Method and apparatus for calibrating a simulation model of a production line

Abstract

A method for calibrating a simulation model of a production line, comprising: obtaining a simulation model of the production line (101); converting the simulation model into a formal model for formal description of the simulation model (102); obtaining historical production data generated during the actual production process of the production line (103); performing a consistency check on the formal model and the historical production data to determine whether the product processes in the formal model are consistent with the product processes reflected in the historical production data (104); and when it is determined that the product processes in the formal model are inconsistent with the product processes reflected in the historical production data, adjusting the simulation model (105). Through the above method, the accuracy of the simulation model and the quality of factory digitization are improved, and it has extensive generality and effectiveness.

Description

Technical Field

[0001] The present disclosure relates to the technical field of industrial manufacturing, and more particularly, to a method, apparatus, computing device, computer-readable storage medium, and program product for calibrating a simulation model of a production line. Background Art

[0002] Establishing a simulation model for a production line in a factory is an important step in realizing factory digitization. The simulation model of the production line can perform virtual simulation on the production and manufacturing process of products in the production line, simulate the production scenario, and provide a reference for the decision-making of management or technical personnel, thereby improving the efficiency of product R & D and manufacturing in manufacturing enterprises. Generally, establishing a simulation model of a production line mainly depends on the structure of the production line and the processing procedures or process routes of products in the manufacturing bill of materials (BOM). Specifically, first, simulation modules for each component are established based on each component of the production line and configuration parameters are set for each simulation module. Subsequently, the operation sequence of these simulation modules is determined based on the production sequence of the products. When using the simulation model to simulate the production of products, by providing appropriate inputs to the simulation model (for example, the time when the product enters the production line), desired simulation results (for example, the output of the production line within a certain period of time) can be obtained. Summary of the Invention

[0003] In fact, the simulation model of the production line constructed in the above manner is often an ideal model. On the one hand, in an actual factory workshop, the actual procedures of products usually do not strictly follow the procedures predefined in the manufacturing bill of materials. For example, when a product needs to be returned to a previous machine for rework of a certain process step during processing, there may be some repeated processing procedures. Another example is that there may be some procedures that do not require machine equipment or workstations but take some time, such as inspection procedures, which refer to the process in which a manufacturing engineer conducts technical quality inspections, reconfirmations, or signatures on a certain process step during product processing. On the other hand, the configuration parameters of the simulation model are usually set as fixed values according to experience, however, the fixed values cannot well reflect the real production process. For example, in

[0004] the actual production process, the time to repair (TTR) and the time between failures (TBF) of a certain device may change according to the situation. Setting them as fixed values will inevitably affect the simulation results.

[0005] Therefore, the simulation model constructed only based on the production line structure and the product procedures in the manufacturing bill of materials has ideal procedures and fixed configuration parameters, and the simulation results obtained using this simulation model will not be accurate enough, thus affecting the decisions made based on these simulation results.

[0006] The first embodiment of the present disclosure proposes a method for calibrating a simulation model of a production line, including: obtaining a simulation model of the production line, which is used to simulate the production process of the production line and includes a plurality of simulation modules corresponding to the respective components of the production line, and the simulation modules are provided with corresponding configuration parameters; converting the simulation model into a formal model, which is used to formally describe the simulation model; obtaining historical production data generated during the actual production process of the production line; performing a consistency check on the formal model and the historical production data to determine whether the product processes in the formal model are consistent with the product processes reflected in the historical production data; and when it is determined that the product processes in the formal model are inconsistent with the product processes reflected in the historical production data, adjusting the simulation model.

[0007] In this embodiment, the historical production data generated during the actual production process of the production line in the factory is used to perform a consistency check on the product processes of the simulation model of the production line, and the simulation model is adjusted using the check result, improving the accuracy of the simulation model and making it closer to the actual production process. Therefore, more accurate simulation results can be obtained, improving the quality of factory digitization. In addition, the method for calibrating the simulation model of the production line is applicable to various different simulation models constructed using different modeling software, so it has broad generality and effectiveness.

[0008] The second embodiment of the present disclosure proposes a device for calibrating a simulation model of a production line, including: a simulation model acquisition unit configured to obtain a simulation model of the production line, which is used to simulate the production process of the production line and includes a plurality of simulation modules corresponding to the respective components of the production line, and the simulation modules are provided with corresponding configuration parameters; a simulation model conversion unit configured to convert the simulation model into a formal model, which is used to formally describe the simulation model; a production data acquisition unit configured to obtain historical production data generated during the actual production process of the production line; a consistency check unit configured to perform a consistency check on the formal model and the historical production data to determine whether the product processes in the formal model are consistent with the product processes reflected in the historical production data; and a simulation model adjustment unit configured to adjust the simulation model when it is determined that the product processes in the formal model are inconsistent with the product processes reflected in the historical production data.

[0009] Adjust.

[0010] The third embodiment of the present disclosure proposes a computing device, which includes: a processor; and a memory for storing computer-executable instructions that, when executed, cause the processor to execute the method in the first embodiment.

[0011] A fourth embodiment of the present disclosure proposes a computer-readable storage medium having computer-executable instructions stored thereon for performing the method of the first embodiment.

[0012] A fifth embodiment of the present disclosure proposes a computer program product tangibly stored on a computer-readable storage medium and including computer-executable instructions that, when executed, cause at least one processor to perform the method of the first embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In conjunction with the accompanying drawings and with reference to the following detailed description, the features, advantages, and other aspects of the embodiments of the present disclosure will become more apparent. Several embodiments of the present disclosure are shown herein by way of example and not limitation. In the drawings:

[0014] Figure 1 illustrates a method for calibrating a simulation model of a production line according to an embodiment of the present disclosure;

[0015] Figure 2 illustrates an example of a production line simulation model according to an embodiment of the present disclosure;

[0016] Figure 3 illustrates a method for calibrating Figure 2 the production line simulation model in;

[0017] Figure 4 illustrates according to Figure 3 a Petri net model constructed from the production line simulation model of;

[0018] Figure 5 illustrates Figure 4 the inspection result of the consistency check between the Petri net model of and the example historical production data;

[0019] Figure 6 illustrates according to Figure 5 the production line simulation model adjusted according to the inspection result of;

[0020] FIG. 7(a) illustrates the fitting result of fitting the repair time TTR of the equipment at workstation 202 in Figure 2 using the normal distribution function;

[0021] FIG. 7(b) illustrates the fitting result of fitting the repair time TTR of the equipment at workstation 202 in Figure 2 using the Poisson distribution function;

[0022] Figure 8 illustrates the use of the exponential distribution function for Figure 2The fitting result of the mean time between failures TBF of the devices at the middle workstation 202;

[0023] Figure 9 Shows an exemplary architecture of a system for calibrating a simulation model of a production line according to Figure 3 an embodiment;

[0024] Figure 10 Shows an apparatus for calibrating a simulation model of a production line according to another embodiment of the present disclosure; and

[0025] Figure 11 Shows a block diagram of a computing device for calibrating a simulation model of a production line according to an embodiment of the present disclosure. Detailed Description of Specific Embodiments

[0026] The following describes in detail various exemplary embodiments of the present disclosure with reference to the accompanying drawings. Although the exemplary methods and apparatuses described below include software and / or firmware executed on hardware among other components, it should be noted that these examples are merely illustrative and should not be considered restrictive. For example, it is contemplated that any or all of the hardware, software, and firmware components may be implemented exclusively in hardware, exclusively in software, or in any combination of hardware and software. Thus, although the exemplary methods and apparatuses have been described below, those skilled in the art should readily appreciate that the examples provided are not intended to limit the manner in which these methods and apparatuses are implemented.

