A method and related device for rescheduling simulation of dynamic disturbance of an industrial production line

Abstract

The application provides a kind of industrial production line dynamic disturbance rescheduling simulation method and related device, when triggering abnormal event, extract disturbance feature vector, and determine matching candidate scheduling rule according to disturbance feature vector;Simulation deduction is carried out based on candidate scheduling rule in the digital twin platform corresponding to industrial production line, and the simulation result of the preliminary selected scheduling rule is obtained;Based on the simulation result of each preliminary selected scheduling rule, determine the target scheduling rule, and issue it to the industrial production line, so that the industrial production line executes the target scheduling rule. Select candidate scheduling rule from rule library, which improves response efficiency compared with complete rescheduling mode, reduces the possibility of production line falling into waiting or executing outdated scheme after disturbance, and retrieves production capacity loss. Determine the target scheduling rule from multiple candidate scheduling rules through digital twin platform simulation, which guarantees global optimization effect, improves scheduling accuracy and avoids local congestion or equipment idling.

Description

Technical Field

[0001] This invention relates to the field of machine simulation, and more specifically, to a method and related apparatus for rescheduling simulation of dynamic disturbances in industrial production lines. Background Technology

[0002] In discrete manufacturing workshops (such as automotive parts machining and 3C electronic product assembly), production scheduling typically employs a hierarchical architecture: the upper layer uses an Advanced Planning and Scheduling System (APS) to generate a daily shift baseline scheduling plan based on mathematical programming or heuristic algorithms; the lower layer uses a Manufacturing Execution System (MES) to execute work assignments according to the baseline plan. When dynamic disturbances occur (such as sudden equipment failures, urgent order insertions, or delayed material arrivals), existing technologies generally employ two approaches: complete rescheduling and partial manual adjustment.

[0003] The complete rescheduling method involves rerunning the optimization algorithm using the APS (Advanced Planning and Scheduling System) to generate a completely new scheduling scheme. This method is computationally time-consuming (typically several minutes to tens of minutes), cannot meet real-time response requirements, and large adjustments can easily cause production line oscillations. The partial manual adjustment method involves production managers manually adjusting task allocations based on experience. This method relies on personal experience, has a slow response time, and struggles to guarantee scheduling quality.

[0004] Full rescheduling takes a long time to compute, and after a disturbance occurs, the production line may be stuck in a waiting state or execute outdated plans, resulting in capacity loss. Local manual adjustment lacks global optimization and is prone to local congestion or equipment idleness.

[0005] Therefore, how to efficiently and accurately complete rescheduling when dynamic disturbances occur has become a problem that needs to be solved by those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a rescheduling simulation method and related apparatus for dynamic disturbances in industrial production lines, so as to improve the above-mentioned problems.

[0007] To achieve the above objectives, the technical solutions adopted in the embodiments of the present invention are as follows: In a first aspect, embodiments of the present invention provide a rescheduling simulation method for dynamic disturbances in industrial production lines, the method comprising: Acquire status signals of various equipment in the industrial production line, as well as material inventory information and order change information corresponding to the industrial production line; Based on the equipment status signal, the material inventory information, and the order change information, determine whether an abnormal event has been triggered; When an abnormal event is triggered, a disturbance feature vector is extracted. The disturbance feature vector includes the disturbance type matching the abnormal event, the time of occurrence of the abnormal event, the severity of the abnormality, and the equipment, materials, and orders involved in the abnormal event. The perturbation feature vector is input into the perturbation classification model so that it outputs the corresponding perturbation subtype; Based on the preset disturbance rule mapping relationship, candidate scheduling rules matching the disturbance subtype are determined from the rule base; Simulation is performed on the digital twin platform corresponding to the industrial production line based on candidate scheduling rules, and simulation results of the initial scheduling rules are obtained. The initial scheduling rules are candidate scheduling rules that have been fully simulated in the digital twin platform. The simulation results include total output, total order delay time, average equipment utilization, and number of task switching within the simulation time window. Based on the simulation results of each preliminary scheduling rule, the target scheduling rule is determined and issued to the industrial production line so that the industrial production line executes the target scheduling rule.

