DESC:FIELD OF DISCLOSURE
The present disclosure relates to simulation modeling in manufacturing systems, and more particularly to an ontology-based context extraction and scenario generation system and method for manufacturing simulation.
BACKGROUND
The field of manufacturing simulation has become increasingly important in optimizing production processes, reducing costs, and improving overall efficiency in industrial settings. Simulation models allow manufacturers to analyze and predict the behavior of complex systems, test various scenarios, and make informed decisions without disrupting actual operations.
Traditional simulation models used in manufacturing shop floor operations often rely on static data and lack the ability to adapt to real-time changes and contextual variations. These models typically struggle to accurately reflect the dynamic nature of manufacturing environments, leading to inefficiencies and suboptimal decision-making. Existing simulation methods have attempted to incorporate adaptability through periodic updates, but these approaches often fail to provide a comprehensive, real-time understanding due to the complexity of the models and the significant time required to run and process updates.
Recent advancements in digital twin technology and advanced data analytics have shown promise in enhancing simulation models. However, these solutions often require significant computational resources and may not be suitable for complex simulation models. Moreover, they typically focus on specific aspects of the manufacturing process rather than providing a holistic view that encompasses all relevant entities and their interactions. The lack of a structured framework to represent the intricate relationships between various manufacturing entities further hampers the effectiveness of these simulations.
Therefore, there exists a need for a technical solution that solves the aforementioned problems of conventional systems and methods for scenario generation in manufacturing simulation.
SUMMARY
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.
In an aspect of the present disclosure, a system for ontology-based context extraction and scenario generation in manufacturing simulation is disclosed. The system includes one or more manufacturing assets and a data processing apparatus comprising processing circuitry coupled to the one or more manufacturing assets. The processing circuitry is configured to receive real-time operational data from the one or more manufacturing assets. The processing circuitry generates an asset ontology for each manufacturing asset based on the received operational data. The asset ontology captures specific attributes, behaviors, and relationships of the manufacturing asset. The processing circuitry integrates the asset ontologies into a combined upper level ontology. The combined upper level ontology provides a holistic view of the entire manufacturing system. The processing circuitry extracts relevant context from the combined upper level ontology based on a simulation objective. The processing circuitry generates simulation scenarios based on the extracted context. The processing circuitry executes a simulation model using the generated scenarios. The processing circuitry displays simulation results through a simulator.
In some aspects of the present disclosure, the processing circuitry transforms the received operational data into probabilistic distributions. The processing circuitry updates the asset ontologies and combined upper level ontology with the probabilistic distributions.
In some aspects of the present disclosure, the processing circuitry executes SPARQL queries on the combined upper level ontology to extract the relevant context.
In some aspects of the present disclosure, the processing circuitry identifies random variables directly influencing outputs of a specific manufacturing asset based on the simulation objective. The processing circuitry substitutes non-critical variables with averaged values from their respective distributions.
In some aspects of the present disclosure, the processing circuitry continuously updates the combined upper level ontology with real-time data from one of, digital twins or Manufacturing Execution Systems (MES).
In some aspects of the present disclosure, the system further includes a processing unit configured to receive the real-time operational data from the one or more manufacturing assets. The processing unit preprocesses the real-time operational data. The processing unit transmits the preprocessed operational data to the data processing apparatus.
In some aspects of the present disclosure, the processing circuitry receives a simulation run trigger. The processing circuitry identifies a target individual for the simulation. The processing circuitry identifies relationships between the target individual and other individuals in the manufacturing system. The processing circuitry determines whether the identified individuals are related to the simulation objective. The processing circuitry classifies related individuals by class type. The processing circuitry calculates an impact of each related individual on the simulation run time. The processing circuitry sets variables for simulation based on the calculated impact. Variables are set as random variables for individuals with high impact and set to mean values for individuals with low impact or not related to the simulation objective.
In another aspect of the present disclosure, a method for ontology-based context extraction and scenario generation in manufacturing simulation is disclosed. The method includes receiving, by processing circuitry of a data processing apparatus, real-time operational data from one or more manufacturing assets. The method includes generating, by the processing circuitry, an asset ontology for each manufacturing asset based on the received operational data. The asset ontology captures specific attributes, behaviors, and relationships of the manufacturing asset. The method includes integrating, by the processing circuitry, the asset ontologies into a combined upper level ontology. The combined upper level ontology provides a holistic view of the entire manufacturing system. The method includes extracting, by the processing circuitry, relevant context from the combined upper level ontology based on a simulation objective. The method includes generating, by the processing circuitry, simulation scenarios based on the extracted context. The method includes executing, by the processing circuitry, a simulation model using the generated scenarios. The method includes displaying, by the processing circuitry, simulation results through a simulator.
