the channel, driving the digital twin to synchronously map the real-time operation parameters, and generating a virtual operation state of the production line; based on the virtual operation state, performing time sequence deduction on the processing flow in the digital twin according to the processing technology logic and the equipment performance parameters to obtain a production line pre-estimation state of a future time point; and comparing the parameters in the pre-estimated state with a preset threshold range to generate prediction information. According to the invention, real-time data driving and bidirectional interaction of the physical production line and the virtual model are realized, the problems of data isolation and feedback lag of a traditional monitoring mode are overcome, the prediction capability is provided, and the operation reliability and intelligent management of the production line are effectively improved.

The invention relates to the technical field of carbon fiber mold optimization, and discloses a carbon fiber box mold optimization method and system based on multiple targets. A multi-target definition library of the system stores a design constraint set composed of a geometric accuracy threshold value, a material strength threshold value and thermal deformation tolerance; the real-time sensing network collects data of layering tension distribution, temperature gradient and resin flow front edge; the topological dependency analyzer constructs a dependency relationship graph of the design parameters and the real-time sensing data; the material characteristic library stores carbon fiber layering parameters and resin curing kinetic parameters; the optimization calculation scheduler dynamically allocates multi-target optimization calculation task nodes; an iterative optimization engine generates a layering path sequence and curing temperature curve combination scheme; and the result verifier compares the combination scheme with the design constraint, and outputs a scheme deviation index. According to the system, the design standardization, the production monitoring comprehensiveness and the optimization verification accuracy of the carbon fiber box mold can be improved, and the product quality and the production stability are guaranteed.

The invention discloses a dynamic optimization method and system for a boron diffusion process of a photovoltaic cell and electronic equipment. Comprising the following steps: collecting process parameters and sheet resistance data, and associating the process parameters and the sheet resistance data to form a process parameter set; optimizing a process parameter set, removing noise data and incomplete data, and extracting an available feature data set; dividing the feature data set into a training set and a verification set, and training to obtain a nonlinear regression model for predicting resistance data under different feature data; carrying out validity verification on the nonlinear regression model, and constructing an optimization function to reduce a difference value between a predicted value and an actual value; and deploying a nonlinear regression model in the diffusion process, adjusting the process parameters of the diffusion process in real time according to the predicted value, and optimizing the obtained sheet resistance data. The problem that the boron diffusion process is difficult to accurately adjust by a traditional process control method can be solved.

The invention discloses a silicon single crystal growth interface deformation detection method, system, equipment and medium, and relates to the technical field of silicon single crystal growth soft measurement modeling. Comprising the following steps: acquiring a process parameter set in a silicon single crystal production process; the process parameters in the process parameter set serve as nodes, mutual information indexes between the nodes serve as edges, and a graph structure model is constructed; performing multi-layer neighborhood aggregation operation on the graph structure model to obtain initial features; performing attention mechanism operation on the initial features to obtain aggregated features; and carrying out weighting operation on the aggregation characteristics by adopting a long-short-term memory network to obtain a deformation detection result of the silicon single crystal growth interface. According to the method, the modeling expressive power of a complex dynamic process is improved, and the sensitivity and the response speed of an abnormal deformation evolution trend are also remarkably enhanced.

The invention provides a lubricating oil production multi-source data fusion analysis method which comprises the following steps: acquiring a stirrer rotating speed signal, acquiring pressure distribution data of a corresponding pipeline, and if the stirrer rotating speed fluctuation range exceeds a preset threshold range, marking that the stirring rotating speed is abnormal; analyzing the pressure distribution change of the pipeline when the stirring rotating speed is abnormal, combining the monitored viscosity change of the oil fluid and the difference of the oil circulating flow speed, and performing fusion calculation to obtain a shear stress distribution index in the pipeline; if the shear stress distribution index is abnormal, the suspension state of oil particles and the deposition rate of pollution particles are detected, and if the suspension state and the deposition rate exceed corresponding preset threshold values, the oil pollution diffusion degree is determined through the suspension state and the deposition rate; and identifying abnormal equipment according to the abnormal signal time sequence correlation, acquiring operation parameters of the abnormal equipment, synchronously analyzing to obtain equipment operation state coupling, analyzing equipment fault chain reaction characteristics, and generating an equipment chain abnormality distribution diagram according to the chain reaction characteristics.