[0008] Secondly, embodiments of the present invention provide a rescheduling simulation device for dynamic disturbances in industrial production lines, the device comprising: The first processing unit is used to acquire various equipment status signals in the industrial production line and material inventory information and order change information corresponding to the industrial production line; The first processing unit is further configured to determine whether an abnormal event is triggered based on the equipment status signal, the material inventory information, and the order change information; The first processing unit is also used to extract a disturbance feature vector when an abnormal event is triggered. The disturbance feature vector includes the disturbance type matching the abnormal event, the time of occurrence of the abnormal event, the severity of the abnormality, and the equipment, materials, and orders involved in the abnormal event. The first processing unit is further configured to input the perturbation feature vector into the perturbation classification model so that it outputs the corresponding perturbation subtype; The first processing unit is further configured to determine, from the rule base, a candidate scheduling rule that matches the disturbance subtype according to a preset disturbance rule mapping relationship; The first processing unit is also used to perform simulation and deduction based on candidate scheduling rules in the digital twin platform corresponding to the industrial production line, and obtain the simulation results of the preliminary scheduling rules. The preliminary scheduling rules are candidate scheduling rules that have been fully simulated and deduced in the digital twin platform. The simulation results include the total output, total order delay time, average equipment utilization, and number of task switching within the simulation time window. The second processing unit is used to determine the target scheduling rule based on the simulation results of each preliminary scheduling rule, and send it to the industrial production line so that the industrial production line executes the target scheduling rule.

[0009] Thirdly, embodiments of the present invention provide a storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method.

[0010] Fourthly, embodiments of the present invention provide an electronic device, the electronic device comprising: a processor and a memory, the memory being used to store one or more programs; when the one or more programs are executed by the processor, the above-described method is implemented.

[0011] Compared to existing technologies, the rescheduling simulation method and related apparatus for dynamic disturbances in industrial production lines provided in this invention extract disturbance feature vectors when abnormal events are triggered, and determine matching candidate scheduling rules based on these vectors. Simulations are then performed on the digital twin platform corresponding to the industrial production line based on these candidate scheduling rules, and simulation results of the initially selected scheduling rules are obtained. Based on the simulation results of each initially selected scheduling rule, a target scheduling rule is determined and distributed to the industrial production line so that it executes the target scheduling rule. Selecting candidate scheduling rules from a rule base improves response efficiency compared to a complete rescheduling approach, reduces the possibility of the production line falling into a waiting state or executing outdated solutions after a disturbance occurs, and retrieves capacity losses. Determining the target scheduling rule from multiple candidate scheduling rules through simulation on a digital twin platform ensures global optimization effects, improves scheduling accuracy, and avoids local congestion or equipment idleness.

[0012] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0015] Figure 2 This is one of the flowcharts illustrating the rescheduling simulation method for dynamic disturbances in industrial production lines provided in this embodiment of the invention.

[0016] Figure 3 This is the second flowchart illustrating the rescheduling simulation method for dynamic disturbances in industrial production lines provided in this embodiment of the invention.

[0017] Figure 4The third flowchart illustrates the rescheduling simulation method for dynamic disturbances in industrial production lines provided in this embodiment of the invention.

[0018] Figure 5 A schematic diagram of a unit for a rescheduling simulation device for dynamic disturbances in an industrial production line provided in an embodiment of the present invention.

[0019] In the diagram: 10-Processor; 11-Memory; 12-Bus; 13-Communication interface; 501-First processing unit; 502-Second processing unit. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0022] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] The following detailed description of some embodiments of the present invention is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0024] This invention aims to provide a real-time rescheduling method for industrial production lines in the face of dynamic disturbances. By utilizing a large model-assisted rule base for construction and decision interpretation, it can generate high-quality rescheduling schemes within seconds, minimize the impact of disturbances on production, and ensure a smooth transition of the schemes.

[0025] This invention provides an electronic device, which may be a server device, a computer device, or a mobile phone device, etc. Please refer to... Figure 1This is a schematic diagram of the structure of an electronic device. The electronic device includes a processor 10, a memory 11, and a bus 12. The processor 10 and the memory 11 are connected via the bus 12. The processor 10 is used to execute executable modules, such as computer programs, stored in the memory 11.

[0026] Processor 10 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the rescheduling simulation method for dynamic disturbances in industrial production lines can be completed through integrated logic circuits in the hardware or software instructions within processor 10. Processor 10 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0027] The memory 11 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage.

[0028] Bus 12 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. Figure 1 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus 12 or one type of bus 12.

