Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Integrating Ontology Design with the CRISP-DM in the context of Cyber-Physical Systems Maintenance

Milapji Singh Gill, Tom Westermann, Gernot Steindl, Felix Gehlhoff, Alexander Fay

TL;DR

The paper tackles the problem of efficiently integrating domain expert–driven ontology design with CRISP-DM to support CPS maintenance. It proposes a three-phase method: (1) systematic ontology requirements specification to derive Competency Questions (CQs) and domain knowledge needs, (2) contextualization of CPS lifecycle data via modular, reusable ontology artifacts (Lightweight Ontology) aligned with standards to support data understanding and preparation, and (3) semantic annotation and alignment of data-driven outputs (leading to a Heavyweight Ontology) with deployment of digital maintenance services. A case study on a modular mixing plant demonstrates how Timed Automata and anomaly detection can be incorporated into a knowledge graph, leveraging OBDA, SPARQL federation, and semantic microservices guided by RAMI 4.0 principles. The approach shows that reusing Ontology Design Patterns accelerates development and enables end-to-end integration of symbolic and subsymbolic AI for CPS maintenance, while highlighting ongoing challenges in mapping effort, data quality, and uncertainty. The work provides a practical framework for building CPS maintenance knowledge graphs that support automated diagnostics and context-rich decision support, with potential extensions to Informed ML and Large Language Model–assisted knowledge extraction.

Abstract

In the following contribution, a method is introduced that integrates domain expert-centric ontology design with the Cross-Industry Standard Process for Data Mining (CRISP-DM). This approach aims to efficiently build an application-specific ontology tailored to the corrective maintenance of Cyber-Physical Systems (CPS). The proposed method is divided into three phases. In phase one, ontology requirements are systematically specified, defining the relevant knowledge scope. Accordingly, CPS life cycle data is contextualized in phase two using domain-specific ontological artifacts. This formalized domain knowledge is then utilized in the CRISP-DM to efficiently extract new insights from the data. Finally, the newly developed data-driven model is employed to populate and expand the ontology. Thus, information extracted from this model is semantically annotated and aligned with the existing ontology in phase three. The applicability of this method has been evaluated in an anomaly detection case study for a modular process plant.

Integrating Ontology Design with the CRISP-DM in the context of Cyber-Physical Systems Maintenance

TL;DR

The paper tackles the problem of efficiently integrating domain expert–driven ontology design with CRISP-DM to support CPS maintenance. It proposes a three-phase method: (1) systematic ontology requirements specification to derive Competency Questions (CQs) and domain knowledge needs, (2) contextualization of CPS lifecycle data via modular, reusable ontology artifacts (Lightweight Ontology) aligned with standards to support data understanding and preparation, and (3) semantic annotation and alignment of data-driven outputs (leading to a Heavyweight Ontology) with deployment of digital maintenance services. A case study on a modular mixing plant demonstrates how Timed Automata and anomaly detection can be incorporated into a knowledge graph, leveraging OBDA, SPARQL federation, and semantic microservices guided by RAMI 4.0 principles. The approach shows that reusing Ontology Design Patterns accelerates development and enables end-to-end integration of symbolic and subsymbolic AI for CPS maintenance, while highlighting ongoing challenges in mapping effort, data quality, and uncertainty. The work provides a practical framework for building CPS maintenance knowledge graphs that support automated diagnostics and context-rich decision support, with potential extensions to Informed ML and Large Language Model–assisted knowledge extraction.

Abstract

In the following contribution, a method is introduced that integrates domain expert-centric ontology design with the Cross-Industry Standard Process for Data Mining (CRISP-DM). This approach aims to efficiently build an application-specific ontology tailored to the corrective maintenance of Cyber-Physical Systems (CPS). The proposed method is divided into three phases. In phase one, ontology requirements are systematically specified, defining the relevant knowledge scope. Accordingly, CPS life cycle data is contextualized in phase two using domain-specific ontological artifacts. This formalized domain knowledge is then utilized in the CRISP-DM to efficiently extract new insights from the data. Finally, the newly developed data-driven model is employed to populate and expand the ontology. Thus, information extracted from this model is semantically annotated and aligned with the existing ontology in phase three. The applicability of this method has been evaluated in an anomaly detection case study for a modular process plant.
Paper Structure (14 sections, 4 figures)

This paper contains 14 sections, 4 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Requirements
  4. Methodology
  5. Overview
  6. Systematic Ontology Requirements Specification
  7. Contextualisation of CPS Life Cycle Data
  8. Semantic Annotation of Extracted Information
  9. Case Study
  10. Ontology Requirements Specification
  11. Contextualisation of Mixing Module Life Cycle Data
  12. Semantic Annotation of Extracted Timed Automata and Anomalies
  13. Discussion
  14. Summary And Outlook

Figures (4)

  • Figure 1: Combination of domain expert-centric ontology design and the CRISP-DM
  • Figure 2: Mixing module of the process plant
  • Figure 3: Anomaly detection process modeled with BPMN
  • Figure 4: Excerpt from the LWO for the case study