Production and environment data fusion and cooperative control method and system

Abstract

The invention discloses a production and environment data fusion and cooperative control method and system, and relates to the field of industrial informatization and intelligent manufacturing. According to the method, production execution data and environment monitoring data are collected, and a unified data structure is constructed; calculating a spatial correlation degree according to a workshop topological structure, determining a monitoring point set and a weight coefficient, and calculating a representative environment parameter value based on a time window; fusing the process parameters and the environment parameters to form a data set; environment influence factors and process response factors are extracted, an incidence matrix is constructed, a constraint function is established, a process parameter value range is determined, and a constraint rule is generated; environmental parameters are monitored in real time, constraint rules are triggered when threshold values are exceeded, adjustment values are calculated, a scheme is generated, and automatic parameter adjustment is achieved. According to the method, the environmental factors are used as constraint conditions for production scheduling and process parameter setting, and the production efficiency is optimized on the premise of environment compliance.

Description

Technical Field

[0001] This application relates to the field of industrial informatization and intelligent manufacturing technology, specifically to a method and system for the fusion and collaborative control of production and environmental data. Background Technology

[0002] In the printing and manufacturing industry, production processes typically rely on Manufacturing Execution Systems (MES) to manage and schedule production tasks, equipment status, and process parameters, thereby achieving refined control of the production process. Simultaneously, to meet environmental regulatory requirements, companies usually deploy Environmental Management Systems (EMS) to monitor environmental parameters such as volatile organic compounds (VOCs), odor gas concentrations, temperature, and humidity in the workshop in real time.

[0003] In existing technologies, Manufacturing Execution System (MES) and Electronic Manufacturing System (EMS) typically operate as two independent systems. MES focuses on production process control and scheduling optimization, while EMS focuses on environmental data acquisition and alarm management. Significant differences exist in their system architecture, data structure, and application objectives, resulting in a lack of effective correlation and integration between production and environmental data. Furthermore, in printing workshops, the inks, solvents, and other substances used in the production process release certain concentrations of volatile pollutants. These environmental factors not only affect workshop air quality but also have potential impacts on production stability, product quality, and equipment operating status. However, existing MES systems typically do not consider environmental factors as constraints when scheduling production and setting parameters, and the environmental data collected by the EMS system is only used for exceeding alarm limits, without participating in the dynamic control of the production process. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for the fusion and collaborative control of production and environmental data, so as to solve the problems mentioned in the background art.

[0005] In a first aspect, one embodiment of this application provides a method for the fusion and collaborative control of production and environmental data. The method includes: collecting production execution data and environmental monitoring data; the production execution data includes production task identifiers and process parameters; the environmental monitoring data includes environmental parameter values, monitoring point location coordinates, and data collection timestamps; constructing a unified data structure for the production execution data and environmental monitoring data using a multi-dimensional tagging system to generate standardized production execution data and environmental monitoring data; the multi-dimensional tagging system includes time dimension tags, spatial dimension tags, production dimension tags, and environmental dimension tags; calculating the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology and determining a set of associated monitoring points and weight coefficients for each production operation area; extracting environmental parameters corresponding to the time period of the production execution data from the environmental monitoring data based on a time window and calculating the weighted average within the time window using a weighted average method. The system collects representative environmental parameter values; queries the corresponding task process requirements based on the production task identifier, and combines the associated monitoring point set and weight coefficients to fuse the process parameters with the corresponding representative environmental parameters, forming a fused dataset containing production and environmental information; extracts environmental impact factors and process response factors from the fused dataset and constructs an environment-process correlation matrix; establishes constraint functions between environmental parameters and process parameters based on the environment-process correlation matrix, determines the allowable value range of process parameters under different environmental conditions, and generates a set of environmental constraint rules; collects current environmental parameters in real time, matches the current environmental parameters with the set of environmental constraint rules, and triggers the corresponding constraint rules when the current environmental parameters exceed the preset threshold; calculates the adjustment value of the process parameters based on the triggered constraint rules and constraint functions and generates a process parameter adjustment plan; and executes the process parameter adjustment plan to achieve automatic adjustment of process parameters.

[0006] In conjunction with the first aspect, in some implementations of the first aspect, after generating the process parameter adjustment plan, the following is also included: assessing the adjusted production cycle time, unit product production time, and task delivery delay risk according to the process parameter adjustment plan; when the task delivery delay risk exceeds the preset risk threshold or the capacity reduction exceeds the preset capacity reduction threshold, performing production scheduling optimization, and compensating for the capacity change caused by the process parameter adjustment by adjusting the task execution order or equipment allocation plan.

[0007] In conjunction with the first aspect, some implementations of the first aspect, after executing the process parameter adjustment plan, also include: monitoring changes in environmental parameters and production process data after control execution, calculating control effectiveness indicators, recording effective control cases to the knowledge base, and optimizing and updating the environmental constraint function based on the control effect.

[0008] In conjunction with the first aspect, in some implementations of the first aspect, the spatial correlation between environmental monitoring points and production operation areas is calculated based on the workshop topology, and a set of associated monitoring points and weight coefficients are determined for each production operation area. Environmental parameters corresponding to the production execution data time period are extracted from the environmental monitoring data based on a time window, and a weighted average method is used to calculate representative environmental parameter values ​​within the time window. This includes: obtaining the spatial location of production equipment, the layout of the ventilation system, workshop zoning information, and airflow direction information in the workshop topology; dividing the workshop space into areas according to production processes based on the spatial location of production equipment, the layout of the ventilation system, workshop zoning information, and airflow direction information, with each production operation area corresponding to a spatial range; and calculating the spatial straight-line distance between each environmental monitoring point and the center point of each production operation area. The wind direction influencing factor is determined based on the layout of the air supply and exhaust system and the prevailing wind direction. The airflow diffusion correction factor is determined based on the distribution of obstacles and airflow paths within the workshop. The spatial correlation between each production operation area and each environmental monitoring point is calculated based on the spatial straight-line distance, wind direction influencing factor, and airflow diffusion correction factor. The spatial correlation is normalized to obtain the weighting coefficient. For each production operation area, a preset number of environmental monitoring points with the highest spatial correlation are selected to form a set of associated monitoring points. For each production record in the production execution data, the environmental parameter values ​​within the time window centered on the timestamp are extracted from the environmental monitoring data. The time weight is calculated based on the time distance between the collection time of the environmental parameter value and the timestamp of the production record. The time weight is used to perform a weighted average of multiple environmental parameter values ​​within the time window to obtain a representative environmental parameter value.

[0009] In conjunction with the first aspect, in certain implementations of the first aspect, the corresponding task process requirements are queried based on the production task identifier. Combined with the set of associated monitoring points and weight coefficients, the process parameters are fused with the corresponding representative environmental parameters to form a fused dataset containing both production and environmental information. This includes: for each production record in the production execution data, querying the corresponding task process requirements from the production process database based on the production task identifier in the production record. The task process requirements include the standard process parameter range, product quality standards, and process control requirements; and querying the associated monitoring points corresponding to the production operation area from the spatial mapping table based on the timestamp and production operation area number of the production record. The process involves: 1) Extracting representative environmental parameter values ​​from each associated monitoring point within the corresponding time window of the production record from the time alignment processing results; 2) For multiple monitoring points associated with the production operation area, weighted aggregation of the representative environmental parameter values ​​of each monitoring point is performed using weighted coefficients to obtain a comprehensive environmental parameter value; 3) Weighted aggregation of the representative environmental parameter values ​​of each monitoring point is performed separately using weighted coefficients to obtain an environmental parameter vector containing multiple types of environmental parameters, including volatile organic compound concentration, temperature, and humidity; 4) Merging the environmental parameter vector, task process requirements, and process parameters, production task identifiers, spatial locations, and timestamps in the production record to form a fused dataset.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, environmental impact factors and process response factors are extracted from the fusion dataset and an environment-process correlation matrix is ​​constructed. Based on the environment-process correlation matrix, constraint functions are established between environmental parameters and process parameters. The allowable range of process parameters under different environmental conditions is determined, and a set of environmental constraint rules is generated. This includes: calculating the correlation coefficient between each environmental impact factor and each process response factor; constructing an environment-process correlation matrix, which represents the correlation strength between corresponding environmental parameters and process parameters; environmental impact factors including volatile organic compound concentration, odor index, temperature, and humidity; and process response factors including printing speed, drying temperature, air supply volume, and exhaust volume; dividing the range of environmental parameters into normal intervals, warning intervals, and over-limit intervals; establishing piecewise constraint functions for different intervals, which determine the adjustment coefficients of process parameters under corresponding environmental parameter values; and generating a set of environmental constraint rules based on the piecewise constraint functions, where each constraint rule includes a trigger condition, the corresponding process parameter, the adjustment direction, and the adjustment magnitude.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the current environmental parameters are matched with a set of environmental constraint rules. When the current environmental parameters exceed a preset threshold, the corresponding constraint rule is triggered. Based on the triggered constraint rule, the adjustment value of the process parameters is calculated using a constraint function, and a process parameter adjustment scheme is generated. This includes: comparing the real-time collected current environmental parameters with the triggering conditions of each constraint rule in the set of environmental constraint rules one by one; when the current environmental parameters exceed the preset threshold, marking the constraint rules that meet the triggering conditions as active; extracting the type, direction, and baseline adjustment range of the process parameters to be adjusted from the active constraint rules; substituting the current environmental parameters into the corresponding constraint function to calculate the target value of the process parameters; calculating the adjustment value of the process parameters based on the difference between the current value and the target value of the process parameters; when multiple environmental parameters exceed the preset threshold simultaneously, assigning constraint priority weights to each environmental parameter, calculating the comprehensive constraint strength based on the constraint priority weights, and determining the joint adjustment value of the process parameters based on the comprehensive constraint strength; and summarizing all process parameters to be adjusted and their adjustment values ​​to form a process parameter adjustment scheme.

