A method for adaptive changeover reconfiguration of production collaboration in a digital twin workshop

Abstract

This invention proposes a method for adaptive production reconfiguration in a digital twin workshop, belonging to the field of digital twin production technology. The method includes: Step 1: Constructing a multi-level subject monitor, including a node layer, community layer, sub-layer, and network layer, to monitor and predict the production collaboration process in the digital twin workshop; Step 2: Utilizing the multi-level subject monitors to comprehensively monitor the production process; Step 3: Combining the multi-level subject monitors with an online detector for multi-source interference to conduct production fluctuation analysis; Step 4: Constructing a joint production reconfiguration decision-maker, which includes community layer and network layer decision-makers, to complete production configuration and task allocation. This method effectively improves workshop production collaboration efficiency and adaptive production reconfiguration capabilities, adapting to complex and ever-changing industrial production environments, and has significant practical and promotional value.

Description

Technical Field

[0001] This invention belongs to the field of digital twin production technology, and relates to a method for adaptive production restructuring in digital twin workshop production collaboration. Background Technology

[0002] Traditional workshop production management models are struggling to cope with increasingly complex production environments. Traditional assembly line workshops typically employ fixed workstation layouts and standardized production processes. Upgraded workshops, structured as cells, flexibly adjust equipment layouts and production processes based on the diversity and dynamism of production tasks. Traditional workshop production management methods rely heavily on manual experience, single data sources, and static models, making it difficult to achieve real-time perception, fluctuation detection, and dynamic optimization of the production process. Especially when faced with multi-dimensional disturbances such as equipment failures, material shortages, and human operational errors, traditional methods often fail to respond and adjust quickly, leading to low production efficiency, resource waste, and decreased product quality. Summary of the Invention

[0003] The technical problem this invention aims to solve is to overcome the shortcomings of existing production changeover and reconfiguration technologies in digital twin workshop production collaboration, and to propose an adaptive production changeover and reconfiguration method for digital twin workshop production collaboration. This method aims to create a digital twin model that effectively describes and correlates the models, data, states, and behaviors of the constituent elements such as equipment, workstations, work sections, and production lines in the digital twin workshop production system. Through multi-level monitoring of the production process, real-time analysis of multi-source interference, and intelligent decision-making for production reconfiguration, it provides a basis for rapid production changeover, efficient collaboration, optimization analysis, and accurate decision-making in the subsequent production system and its operation process. This, in turn, helps improve the flexibility and adaptability of digital twin workshop production collaboration, as well as its operational efficiency and control capabilities during production changeover and reconfiguration.

[0004] This invention proposes a digital twin workshop production collaboration and adaptive changeover reconfiguration method. Through independent yet collaborative monitors, detectors, and decision-makers, it constructs a highly efficient system for real-time monitoring, fluctuation detection, and dynamic changeover reconfiguration. This method can integrate multi-dimensional status data such as equipment parameters, material inventory, and personnel operations in real time to build a dynamic production process model, achieving full lifecycle management of the production process. By analyzing the sources of production fluctuations under multi-source interference, it identifies potential risks and provides real-time feedback. Simultaneously, through a joint decision-maker, it optimizes production configuration and task allocation, ensuring maximum resource utilization while balancing production efficiency, cost control, and product quality. This method effectively improves workshop production collaboration efficiency and adaptive changeover capabilities, providing an intelligent solution for complex and ever-changing industrial production environments, and has significant practical and promotional value.

[0005] The present invention solves its technical problem by adopting the following technical solution: a method for adaptive production changeover and reconfiguration in a digital twin workshop, comprising the following steps:

[0006] Step 1: Construct a multi-level main monitoring system, including node layer, community layer, sub-layer, and network layer, to achieve monitoring and prediction of the production collaboration process in the digital twin workshop;

[0007] Step 2: Utilize multi-level main monitoring devices to comprehensively monitor the production process;

[0008] Step 3: Combine multi-level main monitoring devices and use online detectors for multi-source interference to conduct production fluctuation analysis;

[0009] Step 4: Construct a joint decision-maker for production reconfiguration. The joint decision-maker for production reconfiguration includes a community layer decision-maker and a network layer decision-maker to complete production configuration and task allocation.

