431results 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 belongs to the technical field of equipment management, discloses a health degree evaluation method, system and equipment for assembly line special equipment and a medium, and aims to solve the limitation of health state evaluation of the assembly line special equipment in the prior art. The method comprises the steps of obtaining evaluation indexes of equipment and comprehensive weight values corresponding to the indexes, and performing calculation based on the evaluation indexes to obtain a first health degree score; acquiring historical fault data and historical operation time data of the equipment, calculating a time interval between a fault occurrence moment and a maintenance occurrence moment of each fault based on the historical fault data and the historical operation time data, and constructing a time attenuation model to calculate a weighted risk score of each fault so as to calculate a second health score; and obtaining production scheduling data of the equipment, and performing calculation in combination with the health degree data to obtain a current production scheduling risk score, thereby completing health degree evaluation of the assembly line special machine equipment. According to the method, the comprehensiveness, the accuracy, the dynamism and the real-time performance of health degree evaluation of the assembly line special machine equipment are remarkably improved.

The invention discloses a method for predicting blast furnace TRT equipment maintenance time based on an LSTM model, and the method comprises the steps: constructing a sliding window adaptive algorithm based on vibration signal change characteristics, and dynamically adjusting the size of an input data sliding window of the LSTM model according to the fluctuation amplitude and change rate of a vibration signal; adopting an adaptive sliding window to obtain TRT equipment training data, and training the LSTM model; applying the trained LSTM model to the vibration signals acquired in real time, predicting the vibration trend of the TRT equipment in the future n days at the current point, and outputting a predicted value of the vibration signals in a future period of time; and according to the prediction result of the vibration signal, in combination with a preset threshold value of shutdown maintenance, judging the time when the TRT equipment reaches the threshold value, and further obtaining the remaining days of the TRT equipment away from the maintenance. According to the method, the future development trend of the TRT equipment vibration signal is accurately predicted, the maintenance plan is reasonably arranged, and the TRT equipment operation reliability and production efficiency are improved.

The invention provides a copper wire stretching quality detection method and system for elongation analysis. The method comprises the following steps: obtaining production process record data of a copper wire sample meeting an elongation threshold; on the basis of a preset production process, traversing the production process record data for comparison to obtain a production process deviation parameter; according to the deviation parameters, extracting record data with the deviation parameters smaller than or equal to a threshold value for centralized value evaluation to obtain a production process reference space; when the production process monitoring data of the to-be-detected copper wire falls into the reference space, judging that the copper wire is qualified; when the monitoring data does not fall into the reference space, extracting a single-attribute deviation matrix; and retrieving an elongation threshold value of an abnormal sample meeting the deviation matrix, and executing targeted tensile quality actual measurement. By establishing a production process reference space, accurate prediction and targeted detection of the drawing quality of the copper wire are realized, and the omission ratio is effectively reduced.

The invention discloses a dynamic equipment management service system and method for deep learning. The method comprises the following steps: S1, collecting real-time operation data of equipment and preprocessing the real-time operation data; s2, constructing a long-short-term memory network model, and outputting comprehensive early warning indexes of the equipment; s3, constructing an optimization problem based on the comprehensive early warning index of the equipment, and setting an objective function and constraint conditions; s4, performing global search on the optimization problem by adopting an improved dragon fly algorithm, and generating a plurality of resource scheduling and maintenance candidate schemes; s5, performing local optimization on the candidate scheme by using a simulated annealing algorithm, and determining an optimal resource scheduling and maintenance decision scheme; and S6, feeding back the real-time prediction result and the optimal decision result to form closed-loop control. Through fusion of deep learning prediction, the improved dragon fly algorithm and the simulated annealing algorithm, real-time closed-loop control of accurate early warning of the equipment state and dynamic resource scheduling decision is realized, so that the failure rate is effectively reduced, and the equipment management efficiency is improved.

