Fault diagnosis in aircraft fuel system components with machine learning algorithms
| dc.contributor.advisor | Starr, Andrew | |
| dc.contributor.advisor | Perinpanayagam, Suresh | |
| dc.contributor.author | Subramanian, Nithya | |
| dc.date.accessioned | 2023-03-30T09:37:45Z | |
| dc.date.available | 2023-03-30T09:37:45Z | |
| dc.date.embargo | 2023-05-25 | |
| dc.date.issued | 2022-01 | |