The invention discloses an abnormal risk prediction method and device based on an assembly knowledge graph, equipment and a medium, and relates to the technical field of data processing. The method comprises the steps of obtaining multi-source heterogeneous data, performing association and alignment through a unified primary key set, and performing segmentation to generate a time slice data set; and constructing an assembly domain ontology and an assembly knowledge graph mode layer, instantiating the assembly domain ontology by using the time slice data set, and constructing an assembly knowledge graph snapshot sequence. And based on the assembly knowledge graph snapshot sequence, modeling and updating the influence relationship between variables in the assembly process to obtain an assembly process influence relationship structure. And in combination with the assembly knowledge graph snapshot sequence and the assembly process influence relation structure, coding is carried out, the state representation of the next time window is predicted based on the embedding representation of the historical time window, and an abnormal risk score is calculated. When the risk exceeds a threshold value, influence path tracking is carried out, controllable decision variables are screened, candidate intervention schemes are generated, the effects of the candidate intervention schemes are evaluated, and decision suggestions are output.

The invention discloses an intelligent monitoring method and device for the operation process of a reaction kettle based on visual analysis. The method comprises the following steps: acquiring a video sequence in a reaction kettle in a current period collected by a 5G explosion-proof camera deployed in the reaction kettle according to a preset period, so as to obtain a video sequence in the kettle to be analyzed; inputting the video sequence in the kettle to be analyzed into the chemical product visual analysis model for fuzzy video processing, and extracting product visual information of the current period to obtain the product visual information; determining whether the time distribution condition of the process operation nodes in the current period is consistent with the time distribution condition in preset process operation node information or not to obtain an analysis result; and if not, corresponding operation process prompt information is created and sent to the client. By implementing the method, the accurate control of the production process and the product quality stability can be effectively improved, and the method is particularly suitable for the production requirements of high-end chemical products.

The invention discloses a manufacturing process optimization method and system based on multi-agent autonomous collaboration, and the method is applied to a central coordinator, and comprises the steps: transmitting a received production demand to a task planning agent for the task planning agent to carry out the analysis and decomposition, and forming task information; receiving task information, wherein the task information comprises sub-tasks after the task planning intelligent agent analyzes and decomposes the production demand; the sub-tasks are sent to a plurality of intelligent agents, so that the intelligent agents perform bidding according to self capability evaluation functions and cost estimation to generate bidding information; and bidding information is received, the bidding information comprises a self-ability evaluation function and cost estimation of each agent for each sub-task, the sub-tasks are allocated to the multiple agents according to a total execution cost minimization principle, and a production plan is generated and executed. According to the method provided by the invention, planning and execution of the production task can be autonomously completed in a complex manufacturing scene, and the production efficiency and the product quality are improved.

The invention discloses a high-speed vision measurement method and system for structural deformation of a cross beam of a high-speed forging machine. The method comprises the following steps: image acquisition: two cameras of a binocular camera system synchronously acquire left and right images of the cross beam in the forging process at a high frame rate; feature matching: extracting feature points in the left image and the right image, performing feature point matching, optimizing a matching result, removing wrong matching points, and generating a disparity map according to the optimized matching result; parallax calculation: correcting the parallax image according to a camera geometric model, and calculating depth information of each matching point; three-dimensional reconstruction: obtaining three-dimensional coordinates of each matching point based on the depth information and a camera geometric model, and reconstructing a three-dimensional geometric model of the cross beam; and deformation analysis: obtaining the three-dimensional coordinate data of the cross beam, comparing the three-dimensional coordinate data with the three-dimensional coordinate data of the cross beam at the initial moment, and calculating the displacement of each point on the surface of the cross beam to obtain the deformation of the cross beam. According to the invention, the deformation of the cross beam of the high-speed forging machine in the high-speed forging process can be accurately measured.

The invention belongs to the technical field of instrument board production, and discloses an instrument board tubular beam assembly integrated welding quality control and detection system which comprises the following steps: S1, design stage optimization and simulation prediction; s2, the welding process is precisely controlled; s3, material and equipment collaborative management; the design stage optimization and simulation prediction comprises structure topology optimization, weld joint layout and a welding deformation prediction model, and the welding process precise control comprises a low-heat input welding process and a dynamic parameter adjustment system. Through structural optimization and intelligent process regulation and control, welding deformation and residual stress are remarkably restrained, and high-precision forming of light-weight materials is ensured. A dynamic reverse compensation mechanism and a low-heat input welding technology cooperate to effectively avoid air holes, cracks and other defects, and the strength and fatigue life of the connector are improved. A multi-dimensional material pretreatment and equipment calibration system breaks through the reliability bottleneck of dissimilar material interface bonding, and provides guarantee for stable production under complex working conditions.