[0027] In addition, the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the methods and systems according to various embodiments of the present disclosure. It should be noted that the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented using a dedicated hardware-based system that performs the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.

[0028] As used herein, the terms "comprising," "including," and similar terms are open-ended terms, i.e., "including / including but not limited to," indicating that other elements may also be included. The term "based on" means "at least partially based on." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment," and so on.

[0029] Figure 1A method for calibrating a simulation model of a production line according to an embodiment of the present disclosure is shown. The production line can be any production line used for manufacturing products in a factory, and its simulation model can be constructed via any suitable modeling tool or software. Referring to Figure 1 , method 100 starts from step 101.

[0030] In step 101, a simulation model of the production line is obtained. The simulation model is used to simulate the production process of the production line and includes a plurality of simulation modules corresponding to the respective components of the production line. The simulation modules are provided with corresponding configuration parameters. As mentioned above, the simulation model of the production line can perform virtual simulation on the production and manufacturing process of products in the production line, simulate the production scenario and obtain the desired simulation results for purposes such as production scheduling, production line design and planning, or product research and development. The respective components of the production line can include, for example, manual workstations and machine equipment. The configuration parameters can include, for example, the processing time or handling time of the product to be processed at the manual workstation or machine equipment, the time when the product to be processed enters the manual workstation or machine equipment, the time when the product to be processed leaves the manual workstation or machine equipment, the repair time TTR (Time to Repair) and the mean time between failures TBF (Time Between Failure) of the machine equipment, the waiting time of the manual workstation or machine equipment due to temporary shortage of raw material supply, and so on.

[0031] Continuing to refer to Figure 1 , next, method 100 proceeds to step 102. In step 102, the simulation model is converted into a formal model, and the formal model is used for formal description of the simulation model. Formal description means using a language with preset syntax and semantic definitions to describe the characteristics such as the state and behavior of a system. In some embodiments, the formal model is a Petri net model. The Petri net model can be used to describe discrete parallel systems and is composed of places (P), transitions (T), directed arcs, and tokens. Among them, places represent state elements, transitions represent change or event elements, directed arcs can go from places to transitions or from transitions to places, and tokens are dynamic objects in places and can move from one place to another through transitions.

[0032] Since the Petri net model can describe the characteristics of discrete parallel systems, it can be used to represent the processes of a product on a production line. When converting the simulation model of a production line into a formal model, transitions can be used to represent the processing or treatment of a product at each process, places can be used to represent the states of a product before and after each process, tokens in the places represent the products, and directed arcs represent that the tokens (products) in the places reach another state from one state via a transition (e.g., a process). For example, the process of polishing a product can be described as: the place P1 (the state of the product before polishing) is connected to the transition T1 (polishing) via a directed arc, and then connected to the place P2 (the state of the product after polishing) via a directed arc. In other embodiments, other formal models can also be adopted as long as they can abstractly describe the simulation model as a structure including states, events, and the relationships between them.

[0033] In some embodiments, converting the simulation model into a formal model further includes ( Figure 1 not shown in the figure): extracting model wiring information from the simulation model, where the model wiring information includes the identification information and operation sequence of multiple simulation modules; splitting the model wiring information into multiple groups of sub-wiring information, and each group of sub-wiring information

[0034] includes the identification information and operation sequence of each simulation module of a linear connection from the simulation module representing the starting position of the production line to the simulation module representing the ending position of the production line; and constructing a formal model according to the multiple groups of sub-wiring information.

[0035] In a factory workshop, a production line often has a network structure, that is, the components of the production line are connected in a network relationship. For example, the production line may have two or more parallel and non-interfering processes. Accordingly, the simulation modules in the simulation model of the production line are also connected in a network relationship. To meet the requirements of building a formal model, it is necessary to split the network structure of the simulation model into an end-to-end linearly connected structure. First, the model wiring information can be extracted from the simulation model through the application programming interface (API) of the modeling software or the modeling language supported by the modeling software and exported in tabular form. The model wiring information is used to reflect the processes of the product during production. In some embodiments, the simulation modules corresponding to the components of the production line can be used as objects, and the model wiring information includes four aspects of information: object name, object type, previous object, and subsequent object. Among them, the object name and object type represent the identification information of the simulation module, and the previous object and subsequent object represent the operation sequence of the simulation module. In addition, when the simulation module represents a machine device or a manual work station, the model wiring information can also include the products, parts, or raw materials processed or handled at the machine device or manual work station and the corresponding processing or handling time. In some embodiments, the processes (including processing processes and manual operation processes) implemented by the components of the production line can also be used as objects in the model wiring information.

[0036] After obtaining the model wiring information, the network structure it represents is split into multiple end-to-end sub-lines. For each sub-line, it represents a linear and non-branching process route for a certain raw material of a certain product from the starting position of the production line through each process to the ending position of the production line. It is possible to start from the simulation module representing the starting position of the production line in the model wiring information, find the subsequent simulation module (i.e., the subsequent object) of this simulation module according to the model wiring information, and then find the subsequent simulation module of the found subsequent simulation module again, and so on, until the found simulation module represents the ending position of the production line. The above process route from the simulation module representing the starting position of the production line to the simulation module representing the ending position of the production line is a sub-line. In the process of splitting the network structure into multiple sub-lines, there may be a bifurcation at a certain simulation module, that is, the subsequent simulation module of a certain simulation module may be more than one. Or, more commonly, the simulation model of the production line has multiple simulation modules representing the starting position. Therefore, for each sub-line, only one subsequent simulation module or only one simulation module representing the starting position is selected at each bifurcation to ensure

[0037] that the sub-line is linear and non-branching. The subsequent simulation modules not selected at the bifurcation or the simulation modules representing the starting position not selected can be included in other sub-lines until all the simulation modules are included in the sub-lines.

