A method and system for collaborative scheduling of multiple production lines of a product

Abstract

The application provides a kind of for the collaborative scheduling method and system of multiple production lines of metering product, comprising, obtaining the task execution time sequence information and shared resource use state information of multiple production lines, generate the resource dependency graph containing resource dependency relationship between production lines;Determine the first task time sequence and scheduling quality evaluation value;For the first task time sequence, detect whether there is shared resource in the same time period is occupied by multiple process nodes simultaneously, obtain the second task time sequence;Calculate the overall production capacity completion rate prediction value corresponding to the second task time sequence of production line, obtain the third task time sequence;According to the third task time sequence, generate the shared resource coordination allocation instruction of multiple production lines, obtain the multiple production lines collaborative scheduling result.The application can effectively solve the dynamic coordination problem of shared resource under multiple production line environment, improve the overall production capacity completion rate of production line, reduce the time delay loss caused by resource conflict, realize the efficient collaborative use of multiple production line resources.

Description

Technical Field

[0001] This invention relates to the field of power system automation technology, and in particular to a method and system for collaborative scheduling of multiple production lines for metering products. Background Technology

[0002] The manufacturing of metrology products is a crucial component of intelligent manufacturing, and its production efficiency and resource utilization directly impact a company's market competitiveness. Metrology products are diverse, with significant differences in processes, often requiring multiple production lines to collaborate throughout the entire process from component processing to final assembly. In actual production, different products have significantly different demands for equipment, personnel, and materials, and these resources are both shared and competed for among the various production lines.

[0003] Current scheduling methods primarily focus on optimizing task sequencing within a single production line, neglecting the resource coupling relationships between production lines. This localized optimization approach leads to an inability to effectively handle sudden resource conflicts when critical resources frequently switch between multiple production lines. For example, a precision testing machine needs to simultaneously support the quality inspection processes of three product lines. However, existing methods only allocate equipment usage rights based on the urgency of tasks within each line, without considering equipment switchover preparation time and adjustment costs arising from differences in testing parameters for different products. This results in low equipment utilization and delivery delays.

[0004] The root of this problem lies in the insufficient characterization of the resource constraint transmission mechanism between production lines. When a production line is delayed due to the occupation of critical resources, the material preparation and personnel arrangements of its downstream processes will be affected in a chain reaction, which in turn affects other production lines that rely on the same resource pool. This cross-line resource dependency relationship will be further amplified under disturbances such as order fluctuations and equipment failures, forming a complex constraint transmission chain. Taking a typical scenario as an example, when the assembly process of production line A is delayed by two hours due to waiting for shared tooling, production line B, which was originally scheduled to use the tooling, has to adjust the start time of its subsequent five processes. This, in turn, causes the shared inspection personnel of production line C to be unable to arrive as originally planned. Ultimately, the overall output efficiency of the three production lines drops by more than 30%. Summary of the Invention

[0005] The purpose of this invention is to propose a collaborative scheduling method and system for multiple production lines of metered products, which solves the technical problem of how to accurately identify the resource constraint transmission path across production lines in a dynamic production environment, and coordinate the task execution sequence and resource allocation decisions of multiple production lines accordingly.

[0006] On the one hand, a collaborative scheduling method for multiple production lines of metered products is provided, including: The task execution time sequence information and corresponding shared resource usage status information of multiple production lines are obtained. The task execution time sequence information and shared resource usage status information are correlated and analyzed through a preset feature extraction model to generate a resource dependency map containing the resource dependency relationship between production lines. The corresponding first task time sequence and the corresponding scheduling quality evaluation value are determined based on the resource dependency graph. For the first task time sequence, check whether there are shared resources occupied by multiple process nodes at the same time. If so, adjust the execution start time of the process nodes with resource conflicts in descending order of the corresponding scheduling quality evaluation value to obtain the second task time sequence. Calculate the predicted value of the overall production capacity completion rate of the production line corresponding to the second task time sequence. If the predicted value of the production capacity completion rate is lower than the preset production capacity target achievement rate threshold, the current scheduling result is used as feedback information to optimize parameters and iterate strategies through the scheduling optimization model to obtain the third task time sequence. Based on the execution time arrangement of each process node in the third task time sequence and the corresponding resource allocation relationship, a shared resource coordination and allocation instruction for multiple production lines is generated to obtain the final multi-production line collaborative scheduling result.