[0029] The memory 11 is used to store programs, such as the program corresponding to a rescheduling simulation device for dynamic disturbances in industrial production lines. The rescheduling simulation device for dynamic disturbances in industrial production lines includes at least one software functional module that can be stored in the memory 11 in the form of software or firmware, or embedded in the operating system (OS) of the electronic device. Upon receiving an execution instruction, the processor 10 executes the program to implement the rescheduling simulation method for dynamic disturbances in industrial production lines.

[0030] The electronic device provided in this embodiment of the invention may further include a communication interface 13. The communication interface 13 is connected to the processor 10 via a bus.

[0031] It should be understood that, Figure 1 The structure shown is only a partial schematic diagram of the electronic device; the electronic device may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0032] The rescheduling simulation method for dynamic disturbances in industrial production lines provided in this invention can be applied, but is not limited to, to... Figure 1 For the specific procedures of the electronic devices shown, please refer to [link / reference]. Figure 2 The rescheduling simulation methods for dynamic disturbances in industrial production lines include S110-S150, S170, and S180, which are described in detail below.

[0033] S110 acquires various equipment status signals in the industrial production line, as well as material inventory information and order change information corresponding to the industrial production line.

[0034] The equipment status signals include operating signals, shutdown signals, and suspected fault signals.

[0035] S120: Based on equipment status signals, material inventory information, and order change information, determine whether an abnormal event has been triggered. If yes, proceed to S130; otherwise, continue executing the pre-generated global baseline scheduling scheme.

[0036] The material inventory information includes the remaining inventory of each material.

[0037] S130: When an abnormal event is triggered, extract the perturbation feature vector.

[0038] The disturbance feature vector includes the disturbance type matching the abnormal event, the time of the abnormal event, the severity of the abnormality, and the equipment, materials, and orders involved in the abnormal event.

[0039] The severity of the anomaly is assessed by factors such as estimated repair time (based on historical maintenance records, the longer the estimated repair time, the higher the severity), urgency of the urgent order delivery date (the length of time between the current time and the agreed delivery time, the longer the time, the lower the urgency), and duration of material shortage.

[0040] S140, input the perturbation feature vector into the perturbation classification model so that it outputs the corresponding perturbation subtype.

[0041] The perturbation subtype is a subordinate type of the perturbation type.

[0042] In this embodiment of the invention, a decision tree or random forest algorithm can be used to train a classification model based on historical disturbance data. The input is a historical disturbance feature vector, and the output is a specific historical disturbance subtype (such as machining center spindle failure, urgent customer orders, supplier material delays, etc.).

[0043] Historical disturbance data includes its corresponding historical disturbance feature vector and historical disturbance subtype.

[0044] It should be noted that the perturbation classification model in this embodiment of the invention can be updated online to incorporate newly occurring perturbation cases.

[0045] S150, based on the preset disturbance rule mapping relationship, determine the candidate scheduling rule that matches the disturbance subtype from the rule base.

[0046] If a certain type of rule has multiple variations (such as multiple target device selection strategies for task transfer), all of them are included in the candidate set.

[0047] S170 performs simulation and deduction based on candidate scheduling rules in the digital twin platform corresponding to the industrial production line, and obtains the simulation results of the initial scheduling rules.

[0048] The initial selection scheduling rules are candidate scheduling rules that have been fully simulated and derived in the digital twin platform. The simulation results include the total output, total order delay time, average equipment utilization, and number of task switching within the simulation time window.

[0049] The simulation time window can be, but is not limited to, 30 minutes; the time window should be long enough to observe the system's recovery process after the disturbance, but not too long to avoid excessive simulation time.

[0050] S180 determines the target scheduling rule based on the simulation results of each preliminary scheduling rule and sends it to the industrial production line so that the industrial production line can execute the target scheduling rule.

[0051] The specific process of issuing target scheduling rules to the industrial production line can be as follows: The selected target scheduling rules are parsed into equipment control instructions and task allocation instructions adapted to the industrial production line, and (via MES and SCADA) these instructions are issued to the field equipment on the industrial production line (such as modifying CNC machining programs, rescheduling AGV tasks, and updating workstation displays). Simultaneously, the disturbance event and the selected rule are recorded in the historical case library for subsequent model optimization.

