Manufacturing execution system parameter optimization method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a manufacturing execution system parameter optimization method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that a system parameter optimization request is received; obtaining each to-be-optimized parameter, each target index and a corresponding target index value based on the request; obtaining each current parameter value corresponding to each to-be-optimized parameter and actual production line data from the digital twin system, and performing simulation to obtain simulation result data; processing the simulation result data based on each target index value, and determining whether each to-be-optimized parameter needs to be continuously optimized or not; if so, processing simulation result data through a large model to determine a problem type; and optimizing each to-be-optimized parameter based on the problem type to obtain each current parameter value, continuing the optimization until each to-be-optimized parameter does not need to be continuously optimized, and taking the current parameter value as a target parameter value of each to-be-optimized parameter. The method can improve the performance of an actual production line.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing technology, and in particular, to a method, device, computer device, computer-readable storage medium, and computer program product for optimizing parameters of a manufacturing execution system. Background Art

[0002] As one of the most important components in semiconductor production, the automation system reduces the manual workload, reduces production pollution, significantly improves production efficiency, and promotes cost savings. For semiconductor production foundries with high production volume and large size, it is almost impossible to achieve their expected production goals without the normal operation of the automation system and its supporting equipment. Among the components supporting the automation system, there are various automation devices at the physical level, as well as various decision-making and scheduling systems at the data layer and communication layer. Among the latter, MES (Manufacturing Execution System) is the backbone of the automation system.

[0003] Currently, semiconductor foundries mainly use digital twins to monitor macroscopic indicators and schedule and control production elements, and do not attach importance to various physical properties in the production process. Therefore, production simulation based on mathematical models is sufficient to cover their needs for various types of numerical calculations and statistics.

[0004] However, the current production simulation based on mathematical models does not pay attention to various physical properties in the generation process, resulting in differences between the simulation and the actual production line in terms of fine-grained indicators, which is not conducive to improving the performance of the actual production line. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for optimizing parameters of a manufacturing execution system that can improve the performance of an actual production line.

[0006] In a first aspect, the present application provides a method for optimizing parameters of a manufacturing execution system, the method comprising:

[0007] Receiving a system parameter optimization request;

[0008] Based on the system parameter optimization request, obtaining each parameter to be optimized, each target indicator, and the target indicator value corresponding to each target indicator;

[0009] Obtaining each current parameter value corresponding to each parameter to be optimized and actual production line data from a digital twin system, and performing simulation based on each current parameter value and the actual production line data to obtain simulation result data;

[0010] Processing the simulation result data based on each target indicator value to determine whether each parameter to be optimized needs to be further optimized;

[0011] When it is necessary to continue optimizing each of the parameters to be optimized, the large model is used to process the simulation result data to determine the problem type;

[0012] Based on the problem type, each of the parameters to be optimized is optimized to obtain each current parameter value, and the step of performing simulation based on each current parameter value to obtain simulation result data is continued until, when it is determined based on the simulation result data that each of the parameters to be optimized does not need to be continued to be optimized, the current parameter value is used as the target parameter value of each of the parameters to be optimized.

[0013] In one embodiment, each of the target metrics has a priority; the method further includes: based on the simulation result data and the target metric values corresponding to each of the target metrics, determining the metrics to be optimized that do not meet the requirements;

[0014] When there are no conflicting metrics among the metrics to be optimized, the metric to be optimized with the highest priority is obtained as the current metric to be optimized;

[0015] When there are conflicting metrics among the metrics to be optimized, the first metric to be optimized with a higher priority among the conflicting metrics to be optimized is obtained, and the second metric to be optimized that does not have conflicts and the metric with the highest priority among the first metrics to be optimized are obtained as the current metric to be optimized;

[0016] The determining the problem type by using the large model to process the simulation result data includes:

[0017] Using the large model to determine the problem type based on the current metric to be optimized and the simulation result data; and / or

[0018] When it is determined based on the simulation result data that there is a risk in the manufacturing execution system, the large model is used to determine the problem type corresponding to the risk.

[0019] In one embodiment, the processing the simulation result data based on the target metric values to determine whether each of the parameters to be optimized needs to be continued to be optimized includes at least one of the following:

[0020] Determining whether there is a risk item based on the simulation result data, and when there is a risk item, determining that each of the parameters to be optimized needs to be continued to be optimized; or

[0021] Classify each of the simulation result data to obtain macro data and micro data; process the macro data through a target clustering algorithm, and calculate the current index values corresponding to each macro data index based on the processed macro data; obtain historical data corresponding to the micro data, and obtain the current index values corresponding to the micro data indicators based on the comparison result between the micro data and the historical data; the target indicators and the current indicators to be optimized include micro data indicators and macro data indicators; in the case where at least one of the current index values does not meet the corresponding target indicators, determine that each of the parameters to be optimized needs to be further optimized.

