Sealing integrated collaborative process optimization method and system

Abstract

The invention relates to the technical field of process management, in particular to a sealing integrated collaborative process optimization method and system. The method comprises the following steps: obtaining sealing process data; performing sensor data acquisition according to the sealing process data to obtain a multi-modal sensor acquisition data set; performing data preprocessing on the multi-modal sensor acquisition data set to generate a standard multi-modal sensor acquisition data set; performing process flow analysis on the sealing process data to generate sealing process flow data, the sealing process flow data including a sealing flow, a cover closing flow and a cover pressing flow; and performing intelligent process modeling on the sealing process, the cover closing process and the cover pressing process to generate a process procedure mathematical model. According to the invention, through multi-modal data acquisition, detailed process flow analysis, real-time monitoring and dynamic adjustment strategies, the flexibility and adaptability of sealing process production process management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of process management, and in particular to a collaborative process optimization method and system for integrated sealing. Background Art

[0002] In the early days, enterprises relied on manual operation in the sealing process, which led to low efficiency and prone to errors. After entering the 21st century, with the rise of digital technology, enterprises gradually introduced computer-aided design (CAD) and computer-aided manufacturing (CAM) systems to achieve partial automation of the production process. At this time, although the sealing process has been improved, there is still a lack of effective coordination between different processes, resulting in resource waste and information islands. With the development of the Internet of Things (IoT) and big data analysis technology, manufacturing companies have begun to pay attention to the collection and analysis of real-time data, and thus realized the intelligent interconnection of different production links. The collaborative process optimization method of integrated sealing came into being. Using real-time data feedback, dynamic adjustment and collaborative operation of each process can be achieved. This method not only improves production efficiency, but also improves product consistency and reliability. However, the current traditional process flow analysis is not deep enough, and it is impossible to fully grasp the relationship between each link. At the same time, the monitoring method is often lagging behind and cannot detect abnormal conditions in production in time, which leads to low flexibility and adaptability of production process management. Summary of the invention

[0003] Based on this, it is necessary to provide a collaborative process optimization method and system for integrated sealing to solve at least one of the above technical problems.

[0004] To achieve the above object, a sealing integrated collaborative process optimization method is provided, the method comprising the following steps:

[0005] Step S1: Acquire sealing process data; perform sensor data acquisition according to the sealing process data to obtain a multimodal sensor acquisition data set; perform data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set;

[0006] Step S2: Perform process flow analysis on the sealing process data to generate sealing process flow data, wherein the sealing process flow data includes sealing process, capping process and capping process; perform intelligent process modeling on the sealing process, capping process and capping process to generate a process process mathematical model; use the process process data model to perform process operation position adaptive control on the container to be sealed to generate a real-time production status panel;

[0007] Step S3: construct monitoring nodes for the sealing process, the capping process and the capping process through the real-time production status panel to generate real-time production status monitoring nodes; perform abnormal node monitoring on the real-time production status monitoring nodes to generate abnormal nodes and normal nodes; perform collaborative process strategy execution based on the abnormal nodes and normal nodes to generate a collaborative process execution strategy;

[0008] Step S4: Dynamically adjust the collaborative process execution strategy to generate a collaborative process dynamic adjustment strategy; perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy to generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to perform integrated sealing collaborative process optimization operations.

[0009] The present invention can fully understand various parameters in the sealing process by acquiring sealing process data and performing sensor data collection, thereby ensuring the integrity and accuracy of the data. Data preprocessing generates a standard multimodal sensor acquisition data set, which provides a high-quality data basis for subsequent analysis and modeling, and reduces the impact of noise and errors on the model. The sealing process flow data generated by process flow analysis helps to identify and optimize the key links in the sealing, capping and capping processes, thereby improving the overall process efficiency. Intelligent process modeling makes the sealing process more scientific, provides decision support in a data-driven manner, and improves the accuracy of process operations. The real-time production status panel generated by the process operation position adaptive control can monitor the production status in real time, which is convenient for rapid response and adjustment. By constructing real-time production status monitoring nodes, the monitoring capability of the production process is enhanced, and potential problems can be discovered in a timely manner. The monitoring of abnormal nodes and normal nodes enables the rapid identification of abnormalities in the process, provides timely adjustment solutions, and reduces production risks. The collaborative process execution strategy generated based on the abnormal nodes can effectively integrate the operations of each process and improve the overall production efficiency. The strategy dynamic adjustment mechanism enables the system to self-optimize according to real-time data, thereby improving the flexibility and adaptability of the system. Closed-loop control is performed on the real-time production status panel to ensure the stability of various indicators in the production process, reduce fluctuations and errors, and improve product quality. Uploading the collaborative process closed-loop control data to the cloud server for storage not only ensures the security and traceability of the data, but also provides a basis for subsequent analysis and improvement. The generated collaborative process control traceability data can provide a basis for the collaborative process optimization operation of integrated sealing, and promote the continuous improvement of overall production efficiency. Therefore, the present invention improves the flexibility and adaptability of the sealing process production process management through multimodal data acquisition, detailed process flow analysis, real-time monitoring and dynamic adjustment strategies.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Acquire sealing process data;

[0012] Step S12: Arrange sensors according to the sealing process data to generate sealing process sensor deployment data; configure edge computing nodes for the sealing process sensor deployment data to obtain sealing process edge computing nodes;

[0013] Step S13: performing sensor data collection on the edge computing nodes of the sealing process based on a preset data collection frequency to obtain a multimodal sensor collection data set;

[0014] Step S14: performing data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set, wherein the data preprocessing includes noise filtering, data smoothing, and missing value interpolation.

[0015] The present invention lays the foundation for subsequent analysis through the sealing process data, ensuring that there is enough information to identify process characteristics and potential problems. Sensors are arranged according to the sealing process data, and key parameters (such as temperature, pressure, etc.) in the process can be accurately monitored, so as to grasp the process status in real time. Configuring edge computing nodes in the sealing process can reduce data transmission delays, improve data processing efficiency, and help to feedback the process status in real time. By collecting sensor data from edge computing nodes based on a preset data acquisition frequency, a multimodal sensor acquisition data set is formed, making the data more comprehensive and able to reflect various aspects of process information. Noise filtering can remove interference signals in sensor acquisition, improve the signal-to-noise ratio of data, and provide a more accurate data basis for subsequent analysis. Data smoothing can reduce fluctuations, make trends more obvious, and facilitate analysis and decision-making of process performance. Missing value interpolation ensures the integrity of the data set, avoids inaccurate analysis due to missing data, and thus improves the reliability of the analysis results. Through the system's sensor arrangement and data processing flow, the monitoring and optimization capabilities of the sealing process are improved. By obtaining comprehensive and accurate data, combined with the real-time processing capabilities of edge computing, it can help enterprises to promptly discover and solve problems in the production process, and ultimately improve production efficiency and product quality.

[0016] Preferably, step S2 comprises the following steps:

[0017] Step S21: performing process flow analysis on the sealing process data to generate sealing process flow data, wherein the sealing process flow data includes a sealing process, a capping process, and a capping process; classifying the process data of the standard multimodal sensor acquisition data set according to the sealing process, the capping process, and the capping process to generate process classification sensor data;

[0018] Step S22: Intelligent process modeling is performed on the sealing process, the capping process and the capping process through process classification sensor data to generate a process procedure mathematical model;

[0019] Step S23: using the process data model to predict the state of the container to be sealed for the sealing process, the capping process and the capping process, and generating sealed container state prediction data; performing process operation position adaptive control on the container to be sealed according to the sealed container state prediction data, and generating process operation position adaptive control data;

[0020] Step S24: Based on the process operation position adaptive control data, the sealing process, the capping process and the capping process are visualized in real time, thereby generating a real-time production status panel.

[0021] The present invention can fully understand the various links of sealing, capping and capping by performing process analysis on the sealing process data, and identify the key links and potential bottlenecks in the process. The data collected by the standard multimodal sensor is classified into process data, so that the data of each process is more accurate, convenient for subsequent analysis and modeling, and the reliability of the model is ensured. Through intelligent process modeling, the generated process process mathematical model can provide a scientific basis for production decision-making, help identify the optimal process solution, and improve production efficiency. The state of the container to be sealed is predicted by the process process data model, so that production can identify potential problems in advance, thereby reducing production interruption and material waste. Based on the state prediction data, the process operation position is adaptively controlled, and the production process can be adjusted in real time to cope with the dynamically changing production environment and optimize the process parameters. Through the real-time data visualization to generate the production status panel, the management personnel can quickly grasp the real-time status of the production process, which is convenient for monitoring and decision-making, and improves the management efficiency and response speed. Through the process analysis and intelligent modeling of the system, the controllability and flexibility of the sealing process are improved. Through prediction and adaptive control, combined with real-time data visualization, it can effectively improve production efficiency, reduce resource waste, and provide strong support for decision-making. This intelligent management method will help enterprises maintain their advantages in competition.