[0007] Preferably, determining the corresponding first task time sequence and the corresponding scheduling quality evaluation value includes, Based on the overlapping time periods of resource occupation of each node in the resource dependency graph, identify process nodes with resource usage conflicts during the switching of multiple production lines and obtain a set of conflicting nodes; For each conflict node in the conflict node set, obtain the process switching time parameter of the conflict node, calculate the time delay impact of the subsequent process associated with the conflict node based on the process switching time parameter, and determine the first delay time value. Based on the first delay time value, trace the scope of the resource constraint impact downstream along the process dependency relationship in the resource dependency graph to determine the process transmission chain of the delay impact and obtain the transmission chain; All affected process nodes in the transmission chain are extracted as a set of nodes to be scheduled. The process execution order is adjusted and the scheduling quality is evaluated using a scheduling optimization model to obtain the first task time sequence and the corresponding scheduling quality evaluation value.

[0008] Preferably, it further includes calculating a first delay time value using the following formula:

[0009] in, Indicates conflicting nodes The amount of delay impact, Indicates the number of subsequent processes affected. Indicates conflicting nodes The time consumption parameter during the k-th process switch. Indicates conflicting nodes The weighting coefficient for the impact on the (i+k)th subsequent process node.

[0010] Preferably, the corresponding scheduling quality assessment value is calculated using the following formula:

[0011] in, This represents the scheduling quality assessment value. Represents the set of nodes to be scheduled. Indicates the number of nodes to be scheduled. This represents the actual execution time of process node v. R represents the planned execution time of process node v, and R represents the set of shared resources. Let r represent the number of conflicts for resource r, and α and β represent the time deviation penalty coefficient and the resource conflict penalty coefficient, respectively.

[0012] Preferably, the calculation of the predicted value of the overall production line capacity completion rate corresponding to the second task time sequence includes,

[0013] in, This represents the projected capacity completion rate, where L represents the total number of production lines. This indicates the cycle time of the l-th production line. The output volume predicted internally. This indicates the cycle time of the l-th production line. The target output within.

[0014] Preferably, obtaining the final multi-production line collaborative scheduling result includes, Obtain the third task time sequence, extract the execution period and corresponding resource quantity of each process point in the third task time sequence, and obtain the initial resource allocation matrix. Extract the shared pool occupancy status of each process point in the production line group to obtain the resource occupancy feature vector; By comparing the resource occupancy feature vector with a preset shared pool capacity threshold, it is determined whether there are conflict points in the resource occupancy feature vector. If there are conflict points in the resource occupancy feature vector, the execution period is adjusted according to the priority of the process points corresponding to the conflict points to obtain a conflict-free execution period. Based on the conflict-free execution period and the corresponding release period, a shared pool coordination order is generated for the production line group. A multi-production line collaborative scheduling diagram is constructed based on the shared pool coordination order to obtain the multi-production line collaborative scheduling result.

[0015] On the other hand, a collaborative scheduling system for multiple production lines of metered products is also provided to implement the aforementioned collaborative scheduling method for multiple production lines of metered products, including, The information acquisition module is used to acquire task execution time sequence information and corresponding shared resource usage status information from multiple production lines. It performs correlation analysis on task execution time sequence information and shared resource usage status information through a preset feature extraction model to generate a resource dependency map containing resource dependencies between production lines. The scheduling module is used to determine the corresponding first task time sequence and the corresponding scheduling quality evaluation value based on the resource dependency graph; for the first task time sequence, it checks whether there are shared resources occupied by multiple process nodes at the same time. If so, it adjusts the execution start time of the resource conflict process nodes in descending order of the corresponding scheduling quality evaluation value to obtain the second task time sequence. In addition, calculate the predicted value of the overall production capacity completion rate of the production line corresponding to the second task time sequence. If the predicted value of the production capacity completion rate is lower than the preset production capacity achievement rate threshold, the current scheduling result is used as feedback information to perform parameter optimization and strategy iteration through the scheduling optimization model to obtain the third task time sequence. It is also used to generate shared resource coordination and allocation instructions for multiple production lines based on the execution time arrangement of each process node in the third task time sequence and the corresponding resource allocation relationship, so as to obtain the final multi-production line collaborative scheduling result.

