Method and device for identifying event, equipment and medium

Abstract

A method (200), apparatus, device and medium for identifying an event. The method (200) includes acquiring production-related perturbation events (202) from a production system and generating predicted production data based on real-time production data of the production system (204). The method (200) further includes identifying (206) a type of perturbation event based on the desired production data and the predicted production data, where the desired production data is production data of the production system without the perturbation event. Implementation of the method (200) can automatically identify the type of perturbation event related to production, thereby facilitating rapid decision making and automatic generation of an optimized scheduling scheme, thereby improving production efficiency while conserving production resources.

Description

Method, apparatus, device, and medium for identifying events Technical Field

[0001] Embodiments of the present disclosure relate generally to the field of computer software, and more particularly to methods, apparatuses, devices, and media for identifying events. Background Art

[0002] The workshop is the basic unit of production for a factory or enterprise, responsible for fulfilling its production, processing, and logistics plans. Workshop scheduling optimization is a crucial step in intelligently managing production tasks and resources, directly impacting the efficiency of a factory or enterprise. Automation and intelligent processes are becoming increasingly prevalent in modern industrial production. Automated production provides timely insights into production line conditions, such as production time, downtime, and idle time of processing equipment; the number of raw materials, semi-finished products, finished products, and workers; product quality, process specifications, yield rate, equipment failures, and scheduling errors.

[0003] During the production execution process, dynamic uncertain events are almost inevitable and even occur frequently, such as material shortages, machine failures, quality abnormalities, etc. These events may cause fluctuations, deviations, or even interruptions in the production process, disrupting the production plan and causing a large deviation between the actual production status and the original production plan, which in turn leads to low production efficiency, waste of production resources, disordered production management, and delays in production progress.

[0004] Summary of the Invention

[0005] Embodiments of the present disclosure provide methods, devices, equipment, media, and products for identifying events. According to embodiments of the present disclosure, the types of production-related disturbance events can be automatically identified, thereby facilitating the rapid and automatic generation of optimized scheduling plans, thereby improving production efficiency while conserving production resources.

[0006] In a first aspect of the present disclosure, a method for identifying events is provided, comprising: obtaining a production-related disturbance event from a production system; generating predicted production data based on real-time production data of the production system; and identifying the type of the disturbance event based on expected production data and the predicted production data, where the expected production data is the production data of the production system in the absence of the disturbance event. Implementing the first aspect of the present disclosure automatically identifies the type of the production-related disturbance event, thereby facilitating the rapid and automatic generation of an optimized scheduling plan, thereby improving production efficiency while conserving production resources.

[0007] In conjunction with the first aspect, in some embodiments, generating the predicted production data includes generating the predicted production data using a digital twin simulation model, wherein the digital twin simulation model is used to simulate production data of a production system. In this manner, the digital twin simulation model can facilitate quantitative analysis of production data and identification of disturbance event types through simulation prediction.

[0008] In conjunction with the first aspect, in some embodiments, identifying the type of the disturbance event includes: determining, based on the expected production data and the predicted production data, a deviation between the expected production data and the predicted production data from a first moment to a second moment; and determining that the type of the disturbance event is a dominant disturbance event if the deviation is greater than a target constraint value. By comparing the deviations, dominant disturbance events can be quickly identified.

[0009] In conjunction with the first aspect, in some embodiments, identifying the type of disturbance event further includes, if the deviation is less than or equal to the target constraint value, determining the correlation coefficient between the expected production data and the predicted production data. And if the correlation coefficient is less than or equal to a predetermined threshold, determining the type of disturbance event as a latent disturbance event. Correlation analysis can be used to determine whether the trends between the expected production data and the predicted production data are consistent. The strength of the correlation can be determined by the correlation coefficient. Generally speaking, a positive correlation coefficient indicates a positive correlation, and a negative correlation coefficient indicates a negative correlation. The closer the correlation coefficient is to 1, the higher the degree of correlation, and the closer the correlation coefficient is to 0, the lower the degree of correlation. In some embodiments, a predetermined threshold can be given to determine the strength of the correlation. If the correlation coefficient is less than or equal to the predetermined threshold, it means that the correlation between the expected production data and the predicted production data is weak, indicating that there is a significant deviation between the expected production data and the predicted production data, and an abnormal trend caused by the disturbance event, so the type of the disturbance event is determined to be a latent disturbance event. In some embodiments, if the correlation coefficient between the expected production data and the predicted production data is greater than a predetermined threshold, it indicates that the correlation between the expected production data and the predicted production data is strong, indicating that the expected production data and the predicted production data have the same trend, and other judgments are required to continue to identify the type of disturbance event.

[0010] In conjunction with the first aspect, in some embodiments, identifying the type of disturbance event further includes, if the correlation coefficient is greater than a predetermined threshold, performing a variance analysis on the expected production data and the predicted production data. If the results of the variance analysis meet the predetermined conditions, the type of disturbance event is determined to be a latent disturbance event. And if the results of the variance analysis do not meet the predetermined conditions, the type of disturbance event is determined to be an irrelevant disturbance event. Performing a variance analysis on the expected production data and the predicted production data helps to further identify the type of disturbance event by filtering and eliminating the impact of random fluctuations. For example, in some embodiments, if the significance P value obtained by the variance analysis is less than or equal to a certain threshold, such as 0.05, it indicates that the difference is significant. If the difference is significant, it indicates that the fluctuation is likely caused by the disturbance event, and the disturbance event is determined to be a latent disturbance event. If the significance P value is greater than a certain threshold, such as 0.05, it indicates that the difference is not significant. If the difference is not significant, it indicates that the fluctuation is likely caused by systematic error, and the disturbance event is determined to be an irrelevant disturbance event.

[0011] In conjunction with the first aspect, in some embodiments, explicit disturbance events can represent events that have a significant impact on the production system, such as equipment failure on the critical path, a large shortage of raw materials, a significant change in demand, etc. This situation will definitely violate the operational objectives, such as failure to deliver on time or failure to meet production targets. Explicit disturbance events require immediate response. Implicit disturbance events can represent events that have little impact on the production system at present, but may accumulate into explicit disturbance events with a larger impact over time. For example, a small increase or decrease in demand at the current moment has a negligible impact on the production system, but as time goes by, the cumulative amount of changed demand may produce a large deviation, which may have a significant impact on the production system. Implicit disturbance events may not need to be handled immediately, but attention should be paid and countermeasures should be prepared in advance to avoid serious impacts on future production as soon as possible. Irrelevant disturbance events can be events with very small impact, such as equipment failure in the current workshop that is not involved in production or will not participate in production within the planned time period, or a shortage of raw materials that are not involved in production. These have little impact on the output of the current production system. Irrelevant disturbance events can be ignored and no additional response measures may be taken for the time being. Automatically identifying the type of disturbance event helps to assess the impact of disturbance events on current and future systems, reduce dependence on manual experience, and alleviate the workload of production personnel.

[0012] In conjunction with the first aspect, in some embodiments, the method further includes issuing a reminder related to the production system if the disturbance event is an explicit disturbance event or a implicit disturbance event, wherein the reminder level for explicit disturbance events is higher than the reminder level for implicit disturbance events. Issuing a reminder helps production personnel notice the impact of the disturbance event. Because explicit disturbance events have a more serious impact than implicit disturbance events, setting the reminder level for explicit disturbance events higher than the reminder level for implicit disturbance events can ensure that explicit disturbance events are noticed by production personnel first.

