Date of Award
Doctor of Philosophy (PhD)
Gerald M. Knapp
An innovative new framework for the implementation of reliability centered maintenance (RCM) in industrial settings was developed and implemented during this study. Fuzzy reasoning algorithms were designed to evaluate and assess the likelihood of equipment failure mode precipitation and aggravation. Furthermore, an alternative to the traditional RCM decision tree for prioritizing equipment failure modes was defined through the development of an approximate reasoning scheme. This priority scheme not only takes into account the relevancy of failure modes on local and product effects, but also their possibility of occurrence, as well as associated negative consequences on adjacent machinery. The new RCM approach was implemented through an objected-oriented expert system built to perform reliability centered maintenance analysis on industrial chemical processes. The developed expert system reads the process flowsheet generated by ASPEN Plus, a chemical process simulation package, and, based on relevant machine operating data, it provides the user with the final process RCM availability structure diagram. This availability diagram consists of a listing of all critical machine failure modes likely to occur, prioritized according to their overall negative impact on the process, as well as important information on their corresponding local and system effects, and suggested controls for their detection. Although the chemical process industry was selected as the application domain for this research, the developed RCM framework was designed to be extensible across the entire maintenance activity spectrum, regardless of the type of industry associated. The prototype knowledge based system was constructed and delivered on an IBM compatible Personal Computer through an object oriented computer shell, LEVEL 5 Object.
Fonseca, Daniel Jesus, "A Knowledge-Based System for Reliability-Centered Maintenance in the Chemical Industry." (1998). LSU Historical Dissertations and Theses. 6671.