[0012] In conjunction with the first aspect, in certain implementations of the first aspect, based on the process parameter adjustment plan, the adjusted production cycle time, unit product production time, and task delivery delay risk are assessed; when the task delivery delay risk exceeds a preset risk threshold or the capacity reduction exceeds a preset capacity reduction threshold, production scheduling optimization is performed to compensate for the capacity changes caused by the process parameter adjustment by adjusting the task execution order or equipment allocation plan, including: calculating the adjusted production cycle time and unit product production time based on the process parameter adjustment values ​​in the process parameter adjustment plan; comparing the adjusted production time with the task delivery date in the current production plan to determine whether there is a delivery delay risk; when there is... When facing delivery delay risks, production scheduling optimization is initiated. Optimization strategies include adjusting task execution order, activating backup production lines, increasing equipment parallelism, or optimizing production batches. For task execution order adjustment, tasks with less environmental impact are prioritized, while high-polluting tasks are postponed or distributed. For equipment parallelism strategies, backup equipment is activated or the number of parallel equipment is increased to compensate for capacity losses caused by reduced single-line speed by improving equipment utilization. For batch optimization, production batches and batch changeover frequency are adjusted to reduce changeover time. Based on equipment capacity constraints, material supply constraints, process flow constraints, and process parameter adjustment schemes, a scheduling optimization model is established to solve for the optimized production scheduling scheme.

[0013] In conjunction with the first aspect, in certain implementations of the first aspect, monitoring changes in environmental parameters and production process data after control execution, calculating control effectiveness indicators, and recording effective control cases in a knowledge base include: continuously collecting environmental parameter change data and production process data after control command execution; production process data includes the actual execution values ​​of adjusted process parameters, equipment operating status, and product quality indicators; calculating control effectiveness indicators, including environmental improvement rate, environmental compliance time, control stability, and production efficiency impact rate; determining the control measures are effective when the environmental improvement rate is greater than a preset improvement threshold and the production efficiency impact rate is less than a preset impact threshold; and recording effective control cases in a knowledge base. Control cases are recorded in the knowledge base. These control cases include the initial environmental state, triggered constraint rules, process parameter adjustment schemes, environmental parameter change curves, production process data, and control effectiveness indicators. Based on these control cases, the threshold parameters and adjustment coefficients of the constraint functions are optimized and updated. The environmental improvement rate represents the degree to which environmental parameters improve towards the target value, calculated based on the environmental parameter values ​​before control, the environmental parameter values ​​at the stable point after control, and the target threshold. Environmental compliance time represents the time required for environmental parameters to drop to the normal threshold after control is implemented. Control stability represents the standard deviation of environmental parameter fluctuations after control. Production efficiency impact rate represents the percentage decrease in production capacity caused by control measures.

[0014] Secondly, one embodiment of this application provides a production and environmental data fusion and collaborative control system. This system includes: a data acquisition module for acquiring production execution data and environmental monitoring data; the production execution data includes production task identifiers and process parameters, and the environmental monitoring data includes environmental parameter values, monitoring point location coordinates, and data acquisition timestamps; a data modeling module for constructing a unified data structure for the production execution data and environmental monitoring data using a multi-dimensional labeling system, generating standardized production execution data and environmental monitoring data; the multi-dimensional labeling system includes time dimension labels, spatial dimension labels, production dimension labels, and environmental dimension labels; and a spatiotemporal mapping module for calculating the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, determining a set of associated monitoring points and weight coefficients for each production operation area, extracting environmental parameters corresponding to the time period of the production execution data from the environmental monitoring data based on a time window, and calculating the representativeness within the time window using a weighted average method. The system comprises the following modules: an environmental parameter value module; a data fusion module, used to query the corresponding task process requirements based on the production task identifier, and combine the associated monitoring point set and weight coefficients to fuse the process parameters with the corresponding representative environmental parameters, forming a fused dataset containing production and environmental information; a constraint modeling module, used to extract environmental impact factors and process response factors from the fused dataset and construct an environment-process correlation matrix, establish constraint functions between environmental parameters and process parameters based on the environment-process correlation matrix, determine the allowable value range of process parameters under different environmental conditions, and generate a set of environmental constraint rules; a control decision module, used to collect current environmental parameters in real time, match the current environmental parameters with the set of environmental constraint rules, trigger the corresponding constraint rules when the current environmental parameters exceed a preset threshold, calculate the adjustment value of the process parameters based on the triggered constraint rules and constraint functions, and generate a process parameter adjustment plan; and an instruction issuance module, used to execute the process parameter adjustment plan to achieve automatic adjustment of process parameters.

[0015] Compared with the prior art, the beneficial effects of this application are: 1. This application constructs a unified data structure using a multi-dimensional labeling system, calculates spatial correlation based on the workshop topology, determines the set of associated monitoring points and weight coefficients, and extracts representative environmental parameter values ​​based on time windows. This achieves accurate attribution of environmental monitoring data to production operation areas and precise spatiotemporal correspondence. This enables environmental data to go beyond simply triggering alarms for exceeding limits; it allows for dynamic control of the production process, making environmental factors a crucial constraint for production scheduling and process parameter setting, thereby optimizing production efficiency while ensuring environmental compliance.

[0016] 2. This application extracts the correlation coefficient between environmental impact factors and process response factors, divides the range of environmental parameters into normal, warning, and over-limit intervals, and establishes corresponding constraint functions. It generates a set of environmental constraint rules that include triggering conditions, adjustment directions, and adjustment magnitudes. When real-time environmental parameters exceed preset thresholds, the constraint rules are automatically triggered, and process parameter adjustment values ​​are calculated. This allows for timely adjustment of process parameters such as printing speed, drying temperature, air supply volume, and exhaust volume when environmental quality deteriorates. This ensures that the workshop environment meets standards and compensates for capacity changes caused by process parameter adjustments through production scheduling optimization, achieving a dynamic balance between environmental protection and production efficiency. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a production and environmental data fusion and collaborative control method provided in an embodiment of this application; Figure 2 A flowchart illustrating a production and environmental data fusion and collaborative control method provided in another embodiment of this application; Figure 3 A flowchart illustrating a production and environmental data fusion and collaborative control method provided in another embodiment of this application; Figure 4 This is a flowchart illustrating an embodiment of the present application, which calculates the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, determines the set of associated monitoring points and weight coefficients for each production operation area, extracts environmental parameters from environmental monitoring data corresponding to the time period of production execution data based on a time window, and calculates representative environmental parameter values ​​within the time window using a weighted average method. Figure 5 This is a flowchart illustrating how, in one embodiment of this application, the process parameters are fused with the corresponding representative environmental parameters to form a fused dataset containing production information and environmental information by querying the corresponding task process requirements based on the production task identifier, combining the associated monitoring point set and weight coefficients, and then fusion. Figure 6 This is a flowchart illustrating the process of extracting environmental impact factors and process response factors from a fused dataset and constructing an environment-process correlation matrix, establishing constraint functions between environmental parameters and process parameters based on the environment-process correlation matrix, determining the allowable range of process parameters under different environmental conditions, and generating a set of environmental constraint rules, provided in one embodiment of this application. Figure 7 A flowchart illustrating how this application matches current environmental parameters with a set of environmental constraint rules, triggers the corresponding constraint rule when the current environmental parameter exceeds a preset threshold, calculates the adjustment value of the process parameter based on the constraint function according to the triggered constraint rule, and generates a process parameter adjustment scheme is provided. Figure 8This is a schematic diagram illustrating the process of evaluating the impact of process parameter adjustment schemes on production plans in an embodiment of this application. When the production plan is affected, production scheduling optimization is performed, and the capacity changes caused by process parameter adjustments are compensated by adjusting the task execution sequence or equipment allocation scheme. Figure 9 This is a flowchart illustrating the process of calculating control effectiveness indicators and recording effective control cases to a knowledge base based on changes in environmental parameters and production process data after monitoring and control execution, as provided in one embodiment of this application. Figure 10 This is a schematic diagram of the structure of a production and environmental data fusion and collaborative control system provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] Figure 1 This is a schematic flowchart illustrating a production and environmental data fusion and collaborative control method provided in an embodiment of this application. Figure 1 As shown, an embodiment of the production and environmental data fusion and collaborative control method provided in this application includes the following steps: Step 101: Collect production execution data and environmental monitoring data.

[0020] It should be understood that production execution data comes from the production process information of the MES system, which records specific production tasks and actual operating process parameters.

[0021] Environmental monitoring data comes from workshop environmental information collected by the EMS system, including environmental indicators such as air quality, temperature and humidity, as well as their measurement locations and times.

[0022] Step 102: Use a multi-dimensional tagging system to build a unified data structure for production execution data and environmental monitoring data, and generate standardized production execution data and environmental monitoring data.

[0023] It should be understood that the multidimensional labeling system is a labeling classification system that includes four dimensions: time, space, production, and environment, and is used to uniformly label data from different sources.

[0024] A unified data structure is a structured representation that converts the data from both the MES and EMS systems into the same format.

[0025] Step 103: Calculate the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, determine the set of associated monitoring points and weight coefficients for each production operation area, extract environmental parameters from environmental monitoring data corresponding to the time period of production execution data based on the time window, and calculate the representative environmental parameter values ​​within the time window using a weighted average method.

[0026] It should be understood that workshop topology refers to the physical layout information of the workshop, including equipment locations, ventilation systems, zoning, and other spatial structures. Spatial correlation refers to the intensity of spatial influence between environmental monitoring points and production areas, reflecting the representativeness of monitoring point data for that area.

[0027] The production operation area is a functional area of ​​the workshop divided according to the production process, with each area corresponding to a specific production activity. The set of associated monitoring points is a collection of environmental monitoring points that have the highest correlation with a certain production area.