In some aspects of the present disclosure, the method further includes transforming, by the processing circuitry, the received operational data into probabilistic distributions. The method includes updating, by the processing circuitry, the asset ontologies and combined upper level ontology with the probabilistic distributions. The method includes executing, by the processing circuitry, SPARQL queries on the combined upper level ontology to extract the relevant context. The method includes identifying, by the processing circuitry, random variables directly influencing outputs of a specific manufacturing asset based on the simulation objective. The method includes substituting, by the processing circuitry, non-critical variables with averaged values from their respective distributions. The method includes continuously updating, by the processing circuitry, the combined upper level ontology with real-time data from one of, digital twins or Manufacturing Execution Systems (MES).
In some aspects of the present disclosure, the method further includes receiving, by the processing circuitry, a simulation run trigger. The method includes identifying, by the processing circuitry, a target individual for the simulation. The method includes identifying, by the processing circuitry, relationships between the target individual and other individuals in the manufacturing system. The method includes determining, by the processing circuitry, whether the identified individuals are related to the simulation objective. The method includes classifying, by the processing circuitry, related individuals by class type. The method includes calculating, by the processing circuitry, an impact of each related individual on the simulation run time. The method includes setting, by the processing circuitry, variables for simulation based on the calculated impact. Variables are set as random variables for individuals with high impact and set to mean values for individuals with low impact or not related to the simulation objective.
The foregoing general description of the illustrative aspects and the following detailed description thereof are merely exemplary aspects of the teachings of this disclosure and are not restrictive.
BRIEF DESCRIPTION OF FIGURES
The following detailed description of the preferred aspects of the present disclosure will be better understood when read in conjunction with the appended drawings. The present disclosure is illustrated by way of example, and not limited by the accompanying figures, in which like references indicate similar elements.
FIG. 1 illustrates a block diagram of a system for simulation, according to aspects of the present disclosure;
FIG. 2 illustrates a block diagram of a data processing apparatus of the system of FIG. 1, according to aspects of the present disclosure; and
FIG. 3 illustrates a flowchart of a method for ontology-based context extraction and scenario generation in manufacturing simulation, according to aspects of the present disclosure.
DETAILED DESCRIPTION
The following description sets forth exemplary aspects of the present disclosure. It should be recognized, however, that such description is not intended as a limitation on the scope of the present disclosure. Rather, the description also encompasses combinations and modifications to those exemplary aspects described herein.
The present disclosure provides an ontology-based context extraction and scenario generation system and method for manufacturing simulation. This innovative approach enhances the management and optimization of manufacturing shop floor operations by dynamically adapting to real-time data. The system addresses limitations of traditional simulation models that often lack the ability to adapt to real-time changes and contextual variations.
The present disclosure provides an ontology-based context extraction and scenario generation system and method for manufacturing simulation. This innovative approach enhances the management and optimization of manufacturing shop floor operations by dynamically adapting to real-time data. The system addresses limitations of traditional simulation models that often lack the ability to adapt to real-time changes and contextual variations.
The system comprises key components such as an asset ontology management module, a system ontology integration module, and a context extraction and scenario generation module. These components work together to create a comprehensive, context-aware simulation model that accurately reflects the dynamic nature of manufacturing environments.
By leveraging advanced ontology management techniques alongside dynamic simulation capabilities, the system enables manufacturers to make more informed decisions, improve efficiency, and adapt quickly to changing conditions in the manufacturing environment. The ontology-based approach allows for efficient storage, retrieval, and updating of manufacturing knowledge, reducing redundancy and inconsistencies in the data.
Some advantages of the system may include improved accuracy in simulation models, enhanced adaptability to real-time changes, optimized use of computational resources, and the ability to provide a holistic view of the entire manufacturing system. The system may support continuous improvement initiatives by identifying opportunities for process optimization, quality enhancement, and cost reduction.
