Journal of Mechanical, Civil and Industrial Engineering ISSN: 2710-1436 DOI: 10.32996/jmcie Journal Homepage: www.al-kindipublisher.com/index.php/jmcie JMCIE AL-KINDI CENTER FOR RESEARCH AND DEVELOPMENT Copyright: © 2022 the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) 4.0 license (https://creativecommons.org/licenses/by/4.0/). Published by Al-Kindi Centre for Research and Development, London, United Kingdom. Page | 79 | RESEARCH ARTICLE Determining RUL Predictive Maintenance on Aircraft Engines Using GRU Adryan Fitra Azyus 1 ✉ Sastra Kusuma Wijaya 2 and Mohd Naved 3 1 Faculty of Mathematics and Sciences, Nature/Physics Instrumentation, University of Indonesia, Indonesia 2 Fakultas Matematika dan Ilmu Pengetahuan, Alam/Fisika Instrumentasi, Universitas Indonesia, Indonesia 3 Department of Business Analytics, Jagannath University, D elhi-NCR, India. Corresponding Author: Adryan Fitra Azyus, E-mail: adryan.fitra01@ui.ac.id | ABSTRACT Prognostic and health management (PHM) in the aviation industry is expanding because of its effect on economic and human safety. Advanced maintenance shall be applied to this industry to inform aircraft engine conditions. PdM (Predictive Maintenance) is an advanced maintenance technique that can be applied to the aviation industry because of its high-precision prediction. Combining PdM as a technique to calculate the RUL (Remaining Useful Lifetime ) and ML (Machine Learning) as a tool to make high-accuracy predictions is mixed together that accurately forecasts the state of aircraft machine condition and on the best time to get the maintenance or service. In this work, we use the NASA Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) data set. This work proposes GRU to determine RUL on aircraft engines to implement a Predictive maintenance strategy. For the training parameters tested in this study, we used a batch size of 512, a learning rate with Adam optimizer of 0.001, then epochs of 200. The essence of the results of this experiment is to obtain a new method with a simpler calculation process and the epoch value and a faster prediction process compared to other methods used, and the results obtained can approach the original value from an economic point of view and the RUL prediction process using the GRU. | KEYWORDS RUL Predictive Maintenance; Aircraft Engines; Prognostic and health management | ARTICLE INFORMATION ACCEPTED: 09 December 2022 PUBLISHED: 11 December 2022 DOI: 10.32996/jmcie.2022.3.3.10 1. Introduction Machine learning (ML) is a subsection of Artificial Intelligence. This method or algorithm can learn based on training, which is the given information about something, and it can be used in the future when the algorithm is applied. Deep learning (DL) is the development algorithm from ML to fix its limitation. DL implemented an artificial neural network (ANN) for its algorithm and greatly impacted the supervised learning method. DL algorithms, such as image processing and face and speech recognition, are widely employed. The other function of ML and DL is to predict with high accuracy because both algorithms or models can calculate based on training from a dataset or additional information [Wuest, 2016]. The prediction process that needs mathematical methods and techniques is suitable for maintenance strategies such as Prognostic and health management (PHM). Today's popular PHM is on the aviation industry to predict the state of the aircraft engine condition because the capacity of machinery working cannot last forever. Sometimes, it will be broken-down because of out-date operation. Machinery systems that include sensors are just monitoring the state of the machine but cannot make a report of the machine's condition. A maintenance strategy must apply to the scheduled machinery system to avoid the worst event (failure) and get information about a machine's status. Predictive maintenance (PdM) is strategy maintenance, but continuously monitoring the state of the machine, the maintenance performed optimally. In other words, PdM indicates the state of the machine to perform a maintenance schedule based on historical data, integrity factors, statistical inference methods, and engineering approaches [Susto, 2012].