[0028] Step 104: Based on the production task identifier, query the corresponding task process requirements, combine the associated monitoring point set and weight coefficients, and fuse the process parameters with the corresponding representative environmental parameters to form a fused dataset containing production information and environmental information.

[0029] It should be understood that task process requirements are the process standards for a specific production task, including specifications such as process parameter ranges and quality standards. A fusion dataset is a comprehensive data set that integrates production information and environmental information.

[0030] Step 105: Extract environmental impact factors and process response factors from the fused dataset and construct an environment-process correlation matrix. Based on the environment-process correlation matrix, establish constraint functions between environmental parameters and process parameters, determine the allowable range of process parameters under different environmental conditions, and generate a set of environmental constraint rules.

[0031] It should be understood that environmental impact factors are environmental parameters that affect the production process, such as VOC concentration, odor index, temperature, and humidity. Process response factors are process parameters that need to be adjusted in response to environmental changes, such as printing speed, drying temperature, and air supply and exhaust volume.

[0032] The environment-process correlation matrix represents a mathematical matrix that shows the strength of the correlation between various environmental parameters and various process parameters. The set of environmental constraint rules refers to a set of rules, each defining how process parameters should be adjusted under certain environmental conditions.

[0033] Step 106: Collect current environmental parameters in real time, match the current environmental parameters with the set of environmental constraint rules, and trigger the corresponding constraint rules when the current environmental parameters exceed the preset threshold. Calculate the adjustment value of the process parameters and generate a process parameter adjustment plan based on the triggered constraint rules and constraint functions.

[0034] It should be understood that the current environmental parameters are the workshop environmental parameter values ​​collected in real time at the current moment. The preset threshold is a pre-set critical value for the environmental parameters; exceeding this value indicates an environmental anomaly requiring intervention. Trigger constraint rules are control rules activated when environmental parameters meet specific conditions. Process parameter adjustment values ​​are the values ​​that need to be changed for the process parameters, calculated based on constraint functions. The process parameter adjustment scheme is a control plan that includes all process parameters that need adjustment and their target values.

[0035] Step 107: Execute the process parameter adjustment scheme to achieve automatic adjustment of process parameters.

[0036] By constructing a spatiotemporal fusion of production and environmental data and an environmental-process constraint function, the printing workshop can automatically and collaboratively adjust process parameters when environmental parameters exceed the standard. While ensuring environmental compliance, it can compensate for capacity loss through production scheduling optimization, thus solving the problem of disconnect between production control and environmental management caused by the independent operation of traditional MES and EMS systems.

[0037] Figure 2 This is a flowchart illustrating a production and environmental data fusion and collaborative control method provided in another embodiment of this application. Figure 2 As shown, in one embodiment of the production and environmental data fusion and collaborative control method provided in this application, after generating a process parameter adjustment scheme, the method further includes the following steps: Step 201: Based on the process parameter adjustment plan, assess the adjusted production cycle time, unit product production time, and task delivery delay risk.

[0038] It should be understood that the system will calculate how much the adjusted production speed will slow down and how much the production time for each product will increase, and will determine whether this will lead to the inability to complete the order on time.

[0039] Step 202: When the risk of task delivery delay exceeds the preset risk threshold or the capacity reduction exceeds the preset capacity reduction threshold, perform production scheduling optimization and compensate for the capacity changes caused by the adjustment of process parameters by adjusting the task execution order or equipment allocation scheme.

[0040] It should be understood that if the previous assessment shows that the risk of delivery delays is too high or the loss of production capacity is too large, the system will compensate for the decline in production capacity caused by environmental control by adjusting which orders to be made first and which orders to be made later, or by adjusting which equipment to use and how many production lines to be activated, while keeping environmental control measures effective, thereby finding a balance between environmental compliance and production delivery.

[0041] Figure 3 This is a flowchart illustrating a production and environmental data fusion and collaborative control method provided in another embodiment of this application. Figure 3 As shown, in one embodiment of the production and environmental data fusion and collaborative control method provided in this application, after executing the process parameter adjustment scheme, the method further includes the following steps: Step 301: Monitor changes in environmental parameters and production process data after control execution, calculate control effectiveness indicators, and record effective control cases to the knowledge base.

[0042] It should be understood that the system monitors changes in environmental parameters and production process data in real time after the implementation of control measures, evaluates the control effect by calculating control effectiveness indicators, and records verified and effective control cases as knowledge accumulation in the knowledge base.

[0043] Step 302: Optimize and update the environmental constraint function based on the control effect.

[0044] It should be understood that the system adjusts and optimizes the parameters or weights of the environmental constraint function based on the control effect evaluation results obtained in step 301, so that the constraint function can more accurately reflect the mapping relationship between the actual production environment and control requirements, and realize the continuous improvement of the system control strategy.

[0045] Figure 4 This embodiment of the application provides a flowchart illustrating the process of calculating the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, determining a set of associated monitoring points and weight coefficients for each production operation area, extracting environmental parameters from environmental monitoring data corresponding to the time period of production execution data based on a time window, and calculating representative environmental parameter values ​​within the time window using a weighted average method. Figure 4 As shown in the embodiment of this application, the method for production and environmental data fusion and collaborative control calculates the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, determines the set of associated monitoring points and weight coefficients for each production operation area, extracts environmental parameters from environmental monitoring data corresponding to the time period of production execution data based on a time window, and calculates representative environmental parameter values ​​within the time window using a weighted average method, including the following steps: Step 401: Obtain the spatial location of production equipment, the layout of the ventilation system, workshop zoning information, and airflow direction information in the workshop topology.

[0046] It should be understood that the spatial location of production equipment includes the three-dimensional coordinates of each printing, drying, and post-processing device and the space occupied by the equipment; the layout of the air supply and exhaust system includes the location of air inlets and outlets, fan configuration parameters, and design air volume; workshop zoning information includes the spatial boundary coordinates of functional areas such as the pre-press preparation area, printing operation area, drying and curing area, and post-processing area; and airflow direction information includes the prevailing wind direction, air supply and exhaust airflow paths, and airflow diffusion characteristics within the workshop. The above information is extracted from the workshop facility management system or building information model, providing basic data support for spatial mapping and correlation calculations.

[0047] Step 402: Based on the spatial location of production equipment, the layout of the air supply and exhaust system, workshop zoning information, and airflow direction information, the workshop space is divided into areas according to the production process, with each production operation area corresponding to a spatial range.

[0048] Specifically, the zoning follows the logical sequence of the production process, grouping equipment performing the same or similar processes into the same production area to ensure that each production area has clearly defined spatial boundaries. For the printing workshop, it is divided into pre-press preparation, gravure printing, flexographic printing, drying and curing, lamination, and finishing areas. Each production area records its center point coordinates, coverage area, list of associated equipment, and process type identifier. The center point coordinates are determined by calculating the geometric center of all equipment within the area, serving as a reference point for calculating the spatial correlation between the area and environmental monitoring points.

[0049] Step 403: Calculate the straight-line distance between each environmental monitoring point and the center point of each production operation area, determine the wind direction influence factor based on the layout of the air supply and exhaust system and the prevailing wind direction, and determine the airflow diffusion correction factor based on the distribution of obstacles in the workshop and the airflow path.

[0050] Specifically, the spatial straight-line distance is calculated using the Euclidean distance formula for the production operation area. center point coordinates and environmental monitoring points Position coordinates The straight-line distance between the two for: ; The wind direction influence factor is determined based on the angle between the azimuth of the environmental monitoring point relative to the production area and the prevailing wind direction. When the monitoring point is located downwind of the production area, the wind direction influence factor takes a larger value, indicating that the monitoring point is more susceptible to the influence of pollutants emitted from the production area. When the monitoring point is located upwind or laterally, the wind direction influence factor takes a smaller value. The specific calculation formula is as follows: ,in For monitoring points Relative to the production operation area The angle between the azimuth and the prevailing wind direction. The wind direction influence coefficient is set based on the ventilation intensity of the workshop's air supply and exhaust system. The airflow diffusion correction factor is determined based on the obstruction effect of obstacles such as workshop walls, equipment, and shelves on airflow propagation. When there are physical obstacles between the production area and the monitoring point, the airflow diffusion correction factor decreases, indicating that the pollutant diffusion path is blocked; when there are no obvious obstacles between the two and the airflow path is unobstructed, the airflow diffusion correction factor is close to 1.

[0051] Step 404: Calculate the spatial correlation between each production operation area and each environmental monitoring point based on the spatial straight-line distance, wind direction influence factor and airflow diffusion correction factor, and normalize the spatial correlation to obtain the weight coefficient.

[0052] Specifically, for production operation areas and environmental monitoring points Its spatial correlation The calculation formula is: ; in, Wind direction is an influencing factor. This is the airflow diffusion correction factor. This represents the straight-line distance in space. The production operation area is calculated. After determining the spatial correlation of all environmental monitoring points, the spatial correlation of all monitoring points associated with the production operation area is normalized. The normalization formula is as follows: ,in This is an index of all monitoring points associated with this production area. (Normalized) This refers to the weighting coefficient, ensuring that the sum of the weighting coefficients of all associated monitoring points in the same production operation area is 1, which facilitates weighted aggregation calculation.

[0053] Step 405: For each production operation area, select a preset number of environmental monitoring points with the highest spatial correlation to form a set of related monitoring points.

[0054] Specifically, the preset number is set based on the deployment density of environmental monitoring points in the workshop and the data processing capability, with a typical range of 3 to 8. For production operation areas... All environmental monitoring points were classified according to their spatial correlation with the production and operation area. Sort the monitoring points from largest to smallest, select the top N monitoring points to form a set of associated monitoring points for the production area, and record them as follows: Simultaneously record the weight coefficients corresponding to each monitoring point. The set of associated monitoring points is stored in a spatial mapping table. The data structure of the mapping table is: production operation area number, associated monitoring point list, weight coefficient vector, and update timestamp. When the workshop layout is adjusted or the monitoring point location changes, steps 401 to 405 are re-executed to update the spatial mapping table to ensure the accuracy of the spatial mapping relationship.