[0013] In conjunction with the first aspect, in some embodiments, the method further includes: if the disturbance event is an explicit disturbance event, sending a first request to the rescheduling optimization module to optimize the current scheduling solution; and if the disturbance event is an implicit disturbance event, sending a second request to the rescheduling optimization module to optimize the current scheduling solution. This helps to automatically optimize according to the type of disturbance event, reducing manual workload.

[0014] In conjunction with the first aspect, in some embodiments, the first request is prioritized over the second request. Because explicit disturbance events have a more serious impact than implicit disturbance events and require an immediate response, the first request is prioritized over the second request. Therefore, the rescheduling scheme for explicit disturbance events is prioritized over implicit disturbance events. This helps to reasonably arrange the optimization sequence based on the importance of events.

[0015] In conjunction with the first aspect, in some embodiments, the method further includes receiving, by the rescheduling decision module, an optimized scheduling solution from the rescheduling optimization module. In this way, the optimized scheduling solution can help to improve the negative impact of the disturbance event.

[0016] In conjunction with the first aspect, in some embodiments, the rescheduling decision module is deployed locally in the production system, and the rescheduling optimization module is deployed in the cloud. In this way, the advantages of edge analytics and cloud optimization services are combined to support dynamic optimization of production process control with low latency.

[0017] In conjunction with the first aspect, in some embodiments, the method further includes: determining a first resource consumption for adopting the optimized scheduling solution and a second resource consumption for maintaining the current scheduling solution of the production system, comparing the first resource consumption with the second resource consumption, and if the first resource consumption is less than the second resource consumption, updating the scheduling solution implemented by the production system to the optimized scheduling solution. This helps to quickly and automatically generate an optimized scheduling solution, reduce the workload of the scheduler, improve production efficiency, and save production resources.

[0018] In conjunction with the first aspect, in some embodiments, the method further includes maintaining the current scheduling plan of the production system unchanged if the first resource consumption is greater than or equal to the second resource consumption. If resource consumption is not further reduced, there is no need to change the scheduling plan, thereby saving additional costs associated with adjustments.

[0019] In a second aspect of the present disclosure, a device for identifying events is provided, the device comprising: an event acquisition module configured to acquire production-related disturbance events from a production system; a production prediction module configured to generate predicted production data based on real-time production data of the production system; and an event identification module configured to identify the type of disturbance event based on expected production data and predicted production data, wherein the expected production data is the production data of the production system in the absence of a disturbance event. Implementing the second aspect of the present disclosure can automatically identify the type of disturbance event related to production, thereby facilitating the rapid and automatic generation of optimized scheduling plans, improving production efficiency, and saving production resources.

[0020] In conjunction with the second aspect, in some embodiments, the production forecasting module may also be configured to generate predicted production data using a digital twin simulation model, where the digital twin simulation model is used to simulate production data from the production system. In some embodiments, when a disturbance event is detected, the digital twin simulation model can be used to obtain expected and predicted production data based on real-time production data and the current scheduling plan. The digital twin simulation model can facilitate quantitative analysis of production data and identification of disturbance event types through prediction and simulation.

[0021] In conjunction with the second aspect, in some embodiments, the event identification module may be further configured to determine, based on the expected production data and the predicted production data, a deviation between the expected production data and the predicted production data from a first moment to a second moment. If the deviation is greater than a target constraint value, the disturbance event is determined to be a dominant disturbance event. By comparing the deviation, dominant disturbance events can be quickly identified.

[0022] In conjunction with the second aspect, in some embodiments, the event identification module may also be configured to determine the correlation coefficient between the expected production data and the predicted production data if the deviation is less than or equal to the target constraint value. And if the correlation coefficient is less than or equal to a predetermined threshold, determine that the type of disturbance event is a latent disturbance event. Correlation analysis can be used to determine whether the trends between the expected production data and the predicted production data are consistent. The strength of the correlation can be determined by the correlation coefficient. If the correlation is weak, it means that there is a significant deviation between the expected production data and the predicted production data, and it is an abnormal trend caused by the disturbance event, so the type of the disturbance event is determined to be a latent disturbance event. If the correlation is strong, it means that the expected production data and the predicted production data have the same trend, and other determinations are required to continue to identify the type of disturbance event.

[0023] In combination with the second aspect, in some embodiments, the event identification module can also be configured to perform variance analysis on the expected production data and the predicted production data if the correlation coefficient is greater than a predetermined threshold. If the result of the variance analysis meets the predetermined conditions, the type of the disturbance event is determined to be a latent disturbance event. And if the result of the variance analysis does not meet the predetermined conditions, the type of the disturbance event is determined to be an irrelevant disturbance event. Through variance analysis, a significance test can be performed on the expected production data and the predicted production data, which helps to continue to identify the type of disturbance event by filtering and eliminating the impact of random fluctuations. If the difference is significant, it means that the fluctuation is likely to be caused by a disturbance event, and the disturbance event is determined to be a latent disturbance event; if the difference is not significant, it means that the fluctuation is likely to be caused by a systematic error, and the disturbance event is determined to be an irrelevant disturbance event.

[0024] Automatically identifying the type of disturbance event according to the above embodiment helps to assess the impact of the disturbance event on the current system and future systems, reduces dependence on manual experience, and alleviates the workload of production personnel.

[0025] In conjunction with the second aspect, in some embodiments, the event identification module may be further configured to send a first request to the rescheduling optimization module to optimize the current scheduling solution if the disturbance event is an explicit disturbance event. Furthermore, if the disturbance event is an implicit disturbance event, the event identification module may be further configured to send a second request to the rescheduling optimization module to optimize the current scheduling solution. This facilitates automatic optimization based on the type of disturbance event, reducing manual workload.

[0026] In conjunction with the second aspect, in some embodiments, the first request is prioritized over the second request. Because explicit disturbance events have a more severe impact than implicit disturbance events and require an immediate response, the first request is prioritized over the second request. Consequently, the rescheduling scheme for explicit disturbance events is prioritized over implicit disturbance events, facilitating a reasonable optimization sequence based on the urgency of the events.

[0027] In conjunction with the second aspect, in some embodiments, the device may further include a reminder module, which is configured to issue a reminder related to the production system if the type of disturbance event is an explicit disturbance event or an implicit disturbance event, wherein the reminder level of the explicit disturbance event is higher than the reminder level of the implicit disturbance event. Issuing a reminder helps production personnel notice the impact of the disturbance event. Since the impact of explicit disturbance events is more serious than that of implicit disturbance events, setting the reminder level of explicit disturbance events higher than that of implicit disturbance events can make explicit disturbance events be noticed by production personnel first. In some embodiments, since the impact of explicit disturbance events is more serious than that of implicit disturbance events, the reminder level of explicit disturbance events is higher than that of implicit disturbance events. For example, if a first-level reminder is set for an explicit disturbance event, a reminder can be issued immediately through a buzzer. If a second-level reminder is set for an implicit disturbance event, a reminder can be issued by sending an event log, which may not be immediately noticed by production personnel.