The invention discloses a blast furnace working condition knowledge graph construction method and device, and belongs to the field of blast furnace ironmaking intelligent control. The method comprises the following steps: fusing multi-source data, integrating sensor real-time data, process parameters, operation logs and expert rules, and enhancing abnormal working condition data generation capability by using a time sequence generative adversarial network; a three-layer dynamic body structure with the core abnormal furnace condition as the center is constructed, and a dynamic edge weight updating mechanism is designed; extracting multi-region spatial-temporal characteristics of the blast furnace by adopting a spatial-temporal diagram convolutional network, and generating an interpretable knowledge triple in combination with a causal discovery algorithm FGES; and realizing real-time updating of the knowledge graph based on a streaming graph learning framework, generating a regulation and control instruction through multi-agent reinforcement learning, and issuing the regulation and control instruction to a blast furnace control system through a digital twin interface. The method can clearly represent the symptom incidence relation of the abnormal furnace condition of the blast furnace, rapidly position the abnormal source and generate the regulation and control strategy, and has important practical significance for improving the intelligent level of blast furnace ironmaking.

The invention discloses a self-adaptive industrial time series data acquisition method based on edge calculation. Carrying out feature analysis on the collected data based on the information entropy and obtaining a key threshold parameter; grouping data which are being collected, and calculating the state of each group of data by using information entropy; based on the obtained threshold parameter and the state of the data group, deploying a self-adaptive data acquisition algorithm on an end-side data acquisition sensor, and dynamically adjusting the data acquisition frequency; when the state of the data group is in an extremely unstable state, the sensor immediately stops data acquisition and sends an abnormal early warning to a data center; and finally, the newly collected data can further update the threshold parameter and is used for adjusting the collection frequency, and continuous iteration is carried out to enable the collection frequency to reach a stable value. According to the method, the characteristics of rapid and continuous generation of the time sequence data of the industrial equipment under the background of the industrial internet are fully considered, and unnecessary data acquisition, transmission and storage are reduced while the data integrity and accuracy are ensured.

The invention provides a laser additive manufacturing defect monitoring method, system, medium, equipment and device, and belongs to the technical field of laser additive manufacturing defect recognition. A laser additive manufacturing defect monitoring method comprises the steps that X-ray image information and sound signal information in the melting process of a laser powder bed are obtained; preprocessing the X-ray image information and the sound signal information to obtain preprocessed X-ray image information and sound signal information; marking the preprocessed X-ray image information and sound signal information to construct a data set; inputting the preprocessed X-ray image information and sound signal information into a multi-modal teacher model for training so as to obtain defect identification and positioning capability based on multi-modal information; inputting the preprocessed sound signal information into a single-mode student model to obtain a trained single-mode student model; and migrating the defect identification and positioning capability based on the multi-modal information to the trained single-modal student model through a knowledge distillation strategy.

The invention discloses a numerical control machining process identification method and system based on multi-axis state signals, and belongs to the technical field of machining process type identification. The method comprises the steps that standardized clamping and positioning are conducted on a workpiece; enabling the numerical control machine tool to execute the standardized pre-operation program; a non-synchronous acquisition mode based on working condition triggering is adopted to obtain multi-axis current data; a timestamp alignment algorithm is introduced to realize the consistency of multi-axis current data in time sequence; for the multi-axis current data with the aligned timestamps, constructing a self-adaptive selective noise reduction preprocessing framework in combination with empirical mode decomposition and a wavelet threshold noise reduction algorithm, determining current data to be subjected to sample segmentation, and obtaining a three-dimensional data set by using a multi-axis synchronous sliding window technology; constructing a process feature set; and performing nonlinear feature dimension reduction on the process feature set by adopting principal component analysis, and building a multi-class process identification model by combining a support vector machine of a radial basis function kernel of grid optimization. According to the invention, automatic identification of a plurality of processing technologies is effectively realized.