[0022] Preferably, step S22 includes the following steps:

[0023] Step S221: selecting key process indicators for the sealing process, the capping process and the capping process to obtain key process indicator data, wherein the key process indicator data include key process indicators for the sealing process, key process indicators for the capping process and key process indicators for the capping process; selecting a mathematical model according to the key process indicator data to generate mathematical model selection data, wherein the mathematical model selection data include a state space model, a linear regression model and a nonlinear regression model;

[0024] Step S222: deriving the sealing process model equation for the key indicators of the sealing process using the state space model to obtain the sealing process model derivation equation; wherein the sealing process model equation derivation formula is as follows:

[0025] S = f(T, P, t);

[0026] In the formula, S is the sealing quality, T is the temperature, P is the pressure, t is the time, and f(T,P,t) is the sealing process model function;

[0027] The linear regression model is used to derive the closing process model equation for the key indicators of the closing process, and the closing process model derivation equation is obtained; the closing process model equation derivation formula is as follows:

[0028] C = g(Pc, A, R);

[0029] Where C is the lid closing mass, Pc is the applied force, A is the lid position, R is the lid rotation angle, and g(Pc,A,R) is the lid closing process model function;

[0030] The nonlinear regression model is used to derive the capping process model equation for the key indicators of the capping process, and the capping process model derivation equation is obtained; the capping process model equation derivation formula is as follows:

[0031] W = h(F, V, B);

[0032] Where W is the capping mass, F is the applied pressure, V is the capping speed, B is the ambient temperature, and h(F, V, B) is the capping process model function;

[0033] Step S223: Based on the derived equations of the sealing process model, the state space model is model-verified to generate a sealing process mathematical model; based on the derived equations of the capping process model, the linear regression model is model-verified to generate a capping process mathematical model; based on the derived equations of the capping process model, the nonlinear regression model is model-verified to generate a capping process mathematical model;

[0034] Step S224: combining the sealing process mathematical model, the capping process mathematical model and the capping process mathematical model to generate a process step mathematical model.

[0035] The present invention makes the quality monitoring of each link more accurate by selecting the key indicators of the sealing, capping and capping processes, which helps to timely discover and correct production problems. According to the key indicators of the process, a suitable mathematical model is selected to ensure that the model can accurately reflect the dynamic characteristics of each process and improve the effectiveness of prediction and control. The relationship between the sealing quality and temperature, pressure and time is derived by the state space model, which helps process engineers to deeply understand the factors affecting the sealing quality and formulate effective adjustment strategies. The linear regression model is used to derive the relationship between the quality of the capping process and the applied force, the position of the lid and the rotation angle, so as to provide simplified decision support for actual operation. The nonlinear regression model is used to derive the complex relationship between the capping quality and pressure, speed and ambient temperature, so that the model can better adapt to the changes under real production conditions. Based on the derivation equation, each model is verified to ensure that the generated mathematical model can accurately reflect the actual situation of the production process and improve the credibility and practicality of the model. The mathematical models of the sealing, capping and capping processes are combined to form a comprehensive process process mathematical model, which helps to optimize the production process as a whole and improve efficiency and quality control capabilities. Through this series of steps, enterprises can establish a data-based, scientific production process model, which not only improves the controllability and efficiency of each process, but also provides data support for continuous improvement. Ultimately, this refined management helps reduce production costs and improve product quality.

[0036] Preferably, step S224 includes the following steps:

[0037] The mathematical models of the sealing process, the capping process and the pressing process are prioritized, the mathematical model of the sealing process is assigned a high priority, and a high priority mathematical model is generated; the mathematical model of the capping process is assigned a medium priority, and a medium priority mathematical model is generated; the mathematical model of the pressing process is assigned a low priority, and a low priority mathematical model is generated;

[0038] The high-priority mathematical model, the medium-priority mathematical model and the low-priority mathematical model are combined in series to generate a process series mathematical model; a combination equation is constructed for the process series mathematical model to generate a process combination equation, wherein the formula for constructing the combination equation is as follows:

[0039] K=h(f(T1,P1,t1),g(Pc2,A2,R2),h(F3,V3,B3));

[0040] In the formula, K is the process combination equation, f(T1, P1, t1) represents the sealing process model equation executed with the first priority, g(Pc2, A2, R2) represents the closing process model equation executed with the second priority, and h(F3, V3, B3) represents the capping process model equation executed with the third priority;

[0041] The overall performance of the process series mathematical model is evaluated according to the process combination equation to generate model performance evaluation data; based on the model performance evaluation data, the process series mathematical model is optimized to generate a process procedure mathematical model.

[0042] The present invention ensures that the sealing process model is executed preferentially in the overall process by assigning a high priority to the sealing process model, thereby ensuring the stability and consistency of the sealing quality. Setting the capping process model to a medium priority helps to maintain an appropriate execution order between sealing and capping, and optimizes the process connection. Although the capping process is assigned a low priority, it is still ensured that it is reasonably considered in the entire process to avoid a negative impact on the quality of the final product. Combining high, medium and low priority mathematical models in series to form a process series mathematical model helps to optimize each process link as a whole and improve production efficiency. The generated process combination equation K=h(f(T1, P1, t1), g(Pc2, A2, R2), h(F3, V3, B3)) provides a unified mathematical framework so that the influence of each model can be evaluated and optimized as a whole. An overall performance evaluation of the process series mathematical model based on the combination equation helps to discover potential problems in a timely manner and ensure the stability and efficiency of the production process. The process series mathematical model is optimized according to the model performance evaluation data, so that each process can better adapt to changes in actual operation and improve overall production efficiency and product quality. By prioritizing and combining the sealing, capping and capping process models, companies can achieve a more efficient production process. This approach not only ensures coordination and cooperation among all links, but also provides data support and decision-making basis for the continuous optimization of production, ultimately improving product quality.

[0043] Preferably, the process of adaptively controlling the process operation position of the container to be sealed according to the sealed container state prediction data includes:

[0044] The container to be sealed and the process equipment are three-dimensionally scanned by a laser sensor to obtain three-dimensional scanning data of the container to be sealed and three-dimensional scanning data of the process equipment; the sealing center point position of the container to be sealed is confirmed based on the three-dimensional scanning data of the container to be sealed to obtain the center point position data of the container to be sealed;

[0045] Confirm the edge position of the three-dimensional scanning data of the process equipment to obtain the edge position data of the process equipment; discretize and connect the edge position data of the process equipment to generate the operation range of the process equipment; calculate the center point position data of the container to be sealed and the operation range of the process equipment, and when the center point position data of the container to be sealed is within the operation range of the process equipment, calibrate the container to be sealed around the center point according to the sealed container state prediction data to generate the first process calibration data;

[0046] When the center point position data of the container to be sealed is not within the operating range of the process equipment, the offset calculation is performed on the container to be sealed according to the sealed container state prediction data to obtain the offset data of the container to be sealed; the spatial flip calibration is performed on the container to be sealed based on the offset data of the container to be sealed to generate the second process calibration data;

[0047] The first process calibration data and the second process calibration data are calibrated and integrated to generate process operation position adaptive control data.

[0048] The present invention uses a laser sensor to perform three-dimensional scanning on the container to be sealed and the process equipment to obtain high-precision three-dimensional data, ensuring that the geometric shapes of the container and the equipment are accurately captured. The position of the sealing center point is confirmed by the three-dimensional scanning data of the container to be sealed, ensuring the accuracy of subsequent process operations, and reducing production errors caused by inaccurate positions. Determining the edge position of the process equipment helps to define the operating range of the equipment and improve the safety and controllability of the operation. By discretizing and connecting the edge position data of the process equipment, a clear operating range is generated, which provides a reference for subsequent calibration and control. When the center point of the container to be sealed is within the operating range of the process equipment, calibration around the center point is performed to ensure that the container is correctly positioned. The generated first process calibration data improves the efficiency and accuracy of the sealing operation. When the center point of the container to be sealed is not within the operating range, the second process calibration data is generated by offset calculation and spatial flip calibration. This flexible adjustment method improves the adaptability and fault tolerance of the production process. The first process calibration data and the second process calibration data are integrated to generate comprehensive process operation orientation adaptive control data to ensure that the sealing operation can be effectively supported in various situations. Through precise adaptive control, repeated adjustments and downtime caused by position deviations are reduced, thereby improving overall production efficiency and output. Through the implementation of the above steps, the process operation position adaptive control can ensure the accurate positioning and calibration of the container to be sealed, and improve the stability and reliability of the production process. This method not only optimizes the operation process, but also provides a solid foundation for subsequent production quality, which helps to improve product consistency and quality.