FIG. 1 illustrates a block diagram of a system 100 for simulation. The system 100 for simulation includes a manufacturing asset 102, a processing unit 104, a data processing apparatus 106, a communication network 108, and a simulator 118.
The manufacturing asset 102 may represent an observable manufacturing element. Examples of the manufacturing asset 102 may include, but are not limited to, a CNC machine, a robotic arm, an assembly line, a 3D printer, or the like. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the manufacturing assets 102 including known, related art, and/or later developed technologies.
Although FIG. 1 illustrates that the system 100 includes a single manufacturing asset (i.e., the manufacturing asset 102), it will be apparent to a person skilled in the art that the scope of the present disclosure is not limited to it. In various other aspects, the system 100 may include multiple manufacturing assets without deviating from the scope of the present disclosure. In such a scenario, each manufacturing asset is configured to perform one or more operations in a manner similar to the operations of the manufacturing asset 102 as described herein.
The processing unit 104 may be configured to receive real-time operational data from the manufacturing asset 102 through the communication network 108. The processing unit 104 may include a controller 110 and a communication interface 112 for managing and transmitting the processed data. The processing unit 104 may be configured to preprocess the operational data from the manufacturing asset 102 before transmission to the data processing apparatus 106.
The data processing apparatus 106 may comprise processing circuitry 114, a database 116, a controller 110, and a communication interface 112. The processing circuitry 114 may be configured to process data received from the manufacturing asset 102. The database 116 may be configured to store information related to the manufacturing operations. The controller 110 may be configured to manage operations within the data processing apparatus 106, while the communication interface 112 may be configured to facilitate data exchange between components.
The communication network 108 may include suitable logic, circuitry, and interfaces that may be configured to provide a plurality of network ports and a plurality of communication channels for transmission and reception of data related to operations of various entities in the system 100.
The simulator 118 may be configured to connect to the communication network 108 and receive processed data from the data processing apparatus 106 to perform simulation operations. The simulator 118 may be configured to display simulation results based on the executed simulation model.
In operation, the system 100 may receive real-time operational data from the manufacturing asset 102 through the communication network 108. The processing unit 104 may preprocess this data before transmitting it to the data processing apparatus 106. The data processing apparatus 106 may then process this data further using its processing circuitry 114, generate asset ontologies, integrate them into a combined upper level ontology, extract relevant context, generate simulation scenarios, and execute a simulation model. The simulator 118 may then display the simulation results, providing valuable insights for manufacturing optimization.
FIG. 2 illustrates a block diagram of a data processing apparatus 106. The data processing apparatus 106 includes a network interface 200, an input/output interface 202, a database connection 204, and processing circuitry 114.
The network interface 200 may include suitable logic, circuitry, and interfaces that may be configured to establish and enable a communication between the data processing apparatus 106 and different elements of the system 100, via the communication network 108. The network interface 200 may be implemented by use of various known technologies to support wired or wireless communication of the data processing apparatus 106 with the communication network 108. The network interface 200 may include, but is not limited to, an antenna, a RF transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a CODEC chipset, a SIM card, and a local buffer circuit.
The I/O interface 202 may include suitable logic, circuitry, interfaces, and/or code that may be configured to receive inputs and transmit data processing apparatus's outputs (i.e., one or more outputs generated by the data processing apparatus 106) via a plurality of data ports in the data processing apparatus 106. The I/O interface 202 may include various input and output data ports for different I/O devices. Examples of such I/O devices may include, but are not limited to, a touch screen, a keyboard, a mouse, a joystick, a projector audio output, a microphone, an image-capture device, a liquid crystal display (LCD) screen and/or a speaker.
The database connection 204 may be configured to establish a connection between the processing circuitry 114 and the database 116. The database 116 may be configured to store logic, instructions, circuitry, interfaces, and/or codes of the processing circuitry 114 to enable the processing circuitry 114 to execute the one or more operations associated with the system 100. The database 116 may be further configured to store therein, data associated with the system 100, and the like. It will be apparent to a person having ordinary skill in the art that the database 116 may be configured to store various types of data associated with the system 100, without deviating from the scope of the present disclosure. Examples of the database 116 may include but are not limited to, a Relational database, a NoSQL database, a Cloud database, an Object oriented database, and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the database 116 including known, related art, and/or later developed technologies. In some aspects of the present disclosure, a set of centralized or distributed network of peripheral memory devices may be interfaced with the data processing apparatus 106, as an example, on a cloud server.
