Monitoring operability of production system
By using mapping engines and declarative constraints in the production system to verify the consistency of production data, generate material flow simulation models and compare them with measurement data, the heterogeneous data source integration and verification problems are solved, and efficient operability monitoring and production KPI optimization of the production system are achieved.
Patent Information
- Application Number
- CN202280100587.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2022-09-29
- Publication Date
- 2025-05-13
AI Technical Summary
When generating and synchronizing simulation models of production systems, the prior art faces difficulties in integrating, converting and verifying multiple heterogeneous data sources, which makes it difficult to detect inconsistency problems and affects the accuracy of simulation results.
Production-related data is input through the input unit, the data is mapped to the instance data of the knowledge graph using the mapping engine, and the consistency and integrity of the data are verified using declarative constraints, a material flow simulation model is generated, and a simulated production log is automatically generated, and a second verification unit is compared with the measured production log to output operability monitoring results.
It realizes unified representation and automated verification of data, reduces the workload of simulation model generation and verification, can more easily detect data inconsistencies, generate accurate simulation models, and thus effectively monitor the operability of the production system and optimize production KPIs.
Smart Images
Figure CN119998741A_ABST
Abstract
Description
[0001] The present invention relates to an apparatus and a computer-implemented method for monitoring the operability of a production system, as well as a computer program product.
[0002] When used during the operational phase of a production system, logistics simulation provides great benefits such as decision support systems and / or operability monitoring systems. Ideally, computer simulation models can be generated from various data sources in an enterprise through some kind of automated processing pipeline. However, the generation and synchronization of simulation models are usually quite cumbersome because many different and heterogeneous data sources from the production system need to be considered. Typically, these original data sources contain unnecessary, unupdated, inconsistent information and data elements, and therefore need to be integrated, converted and / or verified before being used for simulation model generation. In particular, verification and / or consistency checks usually take time. Typically, inconsistencies are only detected one by one during the modeling process, which requires frequent communication meetings between simulation experts and factory experts and development iterations of simulation models. In the worst case, inconsistencies are detected during the productive use of the simulation or even not detected at all, resulting in erroneous simulation results.
[0003] It is therefore an object of the present invention to improve data validation of a production system for monitoring the operability of the production system.
[0004] This object is achieved by the features of the independent claim. The dependent claims contain further developments of the invention.
[0005] According to a first aspect, the present invention provides an apparatus for monitoring the operability of a production system, the apparatus comprising:
[0006] - an input unit configured to input production-related data of the production system,
[0007] a mapping engine configured to map the production-related data to instance data of the first knowledge graph according to a given mapping definition,
[0008] - a first verification unit, configured to verify the consistency and / or integrity of the instance data through declarative constraints and output a first verification result,
[0009] a simulator configured to generate a computer-implemented material flow simulation model of the production system based on the instance data and depending on the first validation result,
[0010] - a generator configured to generate a simulated production log using the material flow simulation model,
[0011] - a second verification unit configured to verify the simulated production log against the measured production log of the production system and output a second verification result,
[0012] and
[0013] - an output unit configured to output a second verification result for monitoring operability of the production system.
[0014] According to a second aspect, the present invention provides a computer-implemented method for monitoring the operability of a production system, the method comprising the following steps:
[0015] - Input production-related data into the production system,
[0016] - mapping the production-related data to instance data of the first knowledge graph according to a given mapping definition,
[0017] - verifying the consistency and / or integrity of the instance data through declarative constraints and outputting a first verification result,
[0018] - generating a computer-implemented material flow simulation model of the production system based on the example data and in accordance with the first validation results,
[0019] - Generate simulated production logs using the logistics simulation model,
[0020] - verifying the simulated production log against the measured production log of the production system and outputting a second verification result,
[0021] and
[0022] - outputting the second verification result to monitor the operability of the production system.
[0023] Therefore, the present invention provides a comprehensive use of explicit representations of simulation-related data in a unified and reusable knowledge graph as the basis for a constraint catalog that allows automatic use of, for example, predefined SHACL verification constraints to plant instance data of the knowledge graph. In addition, after verifying the production-related data, a simulation model can be automatically generated. Then, a scheme based on the plant data instance and further application of predefined SHACL verification constraints provides a comparison of real production data with simulated data for checking the operability of the production system. By verifying the input data and generating a simulation model based on the verification results, simulation can be used to generate simulated production logs, which can then be compared with measured production logs, allowing the operability of the production system to be monitored.
