Browsing by Author "Bulka, Dominik"

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    Advancing fault diagnosis through ontology-based knowledge capture and application
    (IEEE, 2024-07-25) Del Amo, Iñigo Fernández; Erkoyuncu, John Ahmet; Bulka, Dominik; Farsi, Maryam; Ariansyah, Dedy; Khan, Samir; Wilding, Stephen
    This article addresses a critical gap in the field of fault diagnosis for complex systems, focusing on the development and application of an ontology-based approach to capture and utilize expert knowledge. The key objective is to enhance fault diagnosis precision and effectiveness, specifically in challenging No-Fault-Found (NFF) scenarios, by harnessing the extensive, often implicit, understanding of seasoned professionals. The study uses a comprehensive methodology that includes creating a specialized ontology called DIAGONT, which captures the expert reasoning in fault diagnosis. Field experts contribute to the development of this ontology, ensuring its relevance and applicability. Real-world case studies and controlled experiments are used to rigorously validate the ontology. The goal of these experiments is to evaluate how effective the ontology is in enhancing fault diagnosis procedures when compared to traditional methods. Our case studies focused on two complex engineering assets, a loading arm and a helicopter mission system, due to their complexity and the frequency of non-functional failure scenarios. The analysis shows that using the DIAGONT ontology leads to improved accuracy and efficiency in fault diagnosis. A structured format allowed experts to successfully capture and reuse diagnostic knowledge, resulting in a noticeable reduction in NFF scenarios. The application of ontology-based approach exhibited potential in enhancing knowledge transfer between experts and less experienced technicians, potentially resulting in long-lasting improvements in maintenance practices. The results highlight how ontology-based systems can improve fault diagnosis in complex engineering systems.
  • No Thumbnail Available
    ItemOpen Access
    Data: A Design Framework for Adaptive Digital Twins
    (Cranfield University, 2023-09-04 09:26) ahmet Erkoyuncu, John; Fernández del amo blanco, Iñigo; Ariansyah, Dedy; Bulka, Dominik; Vrabič, Rok; Roy, Rajkumar
    This paper develops a new DT design framework that uses ontologies to enable co-evolution with the CES by capturing data in terms of variety, velocity, and volume across the asset life-cycle. The framework has been tested successfully on a helicopter gearbox demonstrator and a mobile robotic system across their life cycles, illustrating DT adaptiveness without the data architecture needing to be modified. The data presented in this portal is related to the data that was generated in the validation process.
  • No Thumbnail Available
    ItemOpen Access
    Datasets: Ontology-based diagnosis reporting and monitoring to improve fault finding in Industry 4.0
    (Cranfield University, 2020-08-14 09:41) Fernández del amo blanco, Iñigo; ahmet Erkoyuncu, John; Farsi, Maryam; Bulka, Dominik; Wilding, Stephen
    This repository includes datasets on experimental cases of study and analysis regarding the research called "Ontology-based diagnosis reporting and monitoring to reduce no-fault-found scenarios in Industry 4.0".DOI:Abstract: "Industry 4.0 is bringing a new era of digitalisation for complex equipment. It especially benefits equipment’s monitoring and diagnostics with real-time analysis of heterogenous data sources. Management of such sources is an important research challenge. A relevant research gap involves integration of experts’ diagnosis knowledge. Experts have valuable knowledge on failure conditions that can support monitoring systems and their limitations in no-fault-found scenarios. But their knowledge is normally transferred as reports, which include unstructured data difficult to re-use. Thus, this paper proposes ontology-based diagnosis reporting and monitoring methods to capture and re-use expert knowledge for improving diagnosis efficiency. It aims to capture expert knowledge in a structured format and re-use it in monitoring systems to provide failure recommendations in no-fault-found conditions. This research conducted several methods for validating the proposed methods. Laboratory experiments present time and errors reduction rates of 20% and 12% compared to common data-driven monitoring approaches for diagnosis tasks in no-fault-found scenarios. Subject-matter experts’ surveys evidence the usability of the proposed methods to work in real-life conditions. Thus, this paper’s proposal can be considered as a method to bridge the gap for integrated data management in the context of Industry 4.0."
  • Thumbnail Image
    ItemOpen Access
    A design framework for adaptive digital twins
    (Elsevier, 2020-05-20) Erkoyuncu, John Ahmet; Fernández del Amo, Iñigo; Ariansyah, Dedy; Bulka, Dominik; Vrabič, Rok; Roy, Rajkumar
    Digital Twin (DT) is a ‘living’ entity that offers potential with monitoring and improving functionality of interconnected complex engineering systems (CESs). However, lack of approaches for adaptively connecting the existing brownfield systems and their data limits the use of DTs. This paper develops a new DT design framework that uses ontologies to enable co-evolution with the CES by capturing data in terms of variety, velocity, and volume across the asset life-cycle. The framework has been tested successfully on a helicopter gearbox demonstrator and a mobile robotic system across their life cycles, illustrating DT adaptiveness without the data architecture needing to be modified.