[0010] The advantages of this invention compared to the prior art are:

[0011] (1) This invention proposes a multi-level subject monitoring method for digital twin workshops, which can effectively describe the demand allocation, OEE and maximum completion time of "equipment-workstation-section-production line" in the workshop from the perspective of production collaboration. This is conducive to the digital twin virtual workshop reflecting the production status of the physical workshop more realistically and comprehensively, improving the monitoring effect of the physical workshop, thereby effectively improving the production efficiency of the digital twin workshop and optimizing the allocation of production resources.

[0012] (2) The present invention proposes a production collaboration adaptive reconfiguration method that effectively considers the production status of workshop equipment. When the workshop faces emergencies such as equipment failures or order changes, this method can respond quickly based on the real-time feedback of equipment status from multi-level main monitoring devices. For example, once a failure of a key piece of equipment is detected, the system immediately assesses the role and scope of impact of the equipment in the entire production process, re-plans the affected production tasks, and rationally allocates them to other alternative equipment or workstations to minimize the delay of the failure on the overall production schedule. At the same time, regarding the issue of order changes, by analyzing the priority of raw material demand in different sections and workstations, key production links are prioritized to maintain production continuity. Attached Figure Description

[0013] Figure 1 This is a structural diagram of the workshop production environment;

[0014] Figure 2 This is a structural diagram of a multi-level main monitoring device;

[0015] Figure 3 A flowchart for dynamic optimization of the production process. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other. To achieve the above objectives, this invention adopts the following technical solution.

[0017] like Figure 1 As shown, this invention provides a method for adaptive production changeover and reconfiguration in a digital twin workshop, the specific implementation of which is as follows:

[0018] Step 1: Construction of a multi-level subject monitor, such as... Figure 2 As shown, the specific implementation method is as follows:

[0019] The digital twin workshop is decomposed and a hierarchical architecture of equipment, workstations, work sections, and production lines is constructed. The digital twin workshop covers the four-layer structure of equipment, workstations, work sections, and production lines of the physical workshop, which respectively correspond to the node layer, community layer, sub-layer, and network layer of the monitor.

[0020] a) Construct a node layer based on devices. Specifically, based on the digital twin method, construct geometric, physical, behavioral, and rule models of the devices, and propose solutions for the node layer devices, i.e., nodes. The set of monitored variables:

[0021] ,

[0022] in, Representing the equipment The proceeding Actual production capacity, actual production volume, rated production capacity, rated production volume, expected production capacity, and expected production volume during functional operation. It represents time; and proposes a method for predicting equipment production status based on maximum makespan and overall equipment effectiveness (OEE) to achieve node-level monitoring of production demand and actual production load;

[0023] When the actual production output of the equipment meets the expected production output, the equipment stops working. Maximum completion time is ,Right now ,in, Indicates the functions required for the current task. and Representing the equipment The actual production volume and the expected production volume.

[0024] Based on the equipment's maximum completion time and overall utilization efficiency, the overall utilization efficiency of the equipment is typically... The equipment production status prediction method considers the maximum completion time of equipment based on the overall equipment efficiency (OEE). The specific method for predicting equipment production status includes availability. performance factors quality factor ,but:

[0025] ,

[0026] in, This is the maximum completion time for the equipment. For the equipment Rated production capacity of the function This refers to the equipment production cycle.

[0027] b) Construct a community layer based on workstations. Specifically, this involves proposing methods for predicting the community's average OEE, OEE balance, and maximum completion time, enabling community-level monitoring of production demand and actual production load for each community within a workstation. Workstations consist of entities with the same functionalities. nodes The community is composed of its related relationships. , Let be the index number of the community, where For communities The set of nodes in For communities Number of nodes.

[0028] Methods for calculating community-average OEE: ;

[0029] OEE balance calculation method: ;

[0030] Method for calculating the maximum completion time of a community: ;

[0031] Method for calculating the maximum completion time equilibrium of a community: ;

[0032] c) Construct sub-layers based on work sections. Specifically, this involves proposing a method for predicting the maximum completion time of each work section, enabling sub-layer-level monitoring of production demand and actual load within each work section sub-layer; sub-layers are composed of workstation clusters with different functions. ,in Indicates the different functions of a community. The community number represents the number of the community, where the former... For the section index number, the latter Number the communities within the work section.

[0033] Method for calculating the maximum completion time of a work section:

[0034] ;

[0035] in, For subgraph The last group to complete its production task.

