Intelligent monitoring method and system for plastic bag production process

Abstract

The invention relates to the technical field of intelligent monitoring, in particular to an intelligent monitoring method and system for a plastic bag production process, and the method comprises the following steps: collecting original equipment operation data and production instruction information based on a production line speed sensor and operation state monitoring, generating a preliminary equipment data stream, and storing the preliminary equipment data stream in a database; and applying an energy consumption algorithm to the preliminary equipment data stream, calculating energy consumption of a production unit, and integrating external energy price data to generate an optimized energy use strategy. According to the invention, by adjusting the energy use strategy and optimizing the production process, the production efficiency and resource utilization are obviously improved, the dynamic adjustment of the production speed and the machine load is realized, the energy market change is matched, the energy distribution is more accurate and efficient, and the bottleneck and equipment abnormality in the production process are identified and solved by continuous monitoring and real-time optimization, so that the production efficiency is improved. Equipment operation efficiency and production line performance are greatly improved, and long-term efficiency improvement and cost saving are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring method and system for a plastic bag production process. Background Art

[0002] The field of intelligent monitoring technology covers various systems and methods for automatically analyzing and responding to data obtained from monitoring equipment. The field integrates image recognition, machine learning, sensor technology, and automated control systems to improve efficiency, ensure quality control, and enhance safety. Intelligent monitoring technology is widely used in industrial manufacturing, traffic management, public safety, and resource management. Through automatic analysis and processing of real-time data on site, the technology supports decision-making, optimizes operating processes, reduces labor costs, and can predict and identify potential system failures or safety hazards.

[0003] Among them, the intelligent monitoring method of the plastic bag production process refers to the development of an intelligent system for monitoring and optimizing the plastic bag production line, which integrates high-resolution cameras, sensors and data analysis software to monitor key parameters in the production process in real time, such as material thickness, temperature, speed and machine status. The uses include ensuring that product quality meets standard requirements, reducing waste and downtime in the production process, and optimizing production efficiency through data-driven insights. This method not only improves the level of automation in the production process, but also helps companies maintain their advantages in a highly competitive market environment.

[0004] Although the existing intelligent monitoring methods for the plastic bag production process have a certain foundation in automatic analysis and response, they lack the ability to quickly adapt to real-time market changes. When faced with energy price fluctuations and changes in market demand, they cannot be adjusted immediately, resulting in low energy efficiency and increased production costs. Existing technologies also show certain limitations in identifying bottlenecks and equipment interaction problems in complex production processes, relying on post-analysis rather than real-time problem solving. This delayed response speed leads to reduced production efficiency and potential safety risks. For example, if equipment failures or production anomalies are not discovered and handled in a timely manner, they will result in a large amount of waste and increased downtime, which not only affects production plans, but also increases material and labor costs. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent monitoring method and system for a plastic bag production process.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for intelligent monitoring of a plastic bag production process, comprising the following steps: S1: Based on the production line speed sensor and operation status monitoring, collect the original equipment operation data and production instruction information, generate the preliminary equipment data stream, apply the energy consumption algorithm to the preliminary equipment data stream, calculate the energy consumption of the production unit, and integrate the external energy price data to generate the optimized energy use strategy; S2: Based on the optimized energy usage strategy, adjust the parameters of the mixed integer linear programming model, including production speed and machine load, simulate energy distribution, generate an adjusted energy distribution plan, implement the adjusted energy distribution plan in the control configuration, and match energy market changes to generate a real-time response energy adjustment plan; S3: Based on the real-time response energy adjustment plan, the graph neural network is used to analyze the data interaction between the equipment nodes in the production line, identify the potential bottlenecks of the production process and the abnormalities of equipment interaction, generate equipment interaction analysis results, adjust the production process and equipment configuration according to the equipment interaction analysis results, and generate a process optimization strategy; S4: Apply the process optimization strategy to adjust the production line, evaluate the efficiency changes before and after the equipment adjustment through simulation and real-time operation comparison, continuously monitor the production line efficiency, continuously optimize the production configuration, and generate a continuously monitored production adjustment plan.

[0007] As a further solution of the present invention, the steps of obtaining the optimized energy use strategy are specifically as follows: S111: Based on the production line speed sensor and operation status monitoring, collect monitoring data, combine equipment operation data and production instruction information, and use the formula:

[0008] Get the weighted original device data stream, where represents the weighted raw device data stream, represents the data output of the i-th sensor, represents the corresponding weight coefficient, represents the adjustment parameter; S112: Apply the weighted original device data stream to calculate energy consumption using the formula:

[0009] Calculate and obtain the energy consumption data of the production unit, where: Representative The power of the device, Represents the device operation time, represents the output of device j in the data stream, Represents historical energy consumption data, Indicates the energy consumption data of the production unit; S113: Based on the energy consumption data of the production unit, external energy price data is integrated and the formula is adopted:

[0010] Calculate the energy consumption cost and get the optimized energy use strategy, where: represents the energy cost, represents the unit price of energy, Represents the change in energy prices from the previous day, represents the adjustment parameter, Represents the market volatility coefficient.

