A stainless steel product intelligent factory model construction method based on ontology

Abstract

The application belongs to the field of intelligent manufacturing application, and relates to a stainless steel product intelligent factory model construction method based on ontology, comprising the following steps: collecting heterogeneous data sources of a stainless steel product intelligent factory and preprocessing; extracting concepts in the field of the stainless steel product intelligent factory from the preprocessed data, constructing a main concept ontology, and a plurality of branch ontologies associated with the main concept ontology; constructing an ontology model based on the main concept ontology and the branch ontologies; and iteratively optimizing the ontology model. Through the construction of the main concept ontology and the branch ontologies, the application can efficiently manage and integrate information from multiple data sources, solve problems such as a large and complex concept set, a small number of core concepts, a low similarity between concepts, and a simple hierarchical relationship in the field of the stainless steel product intelligent factory, integrate the ontology model into the information system of the stainless steel product intelligent factory, realize data consistency and sharing, and provide intelligent decision support.

Description

Technical Field

[0001] This invention belongs to the field of intelligent manufacturing applications and relates to a method for constructing an intelligent factory model for stainless steel products based on ontology. Background Technology

[0002] With the rapid development of information technology, the manufacturing industry is undergoing unprecedented transformation. As a core component of Industry 4.0, the smart factory concept integrates advanced technologies such as the Internet of Things (IoT), artificial intelligence (AI), and big data analytics to achieve intelligent, automated, and networked production processes. A key characteristic of smart factories is the need to manage multiple data sources simultaneously. The goals of smart factories are to improve production efficiency, reduce costs, enhance product quality, and achieve flexible production processes to meet personalized and customized market demands.

[0003] In the construction of smart factories, the integration and application of information technology are crucial. However, traditional information systems often suffer from problems such as data silos, information inconsistencies, and insufficient decision support. These problems lead to a waste of information resources and affect the improvement of production efficiency and product quality. To solve these problems, a new technological approach is needed to build a unified knowledge model to achieve information integration and intelligent decision support.

[0004] Currently, ontology is being applied in the field of intelligent manufacturing. As a knowledge representation method in the field of artificial intelligence, ontology has demonstrated its powerful knowledge organization and information integration capabilities in multiple domains. By defining concepts, attributes, and relationships within a domain, ontology provides a standardized framework for information expression and reasoning. In the context of intelligent factories, the application of ontology can achieve unified representation and intelligent processing of knowledge across various stages of production, management, and maintenance.

[0005] It is still in its early stages. Although some research and practice have explored the application of ontology in smart factories, these studies are often limited to specific application scenarios and lack a general ontology construction method and framework. In addition, the implementation and application of ontology also face technical challenges, such as ontology design, editing, reasoning, and integration.

[0006] like Figure 1 The diagram illustrates the typical workflow of a stainless steel products factory. In the field of smart factories for stainless steel products, traditional knowledge management systems face the following technical challenges:

[0007] Diverse data sources: Smart factories for stainless steel products need to process information from various data sources such as sensors, equipment logs, and operation records, and these data sources have differences in format and semantics.

[0008] Complexity of the concept set: The concept set involved in the field of smart factories for stainless steel products is huge and complex, and traditional ontology construction methods are difficult to handle effectively.

[0009] Identification of core concepts: Identifying the most core concepts in a large set of concepts is the key to building an effective ontology, but this process is often time-consuming and error-prone.

[0010] Low similarity between concepts: The concept similarity in the field of smart factories for stainless steel products is low, which increases the difficulty of concept integration and reasoning.

[0011] The hierarchical relationship is not complicated: the conceptual hierarchy in the field of smart factories for stainless steel products is relatively simple, but traditional ontology construction methods are often too complex and not suitable for the characteristics of this field. Summary of the Invention

[0012] To address the aforementioned technical problems in the existing technology, this invention proposes an ontology-based method for constructing a smart factory model for stainless steel products, the specific technical solution of which is as follows:

[0013] An ontology-based method for constructing a smart factory model for stainless steel products, comprising:

[0014] Collect heterogeneous data sources from the smart factory for stainless steel products and perform preprocessing;

[0015] Concepts in the field of smart factories for stainless steel products are extracted from the preprocessed data, and a main concept ontology and multiple branch ontologs associated with the main concept ontology are constructed.