[0028] In conjunction with the second aspect, in some embodiments, the apparatus may further include a rescheduling decision module configured to receive an optimized scheduling solution from the rescheduling optimization module. The optimized scheduling solution may help to improve the negative impact of the disturbance event.

[0029] In conjunction with the second aspect, in some embodiments, the rescheduling decision module is deployed locally in the production system, and the rescheduling optimization module is deployed in the cloud. Combining the advantages of edge analytics and cloud optimization services can support dynamic optimization of production process control with low latency.

[0030] In conjunction with the second aspect, in some embodiments, the rescheduling decision module may be further configured to determine a first resource consumption of adopting an optimized scheduling solution and a second resource consumption of maintaining a current scheduling solution of the production system.

[0031] In conjunction with the second aspect, in some embodiments, the rescheduling decision module may be further configured to compare the first resource consumption with the second resource consumption. If the first resource consumption is less than the second resource consumption, the rescheduling decision module may be further configured to update the scheduling plan implemented by the production system to an optimized scheduling plan. If the first resource consumption is greater than or equal to the second resource consumption, the rescheduling decision module may be further configured to maintain the current scheduling plan of the production system unchanged. This helps to quickly and automatically generate an optimized scheduling plan, reduce the workload of the dispatcher, improve production efficiency, and save production resources.

[0032] In a third aspect of the present disclosure, an electronic device is provided. The electronic device includes one or more processors and a memory for storing computer-executable instructions. When the one or more processors execute the computer-executable instructions, the electronic device implements any method according to the first aspect.

[0033] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored. When the computer-executable instructions are executed, at least one processor is caused to perform the method according to any one of the above first aspects.

[0034] In a fifth aspect of the present disclosure, a computer program product is provided, comprising computer-executable instructions, which, when executed, cause at least one processor to perform the method according to any one of the above first aspects.

[0035] By implementing the above aspects of the present disclosure and combining them with the embodiments, it is possible to utilize digital twin simulation models and disturbance event identification methods to automatically identify the types of disturbance events related to production through quantitative analysis to evaluate the impact of disturbance events on current and future systems, reduce reliance on manual experience, and reduce the workload of production personnel. In addition, the use of scheduling optimization decision-making methods helps to quickly and automatically generate optimized scheduling plans, reduce the workload of dispatchers, thereby improving production efficiency and saving production resources. In addition, it is also possible to integrate the advantages of edge analysis and cloud optimization services to support dynamic optimization of production process control with low latency.

[0036] This summary is provided to introduce a selection of concepts in a simplified form that are further described in the detailed description below. This summary is not intended to identify key features or essential features of the disclosure, nor is it intended to limit the scope of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above-mentioned characteristics, technical features, advantages and implementation methods of the present disclosure will be further described below in a clear and understandable manner through the description of preferred embodiments in conjunction with the accompanying drawings, wherein:

[0038] FIG1 shows a schematic diagram of an application scenario according to an embodiment of the present disclosure;

[0039] FIG2 shows a schematic flow chart of a method for identifying an event according to an embodiment of the present disclosure;

[0040] FIG3 shows a schematic diagram of the architecture of a production system according to an embodiment of the present disclosure;

[0041] FIG4 shows a schematic diagram of a disturbance impact estimation process according to an embodiment of the present disclosure;

[0042] FIG5 shows a schematic flow chart of a disturbance identification method according to an embodiment of the present disclosure;

[0043] FIG6 shows a schematic flow chart of a scheduling optimization decision method according to an embodiment of the present disclosure; and

[0044] FIG7 shows a schematic diagram of an example device that may be used to implement embodiments of the present disclosure.

[0045] List of reference numerals:

[0046] 110: Cloud Server

[0047] 112: Rescheduling Optimization Module

[0048] 120: Edge devices

[0049] 122: Digital Twin Simulation Model

[0050] 124: Event Identification Module

[0051] 126: Rescheduling Decision Module

[0052] 130: Workshop

[0053] 310: Analysis and Decision-making Module

[0054] 312: Event Identification Module

[0055] 314: Rescheduling Decision Module

[0056] 316: Digital Twin Simulation Model

[0057] 320: Optimization module

[0058] 322: Data Collection Module

[0059] 324: Rescheduling Optimization Module

[0060] 330: Production monitoring module

[0061] 332: Production data acquisition module

[0062] 334: Production Execution Module

[0063] 336: Scheduling Update Module

[0064] 340: Production staff

[0065] 342: Operator

[0066] 344: Dispatcher

[0067] 346: Planner

[0068] 402: Time

[0069] 404: Production Data

[0070] 412: Real-time production data series

[0071] 422: Forecasting Production Data Series

[0072] 432: Expected production data sequence

[0073] 701: CPU

[0074] 702: ROM

[0075] 703: RAM

[0076] 704: Bus

[0077] 705: I / O interface

[0078] 706: Input unit

[0079] 707: Output unit

[0080] 708: Storage unit

[0081] 709: Communication unit DETAILED DESCRIPTION

[0082] The principles of the present disclosure will be described below with reference to several exemplary embodiments shown in the accompanying drawings. Although preferred embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that these embodiments are described only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way.

[0083] As used herein, the term "including" and its variations represent open inclusion, i.e., "including but not limited to". Unless otherwise stated, the term "or" means "and / or". The term "based on" means "based at least in part on". The terms "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". Other explicit and implicit definitions may also be included below. Some example embodiments of the present disclosure are described below with reference to Figures 1 to 7.

[0084] Shop floor scheduling optimization is a crucial step in achieving intelligent decision-making regarding production tasks and resources. During production execution, dynamic, uncertain events can directly impact a factory or enterprise's operational efficiency. Traditional manual rescheduling methods are complex to assess the impact of these events, often relying heavily on subjective judgment by professionals. This lacks rigor, the judgment process is subjective, and the results are subject to randomness. Furthermore, the lack of quantitative analysis makes it difficult to accurately determine the circumstances and timing for dynamic rescheduling. Furthermore, determining rescheduling plans is time-consuming, making it difficult to meet the real-time or low-latency response requirements of production systems. Rescheduling methods that solely use neural network models suffer from the problems of relying on a sufficiently large number of training samples for accuracy and the potential for overfitting, leading to significant bias in the results.

[0085] Embodiments of the present disclosure provide methods, devices, equipment, media, and products for identifying events. The method for identifying events includes obtaining production-related disturbance events from a production system, generating predicted production data based on real-time production data of the production system, and identifying the type of disturbance event based on the expected production data and the predicted production data. According to embodiments of the present disclosure, the type of production-related disturbance event can be automatically identified, thereby facilitating the rapid and automatic generation of optimized scheduling plans, dynamically optimizing and controlling the production process, thereby improving production efficiency and saving production resources.

[0086] FIG1 shows a schematic diagram of an example application scenario 100 according to an embodiment of the present disclosure. Example application scenario 100 can be implemented as a production system, such as a production workshop or production line. As shown in FIG1 , an optimization module 112 and other components can be deployed on a cloud server 110, a digital twin simulation model 122, a disturbance analysis module 124, and a rescheduling decision module 126 and other components can be deployed on an edge device 120, and a workshop 130 can include multiple production objects, such as materials and machines. The embodiments of the present disclosure do not impose any restrictions on the implementation type, implementation method, or number of deployments of the multiple production objects included in the cloud server 110, edge device 120, and workshop 130. It should be understood that the application scenario 100 illustrated in FIG1 is merely illustrative. Depending on actual application scenarios, the application scenario 100 in FIG1 can have various other layout forms, implementation combinations, and the like, and the embodiments of the present disclosure do not impose any restrictions on this.