[0038] In the above manner, the network structure represented by the model wiring information can be split into multiple sub-lines. Similar to the model wiring information, the sub-line information can also take the simulation module as the object, which can include four aspects of information: the time when the object is found, the sub-line number, the object name, and the object type. The sub-line number can be used to represent the process route, and the same sub-line number represents the same process route. The sub-line numbers of the same group of sub-line information are the same. In each group of sub-line information, the object name and the object type represent the identification information of the simulation module, and the time when the object is found represents the operation sequence between the simulation modules on the process route represented by the sub-line.

[0039] In some embodiments, a production line may be used to produce different products, and the production processes of different products may be different. In such embodiments, multiple groups of sub-line information need to be obtained based on both the model wiring information and the product type. The sub-line number in the sub-line information can also be used to represent the product type.

[0040] After obtaining multiple groups of sub-line information, a formal model is constructed according to the multiple groups of sub-line information. The formal model can reflect multiple linear process routes corresponding to each group of sub-line information in the multiple groups of sub-line information respectively. Each linear process route can be the process route of the same product or the process routes of different types of products. In some embodiments, the formal model is a Petri net model, and algorithms such as Inductive Miner and Alpha Miner can be used to implement the construction of the Petri net model.

[0041] Continue to refer to Figure 1 , after step 102, the method proceeds to step 103 to obtain the historical production data generated during the actual production process of the production line. The purpose of this step is to obtain the information of each product, the processes passed by the product during the actual production process, and the corresponding timestamps. A large amount of production data (also known as process data) will be generated during the actual production process of the production line. The production data can include the machine equipment, manual workstations through which the product or its raw materials flow, the time of entering or leaving the machine equipment or manual workstation, the processes completed at the machine equipment or manual workstation, the time of machine equipment failure, the time of machine equipment failure elimination, etc., which represent the data of the complete production process. These historical production data can truly reflect the actual production processes of the products on the production line, so they can be used to test or verify the product processes in the formal model of the simulation model. The historical production data within any time period when the production line is in the same state (for example, the production line has not been modified) can be obtained, such as the historical production data within a week or a month.

[0042] In some embodiments, historical production data can be preprocessed. Production data may be stored in different formats, and the data servers storing the data may not be on the same physical machine, and may even be handwritten logs. Therefore, different data formats and the dispersed storage of data result in the heterogeneity of this historical production data. Thus, after obtaining the historical production data generated during the actual production process of the production line, it is first necessary to integrate the heterogeneous production data according to certain rules to form an efficient and centralized historical production data set, and convert it into data targeted at products or their raw materials, such as the names of the various processes passed by a certain raw material and the time when it passed. Additionally, since there may be some missing data or non-target data in the production data, the integrated historical production data can be cleaned to remove incorrect or unreasonable data and supplement the missing data.

[0043] It should be noted that although in the above description, step 103 is executed after step 102, step 103 can also be executed before step 101 or 102, or can be executed synchronously with steps 101 and 102.

[0044] Next, method 100 proceeds to step 104 to perform a consistency check on the formal model and the historical production data to determine whether the product processes in the formal model are consistent with the product processes reflected in the historical production data. As previously described, the formal model includes multiple linear process routes corresponding to each group of sub-line information in the multiple groups of sub-line information, which can reflect the various processes of the product in the simulation model, and through the integration and cleaning of the historical production data, the various processes of the product in the actual production process can be obtained. By comparing the product processes in the formal model with the actual product processes, it can be determined whether the product processes in the simulation model are accurate. Since the historical production data is the production data for a certain period of time, it usually includes multiple groups of production data of the same product (i.e., the production data of multiple products), and each group of production data can reflect the complete processes of this product. Therefore, each group of production data of the product can be subjected to a consistency check with the formal model, and based on the preset rules, it can be determined whether the product processes in the formal model are consistent with the product processes reflected in the historical production data based on the multiple check results of the consistency check of the multiple groups of production data with the formal model. For example, a threshold ratio, such as X%, can be set. When more than this threshold ratio of the multiple check results of the consistency check of the multiple groups of production data with the formal model indicate that there is a certain process in the production data that does not exist in the formal model, it can be considered that the product processes in the formal model are inconsistent with the product processes reflected in the historical production data.

[0045] In some embodiments, checking the consistency of the formalized model and the historical production data further includes: replaying the historical production data on the formalized model, and replaying is used to determine whether the formalized model is consistent with the historical production data.

[0046] Whether there are product processes that are not reflected in the historical production data or whether the historical production data reflects product processes that do not exist in the formal model. Replay is a process in which the historical production data and the formal model are used as input, and the historical production data is re-executed on the formal model. If the trace (product process) completely fits the model, it means that the trace will occur completely according to the model execution action sequence; if the trace does not completely fit the model, the replay will stop when the process where the trace does not match the model is replayed. Through the replay of historical production data, it can be determined whether there are product processes in the formal model that are not reflected in the historical production data or whether the historical production data reflects product processes that do not exist in the formal model.

[0047] Subsequently, the method 110 proceeds to step 105, and when it is determined that the product process in the formalized model is inconsistent with the product process reflected by the historical production data, the simulation model is adjusted. The simulation model is adjusted using the result of the consistency check between the formalized model and the historical production data, so that the product process in the simulation model can be closer to the product process in the actual production process. Since the product process is reflected in the simulation model through the simulation module and the position of the simulation module, the adjustment of the simulation model can include adding, deleting and / or modifying the simulation module in the simulation model.

[0048] In some embodiments, step 105 further includes ( Figure 1 (not shown): determining the difference between the product process in the formalized model and the product process reflected by the historical production data; determining the product process that needs to be added to the simulation model and / or deleted from the simulation model based on the difference; and adjusting the simulation model based on the determined product process that needs to be added and / or deleted.

[0049] When it is determined that the product process in the formal model is inconsistent with the product process reflected by the historical production data, the results of the consistency check may include the differences between the product process in the formal model and the product process reflected by the historical production data, which may include the product process that is inconsistent between the formal model and the historical production data and the position of the product process in the entire process flow.

[0050] Due to the complexity of the actual production process, the product process reflected by the historical production data but not in the formal model is not necessarily the missing process in the simulation model (for example, there is an error in the actual production process), and the product process that exists in the formal model but is not reflected in the historical production data is not necessarily a redundant process in the simulation model (for example, the rework rate of a certain product is low). Therefore, it is necessary to determine the product process that needs to be added to the simulation model and / or deleted from the simulation model based on the determined differences. This process can be automatically executed by software or selected by technicians based on experience.