[0049] Preferably, step S24 includes the following steps:

[0050] Step S241: dynamically collect real-time data of the sealing process, the capping process and the capping process according to the process operation position adaptive control data to obtain a real-time operation data stream;

[0051] Step S242: extract key indicators and trends from the real-time operation data stream to generate key performance indicators and dynamic trend mapping data; aggregate the real-time operation data stream based on the key performance indicators and dynamic trend mapping data to generate real-time operation summary data;

[0052] Step S243: Perform real-time data update on the real-time operation summary data to generate real-time operation summary update data; perform data visualization on the real-time operation summary update data to generate a real-time operation panel; integrate warning rules on the real-time operation panel according to a preset warning threshold, thereby generating a real-time production status panel.

[0053] The present invention collects data of sealing, capping and capping processes in real time by adaptively controlling data according to the process operation position, thereby ensuring real-time monitoring and feedback of the production process. By extracting key indicators and trends from the real-time operation data stream, generating key performance indicators (KPI) and dynamic trend mapping data, it is helpful to timely identify abnormal situations in the production process. Data aggregation is performed based on key performance indicators and dynamic trend data to generate real-time operation summary data, provide a comprehensive overview of production status, and support decision making. The real-time operation summary data is updated in real time to generate real-time operation summary update data to ensure the timeliness and accuracy of production status information, so as to facilitate timely adjustment of production strategies. A real-time operation panel is generated through data visualization to improve the intuitiveness and comprehensibility of information transmission, so that operators can quickly grasp production dynamics and improve response speed. According to the preset warning threshold, the real-time operation panel is integrated with warning rules to timely identify potential risks and abnormal situations to prevent the occurrence of production failures. By generating a real-time production status panel, operators can quickly take measures to deal with abnormalities, reduce downtime, and improve production efficiency. By implementing step S24, the dynamic data collection and processing of process operations significantly improves the visual monitoring and real-time feedback capabilities of the production process. This systematic approach not only enhances the understanding of the production status, but also promotes the timeliness and accuracy of decision-making, providing important support for improving overall production efficiency and quality.

[0054] Preferably, step S3 comprises the following steps:

[0055] Step S31: construct monitoring nodes for the sealing process, the capping process and the capping process through the real-time production status panel to generate real-time production status monitoring nodes;

[0056] Step S32: abnormal node monitoring is performed on the real-time production status monitoring nodes to obtain abnormal nodes and normal nodes; the number of nodes of the abnormal nodes and the normal nodes are compared, and when the number of nodes of the abnormal nodes is greater than or equal to the number of nodes of the normal nodes, the corresponding process equipment of the sealing process, the capping process and the capping process is closed to generate a high abnormal process strategy;

[0057] Step S33: When the number of abnormal nodes is less than the number of normal nodes, the sealing process, the capping process and the pressing process are repaired accordingly according to the abnormal nodes to generate a low-abnormal process strategy; the high-abnormal process strategy and the low-abnormal process strategy are integrated to generate a collaborative process execution strategy.

[0058] The present invention constructs monitoring nodes of sealing, capping and capping processes through a real-time production status panel, ensures that all links of the production process are within the monitoring range, and is convenient for real-time acquisition of status information. By performing abnormal node monitoring on the real-time production status monitoring node, abnormal situations in the production process can be quickly identified, and data support can be provided for subsequent processing. By comparing the number of abnormal nodes with the number of normal nodes, the production status can be quickly judged to form a basis for decision-making. When the number of abnormal nodes is greater than or equal to the number of normal nodes, the relevant process equipment is shut down in time to avoid the expansion of potential risks, ensure production safety, generate high-abnormal process strategies, ensure that the production process can effectively respond to emergencies, and reduce production losses. When the number of abnormal nodes is less than the number of normal nodes, process equipment maintenance is performed on the abnormal nodes to ensure the normal operation of the equipment, reduce the impact of faults on production, generate low-abnormal process strategies, promote continuous optimization and improvement of the production process, and improve overall production efficiency. Through the integration of high-abnormal process strategies and low-abnormal process strategies, a collaborative process execution strategy is generated to achieve comprehensive management and control of the production process. The collaborative process execution strategy enables the production process to be dynamically adjusted according to real-time data, improve response speed, and optimize resource allocation. Through real-time monitoring and intelligent decision-making mechanisms, the management capabilities of sealing, capping and pressing processes have been effectively improved. This systematic monitoring and response mechanism not only enhances the safety of the production process, but also promotes the timeliness and efficiency of equipment maintenance, providing strong support for improving production stability and efficiency.

[0059] Preferably, step S4 comprises the following steps:

[0060] Step S41: implementing feedback on the collaborative process execution strategy to generate collaborative process implementation feedback data; dynamically adjusting the collaborative process execution strategy according to the collaborative process implementation feedback data to generate a collaborative process dynamic adjustment strategy;

[0061] Step S42: Perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy, generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to execute the collaborative process optimization operation of integrated sealing.

[0062] The present invention implements feedback on the collaborative process execution strategy and generates implementation feedback data to ensure that every link in the production process is monitored and recorded. According to the implementation feedback data, problems in process execution can be discovered in time, providing a basis for subsequent adjustments. The collaborative process execution strategy is dynamically adjusted using the implementation feedback data, so that the process execution can quickly adapt to changes in the production environment and improve production flexibility. The generated collaborative process dynamic adjustment strategy makes production decisions more scientific and accurate, thereby optimizing overall production efficiency. The real-time production status panel is closed-loop controlled according to the dynamic adjustment strategy to ensure that all indicators in the production process are always in a controllable state. The closed-loop control mechanism improves the stability of the production process and effectively reduces the risks brought by production fluctuations. The collaborative process closed-loop control data is uploaded to the cloud server for storage, which is convenient for centralized management and long-term preservation, improves the security and accessibility of the data, and the generated collaborative process control traceability data provides a basis for subsequent analysis, auditing and optimization, which helps to improve the transparency and traceability of the process. Through the optimization operation of the collaborative process, the integrated management of the sealing process is realized, and the production efficiency and quality are improved. By implementing mechanisms such as feedback, dynamic adjustment and closed-loop control, comprehensive optimization and control of collaborative processes have been achieved. This systematic management method not only enhances the adaptability and stability of the production process, but also improves the transparency and traceability of the process, laying the foundation for the continuous improvement of production efficiency.

[0063] In this specification, a sealing integrated collaborative process optimization system is provided, which is used to execute the above-mentioned sealing integrated collaborative process optimization method, and the sealing integrated collaborative process optimization system includes:

[0064] A data acquisition module is used to obtain sealing process data; perform sensor data acquisition based on the sealing process data to obtain a multimodal sensor acquisition data set; perform data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set;

[0065] The process optimization module is used to analyze the process flow of the sealing process data and generate the sealing process flow data, wherein the sealing process flow data includes the sealing process, the capping process and the capping process; to perform intelligent process modeling on the sealing process, the capping process and the capping process and generate a process process mathematical model; to use the process process data model to perform adaptive control of the process operation position of the container to be sealed and generate a real-time production status panel;

[0066] The process monitoring and early warning module is used to construct monitoring nodes for the sealing process, capping process and capping process through the real-time production status panel to generate real-time production status monitoring nodes; perform abnormal node monitoring on the real-time production status monitoring nodes to generate abnormal nodes and normal nodes; perform collaborative process strategy execution based on abnormal nodes and normal nodes to generate collaborative process execution strategies;

[0067] The feedback module is used to dynamically adjust the collaborative process execution strategy and generate a collaborative process dynamic adjustment strategy; perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy, generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to execute integrated sealing collaborative process optimization operations.