[0087] Each device may include one or more functional modules and / or units for production, and these modules and / or units may be partially or fully implemented as hardware modules, software modules, firmware modules or any combination thereof. Among them, a first communication connection may be established between the cloud server 110 and the edge device 120, and a second communication connection may be established between the edge device 120 and the workshop 130. Through the second communication connection, the edge device 120 can receive real-time production data from the workshop 130, and the digital twin simulation model 122 of the edge device 120 can simulate and predict the predicted production data of the production system based on the real-time production data. The digital twin simulation model 122 can also generate the corresponding expected production data (also called ideal production data) in the absence of disturbance events based on the current scheduling scheme. For more information about the implementation mechanism of the digital twin simulation model 122, please refer to the embodiment described in Figure 4. The event identification module 124 of the edge device 120 can identify the type of disturbance event based on the predicted production data and the expected production data, for example, classified as a dominant disturbance event (DDE), a recessive disturbance event (RDE), an irrelevant disturbance event (NDE), etc. In some embodiments, the types of disturbance events can also be divided into two categories or more than three categories. The edge device 120 can determine whether to send a request to optimize the current scheduling scheme to the cloud server 110 through the first communication connection, or issue a reminder related to the production system, based on the type of disturbance event. The rescheduling optimization module 112 of the cloud server 110 can be used to generate an optimized scheduling scheme using an optimization algorithm and simulation service when receiving a request to optimize the current scheduling scheme from the edge device 120, and then send it to the edge device 120 through the first communication connection. After receiving the optimized scheduling solution, the rescheduling decision module 126 of the edge device 120 can compare the first resource consumption of the optimized scheduling solution with the second resource consumption of the current scheduling solution of the production system, and decide to adopt the scheduling solution with lower resource consumption. The edge device 120 can send the optimized scheduling solution to the workshop 130 via the second communication connection, and the workshop 130 can re-update the allocation of resources and tasks based on the optimized scheduling solution.

[0088] It is understandable that the application scenario 100 may include more or fewer devices and more or fewer modules, and the embodiments of the present disclosure are not limited thereto. More specific implementations of the functions included in the above-mentioned devices or modules can be understood in conjunction with the descriptions in the embodiments of Figures 2 to 7 below.

[0089] By implementing the application scenario 100 provided in this embodiment, the digital twin simulation model 122 and disturbance identification algorithm can be used to automatically identify the types of production-related disturbance events through quantitative analysis to assess their impact on current and future systems, reducing reliance on operator experience. Furthermore, utilizing a rescheduling decision-making mechanism facilitates the rapid and automatic generation of optimized scheduling plans, reducing dispatcher workloads, improving production efficiency, and conserving production resources. Furthermore, the advantages of edge analytics and cloud optimization services can be integrated to support dynamic optimization of production process control with low latency.

[0090] FIG2 shows a flowchart of a method 200 for identifying an event according to an embodiment of the present disclosure. The method 200 can be performed by an electronic device. The electronic device may include, but is not limited to, a personal computer (PC), a server computer, a handheld or laptop device, a mobile device, a multi-processor system, a wearable electronic device, smart factory equipment, a minicomputer, a mainframe computer, an edge computing device, a distributed computing environment including any one or a combination of the above devices, and the like. The embodiments of the present disclosure do not impose any restrictions on the device type, etc., of the electronic device that implements the method 200. It should be understood that in the embodiments of the present disclosure, the main body of implementing the method 200 can be implemented by a single physical device or by a plurality of physical devices working together. The main body of implementing the method 200 can be one or more logical functional modules within a physical device or one or more logical functional modules composed of multiple physical devices, and the embodiments of the present disclosure do not impose any restrictions on this. It should be understood that the method 200 may also include additional blocks not shown and / or may omit the blocks shown, and the order of the steps in the method 200 is only illustrative. The order of the steps in the method 200 may vary depending on the actual application, and the scope of the present disclosure is not limited in this respect. In some embodiments, the edge device 120 may be used to implement the method 200 .

[0091] At block 202, production-related disturbance events are obtained from the production system. For example, dynamic and uncertain disturbance events often occur during the production process, such as changes in production demand, machine failures, variations in processing time, changes in changeover time, and material shortages. These different disturbance events can have varying degrees of impact on the production process. For example, a failure of equipment on the critical path has a significant impact on the production process, while the cancellation of a small amount of demand has a relatively small impact on the production process.

[0092] At block 204, predicted production data is generated based on the real-time production data of the production system. In some embodiments, the real-time production data may be actual output data recorded during the production process, while the predicted production data may be production output data predicted for a future period based on the current scheduling plan and current production status. In some embodiments, the predicted production data may be generated using a digital twin simulation model, where the digital twin simulation model is used to simulate the production data of the production system. For the specific implementation of the digital twin simulation model, please refer to the description of the embodiment related to FIG4 .

[0093] In box 206, the type of disturbance event is identified based on the expected production data and the predicted production data. The expected production data is the production data of the production system in the absence of a disturbance event. In some embodiments, since the expected production data is the production data predicted in the absence of a disturbance event, the digital twin simulation model can also be used to generate the expected production data. The embodiment of the present method 200 does not impose any restrictions on the disturbance identification algorithm specifically used to identify the disturbance event. In some embodiments, the disturbance identification algorithm can use any one of other analysis algorithms including but not limited to target constraint judgment, correlation analysis, variance analysis, significance test, various neural network models, and their combinations. For the disturbance identification method 500 related to the disturbance identification algorithm used in some embodiments, reference can be made to the description of the relevant embodiment of Figure 5.

[0094] The embodiment of the present method 200 does not impose any restrictions on the types and number of disturbance events. In some embodiments, the types of disturbance events can be divided into, but not limited to, explicit disturbance events, implicit disturbance events, and irrelevant disturbance events. Among them, explicit disturbance events can represent events that have a significant impact on the production system, such as a failure of equipment on the critical path, etc., and explicit disturbance events require immediate response. Implicit disturbance events can represent events that have little impact on the production system at present, but may accumulate into explicit disturbance events with a greater impact over time. For example, at the current moment, a small number of demand cancellations have a negligible impact on the production system, but as time goes by, the number of canceled demands gradually accumulates, which may have a significant impact on the production system. For implicit disturbance events, immediate processing is not required, but attention should be paid and countermeasures should be prepared in advance to avoid serious impacts on future production as soon as possible. Irrelevant disturbance events can be events with very little impact, such as a failure of equipment not involved in production in the current workshop, which has basically no impact on the output of the current production system. For irrelevant disturbance events, no additional response measures may be taken.

[0095] The embodiment of the implementation method 200 can automatically identify the type of disturbance events related to production, thereby facilitating the rapid and automatic generation of optimized scheduling plans, thereby improving production efficiency and utilization of production resources.

