TY - JOUR
T1 - Deep reinforcement learning for predictive aircraft maintenance using probabilistic Remaining-Useful-Life prognostics
AU - Lee, J.
AU - Mitici, M.A.
PY - 2022
Y1 - 2022
N2 - The increasing availability of sensor monitoring data has stimulated the development of Remaining-Useful-Life (RUL) prognostics and maintenance planning models. However, existing studies focus either on RUL prognostics only, or propose maintenance planning based on simple assumptions about degradation trends. We propose a framework to integrate data-driven probabilistic RUL prognostics into predictive maintenance planning. We estimate the distribution of RUL using Convolutional Neural Networks with Monte Carlo dropout. These prognostics are updated over time, as more measurements become available. We further pose the maintenance planning problem as a Deep Reinforcement Learning (DRL) problem where maintenance actions are triggered based on the estimates of the RUL distribution. We illustrate our framework for the maintenance of aircraft turbofan engines. Using our DRL approach, the total maintenance cost is reduced by 29.3% compared to the case when engines are replaced at the mean-estimated-RUL. In addition, 95.6% of unscheduled maintenance is prevented, and the wasted life of the engines is limited to only 12.81 cycles. Overall, we propose a roadmap for predictive maintenance from sensor measurements to data-driven probabilistic RUL prognostics, to maintenance planning.
AB - The increasing availability of sensor monitoring data has stimulated the development of Remaining-Useful-Life (RUL) prognostics and maintenance planning models. However, existing studies focus either on RUL prognostics only, or propose maintenance planning based on simple assumptions about degradation trends. We propose a framework to integrate data-driven probabilistic RUL prognostics into predictive maintenance planning. We estimate the distribution of RUL using Convolutional Neural Networks with Monte Carlo dropout. These prognostics are updated over time, as more measurements become available. We further pose the maintenance planning problem as a Deep Reinforcement Learning (DRL) problem where maintenance actions are triggered based on the estimates of the RUL distribution. We illustrate our framework for the maintenance of aircraft turbofan engines. Using our DRL approach, the total maintenance cost is reduced by 29.3% compared to the case when engines are replaced at the mean-estimated-RUL. In addition, 95.6% of unscheduled maintenance is prevented, and the wasted life of the engines is limited to only 12.81 cycles. Overall, we propose a roadmap for predictive maintenance from sensor measurements to data-driven probabilistic RUL prognostics, to maintenance planning.
KW - predictive maintenance
KW - remaining useful life
KW - probabilistic RUL prognostics
KW - deep reinforcement learning
KW - turbofan engines
UR - http://www.scopus.com/inward/record.url?scp=85141438553&partnerID=8YFLogxK
U2 - 10.1016/j.ress.2022.108908
DO - 10.1016/j.ress.2022.108908
M3 - Article
SN - 0951-8320
VL - 230
JO - Reliability Engineering & System Safety
JF - Reliability Engineering & System Safety
M1 - 108908
ER -