The purpose of this paper is to explain the development and testing of a condition‐monitoring sub‐module of an integrated plant maintenance management application based on artificial intelligence (AI) techniques, mainly knowledge‐based systems, having several modules, sub‐modules and sections.
The approach is applicable to general purpose machinery. A maintenance knowledge base is developed from published information on maintenance management like handbooks, journals, conference proceedings, because of difficulty in accessing expert knowledge and information on actual machine problems, from experts in maintenance management. The knowledge‐based engine comprises intelligent algorithms and software‐generated pop‐ups/alerts/alarms predictive tools. The expert system on an off‐line basis, on a failure in the plant's machinery or deterioration in performance, will trigger fault diagnosis to detect the reason and give immediate advice to the maintenance group.
Knowledge‐based intelligent machine troubleshooting/maintenance software enables maintenance technicians to refer to custom‐made, ready‐to‐use and easily upgradable maintenance software. Its benefits include: reduction in machine down‐time, reduction in skill level for maintenance activities, ease of maintenance, speedy response and affordable cost. The paper collectively deals with the analysis of the state‐of‐the‐art expert systems for diagnosis and maintenance of general‐purpose industrial machinery.
The software is essentially for general purpose industrial machinery (stand‐alone type) applications. For continuously operating machinery, the software has to be altered to accommodate continuous data through strategically mounted sensors.
Knowledge based, ready‐to‐use, custom‐built, maintenance management software application having many modules and sub‐modules on various aspects of modern maintenance practices has direct application for shopfloor maintenance.
A part of fully‐fledged maintenance management application based on AI principles is discussed in the present paper. Its benefits include: use of latest methodology – AI techniques for maintenance field, ready‐to‐install condition, vast and immediate access to maintenance management information, user‐friendly and interactive modules, easily upgradable features for the application.
Nadakatti, M., Ramachandra, A. and Santosh Kumar, A. (2008), "Artificial intelligence‐based condition monitoring for plant maintenance", Assembly Automation, Vol. 28 No. 2, pp. 143-150. https://doi.org/10.1108/01445150810863725Download as .RIS
Emerald Group Publishing Limited
Copyright © 2008, Emerald Group Publishing Limited