[0016] Preferably, the scheduling module is further configured to identify process nodes with resource usage conflicts during the switching process of multiple production lines based on the overlapping status of resource occupation time periods of each node in the resource dependency graph, and obtain a set of conflicting nodes. For each conflict node in the conflict node set, obtain the process switching time parameter of the conflict node, calculate the time delay impact of the subsequent process associated with the conflict node based on the process switching time parameter, and determine the first delay time value. Based on the first delay time value, trace the scope of the resource constraint impact downstream along the process dependency relationship in the resource dependency graph to determine the process transmission chain of the delay impact and obtain the transmission chain; All affected process nodes in the transmission chain are extracted as a set of nodes to be scheduled. The process execution order is adjusted and the scheduling quality is evaluated using a scheduling optimization model to obtain the first task time sequence and the corresponding scheduling quality evaluation value.

[0017] Preferably, the scheduling module is further configured to obtain a third task time sequence, extract the execution period and corresponding resource quantity of each process point in the third task time sequence, and obtain an initial resource allocation matrix based on the initial resource allocation matrix; Extract the shared pool occupancy status of each process point in the production line group to obtain the resource occupancy feature vector; By comparing the resource occupancy feature vector with a preset shared pool capacity threshold, it is determined whether there are conflict points in the resource occupancy feature vector. If there are conflict points in the resource occupancy feature vector, the execution period is adjusted according to the priority of the process points corresponding to the conflict points to obtain a conflict-free execution period. Based on the conflict-free execution period and the corresponding release period, a shared pool coordination order is generated for the production line group. A multi-production line collaborative scheduling diagram is constructed based on the shared pool coordination order to obtain the multi-production line collaborative scheduling result.

[0018] In summary, implementing the embodiments of the present invention has the following beneficial effects: The present invention provides a collaborative scheduling method and system for multiple production lines of metering products. In a dynamic production environment, it accurately identifies the resource constraint transmission path across production lines and coordinates the task execution sequence and resource allocation decisions of multiple production lines accordingly, so as to maximize the overall output rather than the local optimum of a single line, and achieve the optimal processing of collaborative scheduling of multiple production lines of metering products. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, obtaining other drawings based on these drawings without creative effort still falls within the scope of the present invention.

[0020] Figure 1 This is a schematic diagram of the main process of a collaborative scheduling method for multiple production lines of metering products in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings.

[0022] like Figure 1 The diagram shown is a schematic representation of an embodiment of a collaborative scheduling method for multiple production lines of metered products provided by the present invention. In this embodiment, the method includes the following steps: Step S1: Obtain task execution time sequence information and corresponding shared resource usage status information of multiple production lines. Perform correlation analysis on task execution time sequence information and shared resource usage status information through a preset feature extraction model to generate a resource dependency map containing resource dependencies between production lines. Step S2: Determine the corresponding first task time sequence and the corresponding scheduling quality evaluation value based on the resource dependency graph; Step S3: For the first task time sequence, check whether there are shared resources occupied by multiple process nodes at the same time. If so, adjust the execution start time of the resource conflict process nodes in descending order of the corresponding scheduling quality evaluation value to obtain the second task time sequence. Step S4: Calculate the predicted value of the overall production capacity completion rate of the production line corresponding to the second task time sequence. If the predicted value of the production capacity completion rate is lower than the preset production capacity achievement rate threshold, the current scheduling result is used as feedback information to perform parameter optimization and strategy iteration through the scheduling optimization model to obtain the third task time sequence. Step S5: Based on the execution time arrangement of each process node in the third task time sequence and the corresponding resource allocation relationship, generate shared resource coordination and allocation instructions for multiple production lines to obtain the final multi-production line collaborative scheduling result.