[0096] FIG3 shows a schematic diagram of the architecture of a production system 300 according to an embodiment of the present disclosure. The production system 300 may include an analysis and decision module 310, an optimization module 320, a production monitoring module 330, and production personnel 340. In some embodiments, the analysis and decision module 310 may be implemented on the edge device 120, the optimization module 320 may be implemented on the cloud server 110, and the production monitoring module 330 may be implemented in the workshop 130. It should be understood that the architecture of the production system 300 shown in FIG3 is merely schematic. Depending on actual application conditions, the architecture of the production system 300 in FIG3 may have other different forms, and the production system 300 may also include more or fewer one or more functional modules and / or units for production. These modules and / or units may be partially or fully implemented as hardware modules, software modules, firmware modules, or any combination thereof, and the embodiments of the present disclosure are not limited thereto.

[0097] As shown in FIG3 , the analysis and decision module 310 may further include an event identification module 312 (which may be implemented as the aforementioned event identification module 124 ), a digital twin simulation model 316 (which may be implemented as the aforementioned digital twin simulation model 122 ), and a rescheduling decision module 314 (which may be implemented as the aforementioned rescheduling decision module 126 ). The optimization module 320 may further include a data collection module 322 and a rescheduling optimization module 324 (which may be implemented as the aforementioned rescheduling optimization module 112 ). The production monitoring module 330 may further include a production data acquisition module 332 , a production execution module 334 , and a scheduling update module 336 .

[0098] In some embodiments, production system 300 may include production personnel 340, who can monitor and correct the behavior of production system 300, thereby improving production efficiency. Production personnel 340 may include operators 342, dispatchers 344, and planners 346. Operator 342 may be responsible for monitoring and controlling production monitoring module 330, such as interfacing with the execution of production lines in the workshop. Dispatcher 344 may be responsible for adjusting scheduling parameters, such as adjusting parameters related to production scheduling. Based on information fed back by event recognition module 312 and their own experience, dispatcher 344 may adjust scheduling parameters related to the production line. Planner 346 may be responsible for developing scheduling strategies, such as modifying production targets. In some embodiments, changes to production parameters by dispatcher 344 and / or planner 346 may be sent to data collection module 322, which then sends the integrated instructions and / or data to rescheduling optimization module 324.

[0099] The event identification module 312 can be used to receive real-time production data from the production data acquisition module 332. The digital twin simulation model 316 can obtain the real-time production data and the current scheduling plan from the event identification module 312. The digital twin simulation model 316 can also be used to simulate and predict the production system's predicted production data based on the real-time production data. The digital twin simulation model 316 can also generate expected production data corresponding to the absence of a disturbance event based on the current scheduling plan. For more information on the implementation mechanism of the digital twin simulation model 316, please refer to the embodiment described in Figure 4. When a disturbance event is detected, the digital twin simulation model 316 can return predicted production data and expected production data to the event identification module 312. Based on the predicted production data and expected production data, the event identification module 312 can identify the type of disturbance event, for example, classifying it as an explicit disturbance event, an implicit disturbance event, an irrelevant disturbance event, etc. For the disturbance identification method 500 used by the event identification module 316 in some embodiments, please refer to the description of the relevant embodiment in Figure 5. In some embodiments, the event recognition module 312 may send real-time recognition results to the dispatcher 344 as decision support information to facilitate the dispatcher 344 in making adjustments to the dispatch parameters.

[0100] The event identification module 312 can also respond according to the type of disturbance event and determine whether to send a request to the optimization module 320 to optimize the current scheduling plan or issue a reminder related to the production system. In some embodiments, since the impact of explicit disturbance events is more serious than that of implicit disturbance events, the reminder level of explicit disturbance events is higher than that of implicit disturbance events. For example, if a first-level reminder is set for an explicit disturbance event, a reminder can be issued immediately through a buzzer, and if a second-level reminder is set for an implicit disturbance event, a reminder can be sent by sending an event log, which may not be immediately noticed by the production staff. In some embodiments, if it is determined that the type of disturbance event is an explicit disturbance event, a first request for optimizing the current scheduling plan can be sent to the optimization module 320. If it is determined that the type of disturbance event is an implicit disturbance event, a second request for optimizing the current scheduling plan can be sent to the optimization module 320. In some embodiments, since the impact of explicit disturbance events is more serious than that of implicit disturbance events and requires an immediate response, the first request is prioritized relative to the second request, that is, the rescheduling plan of the explicit disturbance event will be optimized in priority relative to the implicit disturbance event.

[0101] The data collection module 322 can be used to receive a request from the event identification module 312 to optimize the current scheduling plan. The data collection module 322 can also be used to receive changes to production parameters from the dispatcher 344 and / or planner 346. The data collection module 322 can integrate the various instructions and / or data received, such as optimization requests for the current scheduling plan, scheduling parameters in the current scheduling plan, manually adjusted scheduling parameters, etc., and then send them to the rescheduling optimization module 324. The rescheduling optimization module 324 can be used to generate an optimized scheduling plan using optimization algorithms and simulation services, and then send the optimized scheduling plan to the rescheduling decision module 314. In some embodiments, the rescheduling optimization module 324 can be deployed on a cloud server, which can utilize the more powerful computing resources and storage resources of the cloud server compared to the local end to provide computing support for the rescheduling optimization of the dynamic process. The embodiments of the present disclosure do not impose any restrictions on the optimization algorithms and simulation services used by the rescheduling optimization module 324 to generate the optimized scheduling plan.

[0102] The rescheduling decision module 314 is used to determine the scheduling scheme adopted by the production system 300. In some embodiments, the rescheduling decision module 314 can be implemented by a dispatcher. The optimized scheduling scheme received by the rescheduling decision module 314 can be a scheduling scheme manually adjusted by the production personnel 340, or a scheduling scheme automatically generated by machine calculation, or a scheduling scheme generated by combining human experience with automatic machine calculation. The embodiments of the present disclosure are not limited to this. In some embodiments, the rescheduling decision module 314 can receive the optimized scheduling scheme from the rescheduling optimization module 324, wherein the rescheduling decision module 314 is deployed locally in the production system 300, and the rescheduling optimization module 324 is deployed in the cloud. In some embodiments, the deployment of the rescheduling decision module 314 on the local end can facilitate real-time and fast scheduling and protect local production privacy data.

[0103] In some embodiments, after receiving the optimized schedule, the rescheduling decision module 314 may calculate and compare a first resource consumption of the optimized schedule and a second resource consumption of the production system's current schedule, and decide to adopt the schedule with the lower resource consumption. Specifically, if the first resource consumption is less than the second resource consumption, the schedule implemented by the production system is updated to the optimized schedule; if the first resource consumption is greater than or equal to the second resource consumption, the production system's current schedule remains unchanged. In some embodiments, the original schedule and the optimized schedule may be compared by comprehensively considering both efficiency and cost factors.

[0104] After deciding to adopt the optimized scheduling plan, the rescheduling decision module 314 can send the optimized scheduling plan to the schedule update module 336 of the production monitoring module 330 to provide guidance to the operator 342 in monitoring the production status and controlling the production process during the dynamic production process. The schedule update module 336 can re-update the allocation of resources and tasks based on the optimized scheduling plan. The production execution module 334 can execute the production process associated with the optimized production parameters according to the scheduling instructions issued by the schedule update module 336. During the production process, the production data collection module 332 can continuously collect real-time production data generated by the production execution module 334 and send the real-time production data to the event recognition module 312.