[0052] In the rescheduling simulation method for dynamic disturbances in industrial production lines provided in this embodiment of the invention, candidate scheduling rules are selected from a rule base. Compared with a complete rescheduling method, this improves response efficiency, reduces the possibility of the production line falling into waiting or executing outdated solutions after a disturbance occurs, and retrieves capacity losses. The target scheduling rule is determined from multiple candidate scheduling rules through simulation on a digital twin platform, ensuring global optimization effects, improving scheduling accuracy, and avoiding local congestion or equipment idleness.

[0053] Based on the preceding text, regarding the content of S120, this embodiment of the invention also provides an optional implementation method, please refer to the following. S120, based on the equipment status signal, material inventory information, and order change information, determines whether an abnormal event is triggered, including: S121, S122, and S123, which are specifically described below.

[0054] S121, if the equipment status signal changes from running to suspected fault and continues for more than a preset time (e.g., 10 seconds), an abnormal event is determined to be triggered, and the abnormal event type is equipment fault.

[0055] S122, when the order change information includes a new order with an emergency identifier, and the current production line load of the industrial production line exceeds the load threshold (80%), an abnormal event is determined to be triggered, and the abnormal event type is emergency order insertion.

[0056] S123, if the remaining inventory of materials required for a single type of task in the material library is lower than the safety stock threshold and the expected delivery time is later than the corresponding current demand time, an abnormal event is triggered. The abnormal event type is material delay.

[0057] Please refer to Figure 3 In an optional implementation, after determining the candidate scheduling rule matching the disturbance subtype from the rule base according to the preset disturbance rule mapping relationship, the rescheduling simulation method for dynamic disturbances of industrial production lines further includes: S160, which is described in detail below.

[0058] S160: Identify and delete candidate scheduling rules whose execution conditions do not match the current equipment status in the industrial production line.

[0059] It should be understood that simulations are performed after candidate scheduling rules whose execution conditions do not match the current equipment status in the industrial production line are deleted.

[0060] When a disturbance occurs, in addition to matching rules based on the classification results, an executability check is also performed. The execution conditions of each rule are dynamically verified based on the current real-time status (equipment load, material inventory, process constraints), and infeasible rules are eliminated. This mechanism ensures that the output candidate rule set is not only relevant but also immediately executable, avoiding the problem of traditional rule bases where matching is successful but execution fails.

[0061] Please refer to the table below, which provides an example of rules and enforcement conditions:

[0062] Optionally, a lightweight simulation engine for rapid simulation of an industrial production line can be created within the digital twin platform. This engine simplifies the detailed simulation of physical processes (e.g., ignoring non-critical details) and focuses on discrete events such as logistics, task allocation, and equipment status changes, while supporting accelerated simulation (the simulation speed multiplier can be set).

[0063] It should be understood that multiple candidate scheduling rules can be simulated and deduced in parallel, thereby improving efficiency.

[0064] Regarding the content in S170, this embodiment of the invention also provides an optional implementation method, please refer to the following. S170, in the digital twin platform corresponding to the industrial production line, simulation and deduction are performed based on candidate scheduling rules, and the simulation results of the initial selection scheduling rules are obtained, including: S171-S175, which are described in detail below.

[0065] S171, simulation and deduction based on candidate scheduling rules in the digital twin platform; S172, sequentially obtain the performance indicators of each simulation evaluation node, and convert the performance indicators of each simulation evaluation node into real-time simulation scores. The performance indicators include the current cumulative output, the current average equipment utilization rate, the current order delay time, and the current number of task switching. S173: Determine if the simulation stop condition has been triggered. If yes, proceed to S174; otherwise, proceed to S175.

[0066] The simulation stopping condition is that the real-time simulation scores of multiple consecutive simulation evaluation nodes are all lower than the scoring threshold.

[0067] Design a dynamic early stop mechanism and set dynamic scoring thresholds. (in (This is the early stopping factor, typically set to 0.6-0.8). For each simulation evaluation node (e.g., performance sampling every minute of simulation duration), the real-time simulation score of all currently simulating candidate rules is first taken. Take the highest score at present. Three consecutive evaluation nodes If all values ​​are below θ, the simulation under this rule is immediately terminated to release computational resources.

[0068] S174, stop simulating candidate scheduling rules and mark them as invalid strategies.

[0069] The simulation of this rule is terminated early to free up computing resources.