The invention discloses a safety production hidden danger intelligent diagnosis system and method, and belongs to the technical field of safety production management, and the method specifically comprises the steps: collecting and preprocessing a field image through a sensor, and inputting the image into a multi-target recognition model to recognize each target element in the image; determining a production scene containing all the target elements by using a preset production scene knowledge graph, calling a corresponding specification file, and outputting specification requirements through the large model; dividing the image into a large-scale information area and a small-scale information area according to specification requirements, splitting the field image into a large-scale sub-image and a small-scale sub-image according to the large-scale information area and the small-scale information area, and respectively inputting the sub-images into a first deep learning model and a second deep learning model of a corresponding production scene for hidden danger identification; identifying and recording potential safety hazards by combining output results of the first deep learning model and the second deep learning model; according to the invention, the accuracy and efficiency of production field potential safety hazard identification are improved.

The invention provides a glass processing dynamic monitoring method and system based on multi-source data fusion, and relates to the field of industrial artificial intelligence, the method comprises the following steps: continuously collecting sound signals generated during processing, and carrying out noise reduction processing on the obtained sound signals to obtain sound data after noise reduction; continuously monitoring the acoustic data after noise reduction, acquiring abnormal acoustic characteristics of the glass in the processing process, determining an accurate time point of the abnormal acoustic characteristics, and acquiring time information of the abnormal acoustic characteristics; acquiring a glass processing position at the time of the abnormal acoustic features according to the time information of the abnormal acoustic features, and acquiring image or video information of a glass processing area within the time range; according to the obtained abnormal acoustic characteristics and the image or video information of the glass processing area, whether defect information appears in the glass processing process or not is judged, so that real-time dynamic monitoring and defect accurate positioning can be realized in the glass processing process, and specific process parameter adjustment suggestions are generated.

The invention provides a filling process prediction method and device based on a discrete element method and data driving, and relates to the technical field of bulk material forming, and the method combines the physical modeling advantage of the discrete element method and the powerful prediction capability of a data driving method. The filling process of the granular material under different process parameters is simulated through a discrete element method, key quality indexes are obtained to serve as input of a data driving model, and the process parameters serve as output for training. The model not only can accurately predict the filling quality, but also can adjust the process parameters in real time according to the target quality index, so that the intelligent optimization of the filling process is realized. According to the method, the calculation efficiency is greatly improved, the generalization ability of the model is enhanced, the dependence on empirical data is reduced, a more efficient and accurate solution is provided for the filling process in the industries of building materials, pharmacy, powder metallurgy and the like, the product quality is improved, the production cost is reduced, and the research, development and application of novel materials and equipment are accelerated.

The invention relates to the technical field of fastener process production, in particular to a process parameter control method and system applied to fastener production. The method comprises the following steps: acquiring three-dimensional cutting force of a tool-workpiece contact area in a fastener thread machining process in real time, and generating cutting force dynamic fluctuation characteristic data; the real-time abnormal situation of the current machining process is recognized according to the cutting force dynamic fluctuation characteristic data, a tool wear mode is judged, thread ring machining deviation prediction is conducted, and a predicted thread geometric deviation value is generated; and adjusting multiple machining control parameter values according to the predicted thread geometric deviation value, and carrying out real-time machining feedback monitoring so as to realize fastener production self-adaptive control. According to the method, intelligent recognition of the tool wear mode and accurate prediction of the machining deviation are achieved through cutting force sensing, and it is ensured that the thread machining precision of the fastener is stable and controllable through multi-parameter cooperative self-adaptive regulation and control.

The invention relates to the technical field of injection molding production process monitoring, and discloses an injection molding production monitoring method, device and system.The injection molding production monitoring method comprises the steps that multi-source sensing data is collected, and pressure time sequence data and material spectrum data in the injection molding process are collected; extracting pressure waveform features to obtain a complete pressure waveform feature set; performing material characteristic analysis, and forming a material characteristic fingerprint in combination with the pressure waveform characteristics and the spectral data; material batch similarity calculation: constructing a material batch fingerprint database, and calculating the similarity between the new batch of materials and the historical batch of materials; process parameter optimization: continuously improving the accuracy of parameter optimization through multi-objective tradeoff optimization and parameter verification and iterative optimization; quality problem root causes are analyzed, and material problems and process parameter problems are accurately distinguished; through fusion of pressure waveform analysis and a material characteristic monitoring technology, comprehensive monitoring and intelligent regulation and control of an injection molding production process are realized.