[0055] Step 406: For each production record in the production execution data, extract the environmental parameter values ​​within the time window centered on the timestamp from the environmental monitoring data.

[0056] Specifically, regarding the timestamps of production records Define the time window length Extracting time range from environmental monitoring data stream All environmental monitoring records within the time window. The time window length is determined based on the rate of change and sampling frequency of environmental parameters. For parameters that change slowly, such as temperature and humidity, the time window length can be set to 10 to 30 minutes; for parameters that change rapidly, such as volatile organic compound (VOC) concentration, the time window length can be set to 3 to 10 minutes. The time window may contain multiple environmental monitoring records from multiple monitoring points. Each record includes the environmental parameter value, monitoring point number, and data collection timestamp. These environmental monitoring records are grouped by monitoring point number to form a sequence of environmental parameter values ​​for each monitoring point within that time window, providing a data basis for weighted average calculations.

[0057] Step 407: Calculate the time weight based on the time distance between the collection time of the environmental parameter value and the timestamp of the production record.

[0058] Specifically, the collection time of a certain environmental parameter value within the time window Its relationship with the production record timestamp The time distance is The time weight of this environmental parameter value is calculated using a Gaussian kernel function, and the formula is as follows: ; in, This is the time window width parameter. The weights at the edges of the time window are ensured to decay to approximately 10% of the weights at the center. This weight allocation method ensures that environmental parameter values ​​whose acquisition time is closer to the production record timestamp receive higher weights, consistent with the temporal correspondence between environmental parameters and the production process. After calculating the time weights for all environmental parameter values ​​at the same monitoring point within the time window, normalization is performed to ensure that the sum of all time weights for that monitoring point is 1.

[0059] Step 408: Use time weighting to perform a weighted average of multiple environmental parameter values ​​within the time window to obtain representative environmental parameter values.

[0060] Specifically, for monitoring points The sequence of environmental parameter values ​​collected within the time window Its corresponding normalized time weight is The representative environmental parameter value of this monitoring point within this time window is calculated as follows: ; in, This serves as the sequence index for the environmental parameter values ​​of the monitoring point within the time window. Representative environmental parameter values ​​comprehensively reflect the environmental state of the monitoring point within the corresponding time period of the production record, eliminating the impact of random fluctuations from single measurements and improving the accuracy of aligning environmental parameters with the production process time. After calculating the representative environmental parameter values ​​for all associated monitoring points, the representative environmental parameter values ​​of each monitoring point are spatially weighted and aggregated using the weighting coefficients determined in step 404 to obtain the comprehensive environmental parameter value for the production operation area within the time period of the production record. This value will be used for fusion processing with process parameters.

[0061] Figure 5 This is a flowchart illustrating an embodiment of the present application, showing how to query the corresponding task process requirements based on the production task identifier, combine the associated monitoring point set and weight coefficients, and fuse process parameters with corresponding representative environmental parameters to form a fused dataset containing production and environmental information. Figure 5 As shown in the embodiment of this application, the production and environmental data fusion and collaborative control method involves querying the corresponding task process requirements based on the production task identifier, combining the associated monitoring point set and weight coefficients, and fusing the process parameters with the corresponding representative environmental parameters to form a fused dataset containing production information and environmental information. The method includes the following steps: Step 501: For each production record in the production execution data, query the corresponding task process requirements from the production process database based on the production task identifier in the production record.

[0062] It should be understood that the standard process parameter range includes the printing speed range, drying temperature range, air supply range, and exhaust range; product quality standards include printing accuracy requirements, color deviation tolerances, and surface quality indicators; and process control requirements include process parameter adjustment step size, parameter response time, and inter-process coupling constraints.

[0063] Step 502: Based on the timestamp of the production record and the production operation area number, query the set of associated monitoring points and weight coefficients corresponding to the production operation area from the spatial mapping table.

[0064] It should be understood that the system can extract basic data such as the three-dimensional coordinates of each production equipment, the layout of the ventilation system, the boundaries of functional areas, and the airflow direction from the workshop facility management system. Based on this, the workshop is divided into several production operation areas according to the production process, and the center point coordinates of each area are determined. Subsequently, for each pair of production operation areas and environmental monitoring points, the spatial correlation is calculated by comprehensively considering the spatial straight-line distance, wind direction influence factor, and airflow diffusion correction factor, and then normalized to obtain a weight coefficient. Finally, a preset number of environmental monitoring points, typically 3 to 8, are selected for each production operation area according to the correlation from high to low to form a set of associated monitoring points. These, along with the corresponding weight coefficient vector, area number, and update timestamp, are written into the spatial mapping table. When the workshop layout or the location of the monitoring points changes, the above process is re-executed to ensure the continued accuracy of the mapping relationship. The spatial mapping table storage format includes the production operation area number, the list of associated monitoring points, the weight coefficient vector, and the update timestamp; the set of associated monitoring points is a preset number of environmental monitoring points selected in step 102 based on spatial correlation; the weight coefficient is a value after normalizing the spatial correlation, reflecting the contribution of each monitoring point to the environmental characterization of the production operation area.

[0065] Step 503: Extract representative environmental parameter values ​​of each associated monitoring point within the time window corresponding to the production record from the time alignment processing results.

[0066] It should be understood that the time alignment processing result is the processing result after aligning the environmental monitoring data in time dimension using the time window method in step 103; the representative environmental parameter value is the representative value obtained by weighting the multiple environmental parameter values ​​within the time window using time weight; for each monitoring point in the associated monitoring point set, its representative environmental parameter value within the time window is extracted, and the representative environmental parameter value includes the representative value of volatile organic compound concentration, the representative value of temperature, and the representative value of humidity.

[0067] Step 504: For multiple monitoring points associated with the production operation area, the representative environmental parameter values ​​of each monitoring point are weighted and aggregated using weighting coefficients to obtain a comprehensive environmental parameter value.

[0068] It should be understood that for each type of environmental parameter, the representative value of that type of environmental parameter at each monitoring point is multiplied by its corresponding weighting coefficient, and then summed. The calculation formula is that the comprehensive environmental parameter value is equal to the sum of the products of the representative environmental parameter values ​​at each monitoring point and their weighting coefficients. Through this weighted aggregation process, data from multiple spatially distributed monitoring points are merged into a single comprehensive environmental status description value, achieving accurate attribution of environmental data to production and operation areas.

[0069] Step 505: The representative environmental parameter values ​​of each monitoring point are weighted and aggregated using weighting coefficients to obtain an environmental parameter vector containing multiple types of environmental parameters.

[0070] It should be understood that for each type of environmental parameter, such as volatile organic compound concentration, temperature, and humidity, the weighted aggregation calculation in step 504 is performed to obtain the comprehensive value of that type of environmental parameter; the comprehensive values ​​of each type of environmental parameter are combined to form an environmental parameter vector, and the data structure of the environmental parameter vector includes parameter type identifier, parameter value, measurement unit, and confidence information.

[0071] Step 506: Merge the environmental parameter vector, task process requirements, and process parameters, production task identifiers, spatial locations, and timestamps in the production records to form a fused dataset.

[0072] It should be understood that the fused dataset is organized using a five-tuple structure, represented as a combination of task identifier, process parameter set, environmental parameter set, timestamp, and spatial location. The process parameter set contains the actual process parameter execution values ​​in the production records and the standard process parameter ranges in the task process requirements. The environmental parameter set contains environmental parameter vectors and the measurement time and monitoring point location information of each environmental parameter. Through this merging operation, deep semantic fusion of production information and environmental information is achieved, ensuring that each fused dataset contains not only detailed information about the production process but also the accurate environmental state associated with the time and location of the process.

[0073] Figure 6 This document provides a flowchart illustrating the process of extracting environmental impact factors and process response factors from a fused dataset and constructing an environment-process correlation matrix, establishing constraint functions between environmental parameters and process parameters based on the environment-process correlation matrix, determining the allowable range of process parameters under different environmental conditions, and generating a set of environmental constraint rules. Figure 6 As shown in the embodiment of this application, the method for production and environmental data fusion and collaborative control extracts environmental impact factors and process response factors from the fused dataset and constructs an environment-process correlation matrix. Based on the environment-process correlation matrix, a constraint function is established between environmental parameters and process parameters. The allowable range of process parameters under different environmental conditions is determined, and a set of environmental constraint rules is generated. The method includes the following steps: Step 601: Calculate the correlation coefficient between each environmental impact factor and each process response factor, and construct an environmental-process correlation matrix. The environmental-process correlation matrix represents the correlation strength between the corresponding environmental parameters and process parameters.

[0074] Specifically, numerical sequences of environmental impact factors and process response factors are extracted from the fused dataset. For each environmental impact factor and each process response factor, the Pearson correlation coefficient is calculated. Let the environmental impact factor be... The process response factor is Then the Pearson correlation coefficient The calculation formula is: ; in, This represents the covariance between environmental impact factors and process response factors. and These represent the standard deviations of the environmental impact factor and the process response factor, respectively. and These represent the means of the two, respectively. The sample size. When the absolute value of the correlation coefficient... When the value exceeds the preset significance threshold, a significant correlation is determined between the environmental impact factor and the process response factor.

[0075] The calculated correlation coefficients are used to construct an environment-process correlation matrix. The rows of the environment-process correlation matrix represent environmental impact factors, the columns represent process response factors, and the matrix elements are the corresponding correlation coefficients. The types of correlation relationships are also labeled. The types of correlation relationships include positive driving, negative driving, and bidirectional coupling. Positive driving means that an increase in process parameters leads to an increase in environmental parameters, negative driving means that an increase in process parameters leads to a decrease in environmental parameters, and bidirectional coupling means that process parameters and environmental parameters influence each other to form a feedback loop.