[0105] The production system 300 provided in this embodiment can utilize the digital twin simulation model 316 and event identification module 312 to automatically identify the types of production-related disturbance events through quantitative analysis to assess their impact on the current and future systems, thereby reducing reliance on the experience of production personnel 340 and alleviating their workload. Furthermore, the rescheduling decision module 314 facilitates the rapid and automatic generation of optimized scheduling plans, reducing the workload of dispatchers and improving production efficiency. Furthermore, the advantages of edge analytics and cloud optimization services can be integrated to support dynamic optimization of production process control with low latency.

[0106] FIG4 shows a schematic diagram of a disturbance impact estimation process 400 using a digital twin simulation model according to an embodiment of the present disclosure. The digital twin simulation model is used to simulate and predict production data of a production system. In some embodiments, a workshop can collect production data 404 in a serial manner in real time over time 402, such as data and status of machines, materials, semi-finished products, finished products, etc., and the edge device can obtain the production data 404 through a communication connection with the workshop. As shown in FIG4 , the digital twin simulation model can be represented by a discrete simulation model. For example, a coordinate graph is generated with the horizontal axis being time 402 and the vertical axis being production data 404 to represent a set of production data 404 that changes over time 402.

[0107] Graph 410 shows a real-time production data sequence 412, which is a collection of actual output data from the current time point and before under the current scheduling scheme in the production system. When an uncertain disturbance event is detected, a digital twin simulation model can be used to determine the changing trend of the production data based on the real-time production data sequence 412 and then simulate and generate a predicted production data sequence 422, as shown in graph 420. Graph 430 shows an expected production data sequence 432, which is the ideal production data generated by the digital twin simulation model based on the current scheduling scheme in the absence of a disturbance event. When an uncertain disturbance event is detected, the disturbance impact estimation module can be called to return the predicted production data sequence 422, which is then compared with the expected production data sequence 432. Graph 440 shows a schematic diagram of combining the predicted production data sequence 422 with the expected production data sequence 432 for comparison. The comparison result between the predicted production data sequence 422 and the expected production data sequence 432 can be used in the disturbance identification method 500 to determine the type of disturbance event.

[0108] FIG5 shows a flow chart of a disturbance identification method 500 according to some embodiments of the present disclosure. According to some embodiments of the present disclosure, the disturbance identification method 500 may be executed by the rescheduling decision module 314 of the production system 300, or by the rescheduling decision module 126 of the edge device 120 deployed locally in the production system.

[0109] In some examples of method 500, based on the degree of impact of uncertain events on the production system, the types of disturbance events can be classified into, but not limited to, explicit disturbance events, implicit disturbance events, and irrelevant disturbance events. Explicit disturbance events can represent events that have a significant impact on the production system, such as equipment failure on the critical path, a large shortage of raw materials, a significant change in demand, etc. These situations will definitely violate operational objectives, such as failure to deliver on time or failure to meet production targets. Explicit disturbance events require immediate response. Implicit disturbance events can represent events that have little impact on the production system at the moment, but may accumulate into explicit disturbance events with a significant impact over time. For example, a small increase or decrease in demand at the current moment may have a negligible impact on the production system, but over time, the accumulated changes in demand may result in a large deviation, which may have a significant impact on the production system. Implicit disturbance events may not require immediate processing, but attention should be paid and countermeasures should be prepared in advance to avoid serious impacts on future production. Irrelevant disturbance events can be events with very small impacts, such as the failure of equipment not involved in production in the current workshop, or the shortage of raw materials not involved in production. These have little impact on the output of the current production system. Irrelevant disturbance events can be ignored and no additional response measures may be taken temporarily.

[0110] At block 510 , expected production data and predicted production data are obtained. In some embodiments, when a disturbance event is detected, a digital twin simulation model can be used to obtain the expected production data and predicted production data based on real-time production data and the current scheduling plan. For a detailed description, please refer to the description of the embodiment related to FIG. 4 .

[0111] At block 511, a deviation between the expected production data and the predicted production data from a first moment to a second moment is determined based on the expected production data and the predicted production data. In some embodiments, the deviation between the expected production data and the predicted production data from the current moment to the predicted moment can be calculated by invoking a loss function.

[0112] At block 512, a determination is made as to whether the deviation between the expected production data and the predicted production data is greater than the target constraint value. If so, the process proceeds to block 502; if not, the process proceeds to block 520. At block 502, a determination is made as to whether the disturbance event is an explicit disturbance event. In some embodiments, a deviation between the expected production data and the predicted production data greater than the target constraint value indicates a violation of an operational objective, such as failure to meet delivery deadlines or production targets. Disturbance events that violate operational objectives are automatically marked as explicit disturbance events. The embodiments of the present disclosure impose no restrictions on target constraint conditions or target constraint values.

[0113] At block 520, a correlation coefficient is determined between the expected production data and the predicted production data. In some embodiments, after determining that the deviation between the expected production data and the predicted production data is less than or equal to the target constraint value, a correlation analysis is performed on the expected production data and the predicted production data. Correlation analysis can be used to determine whether the trends between the expected production data and the predicted production data are consistent. Correlation can be determined using the correlation coefficient. Generally speaking, a positive correlation coefficient indicates a positive correlation, while a negative correlation coefficient indicates a negative correlation. A correlation coefficient closer to 1 indicates a higher degree of correlation, while a correlation coefficient closer to 0 indicates a lower degree of correlation.

[0114] At block 521, a determination is made as to whether the correlation coefficient between the expected production data and the predicted production data is greater than a predetermined threshold. If not, the process proceeds to block 504; if so, the process proceeds to block 530. At block 504, the disturbance event is determined to be a latent disturbance event. In some embodiments, a predetermined threshold can be used to determine the strength of the correlation. If the correlation coefficient is less than or equal to the predetermined threshold, it indicates that the correlation between the expected production data and the predicted production data is weak, indicating a significant deviation between the expected production data and the predicted production data, indicating an abnormal trend caused by the disturbance event. Therefore, the disturbance event is determined to be a latent disturbance event.

[0115] At block 530, a variance analysis is performed on the expected production data and the predicted production data. In some embodiments, if the correlation coefficient between the expected production data and the predicted production data is greater than a predetermined threshold, it indicates that the correlation between the expected production data and the predicted production data is strong, indicating that the expected production data and the predicted production data have the same trend. A variance analysis is then performed on the expected production data and the predicted production data to further identify the type of disturbance event by filtering and eliminating the impact of random fluctuations.

[0116] In box 531, determine whether the result of the variance analysis meets the predetermined conditions. If yes, continue to box 504, if not, continue to box 506. In box 504, determine that the type of disturbance event is a hidden disturbance event. In box 506, determine that the type of disturbance event is an irrelevant disturbance event. The embodiments of the present disclosure do not impose any restrictions on the predetermined conditions. For example, in some embodiments, if the significance P value obtained by the variance analysis is less than or equal to a certain threshold, such as 0.05, it means that the difference is significant. If the difference is significant, it means that the fluctuation is likely to be caused by the disturbance event, and the disturbance event is determined to be a hidden disturbance event; if the significance P value is greater than a certain threshold, such as 0.05, it means that the difference is not significant. If the difference is not significant, it means that the fluctuation is likely to be caused by the systematic error, and the disturbance event is determined to be an irrelevant disturbance event.

