Ensemble trees learning based improved predictive maintenance using IIoT for turbofan engines

Abstract

An unprecedented growth of the industrial sector, has led to an exponential increase in the amount of industrial IoT (IIoT) data. This is sprouting increased interest in the data-driven predictive maintenance (PDM) of the industrial equipments in cyber-physical systems (CPS). PDM is a prominent strategy which can achieve increased reliability and safety of CPS while attaining reduced maintenance cost by estimating the current health status and the remaining user life (RUL). In modern days, schedule-based airline maintenance does not consider prediction of faults in advance, which may result in undue maintenance situations where components are still kept in service even though they might have exceeded their defined limit of failure. Therefore, accurate degradation assessment and RUL prediction makes sense on dual fronts of guiding sensible decision-making regarding aviation safety and rational maintenance. To identify most crucial attributes and critical relationship among the attributes for fault detection of individual equipment(s) in the turbofan aircraft engine, We propose a predictive maintenance model using data-driven prognostic method for RUL estimation with multiple operating conditions. we capture increased insight using improved feature engineering and apply ensemble tree learning. Extensive experiments are performed on a widely used Prognostics and Health Management (PHM) C-MAPSS dataset. It is observed that Gradient Boosted Trees (GBT) with an accuracy of 93.91% performs better over Random Forest (RF) with 91.78% accuracy. However RF performed competitively with a much faster compute time in comparison to GBT.