[0011] As a further solution of the present invention, the steps for obtaining the adjusted energy allocation plan are specifically as follows: S211: Based on the optimized energy use strategy, adjust the production speed parameter of the mixed integer linear programming model, using the formula:

[0012] The adjusted production speed parameters are calculated by quoting the adjustment coefficient, external variables and environmental impact factors, where: represents the adjusted production speed, represents the original production speed, Represents adjustment ratio Represents the influence of external environmental factors, Represents the adjustment coefficient of environmental impact factors S212: Apply the adjusted production speed parameter, combined with the energy efficiency factor, the historical performance index and the historical adjustment coefficient, using the formula:

[0013] Update the load of the machine and generate adjusted machine load parameters, where: represents the adjusted machine load parameter, represents the original load, represents the energy efficiency factor, represents the adjusted production speed, Represents the original production speed, represents the historical performance index, represents the historical adjustment factor; S213: Using the adjusted machine load parameter, referring to the market fluctuation parameter, the price adjustment factor and the adjustment elasticity, using the formula:

[0014] The adjusted energy allocation plan is calculated, where represents the adjusted energy distribution cost, represents the adjusted machine load, represents the current energy unit price, represents the energy price adjustment factor, represents the market volatility parameter, Stands for adjustment flexibility.

[0015] As a further solution of the present invention, the step of obtaining the real-time response energy adjustment plan is specifically as follows: S221: Implement the adjusted energy allocation plan in the control configuration, refer to the real-time monitoring parameters and environmental factors, and use the formula:

[0016] And introduce the control error factor, calculate the new control configuration, and get the updated control configuration parameters, where, Represents the updated control configuration parameters, Represents the basic control configuration, represents the adjustment coefficient, Represents real-time monitoring parameters, Represents the influence of environmental factors, represents the control error factor; S222: Based on the updated control configuration parameters, matching energy market changes, combining market volatility factors and price adjustment indexes, and referring to market response delays, use the formula:

[0017] Generate energy configuration parameters, where Represents energy configuration parameters that match market changes, Represents the current market configuration, Represents the market volatility factor, represents the price-adjusted index, Represents delayed market response; S223: Combine the energy configuration parameters and the updated control configuration parameters, using the formula:

[0018] The energy effect multiplier is introduced to calculate the real-time response energy adjustment plan, where: Represents real-time response to energy adjustment plans, Represents the updated control configuration parameters, Represents energy configuration parameters that match market changes, represents the system dynamic adjustment coefficient, represents the feedback regulation factor, Represents the energy effect multiplier.

[0019] As a further solution of the present invention, the step of obtaining the device interaction analysis result is specifically: S311: Based on the real-time response energy adjustment scheme, load and process the data of the production line equipment nodes, use the adjacency matrix and the feature matrix, and use the formula:

[0020] Calculate the optimized feature representation of the node and generate processed node feature data, where: Represents the connection strength between device nodes. represents the original feature data, represents the node efficiency coefficient, Represents key data indicators, Represents the processed node feature data; S312: Based on the processed node feature data, a graph neural network model is applied to perform feature learning, referring to the node data dependency and node stability factor, through the formula:

[0021] Update node features to generate enhanced features of device nodes, where: Representative The node features after iterations are Representative The weight matrix of the layer, represents the adjacency matrix, Representative The node features of the iteration, represents data dependency, represents the node stability factor; S313: Analyze the enhanced features of the device node, identify anomalies and bottlenecks in data interaction, and use the formula:

[0022] Determine key nodes and generate device interaction analysis results, including: Represents the key node, Represents the node features of the graph neural network, represents the weight factor, Represents the discrimination threshold.

[0023] As a further solution of the present invention, the steps of obtaining the process optimization strategy are specifically as follows: S321: Based on the device interaction analysis result, locate the node with low efficiency by formula:

[0024] Calculate the efficiency loss of the node and generate the node efficiency evaluation result, where: represents the node efficiency evaluation result, represents the efficiency score of the node, Represents the interaction data of the node, represents the node importance index, Represents data stability; S322: According to the node efficiency evaluation result, identify the key bottleneck area, using the formula:

[0025] Adjust the production process and generate a preliminary process adjustment plan, including: Represents the preliminary process adjustment plan, represents the node efficiency evaluation result, Represents the bottleneck resolution strategy, represents the potential improvement factor, Represents the feasibility of adjustment, represents the difficulty of implementation; S323: Summarize the preliminary process adjustment plan and the overall production target, optimize the production configuration, and use the formula:

[0026] Get the process optimization strategy, where Represents process optimization strategy, Represents the preliminary process adjustment plan, represents the resource allocation coefficient, represents the adjustment efficiency, Represents the response speed, Represents the persistence of the effect.

[0027] As a further solution of the present invention, the step of obtaining the continuously monitored production adjustment plan is specifically as follows: S411: Based on the process optimization strategy, conduct simulation tests, collect data, use efficiency indicators, adjust the before and after comparison coefficients, and use the formula:

[0028] Evaluate the efficiency change before and after the equipment is adjusted, and generate the efficiency change evaluation results, where: represents the efficiency change evaluation result, represents the adjusted efficiency, represents the efficiency before adjustment, represents the adjustment effect coefficient, Represents the influence of environmental variables, represents the simulation error, Represents data reliability; S412: According to the efficiency change evaluation result, the production line configuration is adjusted, referring to the resource allocation efficiency and production rhythm adjustment, through the formula:

[0029] Optimize production configuration and generate adjusted production configuration plan, where: Represents the adjusted production configuration plan, represents the efficiency of resource allocation, represents the efficiency change evaluation result, Represents the production rhythm adjustment coefficient, Represents the speed of technological updates. represents the optimized index for adjustment; S413: Based on the adjusted production configuration plan, continuous monitoring and optimization are implemented, using the formula:

[0030] Continuously optimize production configuration and generate continuously monitored production adjustment plans, including: Represents a production adjustment plan that is continuously monitored, Represents the adjusted production configuration plan, represents the real-time feedback adjustment coefficient, Represents the optimization adjustment range, Represents continuous improvement indicators, Represents reaction sensitivity.