[0070] S175, continue the simulation until the simulation time window ends, mark the candidate scheduling rules as the initial scheduling rules, and obtain the simulation results of the initial scheduling rules.

[0071] Regarding the content in S180, this embodiment of the invention also provides an optional implementation method, please refer to the following. S180, based on the simulation results of each initial scheduling rule, determines the target scheduling rule, including: S181 and S182, as detailed below.

[0072] S181. Based on the total output, total order delay time, average equipment utilization, and number of task switching for each preliminary scheduling rule within the simulation time window, determine the comprehensive score of the preliminary scheduling rule.

[0073] Optionally, the formula for the overall score is:

[0074]

[0075] in, Let r represent the overall score of the r-th initial selection scheduling rule. This represents the total output of the r-th initial selection scheduling rule within the simulation time window. This represents the maximum value among all total outputs. This represents the total order delay time within the simulation time window for the r-th initial selection scheduling rule. This represents the maximum total delay time among all orders. This represents the average equipment utilization rate within the simulation time window for the r-th initial scheduling rule. This represents the number of task switching occurrences within the simulation time window for the r-th initial scheduling rule. to This is a weighting coefficient that can be dynamically adjusted based on current production targets (e.g., it can be increased when rushing to meet deadlines). ,reduce ).

[0076] S182, the initial scheduling rule with the highest comprehensive score is determined as the target scheduling rule.

[0077] To ensure a smooth transition of the production line, the adjustment plan with the least impact on the production line (the initial scheduling rule with the highest comprehensive score) is selected through rule matching and simulation evaluation, thereby reducing efficiency losses caused by frequent task switching.

[0078] Please refer to Figure 4In one optional implementation, after determining the target scheduling rule based on the simulation results of each initial scheduling rule, the rescheduling simulation method for dynamic disturbances of industrial production lines further includes: S190, which is described in detail below.

[0079] S190 generates a natural language explanation based on the target scheduling rules and their corresponding simulation results.

[0080] Natural language interpretation, for example, suggests that due to a malfunction in device A, task X should be transferred to device B, which is expected to reduce output by 5%, but will prevent a 30-minute delay in order Y. This helps managers understand and trust the system's decisions, enhancing decision-making transparency and trust in human intervention. It also supports managers in querying hypothetical scenarios such as "what if..." through conversational interaction, enabling flexible scheduling through human-machine collaboration.

[0081] In one optional implementation, deviation calculation: After the target scheduling rule is issued and executed, the system collects actual KPIs in real time through SCADA / MES (consistent with simulation indicators: total output, order delay time, equipment utilization, and number of task switching), and calculates the prediction deviation: % in, Let represent the relative error of the i-th sample. Let i be the simulated predicted value of the i-th sample. Let be the true value of the i-th sample, and let be the relative error calculation formula in percentage form.

[0082] Anomaly detection: If the δi of any KPI exceeds the preset threshold, the event will be marked as an anomaly and stored in the historical case library. The case includes: perturbation feature vector, selected rule, simulation result, actual result, and deviation value.

[0083] Incremental update: If the execution deviation of a rule exceeds the threshold three times in a row, the execution conditions of the rule will be automatically adjusted (e.g., the device load threshold for task transfer will be lowered from 85% to 75%). If a new disturbance pattern that has not been included is found, the large model analysis log will be triggered to generate a new rule candidate, which will be added to the rule library after being confirmed by the engineer.

[0084] This logic enables the system to evolve adaptively, adapting to production line changes such as equipment aging and process adjustments.

[0085] In one alternative implementation, at shift change points or the start of a production plan, a global baseline scheduling scheme is generated using mixed integer programming based on production orders, equipment capacity, and process route information, and then sent to the MES for execution.

[0086] Utilizing large models (such as fine-tuned BERT or GPT models), historical maintenance records (including abnormal event types), shift handover logs, and MES operation logs are automatically analyzed to extract implicit disturbance types and manual response patterns, automatically generating new rule candidates, including: Equipment failure rules include: task transfer (transferring tasks from the failed device to an idle device of the same type), device replacement (activating the backup device corresponding to the failed device), and task reordering (adjusting the priority of subsequent tasks on the failed device).

