Predictive Aircraft Engine Maintenance

Chhikara, Vikas (2020) Predictive Aircraft Engine Maintenance. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

For maintenance decisions and selecting a suitable operation for a machine, it’s necessary to analyze the remaining useful life of the machine accurately. Machine learning techniques for RUL are usually focused as they are faster and easy to use. The existing models for RUL prediction are a single path or based on a top down approach. For increasing the accuracy and to achieve promising results this report proposes a methodology that combines the Convolutional neural networks (CNN) and Long short-term memory in order to predict the useful life of the machine. A different approach than existing models for this report CNN and LSTM model is actually combined rather than just using CNN for extracting features. But as for input single timestamp is used that can further lead to the same batch padding which could affect the model’s prediction. The proposed methodology is used to overcome these issues by sliding the time one step size. For this report turbofan engine degradation data by NASA is used for training, testing, and validation of the RUL Model. By comparing the model using different Models like simple LSTM and transfer learning using the same dataset. With comparison, it will be easy to examine the performance of the proposed approach.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software T Technology > TL Motor vehicles. Aeronautics. Astronautics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	22 Jan 2021 11:22
Last Modified:	22 Jan 2021 11:22
URI:	https://norma.ncirl.ie/id/eprint/4437

Actions (login required)

View Item