The processing circuitry 114 may include multiple interconnected engines that perform different functions. These engines may include a data acquisition engine 206, a machine analytics engine 208, an asset ontology engine 210, a combined ontology engine 212, a context extraction engine 214, and a simulation engine 216.
The data acquisition engine 206 may be configured to receive real-time operational data from the manufacturing asset 102 via the processing unit 104. In some aspects of the present disclosure, the data acquisition engine 206 may be configured to collect historical data and metadata associated with the manufacturing asset 102. The data acquisition engine 206 may be capable of handling various data formats and protocols, ensuring compatibility with a wide range of manufacturing assets. As used herein, "real-time operational data" refers to data that is generated and collected from the manufacturing asset 102 as it operates, reflecting the current state and performance of the asset.
The machine analytics engine 208 may be configured to process the acquired data. The machine analytics engine 208 may employ advanced analytics techniques, including machine learning algorithms, to derive insights from the raw data. In some aspects of the present disclosure, the machine analytics engine 208 may be configured to transform the received operational data into probabilistic distributions required by the simulation model. For example, job processing times might be transformed from raw numerical values into normal distributions with specific means and standard deviations. The machine analytics engine 208 may be capable of identifying patterns, anomalies, and trends in the asset's operational data.
The asset ontology engine 210 may be configured to create and maintain an ontological representation of each manufacturing asset based on the processed data from the machine analytics engine 208. The asset ontology engine 210 may utilize standardized ontology languages such as OWL (Web Ontology Language) or RDF (Resource Description Framework) to create a structured representation of each asset's characteristics, behaviors, and relationships. As used herein, "ontological representation" refers to a formal, explicit specification of a shared conceptualization, providing a structured framework for representing knowledge about an asset and its relationships within the manufacturing environment.
The combined ontology engine 212 may be configured to integrate information from the asset ontology engine 210 and potentially other asset ontologies to create a comprehensive system-wide ontology. This combined upper level ontology provides a holistic view of the entire manufacturing system, capturing relationships between different assets, processes, and operational parameters. In some aspects of the present disclosure, the combined ontology engine 212 may employ advanced ontology merging and alignment techniques to ensure consistency and coherence in the integrated ontology. The combined upper level ontology may be represented in Resource Description Framework (RDF) format, facilitating efficient data integration and querying.
The context extraction engine 214 may be configured to utilize the combined ontology from the combined ontology engine 212 to extract relevant context for simulation. In some aspects of the present disclosure, the context extraction engine 214 may be configured to execute SPARQL queries on the combined upper level ontology to extract the relevant context. For example, a SPARQL query might be used to identify all machines involved in a specific production process and their current operational status. The context extraction engine 214 may employ sophisticated reasoning algorithms to infer complex relationships and dependencies within the manufacturing environment. The context extraction engine 214 may utilize SPARQL (SPARQL Protocol and RDF Query Language) queries to extract relevant context from the combined upper level ontology. SPARQL is a semantic query language for databases, able to retrieve and manipulate data stored in Resource Description Framework (RDF) format. In the context of the present disclosure, SPARQL queries may be used to identify and extract specific information relevant to the simulation objectives.
The simulation engine 216 may be configured to generate simulation scenarios based on the extracted context and execute the simulation model. The simulation engine 216 may utilize advanced simulation techniques, such as discrete event simulation or agent-based modeling, to accurately represent the complex dynamics of the manufacturing system. In some aspects of the present disclosure, the simulation engine 216 may be configured to identify random variables directly influencing outputs of a specific manufacturing asset based on the simulation objective. The simulation engine 216 may be further configured to substitute non-critical variables with averaged values from their respective distributions, reducing computational complexity while maintaining simulation accuracy.
The components within the processing circuitry 114 are interconnected through a second data bus 218, allowing data flow between the various engines. The second data bus 218 may facilitate efficient communication and data exchange between the different components of the processing circuitry 114.