[0023] In one embodiment, determining the corresponding first task time sequence and the corresponding scheduling quality assessment value includes: identifying process nodes with resource usage conflicts during the switching process of multiple production lines based on the overlapping status of resource occupation periods of each node in the resource dependency graph, and obtaining a set of conflicting nodes; for each conflicting node in the set of conflicting nodes, obtaining the process switching time consumption parameter of the conflicting node, calculating the time delay impact of the subsequent process associated with the conflicting node based on the process switching time consumption parameter, and determining the first delay time value; based on the first delay time value, tracing the scope of resource constraint impact downstream along the process dependency relationship in the resource dependency graph, determining the process transmission chain of the delay impact, and obtaining the transmission chain; extracting all affected process nodes on the transmission chain as a set of nodes to be scheduled, and using a scheduling optimization model to adjust the process execution order and assess the scheduling quality of the set of nodes to be scheduled, thereby obtaining the first task time sequence and the corresponding scheduling quality assessment value.

[0024] In one embodiment, the first delay time value is calculated using the following formula:

[0025] in, Indicates conflicting nodes The amount of delay impact, Indicates the number of subsequent processes affected. Indicates conflicting nodes The time consumption parameter during the k-th process switch. Indicates conflicting nodes The weighting coefficient for the impact on the (i+k)th subsequent process node. This formula is used to calculate the time delay impact of the subsequent processes associated with the conflict node, i.e., the first delay time value. This formula quantifies the delay propagation effect by summing the weighted switching times of all subsequent processes.

[0026] In one embodiment, the corresponding scheduling quality assessment value is calculated using the following formula:

[0027] in, This represents the scheduling quality assessment value. Represents the set of nodes to be scheduled. Indicates the number of nodes to be scheduled. This represents the actual execution time of process node v. R represents the planned execution time of process node v, and R represents the set of shared resources. Let represent the number of conflicts for resource r, and α and β represent the time deviation penalty coefficient and resource conflict penalty coefficient, respectively. This formula is used to calculate the scheduling quality assessment value, which comprehensively considers the process execution time deviation and resource conflict situation to evaluate the quality of the scheduling scheme.

[0028] In one embodiment, calculating the predicted overall production capacity completion rate of the production line corresponding to the second task time sequence includes,

[0029] in, This represents the projected capacity completion rate, where L represents the total number of production lines. This indicates the cycle time of the l-th production line. The output volume predicted internally. This indicates the cycle time of the l-th production line. The formula is used to calculate the predicted overall production capacity completion rate of the production line. It assesses whether the scheduling plan meets capacity requirements by calculating the ratio of actual output to target output across all production lines.

[0030] In one embodiment, obtaining the final multi-production line collaborative scheduling result includes: acquiring a third task time sequence; extracting the execution period and corresponding resource quantity of each process point in the third task time sequence to obtain an initial resource allocation matrix; extracting the shared pool occupancy status of each process point in the production line group to obtain a resource occupancy feature vector; comparing the resource occupancy feature vector with a preset shared pool capacity threshold to determine whether there are conflict points in the resource occupancy feature vector; if there are conflict points in the resource occupancy feature vector, adjusting the execution period according to the priority of the process point corresponding to the conflict point to obtain a conflict-free execution period; generating a shared pool coordination order for the production line group based on the conflict-free execution period and the corresponding release period; constructing a multi-production line collaborative scheduling diagram based on the shared pool coordination order to obtain the multi-production line collaborative scheduling result.

[0031] In a specific embodiment, the timing sequence matrix of the third task is read, and it is extracted that the welding process node of production line A is scheduled to be executed from 8:00 to 8:30 and requests the use of transport vehicle number one. At the same time, the assembly process node of production line B is scheduled to be executed from 8:30 to 8:45 and also requests the use of transport vehicle number one.