[0024] Therefore, the advantage of the proposed invention is that the effort of raw production-related data required for verifying plant simulation models during operation, and thus their generation and application, is reduced by using declarative constraints (e.g. SHACL constraints) to check data consistency of raw data required for material flow models. Data inconsistencies can be easily detected. Therefore, material flow simulations can be generated more easily to compare simulation data with measured data from production. This allows efficient monitoring of production systems during operation, resulting in more benefits, such as optimizing production KPIs, such as throughput, utilization, efficiency, etc.
[0025] Additionally, by using a knowledge graph or graph data model as a common representation, the effort for onboarding new data sources or extending the data model with additional concepts is minimized, i.e., it is less time-consuming, less error-prone, more maintainable, and therefore more cost-effective.
[0026] According to an embodiment, the apparatus may further include a storage unit configured to store the simulation log and / or the measurement log in the second knowledge graph.
[0027] This allows for a direct comparison of simulation data logs with measurement data logs.The storage unit may also be configured to map or convert the simulation logs / log files and / or the measurement logs / log files into instance log data of the second knowledge graph.
[0028] According to another embodiment of the apparatus, the second verification unit may be configured to verify the simulated production log against the measured production log by means of the declarative constraints.
[0029] Declarative constraints can be understood as providing predefined rules for checking corresponding data. Therefore, data checking and / or comparison can be automated.
[0030] According to another embodiment of the present invention, the declarative constraints may be based on the Shape Constraint Language (SHACL).
[0031] According to another embodiment of the present invention, the declarative constraints may be based on the SPARQL query language.
[0032] According to another embodiment of the present invention, the production-related data may include a production order, a process list, a resource list and / or a production event.
[0033] According to another embodiment of the present invention, the production-related data may be checked based on the first verification result.
[0034] The first verification result provides information about the consistency and / or completeness of the production-related data. Thus, the first verification result can, for example, summarize violations within the instance data. In the event of violations, the original production-related data can be checked and, for example, reloaded or requested again. The verification result can, for example, be exported as a report to an expert to inform about problems in the source data.
[0035] Furthermore, protection is claimed for a computer program product (a non-transitory computer-readable storage medium having instructions which, when executed by a processor, perform actions), the computer program product having program instructions for executing the aforementioned method according to an embodiment of the present invention, wherein the method according to an embodiment of the present invention can be executed each time with the aid of the computer program product.
[0036] The present invention will be explained in more detail by referring to the accompanying drawings.
[0037] Figure 1 An embodiment of an apparatus for monitoring operability of a production system is shown; and
[0038] Figure 2 An embodiment of a computer-implemented method for monitoring operability of a production system is shown.
[0039] Identical parts in different figures are marked with the same reference numerals.
[0040] Figure 1 An exemplary embodiment of an apparatus 100 for monitoring the operability of a production system SYS is shown. The production system SYS may be, for example, an automated plant for producing or manufacturing products. The apparatus 100 may include software and / or hardware components. In particular, the apparatus 100 may include at least one processor. The apparatus 100 is preferably coupled to the production system SYS, for example, to exchange data for monitoring the production system SYS. In particular, the apparatus 100 is configured to generate and run a computer-aided simulation of the production system, for example in parallel with the operation of the production system, to monitor the operability of the production system SYS, such as productivity, efficiency, performance and / or functionality, by comparing the simulated production log with the measured production log.
[0041] The device 100 includes components for monitoring production-related data of the production system to allow conclusions to be drawn about the operability of the production system SYS. For example, the device 100 may provide information about the performance of the production line, the production progress, the production status, etc. based on the production log of the production system. Such information gives an insight into the operability of the production system, i.e. whether the production system is working as specified.
[0042] The apparatus 100 comprises an input unit 101, a mapping engine 102, a first verification unit 103, a simulator 104, a generator 105, a second verification unit 106 and an output unit 107. Furthermore, the apparatus 100 can comprise a storage unit 108. All these units / components are preferably connected to each other to exchange data.
[0043] The input unit 101 is configured to input production-related data PD of the production system SYS. The production-related data may be raw data from different and / or heterogeneous data sources related to the production system SYS. The data source may be, for example, an enterprise resource planning (ERP) system, a manufacturing execution system (MES), file-based data (Excel, CSV, ...) or other engineering tools (CAD, layout designer, ...). The production-related data PD may include production orders, process lists, resource lists and / or production events. The production-related data PD is preferably provided in a machine-readable format, such as Excel, CSV files, etc. The production-related data PD is provided to a mapping engine 102.
[0044] The mapping engine 102 is configured to map the production-related data PD to the instance data KGD of the first knowledge graph model according to a given mapping definition. Mapping the production-related data PD to the instance data KGD may specifically involve selecting a required portion of the production-related data PD and / or converting the production-related data PD to a data format required by the knowledge graph. The mapping definition includes rules for mapping data to the knowledge graph according to a predefined schema.