The invention relates to the technical field of image processing, in particular to an intelligent detection method and system for support turning. The method comprises the steps that sensor signals of the support in the turning machining process are obtained in real time; constructing a sensor topological graph; extracting real-time time sequence process features reflecting the dynamic response of the tool-workpiece-machine tool system in the sensor topological graph; inputting the real-time time sequence process features into a trained multi-task prediction model, and outputting prediction deviation values of a plurality of geometric dimensions of the support and a prediction surface defect mask pattern; and if all the predicted deviation values are within the corresponding tolerance threshold values and the ratio of the defect area of the predicted surface defect mask pattern to the total area of the bracket is smaller than a set area threshold value, judging that the expected quality state of the bracket is qualified. According to the scheme, the expected quality state of the support product can be comprehensively judged in real time.

The invention discloses a pulse electroplating detection method, a pulse electroplating device and equipment, and the method comprises the steps: synchronously collecting transient current density data of a three-pole assembly in a pulse switching time window, and calculating a time derivative of a current density ratio to obtain electrochemical stress gradient data; performing space-time correlation analysis on the stress gradient data of the continuous pulse period, and tracking a spatial propagation trajectory of stress anomaly; a key monitoring area is determined according to the propagation trajectory, and ion migration impedance sensitivity distribution is detected through micro-amplitude current modulation; performing multi-dimensional coupling analysis on the stress gradient, the propagation trajectory and the impedance sensitivity data, and identifying time sequence correlation characteristics of stress evolution and ion anomaly; and performing quantitative evaluation and grade division on the electrochemical state of the avoidance area based on the coupling correlation characteristics. According to the scheme, early recognition and predictive evaluation of the ion migration abnormity of the boundary layer of the avoidance area can be realized in the pulse electroplating process, and the electroplating quality control precision and the process stability are remarkably improved.

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 provides an insulator sintering furnace temperature control system and method. The method comprises the steps that a preset temperature control scheme is generated; monitoring the real-time heating data of each area in the sintering furnace, and determining the real-time temperature rise data of the insulator in each area based on the real-time heating data; analyzing a first abnormal temperature value under a first area temperature time sequence in the real-time heating data to obtain first predicted sintering quality; performing simulation based on the first abnormal temperature value so as to generate simulation data of the first abnormal temperature value; and analyzing and judging the simulation data to obtain a first judgment result of the first area at the first moment. When the temperature of a certain area in the sintering furnace is abnormal, the abnormal temperature can be taken as a temperature regulation response in time, the technical effects of realizing high-precision temperature control and ensuring excellent sintering yield of the insulator are achieved, meanwhile, when the temperature of a single sintering area is regulated, the temperature influence on the area adjacent to the regulation area is reduced, and the stability of the sintering temperature is improved. And the temperature adjusting precision of the sintering area of the sintering furnace is ensured.

The invention discloses a mechanical automation scheduling test method and system, and relates to the field of mechanical electronic data processing. The method comprises the following steps that the machining process is monitored, and machining parameter data are obtained; the drilling machining condition is analyzed; an edge milling qualification degree evaluation index is obtained according to the machining parameter data, and the edge milling machining condition is analyzed; machining adjustment is conducted according to the drilling machining condition and the edge milling machining condition; after machining adjustment is finished, mechanical task completion condition parameter data are obtained; and according to the mechanical task completion condition parameter data, analyzing the mechanical task completion condition and performing scheduling. According to the invention, the mechanical task completion condition is analyzed and scheduled according to the mechanical task completion condition parameter data, so that the effects of reasonably scheduling according to the state of the equipment and task requirements and improving the production efficiency are achieved; the problem that in the prior art, reasonable scheduling cannot be conducted according to the state of equipment and task requirements, and consequently production efficiency is low is solved.