[0022] In one embodiment, the optimizing each of the parameters to be optimized based on the problem type to obtain each current parameter value includes:

[0023] Compare the problem type with the standard problem types in the expert library to obtain the successfully compared standard problem types;

[0024] Obtain the parameter correction method corresponding to the successfully compared standard problem type;

[0025] Optimize the current parameter values of each of the parameters to be optimized through the parameter correction method to obtain the optimized current parameter values.

[0026] In one embodiment, the method further includes:

[0027] Synchronize the target parameter values of each of the parameters to be optimized to the manufacturing execution system and the digital twin system;

[0028] Call the real-time dispatching system to perform shipping verification based on the target parameter values in the manufacturing execution system.

[0029] In one embodiment, the receiving the system parameter optimization request includes:

[0030] Receive a periodically triggered system parameter optimization request and / or, in the case of an abnormality occurring in the production line, receive a system parameter optimization request carrying abnormality information;

[0031] The simulating based on each of the current parameter values and the actual production line data to obtain simulation result data includes:

[0032] In the case where the system parameter optimization request carries abnormality information, use the abnormality information as a limiting condition, and simulate based on each of the current parameter values and the actual production line data to obtain simulation result data.

[0033] In a second aspect, the present application further provides a manufacturing execution system parameter optimization device, the device includes:

[0034] A receiving module, configured to receive a system parameter optimization request;

[0035] An optimization target determination module, configured to obtain each parameter to be optimized, each target index, and the target index value corresponding to each target index based on the system parameter optimization request;

[0036] A simulation module, configured to obtain each current parameter value corresponding to each parameter to be optimized and actual production line data from a digital twin system, and perform simulation based on each current parameter value and the actual production line data to obtain simulation result data;

[0037] An optimization judgment module, configured to process the simulation result data based on each target index value to determine whether each parameter to be optimized needs to be further optimized;

[0038] A positioning module, configured to, when each parameter to be optimized needs to be further optimized, process the simulation result data through a large model to determine the problem type;

[0039] A target parameter value determination module, configured to optimize each parameter to be optimized based on the problem type to obtain each current parameter value, and continue to execute the step of performing simulation based on each current parameter value to obtain simulation result data until it is determined based on the simulation result data that each parameter to be optimized does not need to be further optimized, and use the current parameter value as the target parameter value of each parameter to be optimized.

[0040] In a third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method in any one of the above embodiments are implemented.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method in any one of the above embodiments are implemented.

[0042] In a fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method in any one of the above embodiments are implemented.

[0043] The above manufacturing execution system parameter optimization method, device, computer device, computer-readable storage medium, and computer program product receive a system parameter optimization request; obtain each parameter to be optimized, each target index, and the target index value corresponding to each target index based on the system parameter optimization request; obtain each current parameter value corresponding to each parameter to be optimized from the digital twin system, and perform simulation based on each current parameter value to obtain simulation result data; process the simulation result data based on each target index value to determine whether each parameter to be optimized needs to be further optimized; in the case where each parameter to be optimized needs to be further optimized, process the simulation result data through a large model to determine the problem type; optimize each parameter to be optimized based on the problem type to obtain each current parameter value, and continue to execute the step of performing simulation based on each current parameter value to obtain simulation result data until it is determined based on the simulation result data that each parameter to be optimized does not need to be further optimized, and use the current parameter value as the target parameter value of each parameter to be optimized. In this way, based on the digital twin system, the manufacturing execution system and the simulation system are functionally integrated, taking the parameters of the manufacturing execution system and the actual production line data as inputs, using the simulation system to evaluate the operation of the production line, and optimizing the parameters of the digital twin system, thereby completing parameter adjustment and optimization, and further improving the performance of the actual production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0045] Figure 1 It is an application environment diagram of the manufacturing execution system parameter optimization method in an embodiment;

[0046] Figure 2 It is a flowchart of the manufacturing execution system parameter optimization method in an embodiment;

[0047] Figure 3 It is a flowchart of the manufacturing execution system parameter optimization method in another embodiment;

[0048] Figure 4 It is a structural block diagram of the manufacturing execution system parameter optimization device in an embodiment;

[0049] Figure 5 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] In order to make the objectives, technical solutions and advantages of this application more clear and understandable, the following further details this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit this application.

[0051] The method for optimizing manufacturing execution system parameters provided by the embodiments of this application can be applied to an application environment as Figure 1 shown. The detection and recording system can obtain various production line data generated on the production line in real time and send the production line data to the MES. The MES is communicatively connected to the digital twin system to send the production line data, various parameters in the MES, and target indicators to the digital twin system, so that the digital twin system can perform simulation processing. The digital twin system includes a mathematical simulation model established for the production line. The input of this mathematical simulation model includes various production line data, traversal of equipment parameters in the MES, etc., and the MPS plan (including various target indicators and the target indicator values corresponding to the target indicators). The RTD system is used to dynamically allocate tasks and schedule resources to verify the solution on the actual production line. The server can obtain the simulation results of the digital twin system, parse the simulation results, and call the corresponding solutions and adjustment strategies in the expert library to process based on the parsing results, optimize various parameters in the MES until the simulation results indicate that the actual production line can reach the corresponding target indicator values. Use the simulation system to evaluate the operation of the production line and optimize the parameters of the digital twin system, thereby completing the parameter adjustment and optimization, and then improving the performance of the actual production line.