[0016] Based on the main concept ontology and branch ontology, an ontology model is constructed;

[0017] The ontology model is iteratively optimized.

[0018] Furthermore, through expert knowledge, literature review, and data analysis, the most core concepts in the field of intelligent factories for stainless steel products are identified, and a backbone concept ontology is constructed. The ontology adopts a modular design, with each backbone concept ontology independently encapsulated as a microservice architecture, supporting on-demand expansion. The backbone concept ontology includes an intelligent logistics system, an intelligent production system, and an intelligent management system.

[0019] Furthermore, based on the main concept ontology, multiple branch ontology related to the lowest-level core concept of the main concept ontology are constructed. The branch ontology of the intelligent logistics system includes an AGV automatic guidance system, a product sales system, a raw material procurement system, an intelligent automated warehouse, and a distribution system; the branch ontology of the intelligent production system includes alarm devices, intelligent workstations, intelligent coding systems, detection devices, automated processing devices, equipment operation and maintenance systems, and error prevention systems; the branch ontology of the intelligent management system includes a safety lighting system, a data monitoring system, an intelligent control system, a production execution management system, a production monitoring management system, a production planning management system, an energy consumption management system, an order management system, an operation and maintenance management system, and a panel system.

[0020] Furthermore, based on the aforementioned main concept ontology and branch ontology, an ontology model containing all relevant concepts and entities in the field of intelligent factories for stainless steel products is constructed using the Protege software. A digital twin interface branch ontology is introduced to achieve real-time mapping between the physical factory and the virtual model. At the same time, the Protege integrates the Pellet inference engine and the SWRL rule engine to define logical rules and use SHACL to perform constraint verification on the ontology model.

[0021] Furthermore, graph theory and machine learning techniques are applied to analyze the relationships between concepts and entities in the ontology model, identify key semantic associations and potential reasoning paths; and the owl:equivalentProperty and owl:sameAs attributes of OWL are used to establish cross-ontology equivalence relations and perform dynamic associations.

[0022] Furthermore, a dynamic concept recognition model based on graph neural networks is constructed to monitor changes in the production environment of the smart factory for stainless steel products in real time, automatically update the core concept library, and derive new conclusions or information from existing knowledge using logical rules and algorithms.

[0023] Furthermore, a distributed data acquisition framework is adopted to collect real-time or batch data from heterogeneous data sources in the smart factory for stainless steel products. These heterogeneous data sources include sensor time-series data, equipment logs, ERP system structured data, and operator text records.

[0024] Furthermore, the collected data undergoes preprocessing, including data cleaning, format unification, and semantic annotation. The data cleaning stage introduces a hybrid cleaning strategy based on a combination of rule engines and machine learning, while the format and semantic unification adopts the ISO 8000 international industry standard.

[0025] Furthermore, core terms for the stainless steel products industry are extracted from historical document data using natural language processing technology to form a domain dictionary of concepts.

[0026] Furthermore, ontology alignment tools are used to eliminate semantic ambiguity across data sources and unify entity representations in heterogeneous data sources.

[0027] The present invention has the following advantages:

[0028] Efficient data integration: By constructing the main concept ontology and branch ontology, information from multiple data sources can be efficiently integrated; the ontology model can be integrated into the information system of the stainless steel product smart factory to achieve data consistency and sharing, and provide intelligent decision support.

[0029] Simplified concept management: By identifying and defining core concepts, the management of the large and complex concept set in the field of smart factories for stainless steel products is simplified; key concepts are extracted from requirements and the relationships between these concepts are defined to form a structured ontology model; ontology description languages ​​such as OWL are used to achieve standardized representation of the ontology, ensuring the interoperability and scalability of the ontology.

[0030] Enhanced semantic reasoning capability: The semantic reasoning process based on ontology model and relational network analysis can derive new conclusions or information from existing knowledge, thereby enhancing the decision support capability of the ontology model of the intelligent factory for stainless steel products.