In operation, the data processing apparatus 106 may receive real-time operational data from the manufacturing asset 102 through the network interface 200. The data acquisition engine 206 collects and preprocesses this data. The machine analytics engine 208 then processes the data, deriving insights and transforming it into probabilistic distributions. The asset ontology engine 210 creates ontological representations of each manufacturing asset, which are then integrated by the combined ontology engine 212 into a comprehensive system-wide ontology. The context extraction engine 214 utilizes this combined ontology to extract relevant context for simulation, which is then used by the simulation engine 216 to generate scenarios and execute the simulation model. The results of these operations may be output through the I/O interface 202 or stored in the database 116 via the database connection 204.
The ontology-based architecture of the system 100 provides inherent scalability and adaptability to different manufacturing environments. The asset ontology engine 210 and combined ontology engine 212 can accommodate new manufacturing assets, processes, or relationships by extending the existing ontologies.
For instance, when a new type of manufacturing asset is introduced, its characteristics, capabilities, and relationships can be defined in a new asset ontology. This new ontology can then be integrated into the combined upper level ontology, allowing the system to incorporate the new asset into its simulations and analyses without requiring significant changes to the overall system architecture.
This scalability extends to different types of manufacturing environments as well. Whether applied to discrete manufacturing, process manufacturing, or hybrid environments, the ontology-based approach allows for flexible representation of diverse manufacturing concepts and relationships.
In some aspects of the present disclosure, the system 100 may be configured to continuously update the combined upper level ontology with real-time data from digital twins or Manufacturing Execution Systems (MES). As used herein, a "digital twin" refers to a virtual representation of a physical manufacturing asset that is dynamically updated with real-time data. The data acquisition engine 206 may be configured to interface with digital twin systems, collecting real-time operational data that reflects the current state of the manufacturing assets. Similarly, the data acquisition engine 206 may be configured to integrate with MES, which provide real-time information about the production process, including work-in-progress, inventory levels, and resource allocation.
The continuous integration of data from digital twins and MES ensures that the simulation model remains aligned with the actual state of the manufacturing shop floor. This real-time synchronization may enable the system 100 to adapt to changes in the manufacturing environment dynamically, providing more accurate and relevant simulations. For example, when a machine's performance degrades, the digital twin may update the corresponding asset ontology, which in turn updates the combined upper level ontology. The simulation engine 216 may then adjust its scenarios and simulations to account for this change, providing more accurate predictions and recommendations. Although the present disclosure explains that various processing operations are performed by the processing circuitry 114 of the data processing apparatus 106, it will be apparent to a person skilled in the art that the scope of the present disclosure is not limited to this configuration. In various other aspects, some or all of these processing operations may be performed at the processing unit 104 level without deviating from the scope of the present disclosure. The distribution of processing tasks between the processing unit 104 and the processing circuitry 114 may be determined based on factors such as computational resources, data transfer efficiency, and system architecture, among others. This flexible approach allows for optimized performance and resource utilization across different implementations of the system 100.
FIG. 3 illustrates a flowchart of a method 300 for ontology-based context extraction and scenario generation in manufacturing simulation.
At step 302, the system 100 receives real-time operational data from one or more manufacturing assets 102. This data may be collected by the data acquisition engine 206 of the data processing apparatus 106. The real-time operational data may include various parameters such as machine status, production rates, quality metrics, and environmental conditions.
At step 304, the system 100 generates an asset ontology for each manufacturing asset based on the received operational data. This step may be performed by the asset ontology engine 210. The asset ontology captures specific attributes, behaviors, and relationships of the manufacturing asset. The asset ontology may include information such as the asset's capabilities, current state, historical performance, and relationships with other assets in the manufacturing environment.
At step 306, the system 100 integrates the asset ontologies into a combined upper level ontology. This integration may be performed by the combined ontology engine 212. The combined upper level ontology provides a holistic view of the entire manufacturing system. This step may involve aligning and merging the individual asset ontologies, resolving any conflicts or inconsistencies, and creating a unified representation of the manufacturing environment.
At step 308, the system 100 extracts relevant context from the combined upper level ontology based on a simulation objective. This extraction may be performed by the context extraction engine 214, using SPARQL queries on the combined upper level ontology. The relevant context may include specific assets, processes, or relationships that are pertinent to the simulation objective. For example, when the simulation objective is to optimize production scheduling, the extracted context may include information about machine availability, production rates, and interdependencies between different production stages.