[0045] In other words, the mapping engine maps raw data to graph instance data (e.g., RDF) aligned with the reusable schema of the knowledge graph model. For the mapping engine 102, existing technologies such as OpenRefine, OntoRefine, and RMLMapper can be used. A mapping definition can be provided in a descriptive manner for each data source according to the selected technology of the mapping engine 102 (e.g., General Refinement Expression Language (GREL) or RDF Mapping Language (RML)), which defines how to map raw data to graph instance data.
[0046] The instance data KGD may be sent to the graph database DB and stored in the graph database DB. The instance data KGD may then be retrieved from the graph database DB by other units. Alternatively, the instance data KGD may be provided to corresponding other units.
[0047] The first verification unit 103 is used to verify the consistency and / or integrity of the instance data KGD through the declarative constraint DC and output a first verification result VAL1. The declarative constraint DC may be based on the Shape Constraint Language (SHACL) or the SPARQL query language, for example.
[0048] The first verification unit 103 verifies the instance data KGD in the graph database by performing consistency and integrity checks. The first verification unit 103 is preferably supported by a directory of verification rules, constraints and / or conditions. Therefore, by applying such verification rules, constraints and / or conditions, the consistency and integrity of the instance data KGD can be checked. These verification constraints can be provided by means of, for example, SPARQL queries or SHACL shapes. The catalog can contain a set of default verification rules that are generally applicable to each use case and can be a set of user-provided rules and application scenario / customer-specific constraints.
[0049] The first verification result VAL1 may be output, for example, for checking the production-related data PD.The first verification result VAL1 may be exported, for example, as part of a report comprising information about the consistency and / or completeness of the input data PD.
[0050] Depending on the verification result VAL1, the instance data KGD may be provided to the simulator 104. For example, if the verification result VAL1 does not provide a violation of the consistency and / or integrity of the instance data KGD within a given uncertainty range, the instance data KGD may be retrieved by the simulator 104.
[0051] The simulator 104 is configured to generate a computer-implemented material flow simulation model SM of the production system SYS based on the instance data KGD and depending on the first verification result VAL1. Thus, if the production data are correct and consistent within a given uncertainty range, the simulator 104 automatically generates the simulation model SM using the master data (e.g., machines, orders, products) from the graphical database DB.
[0052] Based on the generated logistics simulation model SM, the generator 105 is configured to generate a simulated production log / log file SLOG. Preferably, the generator creates a simulated production log SLOG by using the generated material flow simulation model SM and a subset of a given production order and / or other dynamically changing data elements (e.g., the availability of workers and machines and the current status of production). The simulation log SLOG typically includes the start and end time of the production process (process steps), the orders and products to which they belong, and the resources on which the process is executed. Sometimes more information is added, such as the personnel involved or additional tools and equipment.
[0053] The simulated production log / log file SLOG and the corresponding measurement log / log file MLOG may then be uploaded to the graph database DB. The measured logs MLOG may be provided, for example, by sensors of the production system SYS. Preferably, the measured production log MLOG corresponds to the simulated production log SLOG, for example, in the time range of the production process, etc. In particular, the storage unit 108 is configured to store the simulation log SLOG and / or the measurement log MLG in the second knowledge graph. Therefore, the storage unit 108 may be configured as a mapping engine for mapping the simulation log SLOG and / or the measurement log MLOG to graph data of the second knowledge graph.
[0054] Then, the second verification unit 106 verifies the simulated production log SLOG against the measured production log MLOG by means of declarative constraints. Preferably, the simulated production log SLOG is verified against the measured production log MLOG by means of SHACL or SPARQL constraints applied to the second knowledge graph.
[0055] The second verification unit 106 provides a second verification result VAL2, which includes information about the deviation of the measured production log MLOG from the simulated production log SLOG. For example, the second verification result VAL2 may include information about the absence of deviations between the simulated and measured production logs, indicating full operability of the production system SYS. Alternatively, the second verification result may include information about a specific deviation of the measured production log MLOG from the simulated production log, indicating a possible production failure or problem.
[0056] The second validation result VAL2 is provided by the output unit 107 to the user and / or the production system SYS and can be used to monitor the operability of the production system SYS. For example, based on the second validation result VAL2, the production can be continued or at least partially stopped or interrupted. Therefore, the second validation result VAL2 can be provided to the control unit of the production system SYS for controlling the production system SYS according to the second validation result VAL2. For example, in the event of an inconsistency between the measured production log MLOG and the simulated production log SLOG, the production system SYS or the affected part of the production system SYS can be stopped or slowed down.