[0076] Step 602: Divide the range of environmental parameters into normal range, warning range and over-limit range.

[0077] Specifically, for each environmental impact factor, normal thresholds and excess thresholds are set. When the value of an environmental parameter is less than or equal to the normal threshold, the environmental parameter is in the normal range, indicating that the workshop environment is in good condition. When the value of an environmental parameter is greater than the normal threshold but less than or equal to the excess threshold, the environmental parameter is in the warning range, indicating that the environmental quality has begun to decline and intervention measures are needed. When the value of an environmental parameter is greater than the excess threshold, the environmental parameter is in the excess range, indicating that it violates environmental regulations and must be controlled immediately.

[0078] Normal thresholds and exceedance thresholds are set according to the limits for environmental parameters stipulated in national or local environmental protection standards, or according to the company's management strategy for balancing environmental quality and production efficiency.

[0079] Step 603: Establish piecewise constraint functions for different intervals, and determine the adjustment coefficients of process parameters under the corresponding environmental parameter values.

[0080] Specifically, environmental parameters The value range is divided into three intervals: normal interval, warning interval, and over-limit interval. Let the normal threshold be... The threshold for exceeding the limit is The environmental parameters are divided into intervals as follows, with piecewise constraint functions corresponding to different intervals. The expression is defined as follows: ; Within the normal range Process parameters No adjustments are needed due to environmental factors; process parameters remain at standard process values. Or adjustments may be made based on production needs. Within the warning range. A flexible constraint strategy is adopted. Among them, The intensity coefficient is adjusted to reflect the maximum allowable parameter adjustment ratio within the warning range. Within the exceedance range... A forced constraint strategy is adopted, and the process parameters are forcibly limited to the minimum allowable operating values. Or the highest allowed running value These limits are determined by the engineering constraints for stable equipment operation. The choice between a minimum and maximum value depends on the relationship between the process parameter and the environmental parameter. For process parameters that need to be reduced, such as printing speed, the process parameter is forcibly limited to the minimum permissible operating value; for process parameters that need to be increased, such as exhaust volume, the process parameter is forcibly limited to the maximum permissible operating value. These minimum or maximum permissible operating values ​​are determined by the engineering constraints for stable equipment operation, ensuring that the equipment can maintain a basic stable operating state even when environmental conditions are severely exceeded.

[0081] Step 604: Generate a set of environmental constraint rules based on the piecewise constraint function. Each constraint rule includes the triggering condition, the corresponding process parameters, the adjustment direction, and the adjustment range.

[0082] Specifically, piecewise constraint functions are transformed into constraint rules that can be directly invoked by the control system. Each constraint rule is expressed using a condition-action structure, including rule number, trigger condition, target process parameter, adjustment method, adjustment range, priority, and effective time. The trigger condition describes the state determination logic of the environmental parameter, including the type of the environmental parameter, the range of its current value, and its comparison with the threshold; the target process parameter specifies the process parameter object to which the constraint rule applies; the adjustment method describes the calculation method for adjusting the process parameter; the adjustment range provides the specific parameter adjustment value or adjustment formula; the priority is used to determine the execution order when multiple constraint rules are triggered simultaneously; and the effective time specifies the time validity of the constraint rule. The generated constraint rules are categorized and organized according to environmental parameter type and process parameter type to form an environmental constraint rule set, which supports dynamic addition, deletion, and modification operations.

[0083] Figure 7 This application provides a flowchart illustrating how current environmental parameters are matched with a set of environmental constraint rules. When the current environmental parameters exceed a preset threshold, the corresponding constraint rule is triggered. Based on the triggered constraint rule and a constraint function, the adjustment value of the process parameters is calculated, and a process parameter adjustment scheme is generated. Figure 7 As shown in the embodiment of this application, the production and environmental data fusion and collaborative control method matches the current environmental parameters with a set of environmental constraint rules. When the current environmental parameters exceed a preset threshold, the corresponding constraint rule is triggered. Based on the triggered constraint rule and the constraint function, the adjustment value of the process parameters is calculated and a process parameter adjustment scheme is generated. The method includes the following steps: Step 701: Compare the real-time collected current environmental parameters with the trigger conditions of each constraint rule in the environmental constraint rule set one by one.

[0084] It should be understood that the triggering conditions include the type of environmental parameter, the range in which the environmental parameter value is located, and the type of the associated production process.

[0085] Step 702: When the current environmental parameters exceed the preset threshold, mark the constraint rules that meet the trigger conditions as active.

[0086] It should be understood that the preset thresholds include normal thresholds and over-limit thresholds. When an environmental parameter exceeds the normal threshold, an early warning state is entered, and when an environmental parameter exceeds the over-limit threshold, an over-limit state is entered.

[0087] Step 703: Extract the type of process parameter to be adjusted, the adjustment direction, and the baseline adjustment range from the constraint rules in the active state.

[0088] It should be understood that the process parameter types include at least one of printing speed, drying temperature, air supply volume and exhaust volume, and the adjustment direction includes increasing or decreasing. The baseline adjustment range is determined according to the preset adjustment coefficient in the constraint rules.

[0089] Step 704: Substitute the current environmental parameters into the corresponding constraint function to calculate the target values ​​of the process parameters.

[0090] Specifically, different calculation formulas are used depending on the range of the current environmental parameters. Linear or nonlinear adjustment formulas are used in the warning range, and mandatory limits are used in the over-limit range.

[0091] Taking the constraint of VOC concentration in the gravure printing area on printing speed as an example. Let's assume a normal threshold. Exceeding the threshold Standard printing speed Minimum allowed operating speed Adjust the strength coefficient .

[0092] The current environmental parameters are collected in real time. Located in the warning zone Substitute into the linear adjustment formula for the warning interval: The target value is within the allowable operating range of the equipment. Based on this, the system generates a process parameter adjustment plan, instructing the printing speed to be reduced from the current value to 84 m / min.

[0093] If the current VOC concentration further increases to If the print speed exceeds the threshold, it enters the over-limit zone. The constraint function adopts a forced limit strategy, and the printing speed is directly and forcibly limited to the minimum allowable operating value. Linear calculations are no longer performed to ensure that the equipment can maintain basic stable operation even when environmental conditions are severely exceeded.

[0094] Step 705: Calculate the adjustment value of the process parameter based on the difference between the current value and the target value of the process parameter.

[0095] It should be understood that the adjustment value should be checked to see if it is within the allowable operating range of the equipment. If it exceeds the allowable range, the adjustment value should be corrected.

[0096] Step 706: When multiple environmental parameters exceed the preset threshold at the same time, a constraint priority weight is assigned to each environmental parameter, the comprehensive constraint strength is calculated based on the constraint priority weight, and the joint adjustment value of the process parameters is determined based on the comprehensive constraint strength.

[0097] It should be understood that the constraint priority weight is determined based on the comprehensive impact of environmental parameters on production safety, product quality, and environmental compliance. The comprehensive constraint strength is calculated based on the constraint priority weight and the constraint function corresponding to each environmental parameter. The joint adjustment value of the process parameters is determined based on the comprehensive constraint strength, and the engineering feasibility is verified to determine whether the combined process parameter combination after joint adjustment meets the basic requirements of the production process.

[0098] Step 707: Summarize all process parameters that need to be adjusted and their adjustment values ​​to form a process parameter adjustment plan.

[0099] It should be understood that the process parameter adjustment plan includes the values ​​of each process parameter before adjustment, the values ​​after adjustment, the adjustment range, and the expected environmental improvement effect.

[0100] Figure 8 This is a flowchart illustrating an embodiment of the present application, illustrating the process of evaluating the impact of process parameter adjustment schemes on production plans. When production plans are affected, production scheduling optimization is performed, and capacity changes caused by process parameter adjustments are compensated by adjusting task execution order or equipment allocation schemes. Figure 8 As shown in the embodiment of this application, the production and environmental data fusion and collaborative control method assesses the adjusted production cycle time, unit product production time, and task delivery delay risk according to the process parameter adjustment scheme. When the task delivery delay risk exceeds a preset risk threshold or the capacity reduction exceeds a preset capacity reduction threshold, production scheduling optimization is performed to compensate for the capacity changes caused by the process parameter adjustment by adjusting the task execution order or equipment allocation scheme. The method includes the following steps: Step 801: Calculate the adjusted production cycle time and unit product production time based on the process parameter adjustment values ​​in the process parameter adjustment plan.

[0101] Specifically, the adjustment values ​​of various process parameters involved in the process parameter adjustment plan are obtained, including printing speed, drying temperature, air supply volume, and exhaust volume. Based on the mapping relationship between process parameters and production cycle time, the adjusted single-equipment production cycle time is calculated. The reduction in printing speed directly leads to an extension of the production cycle time, and the adjustment of drying temperature affects drying time, thus affecting the overall cycle time. According to the cycle time and number of processes in the product process flow, the unit product production time is calculated, which is the sum of the cycle times of each process. For the currently executed production task, the estimated completion time of the task is calculated by combining the remaining quantity of the task and the adjusted unit product production time.

[0102] Step 802: Compare the adjusted production time with the task delivery date in the current production plan to determine whether there is a risk of delivery delay.