[0032] The system's time window overlap detection algorithm calculated a 15-minute overlap in the resource demand time windows of the two processes, determining a shared resource conflict. To resolve this conflict, the system invoked a genetic algorithm model based on adaptive weights, using process delay penalty cost and resource idle cost as evaluation indicators for the fitness function. After fifty iterations, the analysis concluded that delaying the start time of the assembly process node on production line B to 8:30 AM and temporarily allocating the idle No. 2 transport vehicle could reduce the overall scheduling cost by 12%.

[0033] Based on this analysis, the system automatically generates shared resource coordination and allocation instructions containing equipment numbers and precise timestamps. For example, it sends a navigation control message to transport vehicle number two, instructing it to proceed to workstation B on production line at 8:30 AM. The system encapsulates all adjusted instruction sets to form a multi-production line collaborative scheduling result encompassing three production lines and 50 process nodes, and directly writes it into the registers of each control device via the underlying communication protocol.

[0034] Embodiments of the present invention also provide a collaborative scheduling system for multiple production lines of metered products, used to implement the aforementioned collaborative scheduling method for multiple production lines of metered products, including, The information acquisition module is used to acquire task execution time sequence information and corresponding shared resource usage status information from multiple production lines. It performs correlation analysis on task execution time sequence information and shared resource usage status information through a preset feature extraction model to generate a resource dependency map containing resource dependencies between production lines. The scheduling module is used to determine the corresponding first task time sequence and the corresponding scheduling quality evaluation value based on the resource dependency graph; for the first task time sequence, it checks whether there are shared resources occupied by multiple process nodes at the same time. If so, it adjusts the execution start time of the resource conflict process nodes in descending order of the corresponding scheduling quality evaluation value to obtain the second task time sequence. In addition, calculate the predicted value of the overall production capacity completion rate of the production line corresponding to the second task time sequence. If the predicted value of the production capacity completion rate is lower than the preset production capacity achievement rate threshold, the current scheduling result is used as feedback information to perform parameter optimization and strategy iteration through the scheduling optimization model to obtain the third task time sequence. It is also used to generate shared resource coordination and allocation instructions for multiple production lines based on the execution time arrangement of each process node in the third task time sequence and the corresponding resource allocation relationship, so as to obtain the final multi-production line collaborative scheduling result.

[0035] The scheduling module is also used to identify process nodes with resource usage conflicts during the switching process of multiple production lines based on the overlapping status of resource occupation periods of each node in the resource dependency graph, and obtain a set of conflicting nodes. For each conflict node in the conflict node set, obtain the process switching time parameter of the conflict node, calculate the time delay impact of the subsequent process associated with the conflict node based on the process switching time parameter, and determine the first delay time value. Based on the first delay time value, trace the scope of the resource constraint impact downstream along the process dependency relationship in the resource dependency graph to determine the process transmission chain of the delay impact and obtain the transmission chain; All affected process nodes in the transmission chain are extracted as a set of nodes to be scheduled. The process execution order is adjusted and the scheduling quality is evaluated using a scheduling optimization model to obtain the first task time sequence and the corresponding scheduling quality evaluation value.

[0036] The scheduling module is also used to obtain the third task time sequence, extract the execution period and corresponding resource quantity of each process point in the third task time sequence, and obtain an initial resource allocation matrix based on the initial resource allocation matrix; Extract the shared pool occupancy status of each process point in the production line group to obtain the resource occupancy feature vector; By comparing the resource occupancy feature vector with a preset shared pool capacity threshold, it is determined whether there are conflict points in the resource occupancy feature vector. If there are conflict points in the resource occupancy feature vector, the execution period is adjusted according to the priority of the process points corresponding to the conflict points to obtain a conflict-free execution period. Based on the conflict-free execution period and the corresponding release period, a shared pool coordination order is generated for the production line group. A multi-production line collaborative scheduling diagram is constructed based on the shared pool coordination order to obtain the multi-production line collaborative scheduling result.