[0087] Urgent order insertion rules include: preemptive scheduling (urgent orders are inserted into the task queue according to priority, which is equivalent to pausing low-priority tasks), sequential compression (compressing the estimated remaining time of the current task. The estimated remaining time is dynamically calculated by the scheduling system based on real-time production data. For the currently executing task, the system calculates the time required to complete the task in real time based on the processed time, remaining processing volume, current equipment operating parameters, and standard time in the process library. Without affecting product quality, the time is shortened by adjusting equipment operating parameters (such as increasing the feed speed). For example, if the current task is estimated to have 20 minutes remaining, and the feed speed can be increased by 25% after process verification, the remaining time is 16 minutes. The squeezed-out 4 minutes can be used for the first piece debugging or processing of the urgent order without pausing the original task, reducing task switching losses), and generating overtime tasks, etc.

[0088] Material delay rules include: task forwarding (moving tasks corresponding to available materials forward), equipment standby (adjusting equipment corresponding to material delays to enter low-power standby mode), and task exchange (exchanging the order with another task that uses the same material, where there is a temporary shortage of material, but other tasks in the schedule also need the same material, and the other tasks have more urgent delivery times and different material demand times, so the urgent task is processed first).

[0089] Each rule is stored in a structured format, including: rule ID, applicable disturbance type, execution conditions (such as equipment load rate threshold, manual operation trigger threshold statistically analyzed from MES operation logs by the large model), adjustment action description (converting unstructured log content (such as transferring the spindle's work to adjacent device B) into a structured description conforming to MES instruction specifications (such as transferring task ID:X on faulty device ID:A to idle device ID:B of the same type)), and expected impact factors (such as the estimated impact on output and energy consumption, with initial values ​​derived from historical simulation data from the digital twin platform (such as an average output decrease of 5% and a delay reduction of 30% in the past 100 executions of the task transfer rule); subsequently, through closed-loop feedback, the rules are continuously calibrated and updated using actual operating KPI data to gradually approach the real impact.

[0090] Among them, the historical maintenance records include the specific type of each equipment failure (such as a machining center spindle failure), the repair time, and the actions taken by the maintenance personnel at that time (such as transferring the task to an idle equipment B of the same type). The large model extracts these entities and relationships through NLP to generate candidate rules for equipment failure categories. The shift handover log records production anomalies from the previous shift (such as urgent orders from customer A / materials from supplier B delayed by 2 hours), handling measures, and outstanding issues. The large model extracts unstructured handling experience from this log and transforms it into structured rule logic. The MES operation log records every manual operation performed by the scheduler (such as changing the task priority to the highest or starting the backup equipment), the reason for the operation, and the changes in the system state after the operation. The large model extracts the structured elements of the rules, such as "execution conditions" and "expected impact factors," by statistically analyzing the frequency of these structured operations, their preconditions, and subsequent effects.

[0091] Please see Figure 5 , Figure 5 The present invention provides a rescheduling simulation device for dynamic disturbances of an industrial production line. Optionally, the rescheduling simulation device for dynamic disturbances of an industrial production line is applied to the electronic equipment described above.

[0092] The rescheduling simulation device for dynamic disturbances in industrial production lines includes: a first processing unit 501 and a second processing unit 502.

[0093] The first processing unit 501 is used to acquire various equipment status signals in the industrial production line and material inventory information and order change information corresponding to the industrial production line; The first processing unit 501 is also used to determine whether an abnormal event is triggered based on the equipment status signal, material inventory information and order change information; The first processing unit 501 is also used to extract a disturbance feature vector when an abnormal event is triggered. The disturbance feature vector includes the disturbance type matching the abnormal event, the time of occurrence of the abnormal event, the severity of the abnormality, and the equipment, materials, and orders involved in the abnormal event. The first processing unit 501 is also used to input the perturbation feature vector into the perturbation classification model so that it outputs the corresponding perturbation subtype; The first processing unit 501 is also used to determine, according to the preset disturbance rule mapping relationship, a candidate scheduling rule that matches the disturbance subtype from the rule base; The first processing unit 501 is also used to perform simulation and deduction based on candidate scheduling rules in the digital twin platform corresponding to the industrial production line, and to obtain the simulation results of the preliminary scheduling rules. The preliminary scheduling rules are candidate scheduling rules that have been fully simulated and deduced in the digital twin platform. The simulation results include the total output, total order delay time, average equipment utilization, and number of task switching within the simulation time window. The second processing unit 502 is used to determine the target scheduling rule based on the simulation results of each preliminary scheduling rule, and send it to the industrial production line so that the industrial production line can execute the target scheduling rule.