The invention relates to a dynamic lag compensation method for inclined hole machining of a base of a water jet cutting machine. The dynamic lag compensation method comprises the following steps that S1, machining parameters are obtained; s2, establishing a dynamic lag vector model; s3, based on the target axis vector of the inclined hole, establishing an asymmetric taper prediction model; s4, coupling the dynamic lag vector model and the asymmetric taper prediction model to generate a comprehensive compensation model; s5, real-time reverse compensation is conducted on a preset inclined hole cutting theoretical tool path; s6, the high-pressure abrasive water jet device is controlled to conduct inclined hole machining on the cutting machine base according to the execution path; and S7, in the cutting process, water jet pressure, abrasive flow and nozzle abrasion state parameters are built in real time. The method has the following advantages that accurate compensation of the dynamic hysteresis effect and effective suppression of the asymmetric taper are achieved, the hole axis and position precision is remarkably improved, and the high-quality hole wall shape is obtained.

The invention relates to the technical field of intelligent manufacturing control, in particular to an air cooling control method and system for multi-aggregate pre-cooling. According to the scheme provided by the invention, classified and bin-divided independent pre-cooling is performed according to different aggregate particle sizes and pre-cooling characteristics, so that the cooling effect is good, the pre-cooling time is saved, and the working efficiency is improved. Furthermore, through periodic dynamic pre-cooling control and adjustment, in combination with real-time monitoring of the aggregate temperature of each bin and dynamic calculation of required cooling capacity distribution air cooling, synchronization of the cooling process of each aggregate is ensured, and the pre-cooled aggregates with different particle sizes and different characteristics synchronously reach the preset delivery temperature within the target time. Meanwhile, the scheme of the invention has good robustness for interference factors such as initial temperature fluctuation of the aggregate, environment temperature change and the height of the stock bin position, can automatically adjust the distribution strategy, and keeps the stability of the pre-cooling effect.

The invention discloses a migration distribution analysis method for inclusions in electron beam cold bed furnace smelting, a storage medium and equipment, and belongs to the technical field of metal smelting simulation. Actual working condition data of an electron beam cold bed furnace are obtained, and a cold bed unit model is constructed based on numerical simulation; and then electron beam energy input setting and metal solidification and melting setting are carried out in sequence, and cold bed unit heat exchange setting is carried out based on a convective heat exchange model. Performing steady state simulation on the cold bed unit, and when the field domain of the physical field reaches a steady state, simulating the movement of the inclusion in the melt by adopting a discrete random track model; movement tracks of the inclusions under different operation conditions are simulated, the migration process of the inclusions is tracked, and migration distribution of the inclusions is obtained. Migration behaviors of different types of inclusions in the cold bed unit are accurately simulated through numerical simulation, it is ensured that the inclusions flow into a crystallizer as little as possible, and the overall efficiency of the smelting process and the final product quality are improved.

The invention belongs to the technical field of intelligent manufacturing traceability, and provides a battery part production traceability management system based on the Internet of Things, which comprises the steps of collecting battery part information, setting double identifiers for each battery part, storing the battery part information, calculating a qualified index of the battery part for preliminary evaluation, and determining whether the battery part is qualified or not. And for the preliminarily qualified battery parts, constructing and training an attenuation prediction model to predict the service lives of the battery parts to obtain the predicted actual service lives of the battery parts, dividing the battery parts into inferior products, non-defective products and superior products, constructing and training a defect analysis model to identify the defect root causes of the inferior products, and determining the actual service lives of the battery parts. The method comprises the following steps: determining steps causing defect root causes, setting risk mark values, recording the number of times of causing the defect root causes in a batch, sorting each step in a production line, obtaining a tracing priority sequence, calculating the inferior product rate of battery parts in the batch, and judging whether to trigger forward recall or reverse tracing.

The invention discloses a calcium-based thermochemical particle bed health status assessment method and a related device. The method comprises the following steps: acquiring a surface image of a calcium-based thermochemical particle bed; performing data enhancement on the surface image of the calcium-based thermochemical particle bed layer; inputting the surface image after data enhancement into a multi-task segmentation model to obtain a pixel-level segmentation mask; calculating the expansion rate, the agglomeration index, the crushing degree, the collapse depth and the collapse area ratio of the particle bed layer according to the pixel-level segmentation mask; the performance of the calcium-based thermochemical particle bed layer is evaluated according to the expansion rate, the agglomeration index, the crushing degree, the collapse depth and the collapse area ratio of the calcium-based thermochemical particle bed layer. The method and the related device can accurately detect the health of the calcium-based thermochemical particle bed layer.