[0103] Specifically, the system queries the planned delivery date of the current production task from the production planning system; calculates the time difference between the estimated completion time and the planned delivery date; when the time difference is negative, it indicates a risk of delivery delay; it calculates the proportion of the delay time to the planned production cycle as a quantitative indicator of the delivery delay risk; it compares the delivery delay risk with a preset risk threshold, and triggers a production scheduling optimization process when the threshold is exceeded. The preset risk threshold is based on the proportion of the delay time to the planned production cycle, with a typical range of 5% to 20%. For urgent orders with strict delivery requirements or tasks with high customer service level agreements, the preset risk threshold is set at 5% to 10%, meaning scheduling optimization is triggered when the estimated delay time exceeds 5% to 10% of the planned production cycle; for regular batch production tasks with greater delivery flexibility, the preset risk threshold is relaxed to 15% to 20%. For example, a printing task has a planned production cycle of 100 hours, a planned delivery date at the end of the 100th hour, and a re-estimated estimated completion time after process parameter adjustments at the end of the 108th hour. The time difference is... The delay rate is 8% (8 hours). If the preset risk threshold for this task is set to 5%, then 8% exceeds the threshold, and the system determines that there is a significant risk of delivery delay, triggering the production scheduling optimization process. If the preset risk threshold is set to 10%, then 8% does not exceed the threshold, and the system determines that the current delay risk is within an acceptable range, and scheduling optimization will not be initiated for the time being.

[0104] Step 803: When there is a risk of delivery delay, production scheduling optimization is initiated. Optimization strategies include adjusting the task execution order, activating backup production lines, increasing equipment parallelism, or optimizing production batches.

[0105] Specifically, the current production task queue is analyzed to identify a set of adjustable tasks, which are those with high delivery time leeway or significant differences in environmental impact. The availability of backup production lines is assessed, including equipment status, staffing, and material preparation. The potential for increasing the parallelism of equipment on the current production line is evaluated to determine if there is any idle equipment that can be put into production. The production batch division scheme is analyzed to identify the time loss in batch switching. Based on the severity of the delivery delay risk and the availability of resources, one or more strategies are selected from adjusting the task execution order, activating backup production lines, increasing equipment parallelism, and optimizing production batches.

[0106] Step 804: Regarding the adjustment of the task execution order, tasks with less environmental impact will be prioritized, while high-pollution tasks will be postponed or carried out in a decentralized manner.

[0107] Specifically, based on historical production data and environmental monitoring data, each task in the task queue is labeled with an environmental impact level. The environmental impact level is determined based on the amount of volatile organic compound emissions, the intensity of odor generation, and the duration of the odor during task execution. Tasks with low environmental impact levels are moved to the front of the task queue to prioritize the allocation of production resources. High-pollution tasks with high environmental impact levels are postponed to the back of the task queue, or a single high-pollution task is split into multiple small batches and executed at different times to avoid concentrated emissions of pollutants. During the task sequencing process, the process constraints between tasks and the order of material preparation are also considered to ensure that the adjusted task sequence is technically feasible.

[0108] Step 805: For the equipment parallel strategy, enable backup equipment or increase the number of parallel equipment to compensate for the capacity loss caused by the decrease in single-line speed by improving equipment utilization.

[0109] Specifically, the process involves calculating the decrease in single-line capacity due to process parameter adjustments, where the decrease is the difference between the output per unit time before and after the adjustment; identifying the capacity gap that needs to be compensated to ensure that the adjusted total capacity meets the task delivery requirements; selecting available spare equipment from the equipment resource pool and checking the matching degree between the spare equipment's process capabilities and the current task; calculating the increase in the number of parallel equipment after activating the spare equipment; recalculating the total capacity and the estimated task completion time based on the capacity contribution of the newly added equipment; and evaluating the effect of the parallel equipment strategy on improving equipment utilization to ensure that parallel production can effectively compensate for the capacity loss caused by the decrease in single-line speed.

[0110] Step 806: For batch optimization, adjust the production batch size and batch switching frequency to reduce changeover time.

[0111] Specifically, the batch division scheme in the current production plan is analyzed, and the production batch size and batch changeover frequency of each batch are statistically analyzed. The changeover time required for each batch changeover is calculated, including equipment cleaning time, parameter debugging time, and first-piece inspection time. Under the premise of meeting material batch management requirements and product quality requirements, the production batch size per batch is appropriately increased to reduce the total number of batch changeovers, thereby reducing the cumulative changeover time. For small-batch, multi-variety production tasks, the batch changeover sequence is optimized by arranging product batches with similar process parameters adjacent to each other to reduce the changeover time per changeover. The total changeover time saved after batch optimization is calculated, and the improvement effect on task completion time is evaluated.

[0112] Step 807: Based on equipment capacity constraints, material supply constraints, process flow constraints, and process parameter adjustment schemes, establish a scheduling optimization model and solve for the optimized production scheduling scheme.

[0113] Specifically, a scheduling optimization model is established with the optimization objectives of minimizing the total task completion time and minimizing the penalty cost for delivery delays. A set of constraints is constructed, including equipment capacity constraints (maximum processing capacity of a single piece of equipment per unit time), material supply constraints (material arrival time and inventory limits for each time period), process flow constraints (sequence of task operations and waiting time limits between operations), and constraints on the range of process parameter values ​​determined by the process parameter adjustment scheme. The scheduling optimization model is solved using mixed integer programming or heuristic optimization algorithms to determine the equipment allocation scheme, start time, and end time for each production task. The optimized production scheduling scheme is output, including the updated task execution order, equipment resource allocation table, and production time schedule. The feasibility of the production scheduling scheme is verified to ensure that the risk of delivery delays is minimized while meeting environmental constraints.

[0114] Figure 9 This is a flowchart illustrating the process of calculating control effectiveness indicators and recording effective control cases in a knowledge base based on changes in environmental parameters and production process data after monitoring and control execution, as provided in one embodiment of this application. Figure 9 As shown in the figure, an embodiment of this application provides a production and environmental data fusion and collaborative control method that monitors changes in environmental parameters and production process data after control execution, calculates control effectiveness indicators, and records effective control cases to a knowledge base, including the following steps: Step 901: After the control command is executed, continuously collect environmental parameter change data and production process data.

[0115] Specifically, the data collection cycle for environmental parameter changes is determined based on the response speed of the environmental parameters. For environmental parameters with a fast response speed, a second-level collection cycle is used, while for environmental parameters with a slow response speed, a minute-level collection cycle is used. The actual executed values ​​of the adjusted process parameters include the actual values ​​of printing speed, drying temperature, air supply volume, and exhaust volume. The equipment operating status includes equipment load rate, operating stability, and fault alarm information. The product quality indicators include printing quality pass rate, color difference index, and product appearance defect rate.

[0116] Step 902: Calculate the control effectiveness index.

[0117] Specifically, the environmental improvement rate represents the degree to which environmental parameters improve towards the target value. It is calculated based on the environmental parameter values ​​before control, the environmental parameter values ​​at the stable point after control, and the target threshold. The calculation formula is: the environmental improvement rate equals the difference between the environmental parameter values ​​before control and the environmental parameter values ​​at the stable point after control, divided by the difference between the environmental parameter values ​​before control and the target threshold. The environmental compliance time represents the time required for environmental parameters to drop to the normal threshold from the implementation of control. The control stability represents the standard deviation of the fluctuation of environmental parameters after control, obtained by calculating the standard deviation of environmental parameter values ​​over a period of time after control stabilization. The production efficiency impact rate represents the proportion of production capacity reduction caused by control measures, calculated by dividing the difference between the unit time output before adjustment and the unit time output after adjustment by the unit time output before adjustment.

[0118] After the process parameter adjustment plan is implemented, the system evaluates the effectiveness of the control measures by calculating four indicators. These indicators quantify the control effect from multiple dimensions such as the degree of environmental improvement, response speed, stability, and production impact.

[0119] The environmental improvement rate indicates the degree to which environmental parameters improve towards target values. This indicator is calculated based on the environmental parameter values ​​before control, the environmental parameter values ​​at the stable point after control, and the target threshold. The specific calculation formula is as follows: ; In this formula, Indicates the rate of environmental improvement. This indicates the environmental parameter values ​​before control. This represents the environmental parameter values ​​when the system stabilizes after control. This represents the target threshold. The environmental improvement rate typically ranges from 0 to 1. The closer the value is to 1, the more significant the environmental improvement. When the environmental parameters are fully restored to the target threshold, the environmental improvement rate reaches 100%.

[0120] Environmental compliance time represents the time required from the implementation of controls until environmental parameters drop to normal thresholds. This indicator reflects the response speed of control measures. The specific expression is: ; In this formula, Indicates the time when environmental standards were met. This indicates that the environmental parameter has dropped to the normal threshold for the first time. At that moment, This indicates the moment when the control command begins to be executed. The shorter the time it takes for the environment to meet the standard, the faster the response speed of the control measures and the shorter the disturbance time to the production process.

[0121] Control stability represents the standard deviation of fluctuations in environmental parameters after control is achieved. This indicator is obtained by calculating the standard deviation of environmental parameter values ​​over a period of time after control has stabilized. The specific calculation formula is as follows: ; In this formula, This indicates the stability control index. Indicates the first [unit / item] after control stabilizes. Environmental parameter values ​​at each point in time. This represents the average value of environmental parameters within that time period. This represents the total number of sampling points. The smaller the control stability value, the smaller the fluctuation range of environmental parameters after reaching the standard, and the more stable and reliable the control effect.

[0122] The production efficiency impact rate represents the percentage decrease in production capacity caused by control measures. This indicator is calculated based on the output per unit time before and after the adjustment. The specific calculation formula is as follows: ; In this formula, This indicates the impact rate on production efficiency. This indicates the output per unit time before adjustment. This represents the adjusted output per unit time. When this indicator is less than the preset impact threshold, it indicates that the control measures effectively improve the environment while keeping the loss of production efficiency within an acceptable range.

[0123] By comprehensively evaluating the above four indicators, the system can fully determine the effectiveness of control measures. When the environmental improvement rate is greater than the preset improvement threshold and the production efficiency impact rate is less than the preset impact threshold, the system determines that the control measures are effective and records the control case to the knowledge base, providing data support for constraint function optimization and control strategy improvement.