[0031] A plastic bag production process intelligent monitoring system, the plastic bag production process intelligent monitoring system is used to execute the above-mentioned plastic bag production process intelligent monitoring method, the system comprises: The energy allocation module monitors the real-time energy consumption of the production line and the market energy supply based on the production line speed sensor and operation status monitoring, compares the differences and makes adjustments, dynamically allocates the supply plan according to production demand, reduces ineffective energy consumption, and obtains the best energy utilization benefits; The production adjustment module adopts the optimal energy utilization efficiency, adjusts the production speed and machine operation parameters, synchronizes the machine status in real time and matches the energy supply, optimizes resource utilization, and obtains adjusted production parameters; The equipment maintenance strategy module uses the adjusted production parameters to monitor the performance of key equipment and predict maintenance time, arrange regular inspections and maintenance, avoid sudden failures, and formulate equipment maintenance plans; The production efficiency improvement module optimizes the production process and adjusts the production line layout based on the equipment maintenance plan, implements efficiency testing and records the results, and creates efficiency optimization results; The environmental monitoring module tracks key indicators of the production environment including temperature and humidity according to the efficiency optimization results, adjusts the control configuration response, and builds a production adjustment plan for continuous monitoring.

[0032] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by adjusting the energy use strategy and optimizing the production process, production efficiency and resource utilization are significantly improved, dynamic adjustment of production speed and machine load is achieved, and energy market changes are matched in real time, making energy allocation plans more accurate and efficient. Dynamic adjustment not only reduces energy waste, but also ensures the continuity and stability of the production process, and reduces the risk of production interruption due to improper energy configuration. Through in-depth analysis of data interaction between production line equipment nodes, bottlenecks and equipment interaction anomalies in the production process are effectively identified and resolved. This precise problem identification and timely adjustment greatly improves the operating efficiency of the equipment and the overall performance of the production line. The implementation of continuous monitoring and real-time optimization enables the production line to continuously optimize its configuration autonomously to achieve long-term efficiency improvement and cost savings. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 A flow chart of the energy utilization strategy optimized in the present invention; Figure 3 A flow chart of the energy distribution plan adjusted in the present invention; Figure 4 A flowchart of the real-time response energy adjustment scheme in the present invention; Figure 5 A flow chart showing the results of the device interaction analysis in the present invention; Figure 6 It is a flow chart of the process optimization strategy in the present invention; Figure 7 Flow chart of the continuously monitored production adjustment scheme in the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0035] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. Example

[0036] See also Figure 1 The present invention provides a technical solution: a method for intelligently monitoring a plastic bag production process, comprising the following steps: S1: Based on the production line speed sensor and operation status monitoring, collect the original equipment operation data and production instruction information, generate the preliminary equipment data stream, apply the energy consumption algorithm to the preliminary equipment data stream, calculate the energy consumption of the production unit, and integrate the external energy price data to generate the optimized energy use strategy; S2: Based on the optimized energy usage strategy, adjust the parameters of the mixed integer linear programming model, including production speed and machine load, simulate energy distribution, generate an adjusted energy distribution plan, implement the adjusted energy distribution plan in the control configuration, and match the energy market changes to generate a real-time response energy adjustment plan; S3: Based on the real-time response energy adjustment plan, the graph neural network is used to analyze the data interaction between the equipment nodes in the production line, identify the potential bottlenecks of the production process and the abnormalities of equipment interaction, generate equipment interaction analysis results, adjust the production process and equipment configuration according to the equipment interaction analysis results, and generate process optimization strategies; S4: Apply process optimization strategies to adjust the production line. Through simulation and real-time operation comparison, evaluate the efficiency changes before and after equipment adjustment, continuously monitor the production line efficiency, continuously optimize the production configuration, and generate a continuously monitored production adjustment plan.

[0037] The preliminary equipment data flow includes sensor output data, operation status monitoring, and order input information. The optimized energy use strategy includes energy consumption minimization plan, cost efficiency ratio, and market price response. The adjusted energy allocation plan includes production demand matching, load management strategy, and budget optimization configuration. The real-time response energy adjustment plan includes adjustment logic details and response speed optimization. The equipment interaction analysis results include node efficiency identification, process breakpoints, and abnormal pattern identification. The process optimization strategy includes operation sequence adjustment, equipment collaborative optimization, and efficiency enhancement measures. The continuously monitored production adjustment plan includes monitoring logic update, adjustment strategy implementation, and configuration effect verification.

[0038] See also Figure 2 ,The specific steps for obtaining the optimized energy usage strategy are: S111: Based on the production line speed sensor and operation status monitoring, collect monitoring data, combine equipment operation data and production instruction information, and use the formula:

[0039] Get the weighted original device data stream, where represents the weighted raw device data stream, represents the data output of the i-th sensor, represents the corresponding weight coefficient, represents the adjustment parameter; S112: Apply the weighted raw device data stream to calculate energy consumption using the formula:

[0040] Calculate and obtain the energy consumption data of the production unit, where: Representative The power of the device, Represents the device operation time, represents the output of device j in the data stream, Represents historical energy consumption data, Indicates the energy consumption data of the production unit; S113: Based on the energy consumption data of production units, integrating external energy price data, the formula is:

[0041] Calculate the energy consumption cost and get the optimized energy use strategy, where: represents the energy cost, represents the unit price of energy, Represents the change in energy prices from the previous day, represents the adjustment parameter, Represents the market volatility coefficient.