[0057] Preferably, the device 100 can process the production-related data as described above in iterative steps of a predetermined time span. This allows continuous monitoring of the production system SYS.
[0058] Figure 2 An exemplary example of a computer-implemented method for monitoring the operability of a production system is shown. The method can be performed, for example, by means of Figure 1 The described device is used to perform.
[0059] The method comprises the following method steps:
[0060] In a first step S1 , production-relevant data of the production system can be input, for example read in from a data source connected to the production system.
[0061] In the next step S2, the production-related data is mapped to the instance data of the first knowledge graph according to a given mapping definition. Thus, the production-related data is assigned to the knowledge graph according to the predefined mapping definition.
[0062] In a next step S3 , the consistency and / or completeness of the instance data is verified by means of declarative constraints (eg SHACL or SPARQL constraints), and a first verification result is provided.
[0063] In case of a positive first verification result (ie consistent and valid instance data according to the first verification), in a next step S4 a computer-implemented material flow simulation model of the production system may be generated based on the instance data.
[0064] In case of a negative first verification result (ie, for example, inconsistent instance data), the first verification result is provided (step 13). It is then possible to further check the instance data / production-related data and, for example, request new / updated production-related data and repeat steps S1 to S3.
[0065] In the next step S5, in case of a positive first verification result, a simulated production log is generated using the material flow simulation model. The simulated production log can then be stored in the second knowledge graph. In addition, the measured production log from the production system can be retrieved and also stored in the second knowledge graph.
[0066] In a next step S6 , the simulated production log is validated against the measured production log using declarative constraints (eg SHACL or SPARQL constraints), and a second validation result is provided.
[0067] In the next step S7, a second verification result is provided for monitoring the operability of the production system.
[0068] All described and / or illustrated features as shown in the exemplary embodiments can be advantageously combined within the scope of the invention.
[0069] While the present invention has been described in detail with reference to preferred embodiments, it should be understood that the invention is not limited to the disclosed examples and that numerous additional modifications and variations may be made thereto by those skilled in the art without departing from the scope of the invention.
Claims
1. An apparatus (100) for monitoring the operability of a production system (SYS), the apparatus comprising: - an input unit (101) configured to input production-related data (PD) of said production system (SYS), - a mapping engine (102), configured to map the production-related data to instance data (KGD) of a first knowledge graph according to a given mapping definition, - a first verification unit (103), configured to verify the consistency and / or integrity of the instance data (KGD) through a declarative constraint (DC) and output a first verification result (VAL1); a simulator (104) configured to generate a computer-implemented material flow simulation model (SM) of the production system based on the example data (KGD) and in accordance with the first validation result (VAL1), - a generator (105) configured to generate a simulated production log (SLOG) using the material flow simulation model, - a second verification unit (106) configured to verify the simulated production log (SLOG) against the measured production log (MLOG) of the production system and output a second verification result (VAL2), and - an output unit (107) configured to output the second verification result (VAL2) to monitor the operability of the production system (SYS).
2. The apparatus according to claim 1, further comprising a storage unit (108) configured to store the simulation log and / or the measurement log in a second knowledge graph.
3. The device according to claim 2, wherein: The second verification unit (106) is configured to verify the simulated production log against the measured production log by means of declarative constraints.
4. A device according to any one of the preceding claims, wherein: The declarative constraints (DC) are based on the shape constraint language.
5. A device according to any one of the preceding claims, wherein: The declarative constraints (DC) are based on the SPARQL query language.
6. Apparatus according to any one of the preceding claims, wherein: The production related data (PD) includes a production order, a process list, a resource list and / or a production event.
7. Apparatus according to any one of the preceding claims, wherein: The production-related data (PD) is checked according to the first verification result (VAL1).
8. A computer-implemented method for monitoring operability of a production system, the method comprising the steps of: - input (S1) production-related data of said production system, - mapping (S2) said production-related data to instance data of the first knowledge graph according to a given mapping definition, - verifying (S3) the consistency and / or completeness of the instance data through declarative constraints and outputting a first verification result, - generating (S4) a computer-implemented material flow simulation model of the production system based on the example data and in accordance with the first validation result, - generating (S5) a simulated production log using the material flow simulation model, - verifying (S6) the simulated production log against the measured production log of the production system and outputting a second verification result, and - outputting (S7) the second verification result to monitor the operability of the production system.
9. A computer program product directly loadable into the internal memory of a digital computer, comprising software code portions for performing the method steps of claim 8 when said computer program product is run on a computer.