[0068] The beneficial effect of the present invention is that high-quality data input is ensured through the acquisition and standardized processing of multimodal sensor data, reducing errors caused by incomplete or inconsistent data. In-depth analysis and modeling of the sealing, capping and capping processes make the operating mechanism of each process clearer, which helps to find potential bottlenecks and improvement points. The establishment of a real-time production status panel enables key parameters in the production process to be monitored in real time, and abnormalities are identified and handled in a timely manner, effectively reducing production risks. Based on abnormality detection of monitoring nodes, collaborative process strategies can be automatically generated, which improves the level of intelligent decision-making and reduces the need for manual intervention. Through the dynamic adjustment of collaborative process execution strategies, the production process can be self-optimized according to real-time feedback, so as to adapt to different production environments and demand changes. The generation and cloud storage of collaborative process closed-loop control data enhances the global control ability of the production process, helps long-term data analysis and tracking, and supports continuous improvement. The overall optimized process significantly reduces invalid operations and resource waste, and improves the overall efficiency and output of the production line. Through real-time monitoring and intelligent adjustment, the compliance of each production link is ensured, thereby improving the quality consistency of the final product. Therefore, the present invention improves the flexibility and adaptability of the sealing process management through multimodal data collection, detailed process flow analysis, real-time monitoring and dynamic adjustment strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic diagram of the steps of a collaborative process optimization method for sealing integration;

[0070] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0071] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0072] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0073] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0074] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0075] It should be understood that although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0076] To achieve this, please refer to Figures 1 to 3 , a collaborative process optimization method for sealing integration, the method comprising the following steps:

[0077] Step S1: Acquire sealing process data; perform sensor data acquisition according to the sealing process data to obtain a multimodal sensor acquisition data set; perform data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set;

[0078] Step S2: Perform process flow analysis on the sealing process data to generate sealing process flow data, wherein the sealing process flow data includes sealing process, capping process and capping process; perform intelligent process modeling on the sealing process, capping process and capping process to generate a process process mathematical model; use the process process data model to perform process operation position adaptive control on the container to be sealed to generate a real-time production status panel;

[0079] Step S3: construct monitoring nodes for the sealing process, the capping process and the capping process through the real-time production status panel to generate real-time production status monitoring nodes; perform abnormal node monitoring on the real-time production status monitoring nodes to generate abnormal nodes and normal nodes; perform collaborative process strategy execution based on the abnormal nodes and normal nodes to generate a collaborative process execution strategy;

[0080] Step S4: Dynamically adjust the collaborative process execution strategy to generate a collaborative process dynamic adjustment strategy; perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy to generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to perform integrated sealing collaborative process optimization operations.

[0081] The present invention can fully understand various parameters in the sealing process by acquiring sealing process data and performing sensor data collection, thereby ensuring the integrity and accuracy of the data. Data preprocessing generates a standard multimodal sensor acquisition data set, which provides a high-quality data basis for subsequent analysis and modeling, and reduces the impact of noise and errors on the model. The sealing process flow data generated by process flow analysis helps to identify and optimize the key links in the sealing, capping and capping processes, thereby improving the overall process efficiency. Intelligent process modeling makes the sealing process more scientific, provides decision support in a data-driven manner, and improves the accuracy of process operations. The real-time production status panel generated by the process operation position adaptive control can monitor the production status in real time, which is convenient for rapid response and adjustment. By constructing real-time production status monitoring nodes, the monitoring capability of the production process is enhanced, and potential problems can be discovered in a timely manner. The monitoring of abnormal nodes and normal nodes enables the rapid identification of abnormalities in the process, provides timely adjustment solutions, and reduces production risks. The collaborative process execution strategy generated based on the abnormal nodes can effectively integrate the operations of each process and improve the overall production efficiency. The strategy dynamic adjustment mechanism enables the system to self-optimize according to real-time data, thereby improving the flexibility and adaptability of the system. Closed-loop control is performed on the real-time production status panel to ensure the stability of various indicators in the production process, reduce fluctuations and errors, and improve product quality. Uploading the collaborative process closed-loop control data to the cloud server for storage not only ensures the security and traceability of the data, but also provides a basis for subsequent analysis and improvement. The generated collaborative process control traceability data can provide a basis for the collaborative process optimization operation of integrated sealing, and promote the continuous improvement of overall production efficiency. Therefore, the present invention improves the flexibility and adaptability of the sealing process production process management through multimodal data acquisition, detailed process flow analysis, real-time monitoring and dynamic adjustment strategies.

[0082] In the embodiment of the present invention, reference Figure 1The above is a schematic flow chart of the steps of a collaborative process optimization method for integrated sealing of the present invention. In this example, the collaborative process optimization method for integrated sealing includes the following steps:

[0083] Step S1: Acquire sealing process data; perform sensor data acquisition according to the sealing process data to obtain a multimodal sensor acquisition data set; perform data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set;

[0084] In an embodiment of the present invention, by determining the type of sealing process data that needs to be collected (such as temperature, pressure, humidity, etc.). The time interval and frequency of data collection are clarified. Specific sensors (such as temperature sensors, pressure sensors, humidity sensors, etc.) are selected according to the characteristics of the sealing process. Ensure that the sensor has sufficient accuracy and response speed. Install the sensor at the key position of the sealing equipment to ensure that the relevant data can be accurately captured. Set the parameters of the data acquisition system, including sampling rate, data format, etc. Ensure that the data acquisition system can simultaneously receive data from multimodal sensors. Start the data acquisition system and continuously record sensor data during the operation of the sealing process. Check the working status of the sensor regularly to ensure the reliability of data acquisition. Clean the collected raw data to remove noise and outliers. Check data integrity and fill in missing values. Standardize the data of different sensors for subsequent analysis. Use normalization or standardization methods to make all types of data in the same range. Integrate the processed multimodal sensor data into a standard data set to ensure data consistency and comparability, and store the data set for subsequent analysis.

[0085] Step S2: Perform process flow analysis on the sealing process data to generate sealing process flow data, wherein the sealing process flow data includes sealing process, capping process and capping process; perform intelligent process modeling on the sealing process, capping process and capping process to generate a process process mathematical model; use the process process data model to perform process operation position adaptive control on the container to be sealed to generate a real-time production status panel;

[0086] In the embodiment of the present invention, by clarifying the analysis target, including identifying the key steps and parameters of the sealing process, the capping process and the capping process. The sealing process data is organized into a flow chart or a table form for subsequent analysis. The input, output and key parameters (such as temperature, pressure, time, etc.) of each process are recorded. Based on the organized data, a detailed description of the sealing process, the capping process and the capping process is generated. Ensure that the sequence, steps and conditions of each process are clearly visible. Select a suitable modeling method (such as a state machine model, a Petri net, a dynamic system model, etc.) according to the characteristics of the process. Use the collected process flow data to construct a mathematical model of the sealing process, the capping process and the capping process. Determine the input variables, state variables and output variables of the model, and establish corresponding mathematical relationships. Verify the accuracy of the model through historical data or experimental data. Optimize the model parameters according to the verification results to improve the prediction ability of the model. Design an adaptive control strategy based on the generated process data model to ensure the operational flexibility of the container to be sealed. Define the logic of the adaptive control algorithm, including the response mechanism for different container types and states. Monitor the various parameters of the sealing process in real time, and obtain the current production status through sensor data. Compare real-time data with model outputs to adjust process operations. Design and implement real-time production status panels to display real-time status information of sealing, capping and capping processes, including visualization of key parameters (such as temperature, pressure, production progress, etc.) so that operators can make timely adjustments.

[0087] Step S3: construct monitoring nodes for the sealing process, the capping process and the capping process through the real-time production status panel to generate real-time production status monitoring nodes; perform abnormal node monitoring on the real-time production status monitoring nodes to generate abnormal nodes and normal nodes; perform collaborative process strategy execution based on the abnormal nodes and normal nodes to generate a collaborative process execution strategy;

[0088] In an embodiment of the present invention, by determining the key monitoring points in the sealing process, the capping process and the capping process, such as temperature, pressure, speed and time, each monitoring node should be able to reflect the key status and parameters of the process. In the real-time production status panel, create a monitoring node and assign the corresponding sensor data. Ensure that each monitoring node can update the status information in real time and store the data in a centralized manner. Develop an anomaly detection algorithm, use statistical methods or machine learning models to identify abnormal patterns based on real-time data. Determine thresholds and standards, and set normal ranges to facilitate identification of abnormal nodes. Monitor the data of each monitoring node in real time and compare the difference between the current value and the normal value. Generate a classification of abnormal nodes and normal nodes based on the anomaly detection algorithm. Establish a monitoring record system to save the results of each monitoring, including detailed information and timestamps of abnormal nodes. Design a collaborative process strategy based on the information of abnormal nodes and normal nodes. The strategy should include how to handle abnormal states and adjust process parameters. Considering different types of abnormalities, formulate specific countermeasures and process adjustment plans. Build a strategy execution system to automatically trigger corresponding process adjustments or warnings based on the status of the monitoring nodes. Ensure that the system can quickly execute the preset collaborative process strategy when an abnormality is found. The execution status of collaborative process execution strategies is recorded in real time, including measures taken, adjusted parameters and result feedback, and reports are generated for subsequent analysis and improvement to ensure continuous optimization of the production process.