[0094] The second processing unit 502 can execute S180 as described above, and the first processing unit 501 can execute other steps in the above method embodiment.

[0095] It should be noted that the industrial production line dynamic disturbance rescheduling simulation device provided in this embodiment can execute the method flow shown in the above method flow embodiment to achieve the corresponding technical effects. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above embodiments.

[0096] This invention also provides a storage medium storing computer instructions and programs. When these instructions and programs are read and executed, they perform the rescheduling simulation method for dynamic disturbances in industrial production lines described in the above embodiments. The storage medium may include memory, flash memory, registers, or a combination thereof.

[0097] The following provides an electronic device, which may be a server device, a computer device, or a mobile phone device, etc. This electronic device, for example... Figure 1 As shown, the above-described industrial production line dynamic disturbance rescheduling simulation method can be implemented. Specifically, the electronic device includes: a processor 10, a memory 11, and a bus 12. The processor 10 may be a CPU. The memory 11 is used to store one or more programs. When one or more programs are executed by the processor 10, the industrial production line dynamic disturbance rescheduling simulation method of the above embodiment is executed.

[0098] In summary, the present invention provides a rescheduling simulation method and related apparatus for dynamic disturbances in industrial production lines. When an abnormal event is triggered, the method extracts the disturbance feature vector and determines matching candidate scheduling rules based on the disturbance feature vector. Simulation is performed on the digital twin platform corresponding to the industrial production line based on the candidate scheduling rules, and simulation results of the initially selected scheduling rules are obtained. Based on the simulation results of each initially selected scheduling rule, the target scheduling rule is determined and sent to the industrial production line to execute the target scheduling rule. Selecting candidate scheduling rules from a rule base improves response efficiency compared to a complete rescheduling approach, reduces the possibility of the production line falling into waiting or executing outdated solutions after a disturbance occurs, and retrieves capacity losses. Determining the target scheduling rule from multiple candidate scheduling rules through simulation on a digital twin platform ensures global optimization effects, improves scheduling accuracy, and avoids local congestion or equipment idleness.

[0099] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0100] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention 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 the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A rescheduling simulation method for dynamic disturbances in industrial production lines, characterized in that, The method includes: Acquire status signals of various equipment in the industrial production line, as well as material inventory information and order change information corresponding to the industrial production line; Based on the equipment status signal, the material inventory information, and the order change information, determine whether an abnormal event has been triggered; When an abnormal event is triggered, a disturbance feature vector is extracted. The disturbance feature vector includes the disturbance type matching the abnormal event, the time of occurrence of the abnormal event, the severity of the abnormality, and the equipment, materials, and orders involved in the abnormal event. The perturbation feature vector is input into the perturbation classification model so that it outputs the corresponding perturbation subtype; Based on the preset disturbance rule mapping relationship, candidate scheduling rules matching the disturbance subtype are determined from the rule base; Simulation is performed on the digital twin platform corresponding to the industrial production line based on candidate scheduling rules, and simulation results of the initial scheduling rules are obtained. The initial scheduling rules are candidate scheduling rules that have been fully simulated in the digital twin platform. The simulation results include total output, total order delay time, average equipment utilization, and number of task switching within the simulation time window. Based on the simulation results of each preliminary scheduling rule, the target scheduling rule is determined and issued to the industrial production line so that the industrial production line executes the target scheduling rule.

2. The rescheduling simulation method for dynamic disturbances in industrial production lines as described in claim 1, characterized in that, The step of determining whether an abnormal event is triggered based on the equipment status signal, the material inventory information, and the order change information includes: If the equipment status signal changes from running to suspected fault and continues for more than a preset time, an abnormal event is triggered, and the abnormal event type is equipment fault. When the order change information includes a new order with an emergency identifier, and the current production line load of the industrial production line exceeds the load threshold, an abnormal event is determined to be triggered, and the abnormal event type is "urgent order insertion". An abnormal event is triggered when the remaining inventory of materials required for a single type of task in the material warehouse is lower than the safety stock threshold and the expected delivery time is later than the corresponding current demand time. The abnormal event type is material delay.