The application discloses a precision belt wheel mold life cycle management method and system, and relates to the technical field of mechanical manufacturing, comprising the following steps: in the whole life management process of the precision belt wheel mold, continuously collecting design version change data, processing process record data, running condition waveform data and maintenance disposal track data, and uniformly writing the collected data into a data chain of the same time reference for time sequence management, and generating a time alignment index at the end of the data chain. The application realizes continuous connection and anti-overlapping collection of multi-source data by constructing a data chain with time as the main line and introducing a precursor anchor point, a previous priority constraint and a time sequence traction control, ensures that the deterioration signal is continuously visible in the time dimension, accurately reflects the mold performance attenuation process, and improves the reliability of life prediction and maintenance decision.

The application provides a force-vibration-noise monitoring and prediction system for wet milling, which comprises an externally-mounted cutting fluid transmission system, a numerical control machine tool and workpiece system, a sound pressure and vibration measurement system, and a three-way force measurement system, can monitor and obtain three-way milling force signals, three-way vibration signals and milling sound pressure signals under given milling parameters. Based on experimental data and grey correlation theory, the correlation degrees of force, vibration and noise about milling parameters during wet milling are better than those during dry milling, which shows that the system has a certain optimization effect on the cutting state. Based on the response surface analysis method, the prediction models of force, vibration and noise about milling parameters and the comprehensive model of noise about force-vibration-milling parameters are established. The results show that the noise comprehensive prediction model established based on milling force-vibration is more reliable, and the correlation between milling force, vibration and milling noise is higher. The application can provide scientific guidance for the monitoring and prediction of the milling processing state.

The invention discloses a time sensor scheduling method based on a 5G deterministic network, and relates to the technical field of communication engineering, and the method comprises the steps: enabling an automatic equipment group to be wirelessly connected with a time sensor through a 5G network, and obtaining the real-time operation time, the remaining processing time and the maximum operation time of each equipment; calculating a load value according to the real-time operation time and the maximum operation time, judging the load condition of the equipment according to the load value, marking categories and sorting, and carrying out rest scheduling according to the category and sorting; task load division, preferential distribution of emergency tasks, reasonable distribution of conventional tasks and elastic tasks are carried out by combining the theoretical residual capacity of the equipment, the tasks are stored in a buffer pool for specific equipment application, the task completion condition is monitored in real time, and task load stripping and equipment category adjustment are carried out when necessary; according to the method, automatic equipment scheduling and task allocation can be optimized, the production efficiency is improved, and the equipment fault risk is reduced.

The invention provides a tobacco production monitoring method and system, electronic equipment and a storage medium, and relates to the technical field of tobacco production. The method comprises the following steps: acquiring actual measurement data corresponding to different indexes to be measured in each stage of representing tobacco production; according to the actually measured data, determining a dynamic deviation tensor representing the deviation degree between the actually measured production state of each stage of tobacco production and the ideal production state at the current moment; according to the actually measured data and the dynamic deviation tensor, determining a comprehensive deviation state parameter of the to-be-measured index based on a preset deviation judgment strategy; and according to the actually measured data, the dynamic deviation tensor and the comprehensive deviation state parameter, generating monitoring feedback information of the to-be-measured index. Therefore, the problems of high labor cost and low efficiency of a traditional tobacco production monitoring mode can be improved.

The present invention belongs to the technical field of automated steel production and discloses a method for predicting the composition of molten iron applied to an automated steel production process, wherein the method is: performing a sampling and an examination of molten iron in a process in which the molten iron is tapped from a torpedo tank into a ladle, and calculating a loss of composition of this molten iron, wherein the composition of the molten iron is calibrated before the molten iron is tapped into the ladle;Performing a sampling and analysis of the molten iron in a process where the molten iron is transferred from the ladle to a converter, and calculating any loss in the composition of this molten iron, wherein the composition of the molten iron is calibrated before the molten iron is transferred to the converter. The present invention is easy to use and implement, and can acquire more accurate and reliable real-time parameters for computational models at all levels; in its specific application, the present invention does not require the modernization of existing automated steelmaking equipment; and it can be applied to a wide range of automated steelmaking scenarios.