[0089] Step S4: Dynamically adjust the collaborative process execution strategy to generate a collaborative process dynamic adjustment strategy; perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy to generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to perform integrated sealing collaborative process optimization operations.

[0090] In the embodiment of the present invention, by determining the key parameters that need to be dynamically adjusted, such as temperature, pressure, speed and operation time, etc., establish the standard of dynamic adjustment, and modify the collaborative process execution strategy according to the data feedback of the real-time monitoring node. According to the real-time production status and the abnormal detection results, adjust the process parameters to optimize the production process. Record the parameter changes of each dynamic adjustment to ensure the transparency of the adjustment process. Summarize the dynamic adjustment strategy to form a collaborative process dynamic adjustment strategy document to ensure the traceability of the adjustment process. Design a closed-loop control system and embed the collaborative process dynamic adjustment strategy into the production control process. Ensure that the system can feedback the production status in real time and automatically optimize the operation according to the adjustment strategy. Monitor the production status panel in real time and analyze the difference between the current state and the preset target. According to the collaborative process dynamic adjustment strategy, automatically adjust the process parameters to form a closed-loop control. All data involved in the closed-loop control process (including monitoring data, adjustment strategy, execution results, etc.) are summarized to form a closed-loop control data set. Configure the cloud server to ensure that it can accept and store closed-loop control data. Design a data upload interface to support efficient data transmission. Upload the generated collaborative process closed-loop control data to the cloud server to ensure the security and integrity of the data. Back up data regularly to prevent data loss. Establish a database in the cloud server to store uploaded collaborative process closed-loop control data for subsequent query and analysis. Record the decision-making process, parameter adjustment and results of each control to provide a basis for subsequent collaborative process optimization.

[0091] Preferably, step S1 comprises the following steps:

[0092] Step S11: Acquire sealing process data;

[0093] Step S12: Arrange sensors according to the sealing process data to generate sealing process sensor deployment data; configure edge computing nodes for the sealing process sensor deployment data to obtain sealing process edge computing nodes;

[0094] Step S13: performing sensor data collection on the edge computing nodes of the sealing process based on a preset data collection frequency to obtain a multimodal sensor collection data set;

[0095] Step S14: performing data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set, wherein the data preprocessing includes noise filtering, data smoothing, and missing value interpolation.

[0096] In an embodiment of the present invention, raw data related to the sealing process is obtained from the production line, including equipment status, operator information, process time and environmental conditions, etc., which can be obtained through historical records or real-time monitoring systems. According to the key parameters of the sealing process (such as temperature, pressure, humidity, etc.), the type and number of sensors are determined, and the layout of the sensors is designed to ensure that the process can be fully monitored. According to the sensor layout plan, the edge computing node is configured, and the specific hardware and software platform is selected to ensure that the data can be processed and analyzed near the source, reducing delays and improving efficiency. Based on the preset data acquisition frequency (such as once per second), real-time acquisition of sensor data is performed from the edge computing node of the sealing process to form a multimodal sensor acquisition data set. This data set should include synchronous data from different sensors for subsequent analysis. Apply filtering algorithms (such as Kalman filtering or median filtering) to remove random noise in sensor data and improve data quality. Use moving average or exponential smoothing techniques to smooth the data and reduce data volatility. For the missing parts in the data set, interpolation methods (such as linear interpolation, spline interpolation, etc.) are used to fill in to ensure data integrity. Finally, the multimodal sensor data set collected after the above preprocessing will be standardized for subsequent analysis and application.

[0097] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0098] Step S21: performing process flow analysis on the sealing process data to generate sealing process flow data, wherein the sealing process flow data includes a sealing process, a capping process, and a capping process; classifying the process data of the standard multimodal sensor acquisition data set according to the sealing process, the capping process, and the capping process to generate process classification sensor data;

[0099] Step S22: Intelligent process modeling is performed on the sealing process, the capping process and the capping process through process classification sensor data to generate a process procedure mathematical model;

[0100] Step S23: using the process data model to predict the state of the container to be sealed for the sealing process, the capping process and the capping process, and generating sealed container state prediction data; performing process operation position adaptive control on the container to be sealed according to the sealed container state prediction data, and generating process operation position adaptive control data;

[0101] Step S24: Based on the process operation position adaptive control data, the sealing process, the capping process and the capping process are visualized in real time, thereby generating a real-time production status panel.

[0102] In an embodiment of the present invention, by collecting relevant data of the sealing process, analyzing the key parameters and operation steps of different stages (sealing, capping, and capping), the sealing process flow data is generated, including a detailed description of the sealing process, the capping process, and the capping process. According to the generated sealing process flow data, the standard multimodal sensor acquisition data set is classified. A classification algorithm (such as a support vector machine or a decision tree) is developed to annotate the sensor data and generate process classification sensor data so that it can reflect the status of different process stages. Using the process classification sensor data, an intelligent process model for the sealing, capping, and capping processes is established. Machine learning techniques (such as deep learning) and mathematical modeling methods are used to generate a mathematical model of the process process to capture the relationship between process parameters and product quality. Using the process process data model, a state prediction is performed based on the characteristics and current state of the container to be sealed. Using regression analysis or time series analysis, the state prediction data of the sealed container is generated to provide an expected evaluation of the container quality. According to the state prediction data of the sealed container, the process operation position adaptive control is implemented to dynamically adjust the operation position of sealing, capping, and capping. Develop control algorithms to ensure that appropriate operation strategies are adopted under different conditions and generate process operation position adaptive control data. Develop a real-time data visualization platform based on process operation position adaptive control data. Use data visualization tools (such as dashboards or charts) to display the real-time production status of the sealing process, capping process, and capping process, and generate a real-time production status panel. Ensure that the visualization content includes the key parameters, status prediction information, and control response of each process, so that operators can monitor and adjust the production process in real time.

[0103] Preferably, step S22 includes the following steps:

[0104] Step S221: selecting key process indicators for the sealing process, the capping process and the capping process to obtain key process indicator data, wherein the key process indicator data include key process indicators for the sealing process, key process indicators for the capping process and key process indicators for the capping process; selecting a mathematical model according to the key process indicator data to generate mathematical model selection data, wherein the mathematical model selection data include a state space model, a linear regression model and a nonlinear regression model;

[0105] Step S222: deriving the sealing process model equation for the key indicators of the sealing process using the state space model to obtain the sealing process model derivation equation; wherein the sealing process model equation derivation formula is as follows:

[0106] S = f(T, P, t);

[0107] In the formula, S is the sealing quality, T is the temperature, P is the pressure, t is the time, and f(T,P,t) is the sealing process model function;

[0108] The linear regression model is used to derive the closing process model equation for the key indicators of the closing process, and the closing process model derivation equation is obtained; the closing process model equation derivation formula is as follows:

[0109] C = g(Pc, A, R);

[0110] Where C is the lid closing mass, Pc is the applied force, A is the lid position, R is the lid rotation angle, and g(Pc,A,R) is the lid closing process model function;

[0111] The nonlinear regression model is used to derive the capping process model equation for the key indicators of the capping process, and the capping process model derivation equation is obtained; the capping process model equation derivation formula is as follows:

[0112] W = h(F, V, B);

[0113] Where W is the capping mass, F is the applied pressure, V is the capping speed, B is the ambient temperature, and h(F, V, B) is the capping process model function;

[0114] Step S223: Based on the derived equations of the sealing process model, the state space model is model-verified to generate a sealing process mathematical model; based on the derived equations of the capping process model, the linear regression model is model-verified to generate a capping process mathematical model; based on the derived equations of the capping process model, the nonlinear regression model is model-verified to generate a capping process mathematical model;

[0115] Step S224: combining the sealing process mathematical model, the capping process mathematical model and the capping process mathematical model to generate a process step mathematical model.