[0052] Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0053] In an exemplary embodiment, as Figure 2 shown, a method for optimizing manufacturing execution system parameters is provided. Taking the method applied to the Figure 1 server as an example, it includes the following steps S202 to step S212. Among them:

[0054] S202: Receive a system parameter optimization request.

[0055] The system parameter optimization request can be started regularly, so as to periodically check the non-hardware risks in the current production line, or the system parameter optimization request can be issued passively. For example, when a sudden failure occurs in the production line or there are related adjustment requirements, the system parameter optimization request is triggered to trigger sudden situations or cope with new demands in a timely manner.

[0056] In this way, abnormal situations on the production line can be preferentially processed, reducing the processing time of production line abnormalities, decreasing the proportion of manual participation, and improving the overall efficiency of the production line.

[0057] S204: Obtain each parameter to be optimized, each target indicator, and the target indicator value corresponding to each target indicator based on the system parameter optimization request.

[0058] The parameters to be optimized are the production line-related parameters in the MES. These parameters can be used for processing production data or generating production data.

[0059] The target indicators are related to the production line plan in the MES. The production line plan can include the MPS (Master Production Schedule, that is, the feeding plan) in the short term. The short-term MPS can include WIP (Work In Progress, referring to the products or semi-finished products that have not been completed in the production process).

[0060] Each target indicator corresponds to a target indicator value. During the optimization process, the target indicator is the purpose of this optimization. Optionally, when there are multiple target indicators, the target indicators have priorities. It should be noted that the priorities can be configured by the user or determined based on default priorities, and specific limitations are not made here. The target indicators with higher priorities can be the most critical or urgent indicators, so that limited resources can be preferentially invested in the indicators with higher priorities to ensure that the most important target indicators can be achieved. In this application, each target indicator is optimized in turn based on the priority of the target indicator.

[0061] In some alternative embodiments, the nature of each target indicator can be obtained first to determine whether the target indicators conflict. If there is a conflict, the target indicators are divided based on the conflict to determine the highest priority in each group, and the target indicators with the highest priorities in each group are obtained from the group corresponding to the highest priority, and then the obtained target indicators with the highest priorities are optimized.

[0062] The target indicator value can be quantitative (for example, the production efficiency is increased by 10% and the defect rate is reduced to less than 1%), or it may be qualitative (for example, improving product quality or reducing the production cycle). The setting of the target value is to clarify the direction and expected results of the optimization work, ensuring that the optimization measures can solve problems targeted and achieve the expected effects.

[0063] In some alternative embodiments, the server can preset a corresponding interface, and this interface can retrieve the production line-related parameters in the MES from the database or data platform.

[0064] S206: Obtain the current parameter values corresponding to each parameter to be optimized and the actual production line data from the digital twin system, and perform simulation based on the current parameter values and the actual production line data to obtain simulation result data.

[0065] The digital twin system is established based on digital twin technology. Digital twin technology is a technology that builds on digital modeling and simulation technology, modeling objects, processes, and systems in the physical world as virtual digital models, so as to monitor, analyze, optimize, and predict these entities in real time. In the semiconductor industry, digital twin technology is widely used in production process optimization, equipment performance monitoring and maintenance, product design verification, etc. In semiconductor production, digital twin technology can help simulate the operating state of equipment, predict equipment failures, optimize production processes, and improve production efficiency and product quality. Through digital twin technology, key parameters such as the working state, temperature, and pressure of equipment can be monitored in real time, anomalies can be detected in a timely manner, and measures can be taken to make adjustments to avoid production interruptions and losses. In addition, digital twin can also be used to simulate the design effects of new products, discover potential problems in advance, and reduce R & D costs and cycles.

[0066] The digital twin system includes a digital model and simulation software. The input of the digital twin system is the current parameter values corresponding to each parameter to be optimized and the actual production line data. By configuring the current parameter values and the actual production line data of the digital model in the digital twin system, the simulation software self-checks whether the relevant logic and entities meet the definition and operation requirements, reads the input and starts running to obtain simulation result data. The simulation result data can include the output data of the production line and the operation data corresponding to the production line obtained by the digital model based on the current parameter values and the actual production line data, etc.

[0067] S208: Process the simulation result data based on each target index value to determine whether each parameter to be optimized needs to be further optimized.

[0068] After obtaining the simulation result data, each target index can be calculated based on the simulation result data.

[0069] In some alternative embodiments, the target indexes include macro data indexes and micro data indexes. Based on each simulation result data, the current index value corresponding to each target index can be calculated. Then, based on the target index value and the current index value, it is determined whether there are target indexes that do not meet the requirements, or whether there are risks based on the current index value, etc., so as to determine whether each parameter to be optimized needs to be further optimized.

[0070] S210: In the case where each parameter to be optimized needs to be further optimized, process the simulation result data through a large model to determine the problem type.

[0071] The problem type is generated based on the current metric value and the target metric value. For example, a large model processes the current metric value and the target metric value to obtain the corresponding problem type.