[0042] Weighted raw device data flow formula:

[0043] : Data output of the i-th sensor; : The corresponding weight coefficient depends on the importance or accuracy of the sensor; : Adjustment parameters, related to the operating conditions or environmental variables of the equipment; : Weighted raw device data stream; Assume there are 3 sensors, output are 100, 150 and 200 respectively, and the corresponding weights 1.2, 1.0 and 0.8, adjusting parameters They are 0.5, 1.0 and 1.5 respectively; Apply the formula for each sensor: First sensor: ; Second sensor: ; Second sensor: ; Weighted sum: ; Weighted raw device data stream 551, indicating the comprehensive data output of the device in the current operating state.

[0044] Production unit energy consumption data formula:

[0045] : The power of the jth device; : Equipment operation time; : Output of device j in the data stream; : Historical energy consumption data; : total energy consumption; : Weighted raw device data stream; Assume there are two devices, device power 10kW and 15kW respectively, running time 3 hours and 2 hours respectively, the device output For 200 and 100, the historical energy consumption 4000 and 3000; Apply the formula for each device: First device: ; Second device: ; Total energy consumption: kW·h; Total energy consumption It is 1.035kW·h, reflecting the energy efficiency under given operating conditions and historical energy consumption background.

[0046] Energy cost formula:

[0047] : The total energy consumption obtained from the previous step; : Energy unit price, assumed to be 0.1 / kW·h; : The change in energy price from the previous day, assumed to be 0.02; : Adjustment parameter, assumed to be 1; : Market volatility coefficient, assumed to be 0.5; : Energy consumption cost; Use the Value, calculation :

[0048] Energy cost It is 0.1015, which represents the energy consumption cost under the current energy price and market fluctuation conditions.

[0049] See also Figure 3 , the specific steps for obtaining the adjusted energy allocation plan are: S211: Based on the optimized energy usage strategy, adjust the production speed parameters of the mixed integer linear programming model using the formula:

[0050] The adjusted production speed parameters are calculated by quoting the adjustment coefficient, external variables and environmental impact factors, where: represents the adjusted production speed, represents the original production speed, Represents adjustment ratio Represents the influence of external environmental factors, Represents the adjustment coefficient of environmental impact factors S212: Apply the adjusted production speed parameter, combined with the energy efficiency factor, historical performance index and historical adjustment factor, using the formula:

[0051] Update the load of the machine and generate adjusted machine load parameters, where: represents the adjusted machine load parameter, represents the original load, represents the energy efficiency factor, represents the adjusted production speed, Represents the original production speed, represents the historical performance index, represents the historical adjustment factor; S213: Using the adjusted machine load parameters, referring to the market fluctuation parameters, price adjustment factors and adjustment elasticity, use the formula:

[0052] The adjusted energy allocation plan is calculated, where represents the adjusted energy distribution cost, represents the adjusted machine load, represents the current energy unit price, represents the energy price adjustment factor, represents the market volatility parameter, Stands for adjustment flexibility.

[0053] The formula for adjusted production speed is:

[0054] : Adjusted production speed; : Original production speed; : adjust the ratio; :Influence of external environmental factors; : Adjustment coefficient of environmental impact factors; Assuming original production speed Unit / hour, adjustment ratio , the influence of external environmental factors (about 30 degrees), adjustment coefficient of environmental impact factor ; calculate ; calculate ; calculate ; calculate ; final Unit / hour; Adjusted production speed It is 111.28 units / hour, which means that the production speed is increased by about 11.28% due to the adjustment of parameters.

[0055] The formula for the adjusted machine load parameter is:

[0056] : Adjusted machine load; : original load; : Energy efficiency factor; : Adjusted production speed; : Original production speed; : Historical performance index; : Historical adjustment factor; Assuming original load Unit, Energy Efficiency Factor , historical performance index , historical adjustment factor , known Units / hour and Unit / hour; calculate ; calculate ; calculate ; calculate ; final ; Adjusted machine load It is 66.535 units, indicating that the machine load is increased due to the adjustment of parameters. .

[0057] The formula for the adjusted energy distribution cost is:

[0058] : Adjusted energy distribution cost; : Adjusted machine load; : Current energy unit price; : Energy price adjustment factor; : Market volatility parameters; : Adjust elasticity; Assuming current energy unit price Unit / unit energy, energy price adjustment factor , market volatility parameter Curvature, adjust elasticity , known ; calculate ; calculate ; calculate ; calculate ; final

[0059] Adjusted energy distribution cost The unit cost is 30.33, which represents the final calculated value of energy cost under the adjustment parameters and market conditions.