3. The rescheduling simulation method for dynamic disturbances in industrial production lines as described in claim 1, characterized in that, After determining the candidate scheduling rule matching the disturbance subtype from the rule base according to the preset disturbance rule mapping relationship, the method further includes: Identify and delete candidate scheduling rules whose execution conditions do not match the current equipment status in the industrial production line.

4. The rescheduling simulation method for dynamic disturbances in industrial production lines as described in claim 1, characterized in that, The simulation and deduction based on candidate scheduling rules in the digital twin platform corresponding to the industrial production line, and the acquisition of simulation results of the initially selected scheduling rules, include: Simulation and deduction based on candidate scheduling rules are performed in the digital twin platform; The performance indicators of each simulation evaluation node are obtained sequentially, and the performance indicators of each simulation evaluation node are converted into real-time simulation scores. The performance indicators include the current cumulative output, the current average equipment utilization rate, the current order delay time, and the current number of task switching. Determine whether the simulation stop condition is triggered, wherein the simulation stop condition is that the real-time simulation scores of multiple consecutive simulation evaluation nodes are all lower than the score threshold; If so, then stop the simulation and deduction of the candidate scheduling rule and mark it as an invalid strategy; If not, continue the simulation until the simulation time window ends, mark the candidate scheduling rule as the initial scheduling rule, and obtain the simulation results of the initial scheduling rule.

5. The rescheduling simulation method for dynamic disturbances in industrial production lines as described in claim 1, characterized in that, The target scheduling rule is determined based on the simulation results of each initial scheduling rule, including: The comprehensive score of each preliminary scheduling rule is determined based on the total output, total order delay time, average equipment utilization, and number of task switching within the simulation time window. The initial scheduling rule with the highest comprehensive score is selected as the target scheduling rule.

6. The rescheduling simulation method for dynamic disturbances in industrial production lines as described in claim 5, characterized in that, The formula for the comprehensive score is: in, Let r represent the overall score of the r-th initial selection scheduling rule. This represents the total output of the r-th initial selection scheduling rule within the simulation time window. This represents the maximum value among all total outputs. This represents the total order delay time within the simulation time window for the r-th initial selection scheduling rule. This represents the maximum total delay time among all orders. This represents the average equipment utilization rate within the simulation time window for the r-th initial scheduling rule. This represents the number of task switching occurrences within the simulation time window for the r-th initial scheduling rule. to These are the weighting coefficients.

7. The rescheduling simulation method for dynamic disturbances in industrial production lines as described in claim 5, characterized in that, After determining the target scheduling rule based on the simulation results of each initial scheduling rule, the method further includes: A natural language explanation is generated based on the target scheduling rules and their corresponding simulation results.

8. A rescheduling simulation device for dynamic disturbances in industrial production lines, characterized in that, The device includes: The first processing unit is used to acquire various equipment status signals in the industrial production line and material inventory information and order change information corresponding to the industrial production line; The first processing unit is further configured to determine whether an abnormal event is triggered based on the equipment status signal, the material inventory information, and the order change information; The first processing unit is also used to extract a disturbance feature vector when an abnormal event is triggered. The disturbance feature vector includes the disturbance type matching the abnormal event, the time of occurrence of the abnormal event, the severity of the abnormality, and the equipment, materials, and orders involved in the abnormal event. The first processing unit is further configured to input the perturbation feature vector into the perturbation classification model so that it outputs the corresponding perturbation subtype; The first processing unit is further configured to determine, from the rule base, a candidate scheduling rule that matches the disturbance subtype according to a preset disturbance rule mapping relationship; The first processing unit is also used to perform simulation and deduction based on candidate scheduling rules in the digital twin platform corresponding to the industrial production line, and obtain the simulation results of the preliminary scheduling rules. The preliminary scheduling rules are candidate scheduling rules that have been fully simulated and deduced in the digital twin platform. The simulation results include the total output, total order delay time, average equipment utilization, and number of task switching within the simulation time window. The second processing unit is used to determine the target scheduling rule based on the simulation results of each preliminary scheduling rule, and send it to the industrial production line so that the industrial production line executes the target scheduling rule.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method as described in any one of claims 1-7.

10. An electronic device, characterized in that, include: Processor and memory, the memory being used to store one or more programs; When the one or more programs are executed by the processor, the method as described in any one of claims 1-7 is implemented.

Images