[0072] Optionally, a knowledge base can be pre-established based on historical data and the corresponding problem types. The historical data can include device logs, production records, quality reports, etc.

[0073] The large model can learn from the data in the knowledge base, so that the large model can subsequently process the simulation result data to determine the problem type.

[0074] To facilitate understanding, an implementation manner of the problem type determination step is given: First, determine the target metric to be optimized corresponding to this optimization, such as the good product rate, production efficiency, equipment failure frequency, and clarify the parameter range corresponding to the MES, including process parameters, equipment status, production records, etc.; then perform overall data analysis, such as viewing the historical data in the MES to identify global problems. Compare the change trends of recent data and historical data, and pay attention to abnormal fluctuations. For example: Has the good product rate decreased significantly? Has the equipment utilization rate changed significantly? Has the cycle time increased? The third step is to determine the problem type based on the target metric to be optimized (such as the good product rate, overall equipment efficiency OEE, cycle time, etc.), and compare the recent data with the historical data. For example, display the trend changes through visualization tools such as bar charts and line charts to quickly locate global problems.

[0075] In some alternative embodiments, the analysis results and the chart integrating all data can be output as a report and fed back to the user side.

[0076] S212: Optimize each parameter to be optimized based on the problem type to obtain each current parameter value, and continue to execute the step of performing simulation based on each current parameter value to obtain simulation result data until it is determined based on the simulation result data that each parameter to be optimized does not need to be further optimized, and then use the current parameter value as the target parameter value of each parameter to be optimized.

[0077] After determining the problem type, the corresponding parameter to be optimized can be optimized based on the problem type. For example, determine the parameter to be optimized that causes the problem type, and then adjust the values of these parameters to be optimized to obtain the current parameter value. Subsequently, re-perform the simulation based on the updated current parameter values until it is determined based on the simulation result data that each parameter to be optimized does not need to be further optimized, and then use the current parameter value as the target parameter value of each parameter to be optimized.

[0078] In some alternative embodiments, to improve the simulation efficiency, a threshold for the number of optimization times can be determined. After reaching the threshold for the number of optimization times, if it is still determined based on the simulation result data that each parameter to be optimized needs to be further optimized, an optimization record is output to facilitate troubleshooting by the user. For example, the user can adjust the adjustment step size corresponding to each parameter to be optimized to reduce the number of optimization times. Or the user can view each target metric. If it is determined that the currently interested target metric has been optimized, the optimization can also be terminated in advance to avoid unnecessary metrics being continuously optimized, resulting in an overly long system optimization time, etc.

[0079] The above method for optimizing the parameters of the manufacturing execution system receives a system parameter optimization request; obtains each parameter to be optimized, each target metric, and the target metric value corresponding to each target metric based on the system parameter optimization request; obtains each current parameter value corresponding to each parameter to be optimized from the digital twin system, and performs a simulation based on each current parameter value to obtain simulation result data; processes the simulation result data based on each target metric value to determine whether each parameter to be optimized needs to be further optimized; in the case where each parameter to be optimized needs to be further optimized, processes the simulation result data through a large model to determine the problem type; optimizes each parameter to be optimized based on the problem type to obtain each current parameter value, and continues to execute the step of performing a simulation based on each current parameter value to obtain simulation result data until it is determined based on the simulation result data that each parameter to be optimized does not need to be further optimized, and takes the current parameter value as the target parameter value of each parameter to be optimized. In this way, based on the digital twin system, the manufacturing execution system and the simulation system are functionally integrated in the present application. Using the parameters of the manufacturing execution system and the actual production line data as input, the simulation system is used to evaluate the operation of the production line and optimize the parameters of the digital twin system, thereby completing the parameter adjustment and optimization, and further improving the performance of the actual production line.

[0080] In some of these alternative embodiments, each target metric has a priority; the method further includes: determining the metrics to be optimized that do not meet the requirements based on the simulation result data and the target metric values corresponding to each target metric; obtaining the metric to be optimized with the highest priority as the current metric to be optimized when there are no conflicting metrics among the metrics to be optimized; obtaining the first metric to be optimized with a higher priority among the conflicting metrics to be optimized, obtaining the second metric to be optimized without conflicts, and the metric with the highest priority among the first metrics to be optimized as the current metric to be optimized when there are conflicting metrics among the metrics to be optimized; processing the simulation result data through a large model to determine the problem type, including: determining the problem type through the large model based on the current metric to be optimized and the simulation result data; and / or when it is determined based on the simulation result data that there is a risk in the manufacturing execution system, determining the problem type corresponding to the risk through the large model.

[0081] Among them, each target index has a priority, so that when faced with the premise that multiple target indexes do not meet the requirements, the most serious or globally influential problem can be determined based on the priority to avoid distraction. When only one target index does not meet the requirements, the parameter to be optimized is directly optimized so that the target index meets the requirements.