[0036] d) Network layer construction, based on the production line, specifically: proposing methods for predicting the overall OEE of the network and the maximum completion time of the production line, achieving network-level prediction of the overall production demand and actual load of the production line. The network consists of subgraphs of all work segments within the workshop production line. .

[0037] Methods for calculating the overall OEE of a network:

[0038] ;

[0039] in, It is the set of all subgraphs of the work segments in the network layer. This is a collection of all work section clusters in the sublayer. Represents a community Average OEE.

[0040] Methods for predicting the maximum completion time of a production line:

[0041] ;

[0042] in, This is the set of all subgraphs in the network layer. Representation of work section sub-diagram The maximum completion time.

[0043] Step 2: Figure 1 Production process monitoring, specific implementation methods are as follows: Figure 3 As shown, the details are as follows:

[0044] The production process is monitored using the multi-level subject monitor constructed in step 1: The workshop produces according to the production plan and determines whether the task sequence is 0. If it is 0, production ends; if it is not 0, it checks whether the task can be completed on time. If it can, it continues to monitor using the multi-level subject monitor; if it cannot, it uses an online detector to detect various events in the workshop online.

[0045] After obtaining the aggregated supply and demand relationship through the online detector, check whether the current production line can meet the demand. If so, use the community layer decision-maker to configure production and allocate tasks. The community layer decision-maker mainly redistributes the task load within a single production community within the community layer.

[0046] If not, the network layer decision-maker is used for production configuration and task allocation. Then, it is checked whether the adaptive reconfiguration scheme meets the adaptive reconfiguration requirements, that is, whether it minimizes the network OEE balance. If not, the network layer decision-maker is used again for production configuration and task allocation. If yes, production continues according to the new production plan. The network layer decision-maker mainly performs adaptive production reconfiguration between multiple clusters of production lines in the network layer.

[0047] Step 3: For online detectors for multi-source interference, the specific implementation method is as follows: For production fluctuations in the production process, online detection of the following three types of events is achieved.

[0048] Event 1: Equipment performance degradation or malfunction: Detect whether the equipment is faulty or aging. If the equipment is normal, summarize and analyze the supply and demand relationship at this time. If there is a problem, Event 1 is detected. It is necessary to identify the faulty equipment and check whether the faulty equipment can be restored immediately. If it can be restored, restore the faulty equipment. If it cannot be restored, delete the faulty equipment.

[0049] Event 2: Defective Product Rework: Check if there are any defective products that need to be reworked. If there are no defective products, summarize and analyze the supply and demand relationship at this time. If there is a problem, Event 2 is detected. It is necessary to identify the cluster that caused the product defect, then update the corresponding workshop task sequence, and summarize and analyze the supply and demand relationship at this time.

[0050] Event 3: New order arrives: Check if the demand has changed. If it has not changed, summarize and analyze the supply and demand relationship at this time. If it has changed, Event 3 is detected, the corresponding workshop task sequence needs to be updated, and the supply and demand relationship at this time needs to be summarized and analyzed.

[0051] Step 4: Construct a joint decision-making engine for production reconfiguration. The specific implementation method is as follows:

[0052] The production reconfiguration joint decision-maker comprises a community-level decision-maker and a network-level decision-maker. The community-level decision-maker reallocates tasks based on the current production line's capacity to meet demand. The task reallocation process is based on the current equipment's production capacity.

[0053] ;

[0054] in, and communities any node Expected production volume and actual production capacity For communities The expected production volume.

[0055] When the current production line cannot meet the demand, the network layer decision-maker uses a reinforcement learning algorithm to reallocate limited resources of the production line. The reinforcement learning algorithm includes a state space, an action space, and feedback.

[0056] The state space contains the real-time production state. and production collaboration network topology ,Right now:

[0057] ;

[0058] in, This is a graph convolution function, which is used to implement graph convolution of the current production state and the production collaboration network topology, i.e., the state space.

[0059] The action space contains two action strategies: device function reconfiguration and device maintenance.

[0060] The steps for equipment function reconfiguration are as follows: select the cluster with the smallest average OEE, identify the node with the lowest similarity in the cluster, adjust the production function of the node, and move the cluster with the smallest average OEE to the cluster with the longest maximum completion time; equipment maintenance involves reducing the abnormal maximum completion time of the node through maintenance.