[0051] After determining that a product process needs to be added to and / or deleted from the simulation model, the simulation model can be adjusted according to the position of the process in the entire process flow. In some embodiments, the simulation model can be adjusted automatically. Specifically, when a process needs to be added, the process to be deleted can be

[0052] The added process or the machine equipment / manual workstation corresponding to the process is taken as an object, and the object name, object type, previous object, subsequent object and other related information are generated, wherein the object name can be the name of the process to be added or the machine equipment / manual workstation corresponding to the process, the object type can be obtained through a preset lookup table, and the previous object and the subsequent object can be determined according to the position of the process to be added in the entire process flow. Subsequently, the model wiring information of the simulation model is modified according to the above information to update the model wiring information. When it is necessary to delete a process, the name of the process to be deleted or the machine equipment / manual workstation corresponding to the process can be taken as the object name, and the object can be found from the model wiring information of the simulation model, and the relevant information of the object can be deleted from the model wiring information to update the model wiring information. The simulation model of the updated production line can be automatically generated according to the updated model wiring information. In some embodiments, the simulation model can also be manually adjusted through the modeling software. So far, the wiring calibration of the simulation model of the production line has been achieved.

[0053] In some embodiments, method 100 further includes: Figure 1 (not shown): obtaining historical data of the configuration parameters from the historical production data; determining the frequency distribution characteristics of the configuration parameters in the actual production process based on the historical data of the configuration parameters; and setting the frequency distribution characteristics of the configuration parameters in the adjusted simulation model.

[0054] In addition to reflecting the production processes of products, the historical production data of the production line also includes the actual data of the configuration parameters of each simulation module in the simulation model. The configuration parameters may include, for example, the processing time or handling time of the product to be processed at the manual workstations or machine equipment, the time when the product to be processed enters the manual workstations or machine equipment, the time when the product to be processed leaves the manual workstations or machine equipment, the repair time TTR and the mean time between failures TBF of the machine equipment, the waiting time of the manual workstations or machine equipment, and so on. In order to make the simulation model closer to the actual production line, the configuration parameters can also be calibrated.

[0055] After obtaining the historical production data, the historical data of the configuration parameters can be obtained by performing simple calculations on some of the data in the historical production data. For example, when concerned about the repair time TTR and the mean time between failures TBF of a certain machine equipment, multiple failure occurrence times and corresponding multiple failure elimination times of the machine equipment can be obtained from the historical production data. Subtracting each failure elimination time from the corresponding failure occurrence time respectively gives multiple historical repair times TTR of the machine equipment, and subtracting each failure occurrence time from the previous failure elimination time respectively gives multiple historical mean time between failures TBF of the machine equipment. In other embodiments, the historical data of other configuration parameters (such as the waiting time at a certain machine equipment or manual workstation, the time of entering or leaving a certain machine equipment or manual workstation, etc.) can also be obtained.

[0056] Subsequently, based on the historical data of the configuration parameters obtained from the historical production data, the frequency distribution characteristics of the configuration parameters in the actual production process can be determined. In some embodiments, determining the frequency distribution characteristics of the configuration parameters in the actual production process may further include: fitting the historical data of the configuration parameters using different distribution functions; and determining the distribution function with the highest goodness of fit as the frequency distribution characteristic of the configuration parameters. Common distribution functions include, for example, binomial distribution function, Laplace distribution function, gamma distribution function, exponential distribution function, Poisson distribution function, normal distribution function, etc. The historical data of the configuration parameters can be respectively fitted with some of the common distribution functions, and the parameter values of the distribution functions are calculated during the fitting process. The distribution function with the highest goodness of fit can be determined, for example, through test methods such as K-S test, chi-square test.

[0057] After obtaining the frequency distribution characteristics of the configuration parameters in the actual production process, the frequency distribution characteristics of these configuration parameters, that is, the distribution function with the highest goodness of fit and the parameter values of the function, can be automatically or manually set in the calibrated simulation model through a modeling tool.

[0058] In some embodiments, method 100 further includes ( Figure 1(not shown): verifying the adjusted simulation model by using the frequency distribution characteristics of the configuration parameters; and further adjusting the range of the configuration parameters based on the verification results. To improve the robustness of the simulation model, after the wiring and configuration parameters of the simulation model are calibrated, the adjusted simulation model can also be verified. Techniques such as the Monte Carlo method can be used to generate multiple random values across the distribution function as the values of the configuration parameters according to the distribution function that the configuration parameters conform to, and the production line can be simulated and verified by using the simulation model respectively to obtain the verification results. The verification results can include the relationship between the change of the configuration parameters and the change of the simulation results. The verification results may indicate that the simulation model is sensitive to the change of a certain configuration parameter, that is, the change of a certain configuration parameter may cause a large change in the simulation results. In this case, the numerical range of the configuration parameter can be further adjusted to make the simulation model more robust.

[0059] By using the historical production data generated in the actual production process of the production line in the factory to check the consistency of the product processes of the simulation model of the production line, and using the inspection results to adjust the simulation model, the accuracy of the simulation model is improved, making it closer to the actual production process. Therefore, more accurate simulation results can be obtained, and the quality of factory digitization is improved. In addition, the method for calibrating the simulation model of the production line is applicable to various different simulation models constructed by using different modeling software, so it has wide generality and effectiveness.

[0060] In addition, in the prior art, usually by comparing the outputs of the simulation model and the actual production line under the same input and adjusting a certain configuration parameter in the simulation model according to experience to narrow the gap between the two outputs, it is not only time-consuming and laborious, but also the configuration parameters to be adjusted each time may be different. In the method for calibrating the simulation model of the production line in the present disclosure, the frequency distribution characteristics of the configuration parameters are obtained by using the historical production data generated in the actual production process, so that more accurate configuration parameters can be set in the simulation model, further improving the accuracy and effectiveness of the simulation model.

[0061] The following illustrates with reference to a specific embodiment Figure 1 the method for calibrating the simulation model of the production line shown. Figures 2 - 8 Taking a production line simulation model as an example, the method for calibrating the simulation model is specifically described.

[0062] Figure 2Fig. 200 shows an example of a production line simulation model according to an embodiment of the present disclosure. For simplicity, in this embodiment, the actual production line corresponding to the simulation model 200 is only used to produce one type of product. In the simulation model 200, the simulation modules 201 and 204 are referred to as sources, representing the starting positions in the production line, for example, the supply source of raw materials or the machines that produce components. The simulation modules 202, 203, 205, and 207 represent the workstations in the production line, where a process is performed on the raw materials or components at each workstation. The workstation can be a machine device or a manual work station. The simulation module 206 represents the assembly station in the production line, where the components are assembled. The assembly station can also be a machine device or a manual work station. The simulation module 208 is referred to as the exit, representing the ending position in the production line, for example, the position where the product leaves the production line. The connecting lines with arrows between the simulation modules represent the flow direction of the materials. As can be seen from the simulation model 200, the raw materials or components generated at the simulation module 201 are sequentially conveyed to the workstations 202 and 203, and the raw materials or components generated at the simulation module 204 are conveyed to the workstation 205. After the processes at the workstations 202, 203, and the workstation 205 respectively, the two generated components are conveyed to the assembly station 206, and then reach the simulation module 208 to leave the production line after the processes at the assembly station 206 and the workstation 207 respectively.