[0082] In addition, there may be conflicts among the target indexes. To improve the processing efficiency, first, based on the simulation result data and the target index values corresponding to the target indexes, the indexes to be optimized that do not meet the requirements are determined, and then it is determined whether there are conflicts among the indexes to be optimized. If there are no conflicts, they can be optimized based on the priority; if there are conflicts, the index to be optimized with the highest priority is obtained based on the priority for optimization. Specifically, the first index to be optimized with a high priority among the indexes to be optimized that conflict with each other is obtained, and the second indexes to be optimized (i.e., the remaining indexes to be optimized) that do not conflict with each other and the index with the highest priority among the first indexes to be optimized are used as the current indexes to be optimized. That is to say, although there are conflicts among the indexes to be optimized, it is not the most critical problem to be solved currently, so there is no need to optimize it in this round.

[0083] Among them, when determining the problem type subsequently, the large model can be used to determine the problem type based on the current index to be optimized and the simulation result data. For example, analyze the reasons in the simulation result data that cause the current index to be optimized to fail to meet the standard, so as to determine the problem type.

[0084] In other embodiments, when it is determined based on the simulation result data that there is a risk in the manufacturing execution system, the large model can be used to determine the problem type corresponding to the risk.

[0085] In the above embodiments, during the optimization process, multiple problems or targets may be faced. The priority ranking can help the team focus on solving the most serious or globally influential problems and avoid distraction. When conflicts occur between different targets (for example, improving efficiency may lead to an increase in cost), the priority ranking can provide a basis for decision-making to ensure that the high-priority targets are preferentially met. The priority ranking helps to evaluate the effect after optimization, clarify which high-priority targets have been achieved and which still need further improvement.

[0086] In some alternative embodiments, the simulation result data is processed based on each target index value to determine whether each parameter to be optimized needs to be further optimized, including at least one of the following: determining whether there is a risk item based on the simulation result data, and if there is a risk item, determining that each parameter to be optimized needs to be further optimized; or classifying each simulation result data into macro data and micro data; processing the macro data through a target clustering algorithm, and calculating the current index value corresponding to each macro data index based on the processed macro data; obtaining historical data corresponding to the micro data, and obtaining the current index value corresponding to the micro data index based on the comparison result between the micro data and the historical data; the target index and the current index to be optimized include micro data index and macro data index; if at least one of the current index values does not meet the corresponding target index, it is determined that each parameter to be optimized needs to be further optimized.

[0087] Among them, the evaluation of the simulation result is used to determine whether the parameter to be optimized needs to be further optimized. The judgment of whether to optimize includes two aspects: The first aspect is to process the simulation result data to judge whether there is a risk item. The risk item can be pre-stored in the risk database. After the simulation ends and each simulation result data is obtained, the simulation result data is compared with the risk items in the risk database to determine whether there is a risk. If there is a risk, it is determined that each parameter to be optimized needs to be further optimized. The second aspect is to calculate the current index value corresponding to each target index. If there is a situation where the current index value does not meet the corresponding target index value, it is determined that each parameter to be optimized needs to be further optimized.

[0088] Among them, the calculation of the current index value is divided into the calculation of the macro data index value and the calculation of the micro data index value. In some alternative embodiments, the calculation of the macro data index value and the calculation of the micro data index value can be processed in parallel to improve efficiency. In addition, if there is a dependency relationship between the indexes, the dependency relationship between the indexes can be obtained first, and then the calculation order of the current index value corresponding to each target index is determined based on the dependency relationship. The target indexes with a sequential order are calculated serially, and the target indexes without a sequential order are calculated in parallel.

[0089] Among them, for the macro data index, first select a suitable clustering algorithm according to the data characteristics, such as K-means, hierarchical clustering or DBSCAN. Then perform feature selection, for example, determine the features used for clustering, which may be dates, product types, etc. The third step is to perform clustering based on the selected clustering features. Specifically, the selected algorithm is applied to group the simulation result data. The fourth step is to perform result analysis, such as evaluating the clustering effect, and adjusting parameters or algorithms if necessary. Finally, index calculation and display, such as calculating and displaying indexes by date and product type, and displaying the global situation without filtering.

[0090] For the calculation of micro-data indicators, historical data corresponding to the micro-data is obtained, and the current indicator value corresponding to the micro-data indicator is obtained based on the comparison result between the micro-data and the historical data. The historical data can be historical data within a target time period, such as historical data within a preset time range from the generation time corresponding to the micro-data. The micro-data in the simulation result data is the running data by step, and then the historical data in the MES within the same time period interval is used to analyze the key indicators through reports, such as cycle time, machine utilization rate, in-process quantity, input, and output quantity, etc.

[0091] In one alternative embodiment, optimizing each parameter to be optimized based on the problem type to obtain each current parameter value includes: comparing the problem type with the standard problem types in the expert library to obtain the successfully compared standard problem types; obtaining the parameter correction method corresponding to the successfully compared standard problem types; and optimizing the current parameter values of each parameter to be optimized through the parameter correction method to obtain the optimized current parameter values.

