KBE development for criticality classification of mechanical equipment: A fuzzy expert system

Recent research reveals that a significant number of unwanted events have occurred due to latent failures which route back to human errors linked to maintenance engineering applications. To assure systems safety at different technical levels, it is vital that human errors linked to the maintenance regime are mitigated. Frequent knowledge migration from one industrial organization to another has deteriorated maintenance engineering related assessments, evaluations and recommendations, especially as a result of inexperienced personnel and the lack of expert advice when it is needed. Hence, it is important to develop methodologies to recycle the knowledge accrued in an industrial organization. The knowledge based engineering (KBE) approaches, along with expert systems related analysis, provide a foundation for knowledge recycling. This paper presents an approach to perform functional failure criticality (FFC) based on the guidelines specified in a standard for prioritizing maintenance work orders for mechanical equipment and instrumentation. Use of the ranges and linguistic variables tend to occur suboptimal classifications in FFC assessments due to the lack of a consistent approach. This inhibits incorporating actual circumstances at the boundary of the input ranges or at the levels of linguistic data and criticality levels. This has further been exacerbated by the lack of experienced personnel. Hence, this paper suggests KBE development via a fuzzy logic system (FLS) to overcome the aforementioned challenge and minimize the variations present in the analysis. Membership functions and a rule base have been developed based on the experts’ knowledge, data, information and guidelines specified in the selected standard. An illustrative case has been performed with the help of two engineering contractor companies which provide maintenance support services. FFC assessments using the suggested KBE development have been presented to verify the applicability of the approach.