[0061] The feedback is to minimize the network OEE balance, and the formula is:

[0062] ;

[0063] in, This is the set of all subgraphs in the network layer. This is the collection of all work segment clusters in the sublayer.

[0064] In summary, this invention proposes a method for adaptive production reconfiguration in a digital twin workshop. This method includes four steps: constructing a multi-level subject monitor for the production process; using the multi-level subject monitor for production process monitoring; using online detectors for production fluctuation analysis; and using a joint decision-maker for production configuration and task allocation. On the one hand, it proposes a method for constructing a multi-level subject monitor for a digital twin workshop, which can effectively describe the production status of "equipment-workstation-section-production line" within the workshop; on the other hand, it proposes a method considering adaptive production reconfiguration, which effectively considers the workshop production status and responds rapidly based on the real-time equipment status feedback from the multi-level subject monitor.

[0065] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

[0066] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for adaptive production changeover and reconfiguration in a digital twin workshop, characterized in that: Includes the following steps: Step 1: Construct a multi-level main monitoring system, including node layer, community layer, sub-layer, and network layer, to achieve monitoring and prediction of the production collaboration process in the digital twin workshop; Step 2: Utilize multi-level main monitoring devices to comprehensively monitor the production process; Step 3: Combine multi-level main monitoring devices and use online detectors for multi-source interference to conduct production fluctuation analysis; Step 4: Construct a joint decision-maker for production reconfiguration. The joint decision-maker for production reconfiguration includes a community layer decision-maker and a network layer decision-maker to complete production configuration and task allocation. Step 1 includes: breaking down the digital twin workshop and constructing a hierarchical architecture of equipment, workstations, work sections, and production lines, which correspond to the node layer, community layer, sub-layer, and network layer, respectively. Equipment-based node layer construction: Based on the equipment comprehensive utilization efficiency (OEE) and the equipment maximum completion time, a method for predicting equipment production status is used to achieve node-level monitoring of production demand and actual production load. Community layer construction based on workstations: Based on the community average equipment comprehensive utilization efficiency (OEE), equipment comprehensive utilization efficiency OEE balance degree, and community maximum completion time prediction method, community-level monitoring of production demand and actual production load of each community in the process section is realized. Sub-layer construction based on work sections: Based on the prediction method of the maximum completion time of work sections, sub-map-level monitoring of production demand and actual production load of work section clusters is realized. Network layer construction based on production line: Based on the prediction method of overall equipment efficiency (OEE) and maximum completion time of production line, network-level prediction of overall production demand and actual production load of production line is realized. The construction of the node layer specifically involves: building the geometric, physical, behavioral, and rule models of the device, and proposing specific models for the node layer devices, i.e., nodes. The set of monitored variables: ； in, Representing the equipment The proceeding Actual production capacity, actual production volume, rated production capacity, rated production volume, expected production capacity, and expected production volume during functional operation. It represents time; and proposes a method for predicting equipment production status based on maximum completion time and overall equipment efficiency (OEE) to achieve node-level monitoring of production demand and actual production load; When the actual production output of the equipment meets the expected production output, the equipment stops working. Maximum completion time is ,Right now ,in, Indicates the functions required for the current task. and Representing the equipment The actual production volume and the expected production volume; Equipment comprehensive utilization efficiency for: ； in, The maximum completion time for the equipment. For the equipment Rated production capacity of the function For equipment production cycle, For availability, As a performance factor, For quality factor; Constructing a community layer specifically involves: workstations consisting of individuals with the same functions. nodes The community is composed of its related relationships. , Let be the index number of the community, where For communities The set of nodes in For communities Number of nodes; Methods for calculating the Overall Equipment Effectiveness (OEE) of a community: ; Method for calculating the overall equipment utilization efficiency (OEE) balance: ; Method for calculating the maximum completion time of a community: ; Method for calculating the maximum completion time equilibrium of a community: ; The sub-layer is constructed as follows: the sub-map consists of workstation clusters with different functions. ,in, Indicates the different functions of a community. , Both represent the community number, where the former... For the section index number, the latter Assign community numbers within the work section; Method for calculating the maximum completion time of a work section: ； in, For subgraph The last group to complete its production task.