[0092] Among them, the process of comparing the problem type with the standard problem types in the expert library in this application can be to calculate the similarity between the name corresponding to the problem type and the name corresponding to the standard problem types in the expert library, and obtain the standard problem type with the largest similarity as the target problem type.

[0093] In other embodiments, the problem type can also be compared with the standard problem types in the expert library by calling a large model to determine the successfully compared standard problem types.

[0094] Then, the comparison result is converted into a specific solution. That is, each standard problem type in the expert library corresponds to a solution. Thus, the parameters to be optimized can be adjusted based on the solution, and the new parameters are input into the model for a new round of simulation until the last round of simulation verification makes each target indicator reach the target indicator value and / or eliminates the problem, and then a correction report and recommended parameter values are output.

[0095] In one alternative embodiment, the method further includes: synchronizing the target parameter values of each parameter to be optimized to the manufacturing execution system and the digital twin system; and calling the real-time dispatching system to perform shipping verification based on the target parameter values in the manufacturing execution system.

[0096] Among them, after the optimization is completed, the new MES parameter information is synchronized to the MES and archived in the data storage unit of the digital twin platform.

[0097] Subsequent calls to the RTD use the values in the MES for shipment verification. Shipment verification refers to updating and managing the parameter information of the Manufacturing Execution System (MES) and applying it to the production and logistics processes. By archiving this information into the digital twin platform, enterprises can simulate and optimize production configurations in a virtual environment, thereby improving the efficiency and quality of actual production. At the same time, the Real-Time Database (RTD) is called for shipment verification to ensure the accuracy and timeliness of goods transportation, further supporting the efficient operation of the overall supply chain.

[0098] In one optional embodiment, a system parameter optimization request is received, including: receiving a periodically triggered system parameter optimization request and / or, in the case of an abnormality on the production line, receiving a system parameter optimization request carrying abnormality information; obtaining simulation result data based on each current parameter value and actual production line data, including: in the case where the system parameter optimization request carries abnormality information, using the abnormality information as a limiting condition and obtaining simulation result data based on each current parameter value and actual production line data.

[0099] The system parameter optimization request in this application can be started regularly, so as to periodically check for non-hardware risks in the current production line, or the system parameter optimization request can be issued passively. For example, when a sudden failure occurs on the production line or there are related adjustment requirements, the system parameter optimization request is triggered to immediately respond to sudden situations or meet new demands.

[0100] In this way, production line abnormalities can be prioritized for processing, reducing the processing time of production line abnormalities, decreasing the proportion of manual participation, and improving the overall efficiency of the production line.

[0101] In addition, in the case where the system parameter optimization request carries abnormality information, using the abnormality information as a limiting condition and obtaining simulation result data based on each current parameter value and actual production line data. This is because an abnormality has occurred on the production line and cannot be repaired currently. Therefore, this situation needs to be synchronized to the digital twin system, so that the process of the digital twin system obtaining simulation result data based on each current parameter value and actual production line data is more in line with the production line.

[0102] In each of the above embodiments, by using digital twin and simulation technologies, automation technologies such as MES, and other related supporting auxiliary technologies, rapid correction of MES data, detection of production line risks, and automatic generation of relevant reports can be achieved. A large amount of data generated by simulation iteration can also support the training and analysis of other models. In addition, this mechanism can significantly reduce the response time to anomalies, reduce the proportion of manual participation, and improve the overall automation level of the information service end. With the support of this mechanism, the production line can manage abnormal trends and risks and adapt and correct them automatically or semi-automatically. Here, the semi-automatic mode can be to output the target parameter values, and then the user confirms whether to apply these target parameter values to MES, that is, the decision-making power lies with the user, which improves efficiency while ensuring accuracy.

[0103] For ease of understanding, in combination with Figure 3 as shown in Figure 3 is a flowchart of a method for optimizing manufacturing execution system parameters in another embodiment. First, an execution request, that is, a parameter optimization request, is sent regularly or passively. Then, the real-time parameters of MPS and MES are obtained as inputs, and simulation is performed to obtain simulation result data, and the results are evaluated. The evaluation results can output a problem report. Based on the evaluation results, it is determined whether there is a risk. If there is no risk, it is determined whether the value of the target index is much greater than expected or optimized to the maximum extent (here, the maximum extent of optimization means that if further optimized, the value of this target index will increase, but it will cause the values of other target indices with higher priorities to decrease, or if further optimized, the change degree of the value of this target index is not large). If there is a risk or the value of the target index is less than expected or not optimized to the maximum extent, the expert library is called to match the problem type, and the corresponding correction suggestions are obtained. Based on the correction suggestions, new parameter inputs are generated, and the simulation continues.

[0104] If there is no risk and it is determined that the value of the target index is much greater than expected or optimized to the maximum extent, a correction report and the recommended parameter values (target parameter values) are output. Finally, the target parameter values are synchronized to MES and the digital twin platform, and RTD is called for verification.