The invention relates to the technical field of production monitoring, and discloses a quality monitoring method and system for a non-woven fabric production line, and the method comprises the steps: synchronously capturing the linear speed information, gram weight information and appearance image information in the non-woven fabric production line; performing frame alignment on the gram weight information and the appearance image information to obtain synchronization feature data; fusing the texture anomaly candidate region and the gram weight information fragment in the synchronized feature data to obtain a fused defect description; matching a combination mode of image morphological features and surface density statistical distribution features in the fusion defect description to obtain a defect category; reversely mapping to a process flow diagram, and positioning primary process links causing defect categories to obtain a judgment conclusion; integrating the judgment conclusion, the fragment of the synchronization feature data and the identifier of the primary process link to obtain a quality monitoring report; the quality monitoring efficiency of the non-woven fabric production line can be improved.

The invention discloses an inspection method and system based on big data, and belongs to the technical field of industrial equipment inspection, and the method comprises the steps: obtaining a historical operation data set of hardware equipment, preprocessing the historical operation data, generating a training data set, training the training data set, building an equipment detection model, and installing the equipment detection model at an inspection terminal. A monitoring sensor is installed on hardware equipment, the monitoring sensor monitors the hardware equipment in real time and collects operation data of the hardware equipment in the operation process, an integrated repeater receives the operation data monitored and collected by the monitoring sensor, the data are sorted, integrated and calculated, and an operation state fluctuation diagram of each piece of hardware equipment is generated; an inspector carries the inspection terminal to inspect, uses the equipment detection model to detect the running state fluctuation diagram and judges the state of the hardware equipment, so that the inspection accuracy can be improved, only the integrated repeater needs to be inspected, and the labor cost and the false touch rate are reduced.

The invention discloses a coating anomaly analysis method, related equipment and a storage medium, and the coating anomaly analysis method comprises the steps: obtaining a coating anomaly feature input by a user, the coating anomaly feature reflecting the phenomenon of the coating anomaly; obtaining event features of a plurality of coating anomaly basic events corresponding to the coating anomaly features in the fault tree, and obtaining a target probability corresponding to the coating anomaly features; on the basis of the features of the multiple coating anomaly basic events and the target probability, the anomaly probability for the multiple coating anomaly basic events is obtained through calculation; and calculating the decision game contribution degree of each coating anomaly basic event based on the anomaly probability, and selecting at least one coating anomaly basic event as a key factor of the coating anomaly based on the decision game contribution degree of each coating anomaly basic event. According to the scheme, the problem of key factor omission caused by empirical judgment or local data investigation is relieved.

The invention provides a printed book and periodical automatic cutting management method and system based on image recognition, and belongs to the technical field of image recognition, and the method specifically comprises the steps: determining a quality inspection processing strategy of a cutting result of an image recognition model according to adjustment data and time sequence distribution data of an adjustment time period, and carrying out quality inspection processing on the cutting result by utilizing a quality inspection processing strategy, determining abnormal cutting data under different adjustment modes according to a quality inspection processing result when it is determined that management and control processing of maintenance of the printing mechanism needs to be carried out according to the quality inspection processing result and the correlation degree of the adjustment data between the adjustment time periods, and carrying out management and control on the maintenance of the printing mechanism according to the quality inspection processing result. And based on the abnormal cutting data and the change data of the adjustment mode of the cutting mechanism, the management and control processing method of the maintenance processing of the printing mechanism is determined, and the reliability degree of the cutting processing is improved.

The invention relates to a network abnormity early warning method and device based on digital linkage, equipment and a medium, and belongs to the technical field of semiconductor processing monitoring. The method comprises the following steps: acquiring multi-dimensional production data in a semiconductor cutting process, and carrying out analytical calculation on the multi-dimensional production data to obtain an abnormal data set in the semiconductor cutting process; inputting the exception data set into a pre-trained multi-dimensional exception analysis model to obtain an exception prediction result of each link of semiconductor cutting production; and based on the anomaly prediction result, inputting a pre-trained multi-agent collaborative early warning mechanism, and generating corresponding early warning information. By adopting the method, artificial experience judgment and data recording can be replaced, real-time production monitoring and accurate abnormity early warning are realized, the semiconductor cutting production quality and efficiency are guaranteed, and the potential risk of production is reduced.