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 an optimization method and system for a 42CrMo steel heat treatment process based on digital twinning, and the method comprises the steps: obtaining historical data of 42CrMo steel in each stage of the heat treatment process, and constructing a corresponding digital twinning model based on each cooling rate, deploying all the digital twin models at specified positions in a preset virtual space; acquiring a real-time data packet of the 42CrMo steel in the heat treatment process, and dividing the real-time data packet into a plurality of sub-data packets according to different cooling rates; determining a target time sequence identifier corresponding to each sub-data packet according to the cooling rate, and transmitting the target time sequence identifier to a corresponding target digital twin model; the target digital twin model runs the sub-data packets and generates corresponding optimization information; and detecting the current visual field range of the user, and guiding the user to adjust the visual field until the target digital twinborn model can be seen. By means of the digital twinborn model, accurate control over the cooling rate can be achieved, and therefore the abrasion resistance and hardness of the 42CrMo steel are optimized.

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 relates to the technical field of information retrieval, in particular to an online diagnosis retrieval system for PET processing abnormal logs, which comprises a difference preprocessing module for calculating first-order difference absolute values of adjacent time points, extracting second-order difference symbol change times and generating a key change characteristic parameter set based on a temperature parameter sequence and a pressure parameter sequence of PET processing equipment. According to the method, the difference absolute value of the adjacent time points of the temperature and pressure parameters is calculated in real time, the number of second-order difference symbol changes is extracted, the associated code is generated in combination with the timestamp and the equipment number, the time-space relevance of abnormal fluctuation is enhanced, and the weak process deviation is accurately captured in the early stage. According to the method, interval hash indexes are divided on the basis of temperature difference absolute values, meanwhile, B + tree range indexes are constructed for pressure standard deviations, multi-dimensional joint retrieval is achieved, the two abnormal modes of high-frequency oscillation and steady-state offset can be screened independently or in a combined mode, and the false detection rate under the complex working condition is reduced.

The invention provides a glass production line cold end stress detection system and method. Belongs to the technical field of glass production detection. The method comprises the following steps: carrying out stress-related spectral data acquisition on a cold end area of the glass production line through a multispectral stress sensing array, and preprocessing the acquired spectral data to obtain a preprocessed spectral data set; spectral feature extraction is carried out on the preprocessed spectral data set, and a spectral feature vector set is constructed; based on the spectral feature vector set, utilizing a space-time correlation analysis algorithm to extract space-time features of glass cold end stress to obtain a stress space-time feature matrix; spectral data are collected through the multispectral stress sensing array, the influence of traditional contact type detection on glass products and a production line is avoided, and the detection precision and the real-time performance are improved.

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 a double-screw extrusion mechanism convenient for sampling detection, and belongs to the technical field of sampling, the double-screw extrusion mechanism comprises a conveying motor and two sampling outer frames, the conveying motor is connected with two screw extrusion shafts through a gear set mechanism, and sampling holes are formed in the left inner side wall, the right inner side wall and the lower inner side wall of each sampling outer frame. Through the arrangement of the mounting cavity seat and the sampling assembly, materials conveyed at different positions in the same conveying stage can be sampled and compared through negative pressure sampling on the two sides and in the middle, and comparison sampling of the materials conveyed at the same position in the different conveying stages is achieved through respective sampling of the front sampling outer frame and the rear sampling outer frame; and meanwhile, through the arrangement of an electric push rod and a double-cambered-surface compensation pressing plate, reciprocating downward pressing of the double-cambered-surface compensation pressing plate can be used in cooperation with continuous pressing-in of high-pressure materials at the input end of the whole double-screw extrusion mechanism, and a cavity formed by sampling is compensated.