[0117] In some embodiments, an immediate response is required for an explicit disturbance event, and the response may include issuing a reminder related to the production system and / or sending a request to optimize the current scheduling plan. In some embodiments, a reminder is issued immediately for an explicit disturbance event, and a reminder is not issued for an implicit disturbance event. In other embodiments, reminders are issued for both explicit and implicit disturbance events. Since explicit disturbance events have a more serious impact than implicit disturbance events, the reminder level of explicit disturbance events is higher than that of implicit disturbance events. For example, if a first-level reminder is set for an explicit disturbance event, a reminder can be issued immediately through a buzzer. If a second-level reminder is set for an implicit disturbance event, a reminder can be issued by sending an event log, which may not be immediately noticed by the production staff.

[0118] In some embodiments, if the disturbance event is determined to be an explicit disturbance event, a first request for optimizing the current scheduling solution may be sent to the cloud server. If the disturbance event is determined to be an implicit disturbance event, a second request for optimizing the current scheduling solution may be sent to the cloud server. In some embodiments, because explicit disturbance events have a more serious impact than implicit disturbance events and require an immediate response, the first request is prioritized over the second request, i.e., the rescheduling solution for explicit disturbance events is prioritized over that for implicit disturbance events.

[0119] Implementing method 500 can automatically identify the type of disturbance event related to production, thereby facilitating the rapid and automatic generation of optimized scheduling plans, improving production efficiency, and conserving production resources. It will be appreciated that method 500 is merely an example embodiment, and the embodiments of the present disclosure do not impose any restrictions on the classification and number of types of disturbance events. Furthermore, in other embodiments, other methods, including but not limited to calculating loss functions, correlation analysis, variance analysis, and combinations thereof, may also be employed to identify the type of disturbance event, and the embodiments of the present disclosure are not limited in this respect.

[0120] 6 shows a flowchart of a scheduling optimization decision method 600 provided according to some embodiments of the present disclosure. According to some embodiments of the present disclosure, the scheduling optimization decision method 600 may be executed by the rescheduling decision module 314 of the production system 300, or by the rescheduling decision module 126 of the edge device 120 deployed locally in the production system.

[0121] In box 610, an optimized scheduling solution is received. In conjunction with the embodiment shown in Figure 3, the optimized scheduling solution can be received from the rescheduling optimization module 324 through the rescheduling decision module 314. In some embodiments, the rescheduling decision module 314 is deployed locally in the production system 300, and the rescheduling optimization module 324 is deployed on a cloud server. In some embodiments, the received optimized scheduling solution can be a scheduling solution manually adjusted by production personnel, or a scheduling solution automatically generated by machine calculation, or a scheduling solution generated by combining human experience with automatic machine calculation. The embodiments of the present disclosure are not limited to this. After receiving the optimized scheduling solution, continue to box 612.

[0122] At block 612, a first resource consumption for adopting the optimized scheduling solution and a second resource consumption for maintaining the current scheduling solution for the production system are determined. In some embodiments, the original scheduling solution and the optimized scheduling solution may be compared by comprehensively considering multiple factors such as benefits and costs. The embodiments of the present disclosure do not limit the comparison parameters or comparison method used to determine the scheduling solution.

[0123] In box 614, compare whether the first resource consumption is less than the second resource consumption. If yes, proceed to box 616, if not, proceed to box 618. In box 616, update the scheduling scheme implemented by the production system to an optimized scheduling scheme. In box 618, keep the current scheduling scheme of the production system unchanged. That is, if the first resource consumption is less than the second resource consumption, update the scheduling scheme implemented by the production system to an optimized scheduling scheme, and if the first resource consumption is greater than or equal to the second resource consumption, keep the current scheduling scheme of the production system unchanged. After updating the scheduling scheme implemented by the production system to an optimized scheduling scheme, the allocation of resources and tasks can be re-updated according to the optimized scheduling scheme, and then the workshop can execute the production process related to the optimized production parameters according to the updated scheduling instructions. Implementing the scheduling optimization decision method 600 helps to quickly and automatically generate optimized scheduling schemes, reduce the workload of dispatchers, improve production efficiency, and save production resources.

[0124] Embodiments of the present disclosure also provide a device for identifying events, comprising an event acquisition module, a production prediction module, and an event identification module. The event acquisition module is configured to acquire production-related disturbance events from a production system. The production prediction module is configured to generate predicted production data based on the production system's real-time production data. The event identification module is configured to identify the type of disturbance event based on expected production data and predicted production data, where the expected production data is the production data of the production system in the absence of a disturbance event.

[0125] Additionally, the production forecasting module can be configured to generate predicted production data using a digital twin simulation model, where the digital twin simulation model is used to simulate production data from the production system. In some embodiments, when a disturbance event is detected, the digital twin simulation model can be used to obtain expected and predicted production data based on real-time production data and the current scheduling plan. For a detailed description, please refer to the description of the embodiment related to FIG4 .

[0126] The event identification module may also be configured to determine the deviation between the expected production data and the predicted production data from the first moment to the second moment based on the expected production data and the predicted production data; and if the deviation is greater than the target constraint value, determine the type of the disturbance event to be an explicit disturbance event. The event identification module may also be configured to determine the correlation coefficient between the expected production data and the predicted production data if the deviation is less than or equal to the target constraint value; and if the correlation coefficient is less than or equal to a predetermined threshold, determine the type of the disturbance event to be an implicit disturbance event. The event identification module may also be configured to perform a variance analysis on the expected production data and the predicted production data if the correlation coefficient is greater than a predetermined threshold; if the result of the variance analysis meets a predetermined condition, determine the type of the disturbance event to be an implicit disturbance event; and if the result of the variance analysis does not meet the predetermined condition, determine the type of the disturbance event to be an irrelevant disturbance event.

[0127] The event identification module may also be configured to, if the disturbance event is an explicit disturbance event, send a first request to the rescheduling optimization module to optimize the current scheduling solution. Furthermore, if the disturbance event is an implicit disturbance event, the event identification module may be further configured to, if the disturbance event is an implicit disturbance event, send a second request to the rescheduling optimization module to optimize the current scheduling solution. In some embodiments, the first request is prioritized over the second request.

[0128] In addition, the device may also include a reminder module configured to issue a reminder related to the production system if the disturbance event is of the type of an explicit disturbance event or a covert disturbance event, wherein the reminder level of an explicit disturbance event is higher than the reminder level of a covert disturbance event. In some embodiments, because the impact of an explicit disturbance event is more serious than that of a covert disturbance event, the reminder level of an explicit disturbance event is higher than that of a covert disturbance event. For example, if a level 1 reminder is set for an explicit disturbance event, a reminder may be immediately issued via a buzzer, while if a level 2 reminder is set for a covert disturbance event, a reminder may be issued by sending an event log, which may not be immediately noticed by production personnel.

[0129] In addition, the device may further include a rescheduling decision module configured to receive an optimized scheduling scheme from the rescheduling optimization module. The rescheduling decision module may also be configured to determine a first resource consumption for adopting the optimized scheduling scheme and a second resource consumption for maintaining the current scheduling scheme of the production system. The rescheduling decision module may also be configured to compare the first resource consumption with the second resource consumption. If the first resource consumption is less than the second resource consumption, the rescheduling decision module may also be configured to update the scheduling scheme implemented by the production system to the optimized scheduling scheme. If the first resource consumption is greater than or equal to the second resource consumption, the rescheduling decision module may also be configured to maintain the current scheduling scheme of the production system unchanged.