[0060] See also Figure 4 ,The specific steps for obtaining the real-time response energy adjustment plan are: S221: Implement the adjusted energy allocation plan in the control configuration, referencing the real-time monitoring parameters and environmental factors, using the formula:

[0061] And introduce the control error factor, calculate the new control configuration, and get the updated control configuration parameters, where, Represents the updated control configuration parameters, Represents the basic control configuration, represents the adjustment coefficient, Represents real-time monitoring parameters, Represents the influence of environmental factors, represents the control error factor; S222: Based on the updated control configuration parameters, matching the energy market changes, combining the market volatility factor and the price adjustment index, and referring to the market response delay, use the formula:

[0062] Generate energy configuration parameters, where Represents energy configuration parameters that match market changes, Represents the current market configuration, Represents the market volatility factor, represents the price-adjusted index, Represents delayed market response; S223: Combine the energy configuration parameters and the updated control configuration parameters, using the formula:

[0063] The energy effect multiplier is introduced to calculate the real-time response energy adjustment plan, where: Represents real-time response to energy adjustment plans, Represents the updated control configuration parameters, Represents energy configuration parameters that match market changes, represents the system dynamic adjustment coefficient, represents the feedback regulation factor, Represents the energy effect multiplier.

[0064] Updated control configuration parameter formula:

[0065] : Basic control configuration parameters, assumed to be 100; : Adjustment coefficient, assumed to be 0.05; : Real-time monitoring parameters, expressed as the current load of the system, assuming it is 0.10; : Environmental factors, assumed to be 0.03; : Control error factor, assumed to be 0.02; calculate Parts:

[0066] calculate Parts:

[0067] calculate Parts:

[0068] Add the calculated value to the base parameter and multiply by the base control configuration:

[0069] This result shows that the slightly increased parameters of the adjusted control configuration are mainly due to the influence of system load, environmental factors and regulation coefficient.

[0070] Energy configuration parameter formula that matches market changes:

[0071] : Current market configuration parameter, assumed to be 50; : Market volatility factor, assumed to be 0.04; : Price adjustment index, assumed to be 0.1; : Market response delay, assumed to be 0.05; calculate Parts:

[0072] calculate Parts:

[0073] calculate Parts:

[0074] Add the calculated value to the base parameter and multiply it by the current market configuration to get :

[0075] This result indicates that the market allocation parameter increases slightly due to price adjustments and market volatility.

[0076] Formula for real-time response to energy adjustment scheme

[0077] : Updated control configuration parameters, assumed to be 100.835; : Energy configuration parameters that match market changes, assumed to be 50.5006; : System dynamic adjustment coefficient, assumed to be 0.1; : Feedback adjustment factor, assumed to be 0.2; : Energy effect multiplier, assumed to be 0.05; Calculate the exponential part:

[0078] Multiply this value by and :

[0079] This result indicates that the real-time responsive energy adjustment solution will handle more than 5,200 units of adjustment demand, reflecting the combined impact of control configuration and market changes.

[0080] See also Figure 5 , the specific steps for obtaining the device interaction analysis results are: S311: Based on the real-time response energy adjustment plan, load and process the data of the production line equipment nodes, use the adjacency matrix and feature matrix, through the formula:

[0081] Calculate the optimized feature representation of the node and generate processed node feature data, where: Represents the connection strength between device nodes. represents the original feature data, represents the node efficiency coefficient, Represents key data indicators, Represents the processed node feature data; S312: Based on the processed node feature data, the graph neural network model is applied to perform feature learning, referring to the node data dependency and node stability factor, through the formula:

[0082] Update node features to generate enhanced features of device nodes, where: Representative The node features after iterations are Representative The weight matrix of the layer, represents the adjacency matrix, Representative The node features of the iteration, represents data dependency, represents the node stability factor; S313: Analyze the enhanced features of device nodes and identify anomalies and bottlenecks in data interaction through the formula:

[0083] Determine key nodes and generate device interaction analysis results, including: Represents the key node, Represents the node features of the graph neural network, represents the weight factor, Represents the discrimination threshold.

[0084] The processed node feature data formula is:

[0085] : The connection strength between device nodes (adjacency matrix); : original feature data (feature matrix); : Node efficiency coefficient; :Data key indicators; : processed node data; Assumptions for , indicating that two nodes are connected to each other, assuming for , represents the eigenvalues ​​of the two nodes, set and ; calculate :

[0086]

[0087] This result represents a new feature of the node, where Displays the eigenvalue of each node after weighting and efficiency adjustment.

[0088] No. The node characteristic formula after iterations:

[0089] : No. Node features of the iteration; : No. The weight matrix of the layer; : adjacency matrix; : Data dependency; : Node stability factor; Assumptions: , , , ; calculate :

[0090]

[0091] This result represents the feature value of the updated node, showing how to update node features through graph neural networks.

[0092] Formula analysis of key nodes:

[0093] : The final node features of the graph neural network; : weight factor; : discrimination threshold; Assumptions: , , ; calculate :

[0094] This result represents the most critical nodes identified during the analysis and shows the maximum adjusted node feature value, indicating potential key interactions or bottleneck points.

[0095] See also Figure 6 , the specific steps for obtaining the process optimization strategy are: S321: Based on the results of device interaction analysis, locate the nodes with low efficiency through the formula:

[0096] Calculate the efficiency loss of the node and generate the node efficiency evaluation result, where: represents the node efficiency evaluation result, represents the efficiency score of the node, Represents the interaction data of the node, represents the node importance index, Represents data stability; S322: Based on the node efficiency evaluation results, identify the key bottleneck area using the formula:

[0097] Adjust the production process and generate a preliminary process adjustment plan, including: Represents the preliminary process adjustment plan, represents the node efficiency evaluation result, Represents the bottleneck resolution strategy, represents the potential improvement factor, Represents the feasibility of adjustment, represents the difficulty of implementation; S323: Summarize the preliminary process adjustment plan and the overall production target, optimize the production configuration, and use the formula:

[0098] Get the process optimization strategy, where Represents process optimization strategy, Represents the preliminary process adjustment plan, represents the resource allocation coefficient, represents the adjustment efficiency, Represents the response speed, Represents the persistence of the effect.

