Ontology-Based Schema to Support Maintenance Knowledge Representation With a Case Study of a Pneumatic Valve

This paper proposes a methodology for knowledge representation using ontology concepts. We employ an ontology-based schema to overcome the problems of heterogeneity and inconsistency in maintenance records, which are attributable to abbreviations, noisy data, nongeneric data structures, and ambiguous technical words in textual maintenance records. Our methodology employs a bond graph model (BGM) to produce a function structure of equipment related to fault propagation in part-component levels. Our method combines OWL-Lite/RDF and the ISO 14224 and ISO 15926 international standards in order to obtain a generic system-level representation model. Our approach also constructs transparent cause-effect knowledge, which facilitates interpretation and computer conversion using ISO 14224 and ISO 15926. The web ontology language (OWL) and resource description framework (RDF) are used to convert the generic human-readable interpretation into a standard computer-readable representation, thereby generating a knowledge base with maximum shareability and accessibility. We applied the methodology to a typical pneumatic valve. The results show that BGM can cross-link the identified words and the domain-specific logic to obtain the function structure of an object with causality inference, as well as enriching semantic extraction based on the context of a maintenance report, which improves the interpretation and computer conversion. Using OWL/RDF, actions such as interexchange, retrieval, and storage are possible for fault diagnosis applications in a multidisciplinary environment. Our method provides a generic technical understanding, which enriches semantic extraction and knowledge discovery in a typical maintenance report.

[1]  John W. Sheppard,et al.  Ontologies for Data Mining and Knowledge Discovery to Support Diagnostic Maturation , 2007 .

[2]  Finn Arve Aagesen,et al.  Capability Ontology in Adaptable Service System Framework , 2010, 2010 Fifth International Multi-conference on Computing in the Global Information Technology.

[3]  D Wang,et al.  Ontology-based fault diagnosis for power transformers , 2010, IEEE PES General Meeting.

[4]  Carlos Heny,et al.  Pseudo-bond graph model and simulation of a continuous stirred tank reactor , 2000, J. Frankl. Inst..

[5]  Jian Chen,et al.  Coalition-Based Approach to Task Allocation of Multiple Robots With Resource Constraints , 2012, IEEE Transactions on Automation Science and Engineering.

[6]  Stefan Biffl,et al.  A conceptual framework for semantic case-based safety analysis , 2011, ETFA2011.

[7]  Youmin Zhang,et al.  Bibliographical review on reconfigurable fault-tolerant control systems , 2003, Annu. Rev. Control..

[8]  Shu-Hsien Liao,et al.  Expert system methodologies and applications - a decade review from 1995 to 2004 , 2005, Expert Syst. Appl..

[9]  Samaneh Shokravi,et al.  An ontology approach to support FMEA studies , 2009, 2009 Annual Reliability and Maintainability Symposium.

[10]  S. Yacout.  Logical analysis of maintenance and performance data of physical assets, ID34 , 2012, 2012 Proceedings Annual Reliability and Maintainability Symposium.

[11]  Tim Baines,et al.  State-of-the-art in integrated vehicle health management , 2009 .

[12]  Dnyanesh Rajpathak,et al.  A generic ontology development framework for data integration and decision support in a distributed environment , 2011, Int. J. Comput. Integr. Manuf..