[0105] In the above embodiments, the manufacturing execution system and production simulation are integrated functionally. With MES as the main body, MES parameters and actual production line data as inputs, the operation of the production line in the future for a period of time is evaluated by using simulation, and the output data is fed back to MES and verified through RTD, so as to complete the parameter adjustment and optimization, thus forming a set of dynamically corrected and closed-loop MES information maintenance mechanism, maximizing the simulation accuracy, enhancing the resilience and flexibility of the production line, improving its ability to cope with risks and fluctuations, realizing simulation guidance and empowering actual production, improving the production performance of the production line, and reducing equipment and material losses.

[0106] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of the steps or stages in other steps or other steps.

[0107] Based on the same inventive concept, an embodiment of the present application further provides a manufacturing execution system parameter optimization device for implementing the manufacturing execution system parameter optimization method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the manufacturing execution system parameter optimization device provided below can refer to the limitations on the manufacturing execution system parameter optimization method in the above text, and will not be repeated here.

[0108] In an exemplary embodiment, as Figure 4 shown, a manufacturing execution system parameter optimization device is provided, including:

[0109] A receiving module 401, configured to receive a system parameter optimization request;

[0110] An optimization target determination module 402, configured to obtain each parameter to be optimized, each target index, and the target index value corresponding to each target index based on the system parameter optimization request;

[0111] A simulation module 403, configured to obtain each current parameter value corresponding to each parameter to be optimized and actual production line data from the digital twin system, and perform simulation based on each current parameter value and actual production line data to obtain simulation result data;

[0112] An optimization judgment module 404, configured to process the simulation result data based on each target index value to determine whether each parameter to be optimized needs to be further optimized;

[0113] A positioning module 405, configured to, in the case where each parameter to be optimized needs to be further optimized, process the simulation result data through a large model to determine the problem type;

[0114] The target parameter value determination module 406 is configured to optimize each parameter to be optimized based on the problem type to obtain each current parameter value, and continue to execute the step of performing simulation based on each current parameter value to obtain simulation result data until, when it is determined based on the simulation result data that each parameter to be optimized does not need to be further optimized, the current parameter value is used as the target parameter value of each parameter to be optimized.

[0115] In one optional embodiment, each target metric has a priority; the above device further includes: a current metric to be optimized determination module, configured to determine the metrics to be optimized that do not meet the requirements based on the simulation result data and the target metric values corresponding to each target metric; when there are no conflicting metrics among the metrics to be optimized, obtain the metric to be optimized with the highest priority as the current metric to be optimized; when there are conflicting metrics among the metrics to be optimized, obtain the first metric to be optimized with a higher priority among the conflicting metrics to be optimized, obtain the second metrics to be optimized that do not conflict with each other, and the metric with the highest priority among the first metrics to be optimized as the current metric to be optimized.

[0116] The above positioning module 405 is configured to determine the problem type through a large model based on the current metric to be optimized and the simulation result data; and / or when it is determined based on the simulation result data that there is a risk in the manufacturing execution system, determine the problem type corresponding to the risk through a large model.

[0117] In one optional embodiment, the above positioning module 405 is configured to determine whether each parameter to be optimized needs to be further optimized based on at least one of the following methods: determining whether there are risk items based on the simulation result data, and when there are risk items, determining that each parameter to be optimized needs to be further optimized; or classifying each simulation result data into macro data and micro data; processing the macro data through a target clustering algorithm, and calculating the current metric values corresponding to each macro data metric based on the processed macro data; obtaining the historical data corresponding to the micro data, and obtaining the current metric values corresponding to the micro data metrics based on the comparison result between the micro data and the historical data; the target metrics and the current metrics to be optimized include micro data metrics and macro data metrics; when at least one of the current metric values does not meet the corresponding target metric, determining that each parameter to be optimized needs to be further optimized.

[0118] In one optional embodiment, the above target parameter value determination module 406 is further configured to compare the problem type with the standard problem types in the expert library to obtain the successfully compared standard problem types; obtain the parameter correction methods corresponding to the successfully compared standard problem types; and optimize the current parameter values of each parameter to be optimized through the parameter correction methods to obtain the optimized current parameter values.

[0119] In one alternative embodiment, the above-mentioned device further includes: a synchronization module, configured to synchronize the target parameter values of each parameter to be optimized to the manufacturing execution system and the digital twin system; and call the real-time dispatching system to perform shipment verification based on the target parameter values in the manufacturing execution system.

[0120] In one alternative embodiment, the above-mentioned receiving module 401 is further configured to receive a periodically triggered system parameter optimization request and / or, in the case of an abnormality occurring in the production line, receive a system parameter optimization request carrying abnormality information.

[0121] The above-mentioned simulation module 403 is further configured to, in the case where the system parameter optimization request carries abnormality information, use the abnormality information as a limiting condition and perform simulation based on each current parameter value and actual production line data to obtain simulation result data.

[0122] Each module in the above-mentioned manufacturing execution system parameter optimization device can be implemented in whole or in part by software, hardware, and their combination. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in a computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above-mentioned modules.

[0123] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the output reports and various data related to the production line, etc. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for optimizing manufacturing execution system parameters.