[0116] In an embodiment of the present invention, the key factors affecting the quality are identified by analyzing the production data of the sealing, capping and capping processes. Statistical analysis methods (such as variance analysis or correlation analysis) are used to determine key indicators and generate process key indicator data, including: sealing process key indicators: such as temperature, pressure, time, capping process key indicators: such as applied force, lid position, rotation angle, capping process key indicators: such as applied pressure, capping speed, ambient temperature. According to the selected process key indicator data, a specific mathematical model is evaluated. Use model selection criteria (such as AIC, BIC) for evaluation, select a suitable model, and generate mathematical model selection data, including: state space model, linear regression model, nonlinear regression model. Based on the state space model, the key indicators of the sealing process are modeled, and the sealing process model equation is derived: S = f (T, P, t); where S is the sealing quality, T is the temperature, P is the pressure, t is the time, and f (T, P, t) is the sealing process model function; using the linear regression model, the key indicators of the lid closing process are modeled, and the lid closing process model equation is derived: C = g (Pc, A, R); where C is the lid closing quality, Pc is the applied force, A is the lid position, and R is the lid rotation angle , g(Pc,A,R) is the function of the capping process model; the nonlinear regression model is used to model the key indicators of the capping process, and the capping process model equation is derived: W=h(F,V,B); where W is the capping quality, F is the applied pressure, V is the capping speed, B is the ambient temperature, and h(F,V,B) is the function of the capping process model; the actual data collected are used to verify the derived equation of the sealing process model, evaluate the goodness of fit and prediction ability of the model, and generate a mathematical model of the sealing process. The relevant data of the capping process are used to verify the validity of the derived equation of the capping process model and generate a mathematical model of the capping process. The actual data of the capping process are used to verify the model and generate a mathematical model of the capping process. The verified mathematical model of the sealing process, the mathematical model of the capping process and the mathematical model of the capping process are combined to form a comprehensive mathematical model of the process. The combined model should be able to reflect the dynamic changes of the entire sealing process and provide a basis for real-time monitoring and optimization.

[0117] Preferably, step S224 includes the following steps:

[0118] The mathematical models of the sealing process, the capping process and the pressing process are prioritized, the mathematical model of the sealing process is assigned a high priority, and a high priority mathematical model is generated; the mathematical model of the capping process is assigned a medium priority, and a medium priority mathematical model is generated; the mathematical model of the pressing process is assigned a low priority, and a low priority mathematical model is generated;

[0119] The high-priority mathematical model, the medium-priority mathematical model and the low-priority mathematical model are combined in series to generate a process series mathematical model; a combination equation is constructed for the process series mathematical model to generate a process combination equation, wherein the formula for constructing the combination equation is as follows:

[0120] K=h(f(T1,P1,t1),g(Pc2,A2,R2),h(F3,V3,B3));

[0121] In the formula, K is the process combination equation, f(T1, P1, t1) represents the sealing process model equation executed with the first priority, g(Pc2, A2, R2) represents the closing process model equation executed with the second priority, and h(F3, V3, B3) represents the capping process model equation executed with the third priority;

[0122] The overall performance of the process series mathematical model is evaluated according to the process combination equation to generate model performance evaluation data; based on the model performance evaluation data, the process series mathematical model is optimized to generate a process procedure mathematical model.

[0123] In an embodiment of the present invention, by evaluating the sealing process mathematical model, the capping process mathematical model and the capping process mathematical model, the priority is sorted based on their impact and importance on the overall process. The sealing process mathematical model is assigned a high priority to generate a high priority mathematical model. The capping process mathematical model is assigned a medium priority to generate a medium priority mathematical model. The capping process mathematical model is assigned a low priority to generate a low priority mathematical model. The high priority mathematical model, the medium priority mathematical model and the low priority mathematical model are combined in series to form a process series mathematical model. Based on the process series mathematical model, a combination equation is constructed to generate a process combination equation. The construction formula of the combination equation is: K=h(f(T1, P1, t1), g(Pc2, A2, R2), h(F3, V3, B3)), and the overall performance of the process series mathematical model is evaluated according to the process combination equation to generate model performance evaluation data. The evaluation content includes execution efficiency, resource consumption, stability, etc. Based on the model performance evaluation data, the process series mathematical model is optimized, the parameters are adjusted or the model structure is improved, so as to generate an optimized process process mathematical model.

[0124] Preferably, the process of adaptively controlling the process operation position of the container to be sealed according to the sealed container state prediction data includes:

[0125] The container to be sealed and the process equipment are three-dimensionally scanned by a laser sensor to obtain three-dimensional scanning data of the container to be sealed and three-dimensional scanning data of the process equipment; the sealing center point position of the container to be sealed is confirmed based on the three-dimensional scanning data of the container to be sealed to obtain the center point position data of the container to be sealed;

[0126] Confirm the edge position of the three-dimensional scanning data of the process equipment to obtain the edge position data of the process equipment; discretize and connect the edge position data of the process equipment to generate the operation range of the process equipment; calculate the center point position data of the container to be sealed and the operation range of the process equipment, and when the center point position data of the container to be sealed is within the operation range of the process equipment, calibrate the container to be sealed around the center point according to the sealed container state prediction data to generate the first process calibration data;

[0127] When the center point position data of the container to be sealed is not within the operating range of the process equipment, the offset calculation is performed on the container to be sealed according to the sealed container state prediction data to obtain the offset data of the container to be sealed; the spatial flip calibration is performed on the container to be sealed based on the offset data of the container to be sealed to generate the second process calibration data;

[0128] The first process calibration data and the second process calibration data are calibrated and integrated to generate process operation position adaptive control data.

[0129] In an embodiment of the present invention, a laser sensor is installed at a fixed position or on a movable platform. The laser sensor emits a laser beam and receives the reflected signal, calculates the distance of the object by the time difference, and generates three-dimensional point cloud data. The acquired point cloud data is converted into a visualized three-dimensional model using point cloud processing software. The three-dimensional model of the container to be sealed is processed, and feature points are extracted to identify the sealing center point. An edge detection algorithm (such as Canny or Sobel) is applied to extract edges on the three-dimensional model of the process equipment to obtain edge position data. The center point position data of the container to be sealed is aligned with the edge position data of the process equipment. A geometric algorithm (such as distance calculation, center of gravity calculation, etc.) is used to determine whether the container to be sealed is within the operating range of the process equipment. If the center point of the container to be sealed is within the operating range, a calibration algorithm around the center point is applied to generate the first process calibration data by adjusting the parameters. If the center point of the container to be sealed is not within the operating range, an offset calculation algorithm is applied to determine the distance and direction that the container needs to be offset, and the offset data of the container to be sealed is calculated to perform spatial flip calibration. The first process calibration data and the second process calibration data are merged, and the final process operation position adaptive control data is generated using techniques such as weighted average method or least square method. Sensors are embedded in the process equipment to monitor the sealing process in real time. The real-time data is compared with the adaptive control data, and the process operation parameters are continuously adjusted according to the actual situation to ensure the accuracy of the sealing process.

[0130] Preferably, step S24 includes the following steps:

[0131] Step S241: dynamically collect real-time data of the sealing process, the capping process and the capping process according to the process operation position adaptive control data to obtain a real-time operation data stream;

[0132] Step S242: extract key indicators and trends from the real-time operation data stream to generate key performance indicators and dynamic trend mapping data; aggregate the real-time operation data stream based on the key performance indicators and dynamic trend mapping data to generate real-time operation summary data;

[0133] Step S243: Perform real-time data update on the real-time operation summary data to generate real-time operation summary update data; perform data visualization on the real-time operation summary update data to generate a real-time operation panel; integrate warning rules on the real-time operation panel according to a preset warning threshold, thereby generating a real-time production status panel.

[0134] In an embodiment of the present invention, the sealing process, the lid closing process and the capping process are monitored in real time by using sensors (such as temperature, pressure, and vibration sensors) and a data acquisition system. Corresponding sensors are installed in each process link (sealing, lid closing, and capping). Data acquisition equipment is set up and all sensors are connected to ensure that data can be acquired and transmitted in real time. The collected real-time operation data is transmitted to the central control system through the network to form a real-time operation data stream. Data analysis algorithms and tools (such as Python and MATLAB) are applied to process the real-time data stream. Key performance indicators (KPIs) are defined, such as production efficiency, failure rate, energy consumption, etc. Trend information in the data stream is extracted using statistical methods (such as moving average and regression analysis) to generate dynamic trend mapping data. Data aggregation is performed on the real-time operation data stream, multiple KPIs are integrated, and real-time operation summary data is generated. Real-time databases (such as InfluxDB and TimescaleDB) and visualization tools (such as Tableau and Power BI) are used for data processing and display. The real-time operation summary data is imported into the real-time database for instant data update to generate real-time operation summary update data. Use visualization tools to convert the summary update data into visualization formats such as charts and dashboards to generate real-time operation panels. Set rules based on preset warning thresholds, and trigger warning mechanisms when key indicators exceed thresholds. Integrate warning information, update real-time operation panels, and generate real-time production status panels for operators and managers to monitor in real time.