[0124] Step 903: When the environmental improvement rate is greater than the preset improvement threshold and the production efficiency impact rate is less than the preset impact threshold, the control measures are deemed effective.

[0125] It should be understood that when the environmental improvement rate is less than the preset improvement threshold or environmental parameters continuously exceed the preset threshold, the control measures are deemed insufficient, and secondary adjustments are required. The preset improvement threshold ranges from 0.5 to 0.9, and the preset impact threshold ranges from 0.1 to 0.2. Secondary adjustments include further adjusting process parameters, activating backup environmental control equipment, or adjusting production organization methods.

[0126] Step 904: Record effective control cases into the knowledge base.

[0127] It should be understood that the initial environmental state includes the values ​​of each environmental parameter before control, the range in which they are located, and the environmental state level; the triggered constraint rules include the rule identifier, triggering conditions, and the corresponding process parameter type; the process parameter adjustment plan includes the type of process parameter to be adjusted, the parameter value before adjustment, the parameter value after adjustment, and the adjustment range; the environmental parameter change curve records the trajectory of the environmental parameter value over time from the start of control to the stabilization of the environmental parameters; the production process data includes equipment operation data, product quality data, and production efficiency data during the adjustment process; and the control case also includes the time of control instruction issuance, the time of environmental parameter compliance, and the entity responsible for implementing the control measures.

[0128] Step 905: Optimize and update the threshold parameters and adjustment coefficients of the constraint function based on the control case.

[0129] Specifically, multiple control cases are extracted from the knowledge base to analyze the correlation between control effects and constraint parameters. For threshold parameters, by analyzing the fluctuation patterns of environmental parameters and control response characteristics in historical control cases, the first threshold is increased when the effect of control measures is lower than expected when environmental parameters exceed the first threshold, and the first and second thresholds are decreased when environmental parameters frequently exceed the second threshold. For adjustment coefficients, the optimal coefficient value that maximizes environmental improvement and minimizes the impact on production efficiency is searched using an optimization algorithm by evaluating the control effects under different adjustment ranges. The optimized threshold parameters and adjustment coefficients are updated to the knowledge base, and the time, reason, and expected effect of parameter changes are recorded.

[0130] Figure 10 This is a schematic diagram of the structure of a production and environmental data fusion and collaborative control system provided in one embodiment of this application. Figure 10 As shown in the figure, an embodiment of this application provides a production and environmental data fusion and collaborative control system. The system includes a data acquisition module 1001, used to acquire production execution data and environmental monitoring data. The production execution data includes production task identifiers and process parameters, while the environmental monitoring data includes environmental parameter values, monitoring point location coordinates, and data acquisition timestamps. The data acquisition module 1001 is connected to a data modeling module 1002 via a data transmission interface. The data acquisition module 1001 transmits the acquired production execution data and environmental monitoring data to the data modeling module 1002 in real time, providing raw data input for subsequent unified modeling processing and ensuring the synchronous acquisition of production and environmental data.

[0131] The data modeling module 1002 is used to construct a unified data structure for production execution data and environmental monitoring data using a multi-dimensional labeling system, generating standardized production execution data and environmental monitoring data. The multi-dimensional labeling system includes time dimension labels, spatial dimension labels, production dimension labels, and environmental dimension labels. The data modeling module 1002 is connected to the spatiotemporal mapping module 1003 through a data flow pipeline. The data modeling module 1002 transmits the generated standardized production execution data and environmental monitoring data to the spatiotemporal mapping module 1003, providing a structured data foundation for spatial mapping and time alignment, and eliminating format differences between heterogeneous data sources.

[0132] The spatiotemporal mapping module 1003 is used to calculate the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, and to determine the set of associated monitoring points and weight coefficients for each production operation area. Based on a time window, it extracts environmental parameters from the environmental monitoring data corresponding to the time period of production execution data and calculates representative environmental parameter values ​​within the time window using a weighted average method. The spatiotemporal mapping module 1003 is connected to the data fusion module 1004 through a mapping relationship interface. The spatiotemporal mapping module 1003 transmits the calculated set of associated monitoring points, weight coefficients, and representative environmental parameter values ​​to the data fusion module 1004, achieving accurate attribution of environmental monitoring data to production units and ensuring accurate correspondence of the fused data in the spatiotemporal dimension.

[0133] The data fusion module 1004 is used to query the corresponding task process requirements based on the production task identifier, and combine the associated monitoring point set and weight coefficients to fuse process parameters with corresponding representative environmental parameters, forming a fused dataset containing production and environmental information. The data fusion module 1004 is connected to the constraint modeling module 1005 through a fused dataset interface. The data fusion module 1004 transmits the generated fused dataset to the constraint modeling module 1005, providing high-quality data samples containing complete production process information and environmental status information for environment-process correlation analysis, supporting the establishment of correlations between environmental and process parameters.

[0134] The constraint modeling module 1005 extracts environmental impact factors and process response factors from the fused dataset and constructs an environment-process correlation matrix. Based on this matrix, it establishes constraint functions between environmental and process parameters, determines the allowable range of process parameters under different environmental conditions, and generates a set of environmental constraint rules. The constraint modeling module 1005 and the control decision module 1006 are bidirectionally connected via a constraint rule library interface. The constraint modeling module 1005 stores the generated set of environmental constraint rules, constraint functions, and related parameter configurations in a knowledge base for the control decision module 1006 to access in real time, providing constraint basis and adjustment strategies for collaborative control decisions. Simultaneously, the constraint modeling module 1005 receives control effect evaluation results and effective control cases from the control decision module 1006, which are used to adaptively optimize and update the threshold parameters and adjustment coefficients of the constraint functions, achieving continuous improvement of the constraint model.

[0135] The control decision module 1006 is used to collect current environmental parameters in real time, match these parameters with a set of environmental constraint rules, and trigger the corresponding constraint rules when the current environmental parameters exceed a preset threshold. Based on the triggered constraint rules and constraint functions, it calculates the adjustment values ​​of process parameters and generates a process parameter adjustment plan. The control decision module 1006 is connected to the instruction issuance module 1007 via a control instruction interface. The control decision module 1006 transmits the generated process parameter adjustment plan and scheduling optimization instructions to the instruction issuance module 1007, driving the automatic adjustment of process parameters and the collaborative optimization of production scheduling, transforming environmental constraints into executable control actions.

[0136] The instruction issuing module 1007 is used to execute process parameter adjustment schemes and realize the automatic adjustment of process parameters. The instruction issuing module 1007 connects to the controller of the production equipment through the equipment control interface, issuing process parameter adjustment instructions to the printing equipment, drying equipment, and ventilation equipment to achieve automatic adjustment of parameters such as printing speed, drying temperature, air supply volume, and exhaust volume. The instruction issuing module 1007 is also connected to the data acquisition module 1001 through a feedback data interface. After executing control instructions, the instruction issuing module 1007 triggers the data acquisition module 1001 to continuously collect environmental parameter change data and production process data, forming a complete closed-loop control loop from data acquisition, fusion analysis, constraint modeling, control decision-making to instruction execution and effect feedback, realizing dynamic coordination between the production process and environmental conditions.

[0137] Through the connections and data flow between the above modules, the system achieves deep integration of production execution data and environmental monitoring data, establishes dynamic constraints of environmental parameters on production process parameters, and forms an environment-driven collaborative control capability for the production process.

[0138] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within this application. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for the fusion and collaborative control of production and environmental data, characterized in that, include: Collect production execution data and environmental monitoring data. The production execution data includes production task identifiers and process parameters. The environmental monitoring data includes environmental parameter values, monitoring point location coordinates, and data collection timestamps. A multi-dimensional tagging system is adopted to construct a unified data structure for the production execution data and the environmental monitoring data, generating standardized production execution data and environmental monitoring data. The multi-dimensional tagging system includes time dimension tags, spatial dimension tags, production dimension tags, and environmental dimension tags. Based on the workshop topology, the spatial correlation between environmental monitoring points and production operation areas is calculated, and a set of associated monitoring points and weight coefficients are determined for each production operation area. Based on the time window, environmental parameters corresponding to the time period of the production execution data are extracted from the environmental monitoring data, and a weighted average method is used to calculate the representative environmental parameter values ​​within the time window. Based on the production task identifier, query the corresponding task process requirements, combine the associated monitoring point set and weight coefficient, and fuse the process parameters with the corresponding representative environmental parameters to form a fused dataset containing production information and environmental information. Environmental impact factors and process response factors are extracted from the fused dataset and an environment-process correlation matrix is ​​constructed. Based on the environment-process correlation matrix, a constraint function between the environmental parameters and the process parameters is established. The allowable range of the process parameters under different environmental conditions is determined and a set of environmental constraint rules is generated. Real-time acquisition of current environmental parameters, matching the current environmental parameters with the set of environmental constraint rules, triggering the corresponding constraint rule when the current environmental parameter exceeds a preset threshold, calculating the adjustment value of the process parameter based on the triggered constraint rule and the constraint function, and generating a process parameter adjustment scheme; The process parameter adjustment scheme is executed to achieve automatic adjustment of process parameters.

2. The method according to claim 1, characterized in that, After generating the process parameter adjustment plan, it also includes: Based on the process parameter adjustment plan, the adjusted production cycle time, unit product production time, and task delivery delay risk are assessed. When the task delivery delay risk exceeds the preset risk threshold or the capacity reduction exceeds the preset capacity reduction threshold, production scheduling optimization is performed to compensate for the capacity changes caused by the process parameter adjustment by adjusting the task execution order or equipment allocation plan.