At step 310, the system 100 generates simulation scenarios based on the extracted context. This scenario generation may be performed by the simulation engine 216. The generated scenarios may represent different possible states or configurations of the manufacturing system, taking into account the extracted context and the simulation objective. These scenarios may include variations in production rates, resource allocation, or process flows.
At step 312, the system 100 executes a simulation model using the generated scenarios. This execution may also be performed by the simulation engine 216. The simulation model may use techniques such as discrete event simulation or agent-based modeling to simulate the behavior of the manufacturing system under different scenarios. The simulation results may provide insights into system performance, bottlenecks, or potential optimizations.
In some aspects of the present disclosure, the method 300 may further include transforming the received operational data into probabilistic distributions and updating the asset ontologies and combined upper level ontology with these distributions. The method 300 may also include identifying random variables directly influencing outputs of a specific manufacturing asset based on the simulation objective and substituting non-critical variables with averaged values from their respective distributions.
Furthermore, the method 300 may include continuously updating the combined upper level ontology with real-time data from digital twins or Manufacturing Execution Systems (MES), ensuring that the simulation model remains aligned with the actual state of the manufacturing shop floor. This continuous update allows the system to adapt to changes in the manufacturing environment in real-time, providing more accurate and relevant simulations.
In some aspects of the present disclosure, the method 300 may also include receiving a simulation run trigger, identifying a target individual for the simulation, identifying relationships between the target individual and other individuals in the manufacturing system, determining whether the identified individuals are related to the simulation objective, classifying related individuals by class type, calculating an impact of each related individual on the simulation run time, and setting variables for simulation based on the calculated impact.
Specifically, when a simulation run is triggered, the system identifies a target individual (e.g., a specific machine or process) for the simulation. It then uses the combined upper level ontology to identify relationships between this target individual and other entities in the manufacturing system. The system determines which of these related entities are relevant to the simulation objective.
For the relevant entities, the system classifies them by type (e.g., machine, process, material) and calculates their impact on the simulation run time. This impact calculation may consider factors such as the complexity of the entity's behavior, the number of variables associated with it, and its interactions with other elements in the system.
Based on this impact calculation, the system sets variables for the simulation. Variables are set as random variables for individuals with high impact, allowing for a more detailed representation of their behavior in the simulation. For individuals with low impact or those not directly related to the simulation objective, variables are set to their mean values, simplifying the simulation without significantly affecting its accuracy.
This approach allows the system to focus computational resources on the most critical aspects of the simulation, improving efficiency while maintaining accuracy. It also enables the system to adapt its simulation approach based on the specific objectives of each simulation run, enhancing its versatility and relevance to different manufacturing scenarios.
The method 300 provides a comprehensive approach to context-aware simulation in manufacturing environments, leveraging ontological representations to capture complex relationships and dependencies, and using this knowledge to generate more accurate and relevant simulation scenarios.
The ontology-based approach is particularly adept at handling complex relationships between different manufacturing entities. The combined upper level ontology can represent not only direct relationships between assets (e.g., machine A feeds into machine B) but also more complex, multi-level relationships.
For example, the ontology can represent how a change in one process might affect seemingly unrelated processes through shared resources or dependencies. When running simulations, the context extraction engine 214 can traverse these complex relationships to identify all relevant factors that might impact the simulation outcome.
This capability allows the system to provide insights into non-obvious interactions and dependencies within the manufacturing environment, enabling more comprehensive and accurate simulations and analyses.
Thus, the system 100 and the method 300 provide several key technical advantages in the field of manufacturing simulation. The ontology-based approach enables dynamic adaptation to real-time changes in the manufacturing environment, significantly enhancing the accuracy and relevance of simulations. By integrating data from digital twins and Manufacturing Execution Systems, the system maintains a continuously updated representation of the shop floor, allowing for more timely and informed decision-making. The use of SPARQL queries on the combined upper level ontology facilitates efficient extraction of relevant context, reducing computational overhead and improving simulation performance. The system's ability to identify and focus on critical variables while simplifying non-critical ones optimizes resource utilization and accelerates simulation run times. Furthermore, the ontological representation of complex relationships between manufacturing entities enables the system to uncover non-obvious interactions and dependencies, providing deeper insights into the manufacturing process. Lastly, the scalable and adaptable nature of the ontology-based architecture allows the system to easily incorporate new manufacturing assets or processes, ensuring its long-term relevance and applicability across diverse manufacturing environments.
