Experts’ knowledge renewal and maintenance actions effectiveness in high-mix low-volume industries, using Bayesian approach

Abstract

Increasing demand diversity has resulted in high-mix low-volume production where success depends on the ability to quickly design and develop new products. This requires sustainable production capacities and efficient equipment utilization which are ensured through appropriate maintenance strategies. Presently, these are derived from experts' knowledge, capitalized in FMECA (failure mode, effect and criticality analysis), and effective maintenance procedures. Abu-Samah et al. (Failure prognosis methodology for improved proactive maintenance using bayesian approach. In: 9th IFAC symposium on fault detection, supervision and safety for technical processes. Paris, France, 2015) found increasing unscheduled breakdowns, failure durations and number of repair actions in each failure as the key challenges while sustaining production capacities in complex production environment. Obviously, maintenance based on the historical knowledge is not always effective to cope up with an evolving nature of equipment failure behaviors. Therefore, this paper presents an operational methodology based on Bayesian approach and an extended FMECA method to support experts' knowledge renewal and maintenance actions effectiveness. In the proposed methodology, FMECA files capitalize and model experts' existing knowledge as an operational Bayesian network (O-BN) to provide real-time feedback on poorly executed maintenance actions. The accuracy of O-BN is monitored through drifts in maintenance performance measurement (MPM) indicators that result in learning an unsupervised Bayesian network (U-BN) to discover new causal relations from historical data. The structural difference between O-BN and U-BN highlights potential new knowledge which is validated by experts prior to updating existing FMECA and associated maintenance procedures. The proposed methodology is evaluated in a well-reputed high-mix low-volume semiconductor production line to demonstrate its ability to dynamically renew experts' knowledge and improve maintenance actions effectiveness.