3. The method according to claim 1, characterized in that, After implementing the process parameter adjustment scheme, the following is also included: Monitor changes in environmental parameters and production process data after the implementation of control measures, calculate control effectiveness indicators, and record effective control cases in the knowledge base; The environmental constraint function is optimized and updated based on the control effect.

4. The method according to claim 1, characterized in that, The process involves calculating the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, determining a set of associated monitoring points and weighting coefficients for each production operation area, extracting environmental parameters from the environmental monitoring data corresponding to the production execution data within a time window, and calculating representative environmental parameter values ​​within the time window using a weighted average method. Obtain the spatial location of production equipment, layout of ventilation system, workshop zoning information, and airflow direction information in the workshop topology; Based on the spatial location of the production equipment, the layout of the ventilation system, the workshop zoning information, and the airflow direction information, the workshop space is divided into areas according to the production process, with each production operation area corresponding to a spatial range; Calculate the straight-line spatial distance between each environmental monitoring point and the center point of each production operation area, determine the wind direction influence factor based on the layout of the air supply and exhaust system and the prevailing wind direction, and determine the airflow diffusion correction factor based on the distribution of obstacles in the workshop and the airflow path. Based on the spatial straight-line distance, the wind direction influence factor, and the airflow diffusion correction factor, the spatial correlation between each production operation area and each environmental monitoring point is calculated, and the spatial correlation is normalized to obtain the weighting coefficient. For each production operation area, a preset number of environmental monitoring points with the highest spatial correlation are selected to form the associated monitoring point set; For each production record in the production execution data, extract environmental parameter values ​​within a time window centered on the timestamp from the environmental monitoring data. The time weight is calculated based on the time distance between the collection time of the environmental parameter values ​​and the timestamp of the production record. The representative environmental parameter value is obtained by weighting multiple environmental parameter values ​​within the time window using the time weight.

5. The method according to claim 4, characterized in that, The step involves querying the corresponding task process requirements based on the production task identifier, combining the associated monitoring point set and weight coefficients, and fusing the process parameters with the corresponding representative environmental parameters to form a fused dataset containing production information and environmental information, including: For each production record in the production execution data, the corresponding task process requirements are queried from the production process database based on the production task identifier in the production record. The task process requirements include the standard process parameter range, product quality standards, and process control requirements. Based on the timestamp of the production record and the production operation area number, query the set of associated monitoring points and weight coefficients corresponding to the production operation area from the spatial mapping table; Extract representative environmental parameter values ​​of each associated monitoring point within the time window corresponding to the production record from the time alignment processing results; For multiple monitoring points associated with the production operation area, the representative environmental parameter values ​​of each monitoring point are weighted and aggregated using the weighting coefficient to obtain a comprehensive environmental parameter value. The representative environmental parameter values ​​of each monitoring point are weighted and aggregated using the weighting coefficients respectively to obtain an environmental parameter vector containing multiple types of environmental parameters, including volatile organic compound concentration, temperature, and humidity. The environmental parameter vector, the task process requirements, and the process parameters, production task identifiers, spatial locations, and timestamps in the production records are merged to form the fused dataset.

6. The method according to claim 5, characterized in that, The process involves extracting environmental impact factors and process response factors from the fused dataset and constructing an environment-process correlation matrix. Based on this matrix, a constraint function is established between the environmental parameters and the process parameters. The allowable range of process parameters under different environmental conditions is determined, and a set of environmental constraint rules is generated, including: Calculate the correlation coefficient between each environmental impact factor and each process response factor, and construct the environmental-process correlation matrix. The environmental-process correlation matrix represents the correlation strength between the corresponding environmental parameters and process parameters. The environmental impact factors include volatile organic compound concentration, odor index, temperature and humidity. The process response factors include printing speed, drying temperature, air supply volume and exhaust volume. The range of environmental parameters is divided into normal range, warning range, and exceedance range; Piecewise constraint functions are established for different intervals, and the piecewise constraint functions determine the adjustment coefficients of the process parameters under the corresponding environmental parameter values; The set of environmental constraint rules is generated based on the piecewise constraint function. Each constraint rule includes a triggering condition, a corresponding process parameter, an adjustment direction, and an adjustment range.

7. The method according to claim 6, characterized in that, The process involves matching the current environmental parameters with the set of environmental constraint rules, triggering the corresponding constraint rule when the current environmental parameters exceed a preset threshold, calculating the adjustment value of the process parameters based on the triggered constraint rule and the constraint function, and generating a process parameter adjustment scheme, including: The real-time collected current environmental parameters are compared one by one with the triggering conditions of each constraint rule in the set of environmental constraint rules. When the current environmental parameters exceed the preset threshold, the constraint rules that meet the trigger conditions are marked as active. Extract the type of process parameter to be adjusted, the adjustment direction, and the baseline adjustment range from the constraint rules in the active state; Substitute the current environmental parameters into the corresponding constraint function to calculate the target value of the process parameters; The adjustment value of the process parameter is calculated based on the difference between the current value and the target value. When multiple environmental parameters exceed the preset threshold simultaneously, a constraint priority weight is assigned to each environmental parameter, a comprehensive constraint strength is calculated based on the constraint priority weight, and a joint adjustment value for the process parameters is determined based on the comprehensive constraint strength. Summarize all the process parameters that need to be adjusted and their adjustment values ​​to form the process parameter adjustment plan.

8. The method according to claim 2, characterized in that, The process parameter adjustment plan is used to assess the adjusted production cycle time, unit product production time, and task delivery delay risk. When the task delivery delay risk exceeds a preset risk threshold or the capacity reduction exceeds a preset capacity reduction threshold, production scheduling optimization is performed to compensate for the capacity changes caused by the process parameter adjustment by adjusting the task execution order or equipment allocation plan. Based on the process parameter adjustment values ​​in the process parameter adjustment scheme, calculate the adjusted production cycle time and unit product production time. Compare the adjusted production time with the task delivery dates in the current production plan to determine if there is a risk of delivery delays. When there is a risk of delivery delay, production scheduling optimization is initiated. Optimization strategies include adjusting the task execution order, activating backup production lines, increasing equipment parallelism, or optimizing production batches. Regarding the adjustment of the task execution order, tasks with less environmental impact will be prioritized, while highly polluting tasks will be postponed or carried out in a decentralized manner. For the parallel equipment strategy, backup equipment is activated or the number of parallel equipment is increased to compensate for the capacity loss caused by the decrease in single-line speed by improving equipment utilization. For batch optimization, adjust production batch size and batch changeover frequency to reduce changeover time; Based on equipment capacity constraints, material supply constraints, process flow constraints, and the process parameter adjustment scheme, a scheduling optimization model is established to solve the optimized production scheduling scheme.

9. The method according to claim 3, characterized in that, The monitoring and control measures are used to track changes in environmental parameters and production process data after implementation. Control effectiveness indicators are calculated, and effective control cases are recorded in a knowledge base, including: After the control command is executed, environmental parameter change data and production process data are continuously collected. The production process data includes the actual execution value of the adjusted process parameters, equipment operating status and product quality indicators. Calculate the control effectiveness indicators, which include environmental improvement rate, environmental compliance time, control stability, and production efficiency impact rate; When the environmental improvement rate is greater than a preset improvement threshold and the production efficiency impact rate is less than a preset impact threshold, the control measures are deemed effective. Effective control cases are recorded in the knowledge base. The control cases include the initial environmental state, the triggered constraint rules, the process parameter adjustment scheme, the environmental parameter change curve, the production process data, and the control effectiveness index. Based on the control case, the threshold parameters and adjustment coefficients of the constraint function are optimized and updated; The environmental improvement rate represents the degree to which environmental parameters improve toward the target value, and is calculated based on the environmental parameter values ​​before control, the environmental parameter values ​​when the control is stable, and the target threshold; the environmental compliance time represents the time required from the execution of control to the environmental parameters dropping to the normal threshold; the control stability represents the standard deviation of the fluctuation of environmental parameters after control; and the production efficiency impact rate represents the proportion of production capacity reduction caused by the control measures.

10. A production and environmental data fusion and collaborative control system, characterized in that, include: The data acquisition module is used to collect production execution data and environmental monitoring data. The production execution data includes production task identifiers and process parameters, and the environmental monitoring data includes environmental parameter values, monitoring point location coordinates, and data acquisition timestamps. The data modeling module is used to construct a unified data structure for the production execution data and the environmental monitoring data using a multi-dimensional labeling system, and to generate standardized production execution data and environmental monitoring data. The multi-dimensional labeling system includes time dimension labels, spatial dimension labels, production dimension labels and environmental dimension labels. The spatiotemporal mapping module is used to calculate the spatial correlation between environmental monitoring points and production operation areas based on the workshop topology, and to determine the set of associated monitoring points and weight coefficients for each production operation area. Based on the time window, it extracts environmental parameters from the environmental monitoring data that correspond to the time period of the production execution data and uses a weighted average method to calculate the representative environmental parameter values ​​within the time window. The data fusion module is used to query the corresponding task process requirements based on the production task identifier, combine the associated monitoring point set and weight coefficients, and fuse the process parameters with the corresponding representative environmental parameters to form a fused dataset containing production information and environmental information. The constraint modeling module is used to extract environmental impact factors and process response factors from the fused dataset and construct an environment-process correlation matrix. Based on the environment-process correlation matrix, it establishes constraint functions between the environmental parameters and the process parameters, determines the allowable value range of the process parameters under different environmental conditions, and generates a set of environmental constraint rules. The control decision module is used to collect current environmental parameters in real time, match the current environmental parameters with the set of environmental constraint rules, trigger the corresponding constraint rule when the current environmental parameters exceed a preset threshold, calculate the adjustment value of the process parameters based on the triggered constraint rule and the constraint function, and generate a process parameter adjustment scheme. The instruction issuing module is used to execute the process parameter adjustment scheme to achieve automatic adjustment of process parameters.

Images