Aspects of the present disclosure are discussed here with reference to flowchart illustrations and block diagrams that depict methods, systems, and apparatus in accordance with various aspects of the present disclosure. Each block within these flowcharts and diagrams, as well as combinations of these blocks, can be executed by computer-readable program instructions. The various logical blocks, modules, circuits, and algorithm steps described in connection with the disclosed aspects may be implemented through electronic hardware, software, or a combination of both. To emphasize the interchangeability of hardware and software, the various components, blocks, modules, circuits, and steps are described generally in terms of their functionality. The decision to implement such functionality in hardware or software is dependent on the specific application and design constraints imposed on the overall system. Person having ordinary skill in the art can implement the described functionality in different ways depending on the particular application, without deviating from the scope of the present disclosure.
The flowcharts and block diagrams presented in the figures depict the architecture, functionality, and operation of potential implementations of systems, methods, and apparatus according to different aspects of the present disclosure. Each block in the flowcharts or diagrams may represent an engine, segment, or portion of instructions comprising one or more executable instructions to perform the specified logical function(s). In some alternative implementations, the order of functions within the blocks may differ from what is depicted. For instance, two blocks shown in sequence may be executed concurrently or in reverse order, depending on the required functionality. Each block, and combinations of blocks, can also be implemented using special-purpose hardware-based systems that perform the specified functions or tasks, or through a combination of specialized hardware and software instructions.
Although the preferred aspects have been detailed here, it should be apparent to those skilled in the relevant field that various modifications, additions, and substitutions can be made without departing from the scope of the disclosure. These variations are thus considered to be within the scope of the disclosure as defined in the following claims.
Features or functionalities described in certain example aspects may be combined and re-combined in or with other example aspects. Additionally, different aspects and elements of the disclosed example aspects may be similarly combined and re-combined. Further, some example aspects, individually or collectively, may form components of a larger system where other processes may take precedence or modify their application. Moreover, certain steps may be required before, after, or concurrently with the example aspects disclosed herein. It should be noted that any and all methods and processes disclosed herein can be performed in whole or in part by one or more entities or actors in any manner.
Although terms like "first," "second," etc., are used to describe various elements, components, regions, layers, and sections, these terms should not necessarily be interpreted as limiting. They are used solely to distinguish one element, component, region, layer, or section from another. For example, a "first" element discussed here could be referred to as a "second" element without departing from the teachings of the present disclosure.
The terminology used here is intended to describe specific example aspects and should not be considered as limiting the disclosure. The singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises," "includes," "comprising," and "including," as used herein, indicate the presence of stated features, steps, elements, or components, but do not exclude the presence or addition of other features, steps, elements, or components.
As used herein, the term "or" is intended to be inclusive, meaning that "X employs A or B" would be satisfied by X employing A, B, or both A and B. Unless specified otherwise or clearly understood from the context, this inclusive meaning applies to the term "or."
Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the relevant art. Terms should be interpreted consistently with their common usage in the context of the relevant art and should not be construed in an idealized or overly formal sense unless expressly defined here.
The terms "about" and "substantially," as used herein, refer to a variation of plus or minus 10% from the nominal value. This variation is always included in any given measure.
In cases where other disclosures are incorporated by reference and there is a conflict with the present disclosure, the present disclosure takes precedence to the extent of the conflict, or to provide a broader disclosure or definition of terms. If two disclosures conflict, the later-dated disclosure will take precedence.
The use of examples or exemplary language (such as "for example") is intended to illustrate aspects of the invention and should not be seen as limiting the scope unless otherwise claimed. No language in the specification should be interpreted as implying that any non-claimed element is essential to the practice of the invention.
While many alterations and modifications of the present invention will likely become apparent to those skilled in the art after reading this description, the specific aspects shown and described by way of illustration are not intended to be limiting in any way.