[0124] Those skilled in the art can understand, Figure 5The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0125] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0126] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0127] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0129] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0130] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0131] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for optimizing manufacturing execution system parameters, characterized in that The method includes: Receiving a system parameter optimization request; Obtaining each parameter to be optimized, each target index, and the target index value corresponding to each of the target indexes based on the system parameter optimization request; Obtaining each current parameter value corresponding to each of the parameters to be optimized and actual production line data from the digital twin system, and performing simulation based on each of the current parameter values and the actual production line data to obtain simulation result data; Processing the simulation result data based on each of the target index values to determine whether each of the parameters to be optimized needs to be further optimized; In the case where each of the parameters to be optimized needs to be further optimized, using a large model to process the simulation result data to determine the problem type; Optimizing each of the parameters to be optimized based on the problem type to obtain each current parameter value, and continuing to execute the step of performing simulation based on each of the current parameter values to obtain simulation result data until, in the case where it is determined based on the simulation result data that each of the parameters to be optimized does not need to be further optimized, taking the current parameter value as the target parameter value of each of the parameters to be optimized.

2. The method according to claim 1, characterized in that Each of the target indexes has a priority; the method further includes: determining the indexes to be optimized that do not meet the requirements based on the simulation result data and the target index values corresponding to each of the target indexes; In the case where there are no conflicting indexes among the indexes to be optimized, obtaining the index to be optimized with the highest priority as the current index to be optimized; In the case where there are conflicting indexes among the indexes to be optimized, obtaining the first index to be optimized with a higher priority among the conflicting indexes to be optimized, obtaining the second index to be optimized without conflicts, and the index with the highest priority among the first indexes to be optimized as the current index to be optimized; The determining the problem type by using a large model to process the simulation result data includes: Using a large model to determine the problem type based on the current index to be optimized and the simulation result data; and / or In the case where it is determined based on the simulation result data that there is a risk in the manufacturing execution system, using a large model to determine the problem type corresponding to the risk.

3. The method according to claim 2, characterized in that, The processing the simulation result data based on each of the target index values to determine whether each of the parameters to be optimized needs to be further optimized includes at least one of the following: Determining whether there is a risk item based on the simulation result data, and in the case where there is a risk item, determining that each of the parameters to be optimized needs to be further optimized; or Classifying each of the simulation result data into macro data and micro data; processing the macro data through a target clustering algorithm, and calculating the current index value corresponding to each macro data index based on the processed macro data; obtaining historical data corresponding to the micro data, and obtaining the current index value corresponding to the micro data index based on the comparison result between the micro data and the historical data; the target index and the current index to be optimized include micro data indexes and macro data indexes; in the case where at least one of the current index values does not meet the corresponding target index, determining that each of the parameters to be optimized needs to be further optimized.

4. The method according to claim 1, characterized in that, Optimizing each of the to-be-optimized parameters based on the problem type to obtain each current parameter value includes: Comparing the problem type with the standard problem types in the expert library to obtain the successfully compared standard problem types; Obtaining the parameter correction method corresponding to the successfully compared standard problem type; Optimizing the current parameter values of each of the to-be-optimized parameters through the parameter correction method to obtain the optimized current parameter values.

5. The method according to any one of claims 1 to 4, characterized in that The method further includes: Synchronizing the target parameter values of each of the to-be-optimized parameters to the manufacturing execution system and the digital twin system; Invoking the real-time dispatching system to perform shipping verification based on the target parameter values in the manufacturing execution system.

6. The method according to any one of claims 1 to 4, characterized in that, The receiving the system parameter optimization request includes: Receiving the periodically triggered system parameter optimization request and / or, in the case of an abnormality occurring in the production line, receiving the system parameter optimization request carrying the abnormality information; The simulating based on each of the current parameter values and the actual production line data to obtain the simulation result data includes: In the case where the system parameter optimization request carries the abnormality information, using the abnormality information as a limiting condition and simulating based on each of the current parameter values and the actual production line data to obtain the simulation result data.

7. An apparatus for optimizing parameters of a manufacturing execution system, characterized in that The device includes: A receiving module, configured to receive a system parameter optimization request; An optimization target determination module, configured to obtain each to-be-optimized parameter, each target index, and the target index value corresponding to each of the target indexes based on the system parameter optimization request; A simulation module, configured to obtain each current parameter value corresponding to each of the to-be-optimized parameters and the actual production line data from the digital twin system, and simulate based on each of the current parameter values and the actual production line data to obtain the simulation result data; An optimization judgment module, configured to process the simulation result data based on each of the target index values to determine whether each of the to-be-optimized parameters needs to be further optimized; A positioning module, configured to, in the case where each of the to-be-optimized parameters needs to be further optimized, process the simulation result data through a large model to determine the problem type; A target parameter value determination module, configured to optimize each of the to-be-optimized parameters based on the problem type to obtain each current parameter value, and continue to execute the step of simulating based on each of the current parameter values to obtain the simulation result data until, in the case where it is determined based on the simulation result data that each of the to-be-optimized parameters does not need to be further optimized, using the current parameter value as the target parameter value of each of the to-be-optimized parameters.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images