The invention relates to the technical field of data processing, in particular to a multi-parameter comprehensive monitoring method and system for wet desulphurization. The method comprises the following steps: collecting multi-parameter data in a wet desulphurization process, and obtaining the priority degree of each parameter in initial multi-parameter data according to the characteristic intensity of each parameter in the initial multi-parameter data and the similarity degree between each parameter in the initial multi-parameter data and other parameters, constructing an initial isolated tree for the initial multi-parameter data based on the priority degree of each parameter, adding the real-time data into the initial isolated tree, calculating the structural change degree of the initial isolated tree, and adaptively updating the initial isolated tree according to the structural change degree; and finally, the abnormal score of each multi-parameter data is obtained according to the final isolated tree, early warning is carried out according to the abnormal score result, and the abnormal detection result is more accurate.

The invention discloses a distribution transformer load loss prediction method and system based on pilot-scale test monitoring data. The method comprises the following steps: collecting pilot-scale test data of a distribution transformer load loss related variable; preprocessing the collected pilot plant test data, and performing correlation analysis on the preprocessed variable data to obtain an independent variable in a distribution transformer finished product load loss prediction function; performing multiple regression analysis on the selected independent variables to obtain a regression model, correcting the regression model to obtain a distribution transformer finished product load loss prediction function, and verifying the load loss prediction function; and performing load loss prediction on the distribution transformer finished product based on the verified load loss prediction function. According to the method, the predicted value of the load loss can be quickly obtained by analyzing pilot test data, the time and the cost of a traditional experiment are reduced, and the calculated load loss prediction precision can be effectively improved by analyzing variables and verifying functions.

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 provides a correlation analysis method for technological parameters in a wafer processing process and related equipment. The correlation analysis method comprises the following steps: determining target parameters needing correlation analysis in the wafer processing process; according to the target parameter, acquiring all other process parameters belonging to the same wafer batch as the target parameter and corresponding parameter values in the data warehouse, and packaging into a data set; inputting the data set into a machine learning algorithm model, and calculating the correlation between the target parameter and other process parameters through a machine learning algorithm; and determining key process parameters influencing the target parameters according to a correlation calculation result. The correlation between the target parameter and other process parameters is automatically calculated and identified through a machine learning algorithm. In this way, the key process parameters influencing the target parameters can be effectively screened out, objective data support and decision basis are provided for the process defect problem caused by the common influence of multiple factors, and the difficulty of fault analysis and problem positioning is reduced.

The invention discloses an online injection product quality control method. The method comprises the following steps that key features of technological parameters in the product injection molding process are extracted; constructing a time sequence feature prediction model and a quality prediction model based on the extracted key features; predicting process parameters of the next period through a time sequence feature prediction module, inputting the process parameters into the quality prediction model, and further predicting the size of the product in the next period; the predicted product size is verified, if the product size is qualified, technological parameter optimization does not need to be carried out, and otherwise, global optimal technological parameters are reversely searched through an iterative algorithm and substituted into the quality prediction model to carry out product size re-prediction until the product size verification is qualified. The method has the beneficial effects that by predicting the size of the injection molding product and reversely deducing the corresponding process characteristics to serve as the process data of the current injection molding machine, real-time online correction of the process data of the injection molding machine is achieved, and therefore online control over the injection molding quality is achieved.

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 relates to the technical field of cascade metallurgical process monitoring, and particularly discloses a cascade metallurgical process adaptive and interpretable monitoring method, which comprises the following steps: constructing a hybrid model comprising an incremental learning trigger based on a BSOM model and a trained VGATEPi model, and constructing an anomaly sensing and positioning mechanism for fault positioning and interpretation; according to the method, continuous learning is effectively carried out from dynamically changing cascade metallurgy process variables, interpretable monitoring results are achieved, the process monitoring performance can be remarkably improved, and particularly, in the aspect of reducing the false alarm rate in process monitoring, the problem that a traditional monitoring method based on a static graph model is poor in monitoring effect on non-stable changing data is solved. And the problems of false alarm and missing alarm are easy to occur because the time-varying characteristics cannot be automatically updated at any time. In addition, an interpretable causal relationship between fault variables can be provided, and an important maintenance basis is provided for an abnormal process.