A number of implementations have been described. Nevertheless, it will be understood that various modifications may be made without departing from the scope of the disclosure. Accordingly, other implementations are within the scope of the following claims. ,CLAIMS:1. A system (100) for ontology-based context extraction and scenario generation in manufacturing simulation, the system (100) comprising:
one or more manufacturing assets (102); and
a data processing apparatus (106) comprising processing circuitry (114) coupled to the one or more manufacturing assets (102), and configured to:
receive real-time operational data from the one or more manufacturing assets (102);
generate an asset ontology for each manufacturing asset based on the received operational data, wherein the asset ontology captures specific attributes, behaviors, and relationships of the manufacturing asset (102);
integrate the asset ontologies into a combined upper level ontology, wherein the combined upper level ontology provides a holistic view of an entire manufacturing system;
extract relevant context from the combined upper level ontology based on a simulation objective;
generate simulation scenarios based on the extracted context; and
execute a simulation model using the generated simulation scenarios.

2. The system (100) as claimed in claim 1, wherein the processing circuitry (114) is configured to:
transform the received operational data into probabilistic distributions; and
update the asset ontologies and combined upper level ontology with the probabilistic distributions.

3. The system (100) as claimed in claim 2, wherein the processing circuitry (114) is configured to:
execute SPARQL queries on the combined upper level ontology to extract the relevant context.

4. The system (100) as claimed in claim 3, wherein the processing circuitry (114) is configured to:
identify random variables directly influencing outputs of a specific manufacturing asset based on simulation objective; and
substitute non-critical variables with averaged values from their respective distributions.

5. The system (100) as claimed in claim 4, wherein the processing circuitry (114) is configured to:
continuously update the combined upper level ontology with real-time data from one of, digital twins or Manufacturing Execution Systems (MES).

6. The system (100) as claimed in claim 1, further comprising a processing unit (104) configured to:
receive the real-time operational data from the one or more manufacturing assets (102);
preprocess the real-time operational data; and
transmit preprocessed operational data to the data processing apparatus (106).

7. The system (100) as claimed in claim 1, wherein the processing circuitry (114) is configured to:
receive a simulation run trigger;
identify a target individual for the simulation;
identify relationships between the target individual and other individuals in the manufacturing system;
determine whether the identified individuals are related to the simulation objective;
classify related individuals by class type;
calculate an impact of each related individual on the simulation run time; and
set variables for simulation based on calculated impact, wherein variables are set as random variables for individuals with high impact and set to mean values for individuals with low impact or not related to the simulation objective.

8. A method (300) for ontology-based context extraction and scenario generation in manufacturing simulation, the method (300) comprising:
receiving, by processing circuitry (114) of a data processing apparatus (106), real-time operational data from one or more manufacturing assets (102);
generating, by the processing circuitry, an asset ontology for each manufacturing asset based on the received operational data, wherein the asset ontology captures specific attributes, behaviors, and relationships of the manufacturing asset;
integrating, by the processing circuitry, the asset ontologies into a combined upper level ontology, wherein the combined upper level ontology provides a holistic view of an entire manufacturing system;
extracting, by the processing circuitry, relevant context from the combined upper level ontology based on a simulation objective;
generating, by the processing circuitry, simulation scenarios based on an extracted context;
executing, by the processing circuitry, a simulation model using generated simulation scenarios; and
displaying, by the processing circuitry, simulation results through a simulator.

9. The method (300) as claimed in claim 8, further comprising:
transforming, by the processing circuitry, the received operational data into probabilistic distributions;
updating, by the processing circuitry, the asset ontologies and combined upper level ontology with the probabilistic distributions;
executing, by the processing circuitry, SPARQL queries on the combined upper level ontology to extract the relevant context;
identifying, by the processing circuitry, random variables directly influencing outputs of a specific manufacturing asset based on the simulation objective;
substituting, by the processing circuitry, non-critical variables with averaged values from their respective distributions; and
continuously updating, by the processing circuitry, the combined upper level ontology with real-time data from one of, digital twins or Manufacturing Execution Systems (MES).

10. The method (300) as claimed in claim 8, further comprising:
receiving, by the processing circuitry, a simulation run trigger;
identifying, by the processing circuitry, a target individual for the simulation;
identifying, by the processing circuitry, relationships between the target individual and other individuals in the manufacturing system;
determining, by the processing circuitry, whether the identified individuals are related to the simulation objective;
classifying, by the processing circuitry, related individuals by class type;
calculating, by the processing circuitry, an impact of each related individual on the simulation run time; and
setting, by the processing circuitry, variables for simulation based on calculated impact, wherein variables are set as random variables for individuals with high impact and set to mean values for individuals with low impact or not related to the simulation objective.