[0063] Now refer to Figure 3 , Figure 3 Fig. shows a method for calibrating the simulation model of the production line according to an embodiment of the present disclosure. First, in step 301 of method 300, the simulation model of the production line is obtained. In this embodiment, the simulation model of the production line is the production line simulation model 200 of the example shown in Figure 2 . Next, in step 302, the model wiring information is extracted from the simulation model. The model wiring information includes the identification information and the operation sequence of multiple simulation modules. In this embodiment, the wiring information is saved as a.csv file. The extracted model wiring information according to this embodiment is shown in Table 1 below. Figure 2 Fig.

[0064]

[0065]

[0066] Table 1

[0067] As can be seen from Table 1, taking each simulation module in the simulation model 200 as an object, the model wiring information includes information in four aspects: object name, object type, previous object, and subsequent object. Among them, the object name and object type represent the identification information of the simulation module, and the previous object and subsequent object represent the operation sequence of the simulation module. In other embodiments, the processing time or handling time at each workstation or assembly station may also be included in the model wiring information.

[0068] Next, the method 300 proceeds to step 303 to obtain multiple groups of sub-line information according to the model wiring information. Each group of sub-line information includes the identification information and operation sequence of each simulation module with a linear connection from the simulation module representing the starting position of the production line to the simulation module representing the ending position of the production line. In this embodiment, as shown in Table 1, the simulation model 200 has two sources 201 and 204, which are simulation modules representing the starting position of the production line. Starting from source 201 first, it is found from Table 1 that the subsequent object of source 201 is workstation 202. Then, continuing to search in Table 1, the subsequent object of workstation 202 is found to be workstation 203, the subsequent object of workstation 203 is assembly station 206, the subsequent object of assembly station 206 is workstation 207, and the subsequent object of workstation 207 is exit 208, which represents the ending position of the production line. In this way, a linear and non-branching process route representing each process from source 201 through workstations 202, 203, assembly station 206, and workstation 207 to exit 208 is obtained. In a similar manner, starting from the other source 204 of the simulation model 200 and searching for subsequent objects in Table 1, another linear and non-branching process route representing each process from source 204 through workstation 205, assembly station 206, and workstation 207 to exit 208 can be obtained. In this embodiment, two linear and non-branching sub-lines can be obtained, and the corresponding sub-line information is shown in Table 2 below. In this embodiment, the obtained sub-line information is also saved as a.csv file.

[0069] Time Sub - wire number Object name Object type 9 / 17 / 2019 18:00 1 Source 201 Source 9 / 17 / 2019 18:05 1 Workstation 202 Workstation 9 / 17 / 2019 18:10 1 Workstation 203 Workstation 9 / 17 / 2019 18:15 1 Assembly station 206 Assembly station 9 / 17 / 2019 18:20 1 Workstation 207 Workstation 9 / 17 / 2019 18:25 1 Exit 208 Exit 9 / 17 / 2019 18:30 2 Source 204 Source 9 / 17 / 2019 18:35 2 Workstation 205 Workstation 9 / 17 / 2019 18:40 2 Assembly station 206 Assembly station 9 / 17 / 2019 18:45 2 Workstation 207 Workstation 9 / 17 / 2019 18:50 2 Exit 208 Exit

[0070] Table 2

[0071] As can be seen from Table 2, for each of the two sub-lines, the time when the object is found, the sub-line number, the object name, and the object type are recorded from top to bottom in the order of finding the objects. The object name and object type represent the identification information of the simulation module, and the time when the object is found represents the operation sequence between the simulation modules on the process route represented by the sub-line.

[0072] Continue to refer to Figure 3, in the next step 304, a formal model is constructed based on the obtained multiple sets of sub-line information. In this embodiment, the formal model is a Petri net model, and process mining algorithms such as Inductive Miner and Alpha Miner can be used to implement the construction of the Petri net model. Before constructing the Petri net model, the file format of the file with multiple sets of sub-line information can be converted into the required file format. In this embodiment, the file with multiple sets of sub-line information in.csv file format is converted into a file in XES file format. Figure 4 shows a Petri net model constructed according to Figure 3 the production line simulation model of Figure 4 In the Petri net model 400 shown, circles represent places (P), boxes represent transitions (T), arrows represent directed arcs, and the "·" in the circle represents a token. Transitions represent the processing or handling of products at each process, places represent the states of products before and after each process, tokens represent products, and directed arcs represent that the tokens (products) in the places reach another state via transitions (e.g., processes). Combining Figure 2 and Figure 4 , transition 401 corresponds to the generation of raw materials or components at source 201, transition 402 corresponds to the process at workstation 202, transition 403 corresponds to the process at workstation 203, transition 404 corresponds to the generation of raw materials or components at source 204, transition 405 corresponds to the process at workstation 205, transition 406 corresponds to the process at assembly station 406, transition 407 corresponds to the process at workstation 407, and transition 408 corresponds to leaving the production line at exit 408.

[0073] Return Figure 3 , after steps 301 - 304 or in parallel with 301 - 304, step 305 is carried out to obtain the historical production data generated by the production line to be calibrated during the actual production process. The log file recording the historical production data of this production line can be obtained from the memories of different machine devices, manually recorded log records, the memories of controllers, etc. Next, in step 306, the historical production data is integrated and data-cleaned, and according to the product information, the cleaned historical production data is converted into data with products or their raw materials as objects, that is, the names of each process that the product or raw material has passed through during the actual production process and the start time and end time of each process. In this embodiment, since the exemplary production line is only used to produce one type of product, it is not necessary to record product information. A part of the cleaned historical production data according to this embodiment is shown in Table 3 below. In this embodiment, the obtained historical production data is also saved as a.csv file.

[0074]

[0075]

[0076] Table 3

[0077] Table 3 shows the entire process and corresponding timestamps from the source of raw materials or components to the completion of production through various processes and the departure from the production line during the actual production process of the product on the production line to be calibrated. In this embodiment, for ease of explanation, only 4 sets of production data examples are shown in Table 3, but in other embodiments, any number of sets of production data can be included.

[0078] Then, in step 307 of method 300, a consistency check is performed on the formal model and the historical production data to determine whether the product processes in the formal model are consistent with those reflected in the historical production data. Before the consistency check, the file format of the file storing the cleaned historical production data can be converted to the required file format. In this embodiment, the file storing the cleaned historical production data in.csv file format is converted to a file in XES file format. In this embodiment, the historical production data is Figure 4 replayed on the Petri net model to determine whether there are product processes not reflected in the historical production data in the Petri net model or whether the historical production data reflects product processes that do not exist in the Petri net model. Referring to Figure 4 and Table 3, taking example 1 of the production data as an example, the processes of the product in example 1 are re-executed on the Petri net model. It can be seen that when replaying on the Petri net model to transition 407 (corresponding to the process at workstation 207), the next process in example 1 is the manual inspection process, while there is no next process in the Petri net model, and the product directly leaves the production line at transition 408. Continuing to replay the processes of the product in examples 2 - 4, the same result can be obtained. Therefore, it can be determined that the product processes in this Petri net model are inconsistent with those reflected in the historical production data.