[0031] High practicality: The ontology model of this invention can adapt to the characteristics of low similarity between concepts and simple hierarchical relationships in the field of intelligent factories for stainless steel products, and has strong adaptability. At the same time, by deeply analyzing the needs of intelligent factories for stainless steel products, the goals and scope of ontology construction are determined, ensuring the practicality and relevance of the ontology. Attached Figure Description

[0032] Figure 1 This is a flowchart of the standard workflow in a stainless steel products factory;

[0033] Figure 2 This is a flowchart of the ontology model construction process for the intelligent factory industry of stainless steel products in this embodiment;

[0034] Figure 3 This is the entity relationship constraint diagram for the stainless steel product smart factory industry in this embodiment;

[0035] Figure 4 This is the overall model diagram of the main body for the intelligent factory industry of stainless steel products in this embodiment. Detailed Implementation

[0036] To make the objectives, technical solutions, and technical effects of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0037] This invention discloses an ontology-based method for constructing a smart factory model for stainless steel products. The aim is to build a unified knowledge model through ontology technology to achieve information integration and intelligent decision support across all stages of the smart factory for stainless steel products. This is mainly achieved through the following aspects:

[0038] Definition of the core concept ontology: Collect heterogeneous data sources from the intelligent factory of stainless steel products, define one or more core concept ontologs, and use the above core concept ontology as the core of the intelligent factory ontology model to integrate and manage the lowest-level core concepts.

[0039] Construction of branch ontology: Based on the trunk concept ontology, multiple branch ontology are constructed, and the branch ontology is associated with the lowest core concept of the trunk concept ontology, for processing data and information in specific domains.

[0040] Ontology Model Construction: Using ontology-based knowledge graph technology, an ontology model is constructed that includes all relevant concepts and entities in the field of intelligent factories for stainless steel products. This model can clearly demonstrate the semantic relationships between concepts.

[0041] Relationship network analysis: Through relationship network analysis technology, we identify and analyze the complex relationships between concepts and entities in the field of smart factories for stainless steel products, providing a foundation for semantic reasoning.

[0042] Semantic reasoning process: Based on the semantic associations and logical rules of the ontology model, develop a semantic reasoning process that can derive new conclusions or information from existing knowledge.

[0043] Optimization of ontology construction methods: Analyze the problems and difficulties faced by existing ontology construction methods, find the causes of the problems, and optimize the construction process based on the original construction methods to build an intelligent factory ontology model that does not have the above problems or solves some of the problems.

[0044] More specifically, such as Figure 2 As shown, it includes the following steps:

[0045] Step 1: For the heterogeneous data sources in the smart factory for stainless steel products, a distributed data acquisition framework, such as Apache NiFi, is used for real-time or batch data acquisition. These heterogeneous data sources include sensor time-series data, equipment logs, structured data from the ERP system, and operator text records.

[0046] The second step involves preprocessing various data sources from the stainless steel product smart factory. This includes data cleaning, format and semantic standardization, and semantic annotation to ensure data quality and consistency. The data cleaning stage employs a hybrid cleaning strategy combining rule engines and machine learning. Domain-specific cleaning rules are defined, such as removing sensor outliers and correcting timestamp format errors. Data standardization adopts internationally recognized industry standards such as ISO 8000 to ensure format and semantic consistency.

[0047] The third step: Through expert knowledge, literature review, and data analysis, identify the most core concepts in the field of smart factories for stainless steel products and construct a core concept ontology. This step is the foundation of the entire ontology model. It requires identifying the classes contained in the smart factory industry for stainless steel products, and then classifying objects and data attributes to ensure the accuracy and comprehensiveness of the core concepts. For example... Figure 3 As shown, this embodiment selects three main conceptual entities by classification: intelligent logistics system, intelligent production system, and intelligent management system.

[0048] Step 4: Extract core terms for the stainless steel products industry from historical documents using natural language processing (NLP) technology to create a domain dictionary containing concepts such as "stamping equipment" and "vacuum heat treatment process." The NLP technology can employ a BERT pre-trained model.

[0049] Step 5: Eliminate semantic ambiguity across data sources using ontology alignment tools, such as unifying "AGV vehicle" and "automated guided vehicle" as the same entity. An example ontology alignment tool is LogMap.

