Output details

Multi-step ahead direct prediction for machine condition prognosis using regression trees and neuro-fuzzy systems

This study presents a new approach based on artificial intelligence and time-series forecasting techniques to predict the degradation of machines and trends in fault propagation. In this work, long-term direct prediction method which is a challenging task in time-series prediction is considered. Additionally, a novel method for determining the number of essential observations and the number of steps which can be forecasted is proposed. As a result, the proposed approach allows tracking of changes in machine degradation and has potential for use as a machine prognosis tool.