[0079] In step 308, the differences between the product processes in the formal model and the product processes reflected in the historical production data are determined. As described above, in this embodiment, after the processes of the product in Instances 1 - 4 are reproduced on the Petri net model, it can be determined that the product processes in this Petri net model are inconsistent with the product processes reflected in the historical production data. According to the reproduction results in Instances 1 - 4, it can also be determined that the difference between the product processes in the Petri net model and the product processes reflected in the historical production data is that there is an additional manual inspection process between transition 407 (corresponding to the process at workstation 207 in the simulation model) and transition 408 (corresponding to exit 208 in the simulation model) during the actual production process. In other embodiments, there may also be different situations where the differences between the processes in different instances and the processes in the formal model are different. Figure 5 shows Figure 4 the inspection result of the consistency check between the Petri net model of Figure 5 and the historical production data of the example. The dashed box in

[0080] Then, in step 309, based on the determined differences, the product processes that need to be added to and / or deleted from the simulation model are determined. In this embodiment, the manual inspection before the product leaves the production line belongs to a process that is necessary in the actual production process but missing in the simulation model. Therefore, it is automatically determined that the process of manual inspection needs to be added to Figure 2 the simulation model of

[0081] After that, in step 310, the model wiring information of the simulation model is updated. Specifically, taking the missing manual inspection process in the simulation model as the object, an object name (manual inspection), an object type (manual inspection), a previous object (workstation 207), and a subsequent object (exit 208) are generated and added to the model wiring information of the simulation model in Table 1. Table 4 below shows a part of the updated model wiring information, where the bold part represents the modified or added content.

[0082]

[0083]

[0084] Table 4

[0085] In step 311, a new simulation model is generated based on the updated model wiring information. In this embodiment, a new simulation model is generated through an automatic model generation algorithm. Figure 6 shows according toFigure 5 The production line simulation model adjusted according to the inspection results. As Figure 6 shown, a simulation module is added between the simulation module 207 and the simulation module 208 of the simulation model 600, which means that an additional manual inspection 209 process is added between the process at the workstation 207 and the exit 208. In other embodiments, the simulation model can also be adjusted by an engineer using a modeling tool. Thus, the process of calibrating the wiring of the simulation model of the production line using the historical production data of the production line is realized.

[0086] Back to Figure 3 , on the other hand, the historical production data of the production line integrated and cleaned in step 306 can also be used to calibrate the configuration parameters of the simulation modules in the simulation model. In this embodiment, the cleaned historical production data may also include the fault occurrence time and the fault elimination time of the equipment at each workstation or assembly station. In step 312, the historical data of the configuration parameters is obtained from the cleaned historical production data. In this embodiment, it is necessary to care about Figure 2 the repair time TTR and the mean time between failures TBF of the equipment at the workstation 202 in the simulation model. The multiple fault occurrence times and the corresponding multiple fault elimination times of the equipment at the workstation 202 during the actual production process can be obtained from the historical production data. Subtracting each fault elimination time from the corresponding fault occurrence time respectively gives the multiple historical repair times TTR of the equipment, and subtracting each fault occurrence time from the previous fault elimination time respectively gives the multiple historical mean time between failures TBF of the equipment. In other embodiments, the historical production data can be cleaned according to the concerned configuration parameters to obtain the historical data related to the configuration parameters.

[0087] Next, in step 313, the historical data of the configuration parameters is fitted using different distribution functions. In this embodiment, the multiple historical repair times TTR and the multiple historical mean time between failures TBF are processed to obtain the frequency histograms of the multiple historical repair times TTR and the multiple historical mean time between failures TBF respectively. Subsequently, the common distribution functions available for fitting are roughly determined according to the frequency histograms, and the parameter values of the distribution functions are calculated during the fitting process. In this embodiment, the distribution functions selected for the historical repair time TTR are the normal distribution function and the Poisson distribution function, and the distribution function selected for the historical mean time between failures TBF is the exponential distribution function. Fig. 7(a) shows the fitting result of using the normal distribution function to Figure 2 fit the repair time TTR of the equipment at the workstation 202 in Figure 2 , and Fig. 7(b) shows the fitting result of using the Poisson distribution function to Figure 8 fit the repair time TTR of the equipment at the workstation 202 in Figure 2The fitting result of the mean time between failures (MTBF) of the devices at the middle workstation 202.

[0088] Return to Figure 3 , in step 314, determine the distribution function with the highest goodness of fit as the frequency distribution characteristic of the configuration parameters. In this embodiment, the Kolmogorov-Smirnov (K-S) test method is used to test the fitting of the repair time to repair (TTR) with the normal distribution function and the Poisson distribution function, and it is found that the distribution function with the highest goodness of fit is the normal distribution function. Therefore, the normal distribution function is used as the frequency distribution characteristic of the repair time TTR. Additionally, since in step 313, only the MTBF was fitted with the exponential distribution function, there is no need to test it, and the exponential distribution function can be directly used as the frequency distribution characteristic of the MTBF.

[0089] Subsequently, in step 315, set the frequency distribution characteristics of the above configuration parameters in the calibrated simulation model of the wiring. In this embodiment, the setting of the frequency distribution characteristics of the configuration parameters can be performed by an automatic model generation algorithm. Thus, the process of calibrating the configuration parameters of the simulation model of the production line using the historical production data of the production line is achieved. Finally, in step 316, verify the adjusted simulation model using the frequency distribution characteristics of the configuration parameters, and further adjust the range of the configuration parameters based on the verification results. In this embodiment, the Monte Carlo method is used to perform the verification. Generate thousands of random values across the distribution functions as the test data for the repair time TTR and the MTBF respectively according to the frequency distribution characteristics (normal distribution) of the repair time TTR and the frequency distribution characteristics (exponential distribution) of the MTBF. Simulate the adjusted simulation model and determine the configuration parameters to which the simulation model is more sensitive, and further adjust the numerical range of the configuration parameters to increase the robustness of the simulation model.

[0090] By using the historical production data generated during the actual production process of the production line in the factory to check the consistency of the product processes of the simulation model of the production line, and using the inspection results to adjust the simulation model, the accuracy of the simulation model is improved, making it closer to the actual production process. Therefore, more accurate simulation results can be obtained, improving the quality of factory digitization. In addition, the method for calibrating the simulation model of the production line is applicable to various different simulation models constructed using different modeling software, so it has broad generality and effectiveness.