[0050] Step 6: Based on the main concept ontology, construct branch ontologies related to specific domains. These branch ontologies contain more specific sub-concepts and entities related to the main concept. (Continue to refer to...) Figure 3 For the main body of the intelligent logistics system, the branch bodies include AGV automatic guidance systems, product sales systems, raw material procurement systems, intelligent automated warehouses, and distribution systems. For the intelligent production system, the branch bodies include alarm devices, intelligent workstations, intelligent coding systems, detection devices, automated processing devices, equipment operation and maintenance systems, and error prevention systems. Among them, automated processing devices include stamping equipment, shearing equipment, spot welding machines, vacuum heat treatment furnaces, and surface treatment equipment. For the intelligent management system, the branch bodies include safety lighting systems, data monitoring systems, intelligent control systems, production execution management systems, production monitoring management systems, production planning management systems, energy consumption management systems, order management systems, operation and maintenance management systems, and panel systems.

[0051] Step 7: Use Protege software to construct an ontology model that includes all relevant concepts and entities in the field of smart factories for stainless steel products, such as... Figure 4As shown, the intelligent production system's "error prevention system" is subdivided into "process error prevention" and "equipment error prevention" sub-branches. The "process error prevention" branch is associated with process parameter thresholds, such as the stamping pressure range, while the "equipment error prevention" branch integrates equipment self-inspection protocols, such as vibration sensor anomaly detection. A "digital twin interface" branch ontology is introduced into the intelligent management system to achieve real-time mapping between the physical factory and the virtual model, supporting simulation optimization. Through continuous iteration and optimization, the accuracy and completeness of the ontology model are ensured.

[0052] Step 8: Integrate the Pellet inference engine and SWRL rule engine into Protege to support complex logical reasoning. For example, define the rule: Copy Device(?d) ∧ hasStatus(?d, "fault") → triggerMaintenanceRequest(?d), and use SHACL (Shapes Constraint Language) to perform constraint verification on the ontology model to ensure data integrity. For example, stipulate that "vacuum heat treatment furnace" must be associated with temperature sensor data.

[0053] Step 9: Apply graph theory and machine learning techniques to conduct in-depth analysis of the relationships between concepts and entities in the ontology model, identifying key semantic associations and potential reasoning paths. The core concept ontology adopts a modular design, with each core concept ontology independently encapsulated as a microservice architecture, supporting on-demand expansion. For example, the "Intelligent Production System" ontology connects to edge computing nodes via API to receive real-time equipment status data.

[0054] Step 10: Use the owl:equivalentProperty and owl:sameAs properties of OWL to establish cross-ontology equivalence relationships. For example, dynamically associate the inventory quantity attribute of the "intelligent automated warehouse" with the material requirements attribute of the "production planning management system".

[0055] Step 11: Build an automated testing environment based on Robot Framework to simulate factory scenarios, such as order surges and equipment failures, to verify the inference response speed and accuracy of the ontology model. Evaluate the logical branch coverage of the ontology model using coverage analysis tools, such as JaCoCo, to ensure there is no redundancy or omissions.

[0056] Step 12: Based on the results of ontology model and relational network analysis, develop a semantic reasoning process. Construct a dynamic concept recognition model based on graph neural networks to monitor changes in the production environment in real time, such as the addition of new equipment models, and automatically update the core concept base. This process will utilize logical rules and algorithms to derive new conclusions or information from existing knowledge.

[0057] Step 13: Validate the effectiveness and accuracy of the ontology model through practical cases and experiments. Based on feedback and results, continuously iterate and optimize the ontology model to adapt to the changes and developments in the smart factory industry for stainless steel products.

[0058] In summary, this invention delves into ontology-based knowledge graph and relational network analysis, mastering the semantic reasoning process of deriving new conclusions or information based on semantic associations and logical rules of knowledge graphs. It analyzes the problems and difficulties faced by existing ontology construction methods, identifies the root causes of these problems, and then constructs an ontology model for the stainless steel product smart factory industry that avoids or partially solves these problems. This model can efficiently manage and integrate information from multiple data sources, while also addressing issues in the stainless steel product smart factory field such as a large and complex concept set, a small number of core concepts, low similarity between concepts, and uncomplicated hierarchical relationships.