[0135] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0136] Step S31: construct monitoring nodes for the sealing process, capping process and capping process through the real-time production status panel to generate real-time production status monitoring nodes;

[0137] Step S32: abnormal node monitoring is performed on the real-time production status monitoring nodes to obtain abnormal nodes and normal nodes; the number of nodes of the abnormal nodes and the normal nodes are compared, and when the number of nodes of the abnormal nodes is greater than or equal to the number of nodes of the normal nodes, the corresponding process equipment of the sealing process, the capping process and the capping process is closed to generate a high abnormal process strategy;

[0138] Step S33: When the number of abnormal nodes is less than the number of normal nodes, the sealing process, the capping process and the pressing process are repaired accordingly according to the abnormal nodes to generate a low-abnormal process strategy; the high-abnormal process strategy and the low-abnormal process strategy are integrated to generate a collaborative process execution strategy.

[0139] In an embodiment of the present invention, by determining the key monitoring nodes in the sealing process, the capping process and the capping process, such as temperature, pressure, speed, etc., the data of the above monitoring nodes are collected in real time by sensors to form real-time production status monitoring nodes. A monitoring node model is established based on the collected data to ensure the real-time update and accuracy of the data. An abnormality detection algorithm (such as a statistical control chart, a machine learning model) is applied to monitor the real-time production status monitoring nodes. An abnormality detection is performed on the real-time monitoring nodes to identify abnormal nodes (such as nodes exceeding a preset threshold) and normal nodes. The monitored nodes are divided into abnormal nodes and normal nodes, and the number of each is recorded. The number of abnormal nodes and normal nodes is compared. If the number of abnormal nodes is greater than or equal to the number of normal nodes, a process equipment shutdown strategy is executed. If the number of abnormal nodes is less than the number of normal nodes, a maintenance strategy is performed. When the number of abnormal nodes is greater than or equal to the number of normal nodes, a high abnormal process strategy is generated, and the corresponding process equipment shutdown operations of the sealing process, the capping process and the capping process are executed to ensure safety. When the number of abnormal nodes is less than the number of normal nodes, according to the state of the abnormal nodes, the process equipment maintenance of the sealing process, the capping process and the capping process is arranged to generate a low abnormal process strategy. Integrate high-abnormal process strategies and low-abnormal process strategies to generate collaborative process execution strategies to optimize equipment operation and maintenance efficiency.

[0140] Preferably, step S4 comprises the following steps:

[0141] Step S41: implementing feedback on the collaborative process execution strategy to generate collaborative process implementation feedback data; dynamically adjusting the collaborative process execution strategy according to the collaborative process implementation feedback data to generate a collaborative process dynamic adjustment strategy;

[0142] Step S42: Perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy, generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to execute the collaborative process optimization operation of integrated sealing.

[0143] In an embodiment of the present invention, collaborative process implementation feedback data is generated by collecting real-time data during the execution of the collaborative process, including information such as equipment operating status, product quality, and production efficiency. The implementation feedback data is analyzed to identify deficiencies and improvement points in the execution of the collaborative process. Based on the feedback data analysis results, the collaborative process execution strategy is dynamically adjusted to optimize the process flow and equipment parameters, and a collaborative process dynamic adjustment strategy is generated. Real-time control and data management are achieved using closed-loop control systems and cloud storage technologies. According to the collaborative process dynamic adjustment strategy, the real-time production status panel is closed-loop controlled to ensure that the parameters of each process link are consistent with the target, generate collaborative process closed-loop control data, and record real-time parameters and status changes during the closed-loop control process. The collaborative process closed-loop control data is uploaded to the cloud server through a secure network for cloud storage. The closed-loop control data stored in the cloud server is sorted and stored to generate collaborative process control traceability data for subsequent query and analysis, supporting the collaborative process optimization operation of integrated sealing.

[0144] In this specification, a sealing integrated collaborative process optimization system is provided, which is used to execute the above-mentioned sealing integrated collaborative process optimization method, and the sealing integrated collaborative process optimization system includes:

[0145] A data acquisition module is used to obtain sealing process data; perform sensor data acquisition based on the sealing process data to obtain a multimodal sensor acquisition data set; perform data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set;

[0146] The process optimization module is used to analyze the process flow of the sealing process data and generate the sealing process flow data, wherein the sealing process flow data includes the sealing process, the capping process and the capping process; to perform intelligent process modeling on the sealing process, the capping process and the capping process and generate a process process mathematical model; to use the process process data model to perform adaptive control of the process operation position of the container to be sealed and generate a real-time production status panel;

[0147] The process monitoring and early warning module is used to construct monitoring nodes for the sealing process, capping process and capping process through the real-time production status panel to generate real-time production status monitoring nodes; perform abnormal node monitoring on the real-time production status monitoring nodes to generate abnormal nodes and normal nodes; perform collaborative process strategy execution based on abnormal nodes and normal nodes to generate collaborative process execution strategies;

[0148] The feedback module is used to dynamically adjust the collaborative process execution strategy and generate a collaborative process dynamic adjustment strategy; perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy, generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to execute integrated sealing collaborative process optimization operations.

[0149] The beneficial effect of the present invention is that high-quality data input is ensured through the acquisition and standardized processing of multimodal sensor data, reducing errors caused by incomplete or inconsistent data. In-depth analysis and modeling of the sealing, capping and capping processes make the operating mechanism of each process clearer, which helps to find potential bottlenecks and improvement points. The establishment of a real-time production status panel enables key parameters in the production process to be monitored in real time, and abnormalities are identified and handled in a timely manner, effectively reducing production risks. Based on abnormality detection of monitoring nodes, collaborative process strategies can be automatically generated, which improves the level of intelligent decision-making and reduces the need for manual intervention. Through the dynamic adjustment of collaborative process execution strategies, the production process can be self-optimized according to real-time feedback, so as to adapt to different production environments and demand changes. The generation and cloud storage of collaborative process closed-loop control data enhances the global control ability of the production process, helps long-term data analysis and tracking, and supports continuous improvement. The overall optimized process significantly reduces invalid operations and resource waste, and improves the overall efficiency and output of the production line. Through real-time monitoring and intelligent adjustment, the compliance of each production link is ensured, thereby improving the quality consistency of the final product. Therefore, the present invention improves the flexibility and adaptability of the sealing process management through multimodal data collection, detailed process flow analysis, real-time monitoring and dynamic adjustment strategy.

[0150] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0151] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A collaborative process optimization method for sealing integration, characterized in that: Acting on the container to be sealed, including the following steps: Step S1: Acquire sealing process data; perform sensor data acquisition according to the sealing process data to obtain a multimodal sensor acquisition data set; perform data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set; Step S2: Perform process flow analysis on the sealing process data to generate sealing process flow data, wherein the sealing process flow data includes sealing process, capping process and capping process; perform intelligent process modeling on the sealing process, capping process and capping process to generate a process process mathematical model; use the process process data model to perform process operation position adaptive control on the container to be sealed to generate a real-time production status panel; Step S3: construct monitoring nodes for the sealing process, the capping process and the capping process through the real-time production status panel to generate real-time production status monitoring nodes; perform abnormal node monitoring on the real-time production status monitoring nodes to generate abnormal nodes and normal nodes; perform collaborative process strategy execution based on the abnormal nodes and normal nodes to generate a collaborative process execution strategy; Step S4: Dynamically adjust the collaborative process execution strategy to generate a collaborative process dynamic adjustment strategy; perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy to generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to perform integrated sealing collaborative process optimization operations.

2. The collaborative process optimization method for sealing integration according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire sealing process data; Step S12: Arrange sensors according to the sealing process data to generate sealing process sensor deployment data; configure edge computing nodes for the sealing process sensor deployment data to obtain sealing process edge computing nodes; Step S13: performing sensor data collection on the edge computing nodes of the sealing process based on a preset data collection frequency to obtain a multimodal sensor collection data set; Step S14: performing data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set, wherein the data preprocessing includes noise filtering, data smoothing, and missing value interpolation.