[0091] In addition, by using the historical production data generated during the actual production process to obtain the frequency distribution characteristics of the configuration parameters, more accurate configuration parameters can be set in the simulation model, further improving the accuracy and effectiveness of the simulation model.

[0092] Figure 9 Shows according toFigure 3 Exemplary architecture of a system for calibrating a simulation model of a production line in an embodiment. In the system architecture 900, it mainly includes three parts: modeling software 901, calibration software 902, and historical production log 903. The calibration software 902 executes Figure 3 A method for calibrating a simulation model of a production line. The model information processing module 9021 in the calibration software 902 is used to obtain the simulation model 9011 of the production line from the modeling software 901, extract the model wiring information from the simulation model and split the model wiring information into multiple groups of sub-line information, and provide the multiple groups of sub-line information to the wiring and parameter calibration module 9025. In addition, the historical production data preprocessing module 9024 in the calibration software 902 obtains the historical production data of the production line during the actual production process from the historical production log 903, and performs preprocessing such as integration and cleaning on it, and provides the preprocessed historical production data to the wiring and parameter calibration module 9025. The historical production log 903 can be obtained from the manual record log 9031, the database 9032 at each device, and the manufacturing execution system MES 9033.

[0093] On the one hand, the wiring and parameter calibration module 9025 constructs a formal model based on the obtained multiple groups of sub-line information, and performs consistency checks on the formal model and the preprocessed historical production data to achieve calibration of the wiring of the simulation model. On the other hand, the wiring and parameter calibration module 9025 also obtains the historical data of the configuration parameters from the preprocessed historical production data, and determines the frequency distribution characteristics of the configuration parameters during the actual production process. The wiring and parameter calibration module 9025 provides the consistency check result and the frequency distribution characteristics of the configuration parameters to the automatic model generation module 9022, thereby generating a simulation model calibrated for wiring and parameters. The model verification module 9023 is used to verify the calibrated simulation model.

[0094] Figure 10 Shows an apparatus for calibrating a simulation model of a production line according to an embodiment of the present disclosure. Refer to Figure 10, the apparatus 1000 includes a simulation model acquisition unit 1001, a simulation model conversion unit 1002, a production data acquisition unit 1003, a consistency check unit 1004, and a simulation model adjustment unit 1005. The simulation model acquisition unit is configured to obtain a simulation model of a production line, the simulation model being used to simulate the production process of the production line and including a plurality of simulation modules corresponding to the respective components of the production line, and the simulation modules being provided with corresponding configuration parameters. The simulation model conversion unit 1002 is configured to convert the simulation model into a formal model, the formal model being used to formally describe the simulation model. The production data acquisition unit 1003 is configured to obtain historical production data generated during the actual production process of the production line. The consistency check unit 1004 is configured to perform a consistency check on the formal model and the historical production data to determine whether the product processes in the formal model and the product processes

[0095] embodied in the historical production data are consistent. The simulation model adjustment unit 1005 is configured to adjust the simulation model when it is determined that the product processes in the formal model and the product processes embodied in the historical production data are inconsistent. Figure 10 Each unit in can be implemented by software, hardware (such as integrated circuits, FPGAs, etc.), or a combination of software and hardware.

[0096] In some embodiments, the simulation model adjustment unit 1005 is further configured to: determine the difference between the product processes in the formal model and the product processes embodied in the historical production data; and determine the product processes that need to be added to and / or deleted from the simulation model based on the difference; and adjust the simulation model based on the determined product processes to be added and / or deleted.

[0097] In some embodiments, the plurality of simulation modules are connected in a network in the simulation model, and the simulation model conversion unit 1002 is further configured to: extract model wiring information from the simulation model, the model wiring information including identification information and operation sequences of the plurality of simulation modules; split the model wiring information into multiple groups of sub-wiring information, each group of sub-wiring information including the identification information and operation sequences of the simulation modules of a linear connection from the simulation module representing the starting position of the production line to the simulation module representing the ending position of the production line; and construct a formal model according to the multiple groups of sub-wiring information.

[0098] In some embodiments, the consistency check unit 1004 is further configured to: replay the historical production data on the formal model, the replay being used to determine whether there are product processes in the formal model that are not embodied in the historical production data or whether the historical production data embodies product processes that do not exist in the formal model.

[0099] In some embodiments, the apparatus 1000 further includes a historical data acquisition unit (Figure 10 (not shown in the figure) and is configured to obtain historical data of configuration parameters from historical production data.

[0100] In some embodiments, the apparatus 1000 further includes a distribution feature determination unit ( Figure 10 not shown in the figure) and is configured to determine the frequency distribution feature of the configuration parameters in the actual production process based on the historical data of the configuration parameters.

[0101] In some embodiments, the apparatus 1000 further includes a configuration parameter setting unit ( Figure 10 not shown in the figure) and is configured to set the frequency distribution feature of the configuration parameters in the adjusted simulation model.

[0102] In some embodiments, the distribution feature determination unit is further configured to: fit the historical data of the configuration parameters with different distribution functions; and determine the distribution function with the highest goodness of fit as the frequency distribution feature of the configuration parameters.

[0103] In some embodiments, the apparatus 1000 further includes a configuration parameter verification unit ( Figure 10 not shown in the figure) and is configured to: verify the adjusted simulation model by using the frequency distribution feature of the configuration parameters;

[0104] and further adjust the range of the configuration parameters based on the verification result.

[0105] In some embodiments, the formal model is a Petri net model.

[0106] In some embodiments, the apparatus 1000 further includes a production data processing unit ( Figure 10 not shown in the figure) and is configured to preprocess the historical production data before performing consistency check on the formal model and the historical production data.

[0107] Figure 11 The block diagram of a computing device 1100 for detecting mechanical equipment parts according to an embodiment of the present disclosure is shown. As Figure 11 can be seen from the figure, the computing device 1100 for detecting mechanical equipment parts includes a processor 1101 and a memory 1102 coupled to the processor 1101. The memory 1102 is used to store computer-executable instructions, and when the computer-executable instructions are executed, the processor 1101 executes the method in the above embodiments.

[0108] In addition, alternatively, the above method can be implemented by a computer-readable storage medium. A computer-readable program instruction for executing various embodiments of the present disclosure is uploaded on the computer-readable storage medium. The computer-readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as a punched card or raised structures in grooves storing instructions thereon, and any suitable combination of the above. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0109] Therefore, in another embodiment, the present disclosure proposes a computer-readable storage medium having computer-executable instructions stored thereon for executing the methods in various embodiments of the present disclosure.

[0110] In another embodiment, the present disclosure proposes a computer program product tangibly stored on a computer-readable storage medium and including computer-executable instructions that, when executed, cause at least one processor to execute the methods in various embodiments of the present disclosure.

[0111] Example methods.

