Capturing symbolic expert knowledge for the development of industrial fault detection systems : manual and automated approaches

Young, Andrew and West, Graeme and Brown, Blair and Stephen, Bruce and Duncan, Andrew and Michie, Craig and McArthur, Stephen (2022) Capturing symbolic expert knowledge for the development of industrial fault detection systems : manual and automated approaches. International Journal of Condition Monitoring and Diagnostic Management, 25 (2). pp. 67-75. ISSN 1363-7681 (https://apscience.org/comadem/index.php/comadem/ar...)

[thumbnail of Young-etal-IJCMDM-2022-Capturing-symbolic-expert-knowledge-for-the-development-of-industrial-fault-detection]
Preview
Text. Filename: Young_etal_IJCMDM_2022_Capturing_symbolic_expert_knowledge_for_the_development_of_industrial_fault_detection.pdf
Accepted Author Manuscript
License: Strathprints license 1.0

Download (1MB)| Preview

Abstract

In critical infrastructure, such as nuclear power generation, constituent assets are continually monitored to ensure reliable service delivery through pre-empting operational abnormalities. Currently, engineers analyse this condition monitoring data manually using a predefined diagnostic process, however, rules used by the engineers to perform this analysis are often subjective and therefore it can be difficult to implement these in a rule-based diagnostic system. Knowledge elicitation is a crucial component in the transfer of the engineer’s expert knowledge into a format suitable to be encoded into a knowledge-based system. Existing methods to perform this are extremely time-consuming, therefore a significant amount of research has been undertaken in an attempt to reduce this. This paper presents an approach to reduce the time associated with the knowledge elicitation process for the development of industrial fault diagnostic systems. Symbolic representation of the engineer's knowledge is used to create a common language that can easily be communicated with the domain experts but also be formalised as the rules for a rule-based diagnostic system. Additionally, an automated approach is proposed to capture and formalise the domain expert knowledge without the need for formal knowledge elicitation sessions. Two case studies are then presented using both the manual and automated approaches. The results show that using the manual approach it is possible to quickly develop a system that can accurately detect various types of faults, and also there is a significant time saving using the automated approach without an equivalent loss in accuracy.