[0059] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention in any way. Although the implementation process of the present invention has been described in detail above, those skilled in the art can still modify the technical solutions described in the foregoing examples or make equivalent substitutions for some of the technical features. All modifications and equivalent substitutions made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for constructing an intelligent factory model for stainless steel products based on ontology, characterized in that, include: Collect heterogeneous data sources from the smart factory for stainless steel products and perform preprocessing; Concepts in the field of smart factories for stainless steel products are extracted from the preprocessed data, and a main concept ontology and multiple branch ontologs associated with the main concept ontology are constructed. Based on the main concept ontology and branch ontology, an ontology model is constructed; Iterative optimization of the ontology model; Through expert knowledge, literature review, and data analysis, the most core concepts in the field of intelligent factories for stainless steel products are identified, and a backbone concept ontology is constructed. The backbone concept ontology adopts a modular design, with each backbone concept ontology independently encapsulated as a microservice architecture, supporting on-demand expansion. The backbone concept ontology includes an intelligent logistics system, an intelligent production system, and an intelligent management system. Based on the main concept ontology, multiple branch ontology structures are constructed that are associated with the lowest-level core concept of the main concept ontology. The branch ontology of the intelligent logistics system includes an AGV automatic guidance system, a product sales system, a raw material procurement system, an intelligent automated warehouse, and a distribution system. The branch ontology of the intelligent production system includes alarm devices, intelligent workstations, intelligent coding systems, detection devices, automated processing devices, equipment operation and maintenance systems, and error prevention systems. The branch ontology of the intelligent management system includes a safety lighting system, a data monitoring system, an intelligent control system, a production execution management system, a production monitoring management system, a production planning management system, an energy consumption management system, an order management system, an operation and maintenance management system, and a panel system.

2. The method for constructing a smart factory model for stainless steel products as described in claim 1, characterized in that, Based on the aforementioned main concept ontology and branch ontology, an ontology model containing all relevant concepts and entities in the field of intelligent factories for stainless steel products is constructed using Protege software. A digital twin interface branch ontology is introduced to achieve real-time mapping between the physical factory and the virtual model. At the same time, Protege integrates the Pellet inference engine and the SWRL rule engine to define logical rules and use SHACL to perform constraint verification on the ontology model.

3. The method for constructing a smart factory model for stainless steel products as described in claim 2, characterized in that, By applying graph theory and machine learning techniques, the relationships between concepts and entities in the ontology model are analyzed to identify key semantic associations and potential reasoning paths. The owl:equivalentProperty and owl:sameAs attributes of OWL are used to establish cross-ontology equivalence relations and make dynamic associations.

4. The method for constructing a smart factory model for stainless steel products as described in claim 3, characterized in that, A dynamic concept recognition model based on graph neural networks is constructed to monitor changes in the production environment of a smart factory for stainless steel products in real time, automatically update the core concept library, and derive new conclusions or information from existing knowledge using logical rules and algorithms.

5. The method for constructing a smart factory model for stainless steel products as described in claim 1, characterized in that, A distributed data acquisition framework is used to collect real-time or batch data from heterogeneous data sources in a smart factory for stainless steel products. These heterogeneous data sources include sensor time-series data, equipment logs, structured data from the ERP system, and operator text records.

6. The method for constructing a smart factory model for stainless steel products as described in claim 1, characterized in that, The collected data is preprocessed, including data cleaning, format unification, and semantic annotation. The data cleaning stage introduces a hybrid cleaning strategy based on rule engine and machine learning, and the format and semantic unification adopt the ISO 8000 international industry standard.

7. The method for constructing a smart factory model for stainless steel products as described in claim 1, characterized in that, Core terms for the stainless steel products industry are extracted from historical document data using natural language processing technology to form a domain dictionary of concepts.

8. The method for constructing a smart factory model for stainless steel products as described in claim 1, characterized in that, Ontology alignment tools eliminate semantic ambiguity across data sources and unify entity representations in heterogeneous data sources.

Images