3. The collaborative process optimization method for sealing integration according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing process flow analysis on the sealing process data to generate sealing process flow data, wherein the sealing process flow data includes a sealing process, a capping process, and a capping process; classifying the process data of the standard multimodal sensor acquisition data set according to the sealing process, the capping process, and the capping process to generate process classification sensor data; Step S22: Intelligent process modeling is performed on the sealing process, the capping process and the capping process through process classification sensor data to generate a process procedure mathematical model; Step S23: using the process data model to predict the state of the container to be sealed for the sealing process, the capping process and the capping process, and generating sealed container state prediction data; performing process operation position adaptive control on the container to be sealed according to the sealed container state prediction data, and generating process operation position adaptive control data; Step S24: Based on the process operation position adaptive control data, the sealing process, the capping process and the capping process are visualized in real time, thereby generating a real-time production status panel.

4. The collaborative process optimization method for sealing integration according to claim 3, characterized in that: Step S22 includes the following steps: Step S221: selecting key process indicators for the sealing process, the capping process and the capping process to obtain key process indicator data, wherein the key process indicator data include key process indicators for the sealing process, key process indicators for the capping process and key process indicators for the capping process; selecting a mathematical model according to the key process indicator data to generate mathematical model selection data, wherein the mathematical model selection data include a state space model, a linear regression model and a nonlinear regression model; Step S222: deriving the sealing process model equation for the key indicators of the sealing process using the state space model to obtain the sealing process model derivation equation; wherein the sealing process model equation derivation formula is as follows: S = f(T, P, t); In the formula, S is the sealing quality, T is the temperature, P is the pressure, t is the time, and f(T,P,t) is the sealing process model function; The linear regression model is used to derive the closing process model equation for the key indicators of the closing process, and the closing process model derivation equation is obtained; the closing process model equation derivation formula is as follows: C = g(Pc, A, R); Where C is the lid closing mass, Pc is the applied force, A is the lid position, R is the lid rotation angle, and g(Pc,A,R) is the lid closing process model function; The nonlinear regression model is used to derive the capping process model equation for the key indicators of the capping process, and the capping process model derivation equation is obtained; the capping process model equation derivation formula is as follows: W = h(F, V, B); Where W is the capping mass, F is the applied pressure, V is the capping speed, B is the ambient temperature, and h(F, V, B) is the capping process model function; Step S223: Based on the derived equations of the sealing process model, the state space model is model-verified to generate a sealing process mathematical model; based on the derived equations of the capping process model, the linear regression model is model-verified to generate a capping process mathematical model; based on the derived equations of the capping process model, the nonlinear regression model is model-verified to generate a capping process mathematical model; Step S224: combining the sealing process mathematical model, the capping process mathematical model and the capping process mathematical model to generate a process step mathematical model.

5. The collaborative process optimization method for sealing integration according to claim 4, characterized in that: Step S224 includes the following steps: The mathematical models of the sealing process, the capping process and the pressing process are prioritized, the mathematical model of the sealing process is assigned a high priority, and a high priority mathematical model is generated; the mathematical model of the capping process is assigned a medium priority, and a medium priority mathematical model is generated; the mathematical model of the pressing process is assigned a low priority, and a low priority mathematical model is generated; The high-priority mathematical model, the medium-priority mathematical model and the low-priority mathematical model are combined in series to generate a process series mathematical model; a combination equation is constructed for the process series mathematical model to generate a process combination equation, wherein the formula for constructing the combination equation is as follows: K=h(f(T1,P1,t1),g(Pc2,A2,R2),h(F3,V3,B3)); In the formula, K is the process combination equation, f(T1, P1, t1) represents the sealing process model equation executed with the first priority, g(Pc2, A2, R2) represents the closing process model equation executed with the second priority, and h(F3, V3, B3) represents the capping process model equation executed with the third priority; The overall performance of the process series mathematical model is evaluated according to the process combination equation to generate model performance evaluation data; based on the model performance evaluation data, the process series mathematical model is optimized to generate a process procedure mathematical model.

6. The collaborative process optimization method for sealing integration according to claim 3, characterized in that: Adaptive control of process operation position of the container to be sealed based on the predicted data of the sealed container state includes: The container to be sealed and the process equipment are three-dimensionally scanned by a laser sensor to obtain three-dimensional scanning data of the container to be sealed and three-dimensional scanning data of the process equipment; the sealing center point position of the container to be sealed is confirmed based on the three-dimensional scanning data of the container to be sealed to obtain the center point position data of the container to be sealed; Confirm the edge position of the three-dimensional scanning data of the process equipment to obtain the edge position data of the process equipment; discretize and connect the edge position data of the process equipment to generate the operation range of the process equipment; calculate the center point position data of the container to be sealed and the operation range of the process equipment, and when the center point position data of the container to be sealed is within the operation range of the process equipment, calibrate the container to be sealed around the center point according to the sealed container state prediction data to generate the first process calibration data; When the center point position data of the container to be sealed is not within the operating range of the process equipment, the offset calculation is performed on the container to be sealed according to the sealed container state prediction data to obtain the offset data of the container to be sealed; the spatial flip calibration is performed on the container to be sealed based on the offset data of the container to be sealed to generate the second process calibration data; The first process calibration data and the second process calibration data are calibrated and integrated to generate process operation position adaptive control data.

7. The collaborative process optimization method for sealing integration according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: dynamically collect real-time data of the sealing process, the capping process and the capping process according to the process operation position adaptive control data to obtain a real-time operation data stream; Step S242: extract key indicators and trends from the real-time operation data stream to generate key performance indicators and dynamic trend mapping data; aggregate the real-time operation data stream based on the key performance indicators and dynamic trend mapping data to generate real-time operation summary data; Step S243: Perform real-time data update on the real-time operation summary data to generate real-time operation summary update data; perform data visualization on the real-time operation summary update data to generate a real-time operation panel; integrate warning rules on the real-time operation panel according to a preset warning threshold, thereby generating a real-time production status panel.

8. The sealing integrated collaborative process optimization method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: construct monitoring nodes for the sealing process, capping process and capping process through the real-time production status panel to generate real-time production status monitoring nodes; Step S32: abnormal node monitoring is performed on the real-time production status monitoring nodes to obtain abnormal nodes and normal nodes; the number of nodes of the abnormal nodes and the normal nodes are compared, and when the number of nodes of the abnormal nodes is greater than or equal to the number of nodes of the normal nodes, the corresponding process equipment of the sealing process, the capping process and the capping process is closed to generate a high abnormal process strategy; Step S33: When the number of abnormal nodes is less than the number of normal nodes, the sealing process, the capping process and the pressing process are repaired accordingly according to the abnormal nodes to generate a low-abnormal process strategy; the high-abnormal process strategy and the low-abnormal process strategy are integrated to generate a collaborative process execution strategy.

9. The collaborative process optimization method for sealing integration according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: implementing feedback on the collaborative process execution strategy to generate collaborative process implementation feedback data; dynamically adjusting the collaborative process execution strategy according to the collaborative process implementation feedback data to generate a collaborative process dynamic adjustment strategy; Step S42: Perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy, generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to execute the collaborative process optimization operation of integrated sealing.

10. A sealing integrated collaborative process optimization system, characterized in that: The method for implementing the collaborative process optimization method for sealing integration according to claim 1, wherein the collaborative process optimization system for sealing integration comprises: A data acquisition module is used to obtain sealing process data; perform sensor data acquisition based on the sealing process data to obtain a multimodal sensor acquisition data set; perform data preprocessing on the multimodal sensor acquisition data set to generate a standard multimodal sensor acquisition data set; The process optimization module is used to analyze the process flow of the sealing process data and generate the sealing process flow data, wherein the sealing process flow data includes the sealing process, the capping process and the capping process; to perform intelligent process modeling on the sealing process, the capping process and the capping process and generate a process process mathematical model; to use the process process data model to perform adaptive control of the process operation position of the container to be sealed and generate a real-time production status panel; The process monitoring and early warning module is used to construct monitoring nodes for the sealing process, capping process and capping process through the real-time production status panel to generate real-time production status monitoring nodes; perform abnormal node monitoring on the real-time production status monitoring nodes to generate abnormal nodes and normal nodes; perform collaborative process strategy execution based on abnormal nodes and normal nodes to generate collaborative process execution strategies; The feedback module is used to dynamically adjust the collaborative process execution strategy and generate a collaborative process dynamic adjustment strategy; perform closed-loop control on the real-time production status panel according to the collaborative process dynamic adjustment strategy, generate collaborative process closed-loop control data, and upload the collaborative process closed-loop control data to the cloud server for cloud storage, thereby generating collaborative process control traceability data to execute integrated sealing collaborative process optimization operations.

Images