[0099] The formula for node efficiency evaluation results is:

[0100] : The interaction data of the node, assumed to be the number of interactions or interaction quality indicators; : The efficiency score of the node, the efficiency index obtained through historical data analysis; : Node importance index, which is evaluated based on the role and influence of the node in the production line; : Data stability, measuring the standard deviation or coefficient of variation of data changes; : Node comprehensive efficiency evaluation results.

[0101] Assumed data: (number of interactions), (efficiency index), (node ​​importance), (Data stability); calculate :

[0102] calculate :

[0103] Sum: 40+75=115 Divide by ,calculate :

[0104] Indicates the overall efficiency score. The higher the score, the more attention and optimization the node needs.

[0105] Formula for the preliminary process adjustment plan:

[0106] : The effectiveness of bottleneck resolution strategies, as assessed by experts based on the severity of the problem; : Potential improvement factor, based on the evaluation of the expected benefits after improvement; : Adjust feasibility and consider obstacles in actual operation; : Difficulty of implementation, estimated based on required resources and time; :Preliminary process adjustment plan; Assumed data: (Strategic Effectiveness), (Improvement Factor), (feasibility), (difficulty of implementation), ; Calculate the denominator:

[0107] Calculate the fraction:

[0108] Multiply ,calculate :

[0109] Indicates the effectiveness score of the preliminary process adjustment plan. A higher value indicates that the adjustment plan improves overall efficiency.

[0110] Formula for process optimization strategy:

[0111] : Resource allocation coefficient, which reflects the degree of support of resource allocation for the adjustment plan; : Adjusted efficiency, expected efficiency improvement after adjustment; : Response speed, the speed at which the system reaches a new state after the adjustment plan is implemented; : Effect persistence, the duration of the adjusted effect; : The final process optimization strategy; Assumed data: , , , , ; Calculate the sum inside the brackets:

[0112] Multiply ,calculate :

[0113] Represents the overall effectiveness score of the final process optimization strategy, indicating the comprehensive effect of the plan and its sustainability.

[0114] See also Figure 7, the specific steps for obtaining the production adjustment plan for continuous monitoring are: S411: Based on the process optimization strategy, conduct simulation tests, collect data, use efficiency indicators, adjust the before and after comparison coefficients, and use the formula:

[0115] Evaluate the efficiency change before and after the equipment is adjusted, and generate the efficiency change evaluation results, where: represents the efficiency change evaluation result, represents the adjusted efficiency, represents the efficiency before adjustment, represents the adjustment effect coefficient, Represents the influence of environmental variables, represents the simulation error, Represents data reliability; S412: According to the results of the efficiency change evaluation, adjust the production line configuration, refer to the resource allocation efficiency and production rhythm adjustment, through the formula:

[0116] Optimize production configuration and generate adjusted production configuration plan, where: Represents the adjusted production configuration plan, represents the efficiency of resource allocation, represents the efficiency change evaluation result, Represents the production rhythm adjustment coefficient, Represents the speed of technological updates. represents the optimized index for adjustment; S413: Based on the adjusted production configuration plan, implement continuous monitoring and optimization, using the formula:

[0117] Continuously optimize production configuration and generate continuously monitored production adjustment plans, including: Represents a production adjustment plan that is continuously monitored, Represents the adjusted production configuration plan, represents the real-time feedback adjustment coefficient, Represents the optimization adjustment range, Represents continuous improvement indicators, Represents reaction sensitivity.

[0118] Efficiency change evaluation result formula:

[0119] Assumed parameters: , assuming that the adjustment effect is high; , the efficiency of the adjusted equipment; , the efficiency of the equipment before adjustment; , environmental variables have little impact; , small errors in the simulation; , higher data reliability; Computational efficiency changes:

[0120] Reference to environmental variables affecting calculations :

[0121] Apply the adjusted effect coefficient:

[0122] Add simulation error adjustment:

[0123] Final calculation :

[0124] This represents an actual efficiency improvement of 7.639% after adjustment, taking into account environmental changes and simulation errors.

[0125] The adjusted production configuration formula is:

[0126] Assumed parameters: Indicates high resource allocation efficiency; It represents a small adjustment in the rhythm of production; Indicates the speed of technology update; represents the optimized index for adjustment; Adjust the formula :

[0127] Calculate the total adjustment:

[0128] Application resource allocation efficiency:

[0129] This means that the adjusted production configuration plan has improved efficiency by approximately 6.8751%.

[0130] Formula for continuously monitored production adjustment plan:

[0131] Assumed parameters: , real-time feedback adjustment coefficient; , optimize the adjustment range; , continuous improvement indicators; , reaction sensitivity; Calculate the total adjustment factor:

[0132] Apply the total adjustment factor:

[0133] This shows that continuous monitoring and optimization improves the efficiency of production adjustment plans by approximately 1.375%.