[0112] Generally, the various example embodiments of the present disclosure can be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software that can be executed by a controller, a microprocessor, or other computing devices. When aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0113] The computer-readable program instructions or computer program products for implementing the various embodiments of the present disclosure can also be stored in the cloud. When needed, users can access the computer-readable program instructions stored in the cloud for implementing an embodiment of the present disclosure through the mobile Internet, fixed network, or other networks, so as to implement the technical solutions disclosed according to the various embodiments of the present disclosure.

[0114] Although the embodiments of the present disclosure have been described with reference to several specific embodiments, it should be understood that the embodiments of the present disclosure are not limited to the specific embodiments disclosed. The embodiments of the present disclosure are intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims

1. A method for calibrating a simulation model of a production line, comprising: obtaining a simulation model of the production line, the simulation model being used to simulate the production process of the production line and including a plurality of simulation modules corresponding to the respective components of the production line, and the simulation modules being provided with corresponding configuration parameters; converting the simulation model into a formal model, the formal model being used to formally describe the simulation model; obtaining historical production data generated during the actual production process of the production line; performing a consistency check on the formal model and the historical production data to determine whether the product processes in the formal model are consistent with the product processes reflected in the historical production data; and when it is determined that the product processes in the formal model are not consistent with the product processes reflected in the historical production data, adjusting the simulation model; wherein, when it is determined that the product processes in the formal model are not consistent with the product processes reflected in the historical production data, adjusting the simulation model includes: determining the difference between the product processes in the formal model and the product processes reflected in the historical production data; determining, based on the difference, the product processes that need to be added to and / or deleted from the simulation model; and adjusting the simulation model based on the determined product processes that need to be added and / or deleted.

2. The method according to claim 1, wherein, the plurality of simulation modules are connected in a network in the simulation model, and converting the simulation model into a formal model includes: extracting model wiring information from the simulation model, the model wiring information including identification information and operation sequences of the plurality of simulation modules; obtaining multiple sets of sub-line information according to the model wiring information, each set of sub-line information including identification information and operation sequences of the respective simulation modules of a linear connection from the simulation module representing the starting position of the production line to the simulation module representing the ending position of the production line; and constructing the formal model according to the multiple sets of sub-line information.

3. The method according to claim 1, wherein, performing a consistency check on the formal model and the historical production data further includes: replaying the historical production data on the formal model, the replaying being used to determine whether there are product processes in the formal model that are not reflected in the historical production data or whether the historical production data reflects product processes that do not exist in the formal model.

4. The method according to claim 1, the method further comprising: obtaining historical data of the configuration parameters from the historical production data; determining the frequency distribution characteristics of the configuration parameters during the actual production process based on the historical data of the configuration parameters; and setting the frequency distribution characteristics of the configuration parameters in the adjusted simulation model.

5. The method according to claim 4, wherein, determining the frequency distribution characteristics of the configuration parameters during the actual production process based on the historical data of the configuration parameters further includes: Fitting the historical data of the configuration parameters using different distribution functions; and Determining the distribution function with the highest goodness of fit as the frequency distribution characteristic of the configuration parameter.

6. The method according to claim 5, further comprising: Validating the adjusted simulation model using the frequency distribution characteristic of the configuration parameter; and Further adjusting the range of the configuration parameter based on the validation result.

7. The method according to claim 1, wherein, The formal model is a Petri net model.

8. The method according to claim 1, further comprising: Preprocessing the historical production data before performing consistency checking on the formal model and the historical production data.

9. An apparatus for calibrating a simulation model of a production line, comprising: A simulation model acquisition unit configured to obtain a simulation model of a production line, the simulation model being used to simulate the production process of the production line and including a plurality of simulation modules corresponding to the respective components of the production line, and the simulation modules being provided with corresponding configuration parameters; A simulation model conversion unit configured to convert the simulation model into a formal model, the formal model being used to formally describe the simulation model; A production data acquisition unit configured to obtain historical production data generated during the actual production process of the production line; A consistency checking unit configured to perform consistency checking on the formal model and the historical production data to determine whether the product processes in the formal model are consistent with the product processes reflected in the historical production data; and A simulation model adjustment unit configured to adjust the simulation model when it is determined that the product processes in the formal model are not consistent with the product processes reflected in the historical production data; wherein, the simulation model adjustment unit is further configured to: Determine the difference between the product processes in the formal model and the product processes reflected in the historical production data; and Based on the difference, determine the product processes that need to be added to and / or deleted from the simulation model; and Adjust the simulation model based on the determined product processes that need to be added and / or deleted.

10. The apparatus according to claim 9, wherein, The plurality of simulation modules are connected in a network in the simulation model, and the simulation model conversion unit is further configured to: Extract model wiring information from the simulation model, the model wiring information including identification information and operation sequence of the plurality of simulation modules; Split the model wiring information into multiple groups of sub-line information, each group of sub-line information including the identification information and operation sequence of the simulation modules of the linear connection from the simulation module representing the starting position of the production line to the simulation module representing the ending position of the production line; and Construct the formal model according to the multiple groups of sub-line information.

11. The apparatus according to claim 9, wherein, The consistency checking unit is further configured to: Replay the historical production data on the formal model, where the replay is used to determine whether there are product processes not reflected in the historical production data in the formal model or whether the historical production data reflects product processes not existing in the formal model.

12. The apparatus according to claim 9, further comprises: a historical data acquisition unit configured to obtain historical data of the configuration parameters from the historical production data; a distribution characteristic determination unit configured to determine the frequency distribution characteristic of the configuration parameters in the actual production process based on the historical data of the configuration parameters; and a configuration parameter setting unit configured to set the frequency distribution characteristic of the configuration parameters in the adjusted simulation model.

13. The apparatus according to claim 12, wherein the distribution characteristic determination unit is further configured to: fit the historical data of the configuration parameters using different distribution functions; and determine the distribution function with the highest goodness of fit as the frequency distribution characteristic of the configuration parameters.

14. The apparatus according to claim 12, further comprises a configuration parameter verification unit configured to: verify the adjusted simulation model using the frequency distribution characteristic of the configuration parameters; and further adjust the range of the configuration parameters based on the verification result.

15. The apparatus according to claim 9, wherein the formal model is a Petri net model.

16. The apparatus according to claim 9, further comprises a production data processing unit configured to: preprocess the historical production data before performing a consistency check on the formal model and the historical production data.

17. A computing device, comprises: a processor; and a memory for storing computer-executable instructions, which when executed cause the processor to execute the method according to any one of claims 1-8.

18. A computer-readable storage medium having computer-executable instructions stored thereon, the computer-executable instructions for executing the method according to any one of claims 1-8.

19. A computer program product tangibly stored on a computer-readable storage medium and comprising computer-executable instructions, the computer-executable instructions when executed causing at least one processor to execute the method according to any one of claims 1-8.

Images