[0037] It should be noted that the system described in the above embodiments corresponds to the method described in the above embodiments. Therefore, the parts of the system described in the above embodiments that are not described in detail can be obtained by referring to the content of the method described in the above embodiments, and will not be repeated here.

[0038] In summary, implementing the embodiments of the present invention has the following beneficial effects: The present invention provides a collaborative scheduling method and system for multiple production lines of metering products. In a dynamic production environment, it accurately identifies the resource constraint transmission path across production lines and coordinates the task execution sequence and resource allocation decisions of multiple production lines accordingly, so as to maximize the overall output rather than the local optimum of a single line, and achieve the optimal processing of collaborative scheduling of multiple production lines of metering products.

[0039] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for collaborative scheduling of multiple production lines for metered products, characterized in that, include: The task execution time sequence information and corresponding shared resource usage status information of multiple production lines are obtained. The task execution time sequence information and shared resource usage status information are correlated and analyzed through a preset feature extraction model to generate a resource dependency map containing the resource dependency relationship between production lines. The corresponding first task time sequence and the corresponding scheduling quality evaluation value are determined based on the resource dependency graph. For the first task time sequence, check whether there are shared resources occupied by multiple process nodes at the same time. If so, adjust the execution start time of the process nodes with resource conflicts in descending order of the corresponding scheduling quality evaluation value to obtain the second task time sequence. Calculate the predicted value of the overall production capacity completion rate of the production line corresponding to the second task time sequence. If the predicted value of the production capacity completion rate is lower than the preset production capacity target achievement rate threshold, the current scheduling result is used as feedback information to optimize parameters and iterate strategies through the scheduling optimization model to obtain the third task time sequence. Based on the execution time arrangement of each process node in the third task time sequence and the corresponding resource allocation relationship, a shared resource coordination and allocation instruction for multiple production lines is generated to obtain the final multi-production line collaborative scheduling result.

2. The method as described in claim 1, characterized in that, The determination of the corresponding first task time sequence and the corresponding scheduling quality evaluation value includes... Based on the overlapping time periods of resource occupation of each node in the resource dependency graph, identify process nodes with resource usage conflicts during the switching of multiple production lines and obtain a set of conflicting nodes; For each conflict node in the conflict node set, obtain the process switching time parameter of the conflict node, calculate the time delay impact of the subsequent process associated with the conflict node based on the process switching time parameter, and determine the first delay time value. Based on the first delay time value, trace the scope of the resource constraint impact downstream along the process dependency relationship in the resource dependency graph to determine the process transmission chain of the delay impact and obtain the transmission chain; All affected process nodes in the transmission chain are extracted as a set of nodes to be scheduled. The process execution order is adjusted and the scheduling quality is evaluated using a scheduling optimization model to obtain the first task time sequence and the corresponding scheduling quality evaluation value.

3. The method as described in claim 2, characterized in that, It also includes calculating the first delay time value using the following formula: in, Indicates conflicting nodes The amount of delay impact, Indicates the number of subsequent processes affected. Indicates conflicting nodes The time consumption parameter during the k-th process switch. Indicates conflicting nodes The weighting coefficient for the impact on the (i+k)th subsequent process node.

4. The method as described in claim 2, characterized in that, It also includes calculating the corresponding scheduling quality assessment value using the following formula: in, This represents the scheduling quality assessment value. Represents the set of nodes to be scheduled. Indicates the number of nodes to be scheduled. This represents the actual execution time of process node v. R represents the planned execution time of process node v, and R represents the set of shared resources. Let r represent the number of conflicts for resource r, and α and β represent the time deviation penalty coefficient and the resource conflict penalty coefficient, respectively.

5. The method as described in claim 1, characterized in that, The calculation of the predicted overall production capacity completion rate of the production line corresponding to the second task time sequence includes... in, This represents the projected capacity completion rate, where L represents the total number of production lines. This indicates the cycle time of the l-th production line. The output volume predicted internally. This indicates the cycle time of the l-th production line. The target output within.