[0134] A plastic bag production process intelligent monitoring system, the plastic bag production process intelligent monitoring system is used to execute the above-mentioned plastic bag production process intelligent monitoring method, the system comprises: The energy allocation module monitors the real-time energy consumption of the production line and the market energy supply based on the production line speed sensor and operation status monitoring, compares the differences and makes adjustments, dynamically allocates the supply plan according to production demand, reduces ineffective energy consumption, and obtains the best energy utilization benefits; The production adjustment module adopts the best energy utilization efficiency, adjusts the production speed and machine operating parameters, synchronizes the machine status in real time and matches the energy supply, optimizes resource utilization, and obtains the adjusted production parameters; The equipment maintenance strategy module uses the adjusted production parameters to monitor the performance of key equipment and predict maintenance time, arrange regular inspections and maintenance, avoid sudden failures, and formulate equipment maintenance plans; The production efficiency improvement module optimizes the production process and adjusts the production line layout based on the equipment maintenance plan, implements efficiency testing and records the results, and creates efficiency optimization results; The environmental monitoring module tracks key indicators of the production environment including temperature and humidity based on the efficiency optimization results, adjusts the control configuration response, and builds a production adjustment plan for continuous monitoring.

[0135] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for intelligent monitoring of a plastic bag production process, characterized in that: The following steps are involved: Based on production line speed sensors and operation status monitoring, raw equipment operation data and production instruction information are collected to generate a preliminary equipment data stream, an energy consumption algorithm is applied to the preliminary equipment data stream to calculate the energy consumption of the production unit, and external energy price data is integrated to generate an optimized energy use strategy; Based on the optimized energy use strategy, adjusting the parameters of the mixed integer linear programming model, including production speed and machine load, simulating energy distribution, generating an adjusted energy distribution plan, implementing the adjusted energy distribution plan in the control configuration, and matching energy market changes to generate a real-time response energy adjustment plan; Based on the real-time response energy adjustment plan, the graph neural network is used to analyze the data interaction between the equipment nodes in the production line, identify the potential bottlenecks of the production process and the abnormalities of equipment interaction, generate equipment interaction analysis results, adjust the production process and equipment configuration according to the equipment interaction analysis results, and generate a process optimization strategy; Apply the process optimization strategy to adjust the production line, evaluate the efficiency changes before and after the equipment adjustment through simulation and real-time operation comparison, continuously monitor the production line efficiency, continuously optimize the production configuration, and generate a continuously monitored production adjustment plan.

2. The intelligent monitoring method for the plastic bag production process according to claim 1 is characterized in that: The steps for obtaining the optimized energy use strategy are specifically as follows: Based on production line speed sensors and operation status monitoring, and collecting monitoring data, combined with equipment operation data and production instruction information, through the formula: ； Get the weighted original device data stream, where represents the weighted raw device data stream, represents the data output of the i-th sensor, represents the corresponding weight coefficient, represents the adjustment parameter; Applying the weighted raw device data stream, energy consumption is calculated using the formula: ； Calculate and obtain the energy consumption data of the production unit, where: Representative The power of the device, Represents the device operation time, represents the output of device j in the data stream, Represents historical energy consumption data, Indicates the energy consumption data of the production unit; Based on the energy consumption data of the production unit, integrating external energy price data, the formula is adopted: ； Calculate the energy consumption cost and get the optimized energy use strategy, where: represents the energy cost, represents the unit price of energy, Represents the change in energy prices from the previous day, represents the adjustment parameter, Represents the market volatility coefficient.

3. The intelligent monitoring method for the plastic bag production process according to claim 2 is characterized in that: The steps for obtaining the adjusted energy allocation plan are specifically as follows: Based on the optimized energy usage strategy, the production speed parameter of the mixed integer linear programming model is adjusted using the formula: ； The adjusted production speed parameters are calculated by quoting the adjustment coefficient, external variables and environmental impact factors, where: represents the adjusted production speed, represents the original production speed, Represents adjustment ratio Represents the influence of external environmental factors, Represents the adjustment coefficient of environmental impact factors Apply the adjusted production speed parameter, combined with the energy efficiency factor, historical performance index and historical adjustment factor, using the formula: ； Update the load of the machine and generate adjusted machine load parameters, where: represents the adjusted machine load parameter, represents the original load, represents the energy efficiency factor, represents the adjusted production speed, Represents the original production speed, represents the historical performance index, represents the historical adjustment factor; Using the adjusted machine load parameters, referring to the market fluctuation parameters, price adjustment factors and adjustment elasticity, the formula is used: ； The adjusted energy allocation plan is calculated, where represents the adjusted energy distribution cost, represents the adjusted machine load, represents the current energy unit price, represents the energy price adjustment factor, represents the market volatility parameter, Stands for adjustment flexibility.

4. The intelligent monitoring method for the plastic bag production process according to claim 3 is characterized in that: The steps for obtaining the real-time response energy adjustment plan are specifically as follows: Implement the adjusted energy allocation plan in the control configuration, referencing the real-time monitoring parameters and environmental factors, using the formula: ； And introduce the control error factor, calculate the new control configuration, and get the updated control configuration parameters, where, Represents the updated control configuration parameters, Represents the basic control configuration, represents the adjustment coefficient, Represents real-time monitoring parameters, Represents the influence of environmental factors, represents the control error factor; Based on the updated control configuration parameters, matching energy market changes, combining market volatility factors and price adjustment indexes, and referring to market response delays, the formula is used: ； Generate energy configuration parameters, where Represents energy configuration parameters that match market changes, Represents the current market configuration, Represents the market volatility factor, represents the price-adjusted index, Represents delayed market response; Combine the energy configuration parameters with the updated control configuration parameters and use the formula: ； The energy effect multiplier is introduced to calculate the real-time response energy adjustment plan, where: Represents real-time response to energy adjustment plans, Represents the updated control configuration parameters, Represents energy configuration parameters that match market changes, represents the system dynamic adjustment coefficient, represents the feedback regulation factor, Represents the energy effect multiplier.