2. The method for adaptive production changeover and reconfiguration in a digital twin workshop as described in claim 1, characterized in that: The network layer is constructed as follows: the network consists of all sub-graphs of the production line within the workshop. ; Methods for calculating the overall OEE of a network: ； in, It is the set of all subgraphs of the work segments in the network layer. This is a collection of all work section clusters in the sublayer. Represents a community Average OEE; Methods for predicting the maximum completion time of a production line: ； in, Representation of work section sub-diagram The maximum completion time.

3. The method for adaptive production changeover and reconfiguration in a digital twin workshop as described in claim 1, characterized in that: In step 2, the multi-level subject monitor monitors the production process as follows: the workshop produces according to the production plan and determines whether the task sequence is 0. If it is 0, production ends; if it is not 0, it checks whether the task can be completed on time. If it can, it continues to monitor using the multi-level subject monitor; if it cannot, it uses an online detector to detect various events in the workshop online. After obtaining the aggregated supply and demand relationship through the online detector, check whether the current production line can meet the demand. If so, use the community layer decision-maker to configure production and allocate tasks. The community layer decision-maker redistributes the task load within a single production community within the community layer. If not, the network layer decision-maker is used to configure production and allocate tasks. Then, it is checked whether the adaptive reconfiguration scheme meets the adaptive reconfiguration requirements, that is, whether it minimizes the overall efficiency of network devices (OEE). If not, the network layer decision-maker is used to configure production and allocate tasks. If yes, production continues according to the new production plan. The network layer decision-maker performs adaptive production reconfiguration between multiple clusters of production lines in the network layer.

4. The method for adaptive production changeover and reconfiguration in a digital twin workshop as described in claim 1, characterized in that: Step 3 includes: implementing online detection for the following three types of events in response to production fluctuations during the production process; Event 1: Equipment performance degradation or malfunction: Detect whether the equipment is faulty or aging. If the equipment is normal, summarize and analyze the supply and demand relationship at this time. If there is a problem, Event 1 is detected. It is necessary to identify the faulty equipment and check whether the faulty equipment can be restored immediately. If it can be restored, restore the faulty equipment. If it cannot be restored, delete the faulty equipment. Event 2: Defective Product Rework: Check if there are any defective products that need to be reworked. If there are no defective products, summarize and analyze the supply and demand relationship at this time. If there is a problem, Event 2 is detected. It is necessary to identify the cluster that causes the product defect, then update the corresponding workshop task sequence, and summarize and analyze the supply and demand relationship at this time. Event 3: New order arrives: Check if the demand has changed. If it has not changed, summarize and analyze the supply and demand relationship at this time. If it has changed, Event 3 is detected, the corresponding workshop task sequence needs to be updated, and the supply and demand relationship at this time needs to be summarized and analyzed.

5. The method for adaptive production changeover and reconfiguration in a digital twin workshop as described in claim 3, characterized in that: In step 4: The production reconfiguration joint decision-maker comprises a community-level decision-maker and a network-level decision-maker. The community-level decision-maker reallocates tasks based on the current production line's capacity to meet demand. The task reallocation process is based on the current equipment's production capacity. ； in, and communities any node Expected production volume and actual production capacity For communities Expected production volume; When the current production line cannot meet the demand, the network layer decision-maker uses a reinforcement learning algorithm to reallocate the limited resources of the production line; the reinforcement learning algorithm includes a state space, an action space, and feedback. The state space contains the real-time production state. and production collaboration network topology ,Right now: ； in, This is a graph convolution function, which is used to implement graph convolution of the current production state and the production collaboration network topology, i.e., the state space.

6. The method for adaptive production changeover and reconfiguration in a digital twin workshop as described in claim 5, characterized in that: The action space includes two action strategies: device function reconfiguration and device maintenance. The steps for equipment function reconfiguration are as follows: select the cluster with the lowest average equipment comprehensive utilization efficiency (OEE), identify the node with the lowest similarity in the cluster, adjust the production function of the node, and move the cluster with the lowest average equipment comprehensive utilization efficiency (OEE) to the cluster with the longest maximum completion time; equipment maintenance involves reducing the abnormal maximum completion time of the node through maintenance. The feedback is to minimize the overall efficiency of network devices (OEE) balance, and the formula is: ； in, This is the set of all subgraphs in the network layer. This is the collection of all work segment clusters in the sublayer.

Images