[0130] The implementation of the above-mentioned device can automatically identify the type of disturbance events related to production, thereby facilitating the rapid and automatic generation of optimized scheduling plans, improving production efficiency, and saving production resources.

[0131] It is understood that the device may include more or fewer modules and / or units, and these modules and / or units may be partially or completely implemented as hardware modules, software modules, firmware modules, or any combination thereof, and the embodiments of the present disclosure are not limited thereto. More specific implementations of the functions included in the above-mentioned modules or other modules can be understood in conjunction with the description of the relevant embodiments of Figures 1 to 6 of the present disclosure.

[0132] FIG7 shows a schematic block diagram of an example device 700 that can be used to implement an embodiment of the present disclosure. The device 700 can be used to implement the method 200 described in FIG2 and / or the method 500 described in FIG5 and / or the method 600 described in FIG6. The device 700 can also be implemented as an edge device 120. For example, the local device and / or cloud server described above can be implemented by one or more components in the example device 700. As shown in FIG7, the device 700 includes a processor, such as a central processing unit (CPU) 701, which can perform various appropriate actions and processes based on computer program instructions stored in a read-only memory (ROM) 702 or loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The CPU 701, ROM 702, and RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0133] Various components in device 700 are connected to I / O interface 705, including an input unit 706, such as a keyboard, mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, optical disk, etc.; and a communication unit 709, such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0134] The processing unit 701 performs the various methods and processes described above, such as method 200 and / or method 500 and / or method 600. For example, in some embodiments, method 200 and / or method 500 and / or method 600 can be implemented as a computer software program or computer program product, which is tangibly contained in a computer-readable medium, such as a non-transient computer-readable medium (e.g., storage unit 708). In some embodiments, part or all of the computer program can be loaded and / or installed on the device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by CPU 701, one or more steps in the method or process described above can be performed. Alternatively, in other embodiments, CPU 701 can be configured to perform the method or process of an embodiment of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0135] It should be understood by those skilled in the art that the various steps of the method of the present disclosure described above can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Alternatively, they can be implemented using program codes executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present disclosure is not limited to any specific combination of hardware and software. For example, certain embodiments of the present disclosure also include various program modules and / or integrated circuit modules for executing one or more steps of method 200 and / or one or more other steps described in other embodiments of the present disclosure. These program modules can be included or embodied in a device, such as the device 700 in Figure 7.

[0136] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0137] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, storage media, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0138] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable information presentation device, thereby producing a machine such that when these instructions are executed by the processing unit of the computer or other programmable information presentation device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable information presentation device, and / or other device to operate in a specific manner, such that the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0139] Computer-readable program instructions can be loaded onto a computer, other programmable information presentation apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable information presentation apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable information presentation apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowcharts and / or block diagrams of the embodiments of the present disclosure.

[0140] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0141] In addition, although adopting specific order to describe each operation, this should be understood as requiring such operation to be carried out in the specific order shown or in sequential order, or requiring that all illustrated operations should be carried out to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although comprising some specific implementation details in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation also can be implemented in a plurality of implementations individually or in the mode of any suitable subcombination.

[0142] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method (200) for identifying an event, comprising: Acquire (202) a disturbance event related to production from the production system; generating (204) predicted production data based on the real-time production data of the production system; as well as Based on expected production data and the predicted production data, a type of the disturbance event is identified (206), wherein the expected production data is production data of the production system in the absence of a disturbance event.

2. The method (200) of claim 1, wherein generating (204) the forecast production data comprises: The predicted production data is generated by a digital twin simulation model (316), wherein the digital twin simulation model (316) is used to simulate production data of the production system.

3. The method (200) of claim 1, wherein identifying (206) the type of the disturbance event comprises: Based on the expected production data and the predicted production data, determining (511) a deviation between the expected production data and the predicted production data from a first moment to a second moment; as well as If the deviation is greater than the target constraint value, it is determined (502) that the type of the disturbance event is a dominant disturbance event.

4. The method (200) of claim 3, wherein identifying (206) the type of the disturbance event further comprises: If the deviation is less than or equal to the target constraint value, determining (520) a correlation coefficient between the expected production data and the predicted production data; as well as If the correlation coefficient is less than or equal to a predetermined threshold, it is determined (504) that the type of the disturbance event is a hidden disturbance event.

5. The method (200) of claim 4, wherein identifying (206) the type of the disturbance event further comprises: If the correlation coefficient is greater than the predetermined threshold, performing (530) variance analysis on the expected production data and the predicted production data; If the result of the variance analysis satisfies a predetermined condition, determining (504) that the type of the disturbance event is the implicit disturbance event; as well as If the result of the variance analysis does not satisfy the predetermined condition, it is determined (506) that the type of the disturbance event is an irrelevant disturbance event.

6. The method (200) of claim 5, further comprising: If the type of the disturbance event is the explicit disturbance event or the implicit disturbance event, a reminder related to the production system is issued, wherein the reminder level of the explicit disturbance event is higher than the reminder level of the implicit disturbance event.

7. The method (200) of claim 5, further comprising: If the type of the disturbance event is the explicit disturbance event, sending a first request for optimizing the current scheduling solution to a rescheduling optimization module (324); as well as If the type of the disturbance event is the implicit disturbance event, a second request for optimizing the current scheduling solution is sent to the rescheduling optimization module (324).

8. The method (200) of claim 7, wherein the first request is prioritized over the second request.

9. The method (200) of claim 7, further comprising: An optimized scheduling solution is received (610) from the rescheduling optimization module (324) via the rescheduling decision module (314).

10. The method (200) of claim 8, wherein the rescheduling decision module (314) is deployed locally in the production system, and the rescheduling optimization module (324) is deployed in the cloud.

11. The method (200) of claim 9, further comprising: determining (612) a first resource consumption for adopting the optimized scheduling solution and a second resource consumption for maintaining the current scheduling solution for the production system; comparing (614) the first resource consumption with the second resource consumption; as well as If the first resource consumption is less than the second resource consumption, the scheduling plan implemented by the production system is updated (616) to the optimized scheduling plan.

12. The method (200) of claim 11, further comprising: If the first resource consumption is greater than or equal to the second resource consumption, the current scheduling plan of the production system is maintained (618) unchanged.

13. An apparatus for identifying an event, comprising: An event acquisition module is configured to acquire disturbance events related to production from a production system; a production forecasting module configured to generate forecasted production data based on the real-time production data of the production system; as well as The event identification module is configured to identify the type of the disturbance event based on expected production data and the predicted production data, wherein the expected production data is production data of the production system in the absence of a disturbance event.

14. An electronic device (700), comprising: one or more processors (701); as well as A memory (703) is configured to store computer-executable instructions, wherein the computer-executable instructions, when executed by the one or more processors (701), enable the electronic device (700) to implement the method according to any one of claims 1 to 12.

15. A computer-readable storage medium (703) storing computer-executable instructions, wherein the computer-executable instructions, when executed by a processor (701), implement the method according to any one of claims 1 to 12.

16. A computer program product comprising computer executable instructions which, when executed by a processor (701), implement the method according to any one of claims 1 to 12.

Images