5. The intelligent monitoring method for the plastic bag production process according to claim 4 is characterized in that: The steps for obtaining the device interaction analysis result are specifically as follows: Based on the real-time response energy adjustment scheme, the data of the production line equipment nodes are loaded and processed, and the adjacency matrix and the feature matrix are used through the formula: ； Calculate the optimized feature representation of the node and generate processed node feature data, where: Represents the connection strength between device nodes. represents the original feature data, represents the node efficiency coefficient, Represents key data indicators, Represents the processed node feature data; Based on the processed node feature data, the graph neural network model is used for feature learning, referring to the node data dependency and node stability factor, through the formula: ； Update node features to generate enhanced features of device nodes, where: Representative The node features after iterations are Representative The weight matrix of the layer, represents the adjacency matrix, Representative The node features of the iteration, represents data dependency, represents the node stability factor; Analyze the enhanced features of the device nodes, identify anomalies and bottlenecks in data interaction, and use the formula: ； Determine key nodes and generate device interaction analysis results, including: Represents the key node, Represents the node features of the graph neural network, represents the weight factor, Represents the discrimination threshold.

6. The intelligent monitoring method for the plastic bag production process according to claim 5 is characterized in that: The steps for obtaining the process optimization strategy are specifically as follows: Based on the device interaction analysis results, the nodes with low efficiency are located by the formula: ； Calculate the efficiency loss of the node and generate the node efficiency evaluation result, where: represents the node efficiency evaluation result, represents the efficiency score of the node, Represents the interaction data of the node, represents the node importance index, Represents data stability; Based on the node efficiency evaluation results, the key bottleneck area is identified using the formula: ； Adjust the production process and generate a preliminary process adjustment plan, including: Represents the preliminary process adjustment plan, represents the node efficiency evaluation result, Represents the bottleneck resolution strategy, represents the potential improvement factor, Represents the feasibility of adjustment, represents the difficulty of implementation; Summarize the preliminary process adjustment plan and the overall production target, optimize the production configuration, and use the formula: ； Get the process optimization strategy, where Represents process optimization strategy, Represents the preliminary process adjustment plan, represents the resource allocation coefficient, represents the adjustment efficiency, Represents the response speed, Represents the persistence of the effect.

7. The intelligent monitoring method for the plastic bag production process according to claim 6, characterized in that: The specific steps for obtaining the continuously monitored production adjustment plan are: Based on the process optimization strategy, simulation tests are conducted, data is collected, efficiency indicators are used, and the comparison coefficients before and after are adjusted. The formula is: ； Evaluate the efficiency change before and after the equipment is adjusted, and generate the efficiency change evaluation results, where: represents the efficiency change evaluation result, represents the adjusted efficiency, represents the efficiency before adjustment, represents the adjustment effect coefficient, Represents the influence of environmental variables, represents the simulation error, Represents data reliability; According to the above efficiency change evaluation results, adjust the production line configuration, refer to resource allocation efficiency and production rhythm adjustment, through the formula: ； Optimize production configuration and generate adjusted production configuration plan, where: Represents the adjusted production configuration plan, represents the efficiency of resource allocation, represents the efficiency change evaluation result, Represents the production rhythm adjustment coefficient, Represents the speed of technological updates. represents the optimized index for adjustment; Based on the adjusted production configuration plan, continuous monitoring and optimization are implemented using the formula: ； Continuously optimize production configuration and generate continuously monitored production adjustment plans, including: Represents a production adjustment plan that is continuously monitored, Represents the adjusted production configuration plan, represents the real-time feedback adjustment coefficient, Represents the optimization adjustment range, Represents continuous improvement indicators, Represents reaction sensitivity.

8. An intelligent monitoring system for the production process of plastic bags, characterized in that: According to the method for intelligent monitoring of the plastic bag production process according to any one of claims 1 to 7, the system comprises: The energy allocation module monitors the real-time energy consumption of the production line and the market energy supply based on the production line speed sensor and operation status monitoring, compares the differences and makes adjustments, dynamically allocates the supply plan according to production demand, reduces ineffective energy consumption, and obtains the best energy utilization benefits; The production adjustment module adopts the optimal energy utilization efficiency, adjusts the production speed and machine operation parameters, synchronizes the machine status in real time and matches the energy supply, optimizes resource utilization, and obtains adjusted production parameters; The equipment maintenance strategy module uses the adjusted production parameters to monitor the performance of key equipment and predict maintenance time, arrange regular inspections and maintenance, avoid sudden failures, and formulate equipment maintenance plans; The production efficiency improvement module optimizes the production process and adjusts the production line layout based on the equipment maintenance plan, implements efficiency testing and records the results, and creates efficiency optimization results; The environmental monitoring module tracks key indicators of the production environment including temperature and humidity according to the efficiency optimization results, adjusts the control configuration response, and builds a production adjustment plan for continuous monitoring.

Images