6. The method as described in claim 1, characterized in that, The process of obtaining the final multi-production line collaborative scheduling result includes, Obtain the third task time sequence, extract the execution period and corresponding resource quantity of each process point in the third task time sequence, and obtain the initial resource allocation matrix. Extract the shared pool occupancy status of each process point in the production line group to obtain the resource occupancy feature vector; By comparing the resource occupancy feature vector with a preset shared pool capacity threshold, it is determined whether there are conflict points in the resource occupancy feature vector. If there are conflict points in the resource occupancy feature vector, the execution period is adjusted according to the priority of the process points corresponding to the conflict points to obtain a conflict-free execution period. Based on the conflict-free execution period and the corresponding release period, a shared pool coordination order is generated for the production line group. A multi-production line collaborative scheduling diagram is constructed based on the shared pool coordination order to obtain the multi-production line collaborative scheduling result.

7. A collaborative scheduling system for multiple production lines of metered products, used to implement the method as described in any one of claims 1-6, characterized in that, include, The information acquisition module is used to acquire task execution time sequence information and corresponding shared resource usage status information from multiple production lines. It performs correlation analysis on task execution time sequence information and shared resource usage status information through a preset feature extraction model to generate a resource dependency map containing resource dependencies between production lines. The scheduling module is used to determine the corresponding first task time sequence and the corresponding scheduling quality evaluation value based on the resource dependency graph; for the first task time sequence, it checks whether there are shared resources occupied by multiple process nodes at the same time. If so, it adjusts the execution start time of the resource conflict process nodes in descending order of the corresponding scheduling quality evaluation value to obtain the second task time sequence. In addition, calculate the predicted value of the overall production capacity completion rate of the production line corresponding to the second task time sequence. If the predicted value of the production capacity completion rate is lower than the preset production capacity achievement rate threshold, the current scheduling result is used as feedback information to perform parameter optimization and strategy iteration through the scheduling optimization model to obtain the third task time sequence. It is also used to generate shared resource coordination and allocation instructions for multiple production lines based on the execution time arrangement of each process node in the third task time sequence and the corresponding resource allocation relationship, so as to obtain the final multi-production line collaborative scheduling result.

8. The system as described in claim 7, characterized in that, The scheduling module is also used to identify process nodes with resource usage conflicts during the switching process of multiple production lines based on the overlapping status of resource occupation periods of each node in the resource dependency graph, and obtain a set of conflicting nodes. For each conflict node in the conflict node set, obtain the process switching time parameter of the conflict node, calculate the time delay impact of the subsequent process associated with the conflict node based on the process switching time parameter, and determine the first delay time value. Based on the first delay time value, trace the scope of the resource constraint impact downstream along the process dependency relationship in the resource dependency graph to determine the process transmission chain of the delay impact and obtain the transmission chain; All affected process nodes in the transmission chain are extracted as a set of nodes to be scheduled. The process execution order is adjusted and the scheduling quality is evaluated using a scheduling optimization model to obtain the first task time sequence and the corresponding scheduling quality evaluation value.

9. The system as described in claim 8, characterized in that, The scheduling module is also used to obtain the third task time sequence, extract the execution period and corresponding resource quantity of each process point in the third task time sequence, and obtain an initial resource allocation matrix based on the initial resource allocation matrix; Extract the shared pool occupancy status of each process point in the production line group to obtain the resource occupancy feature vector; By comparing the resource occupancy feature vector with a preset shared pool capacity threshold, it is determined whether there are conflict points in the resource occupancy feature vector. If there are conflict points in the resource occupancy feature vector, the execution period is adjusted according to the priority of the process points corresponding to the conflict points to obtain a conflict-free execution period. Based on the conflict-free execution period and the corresponding release period, a shared pool coordination order is generated for the production line group. A multi-production line collaborative scheduling diagram is constructed based on the shared pool coordination order to obtain the multi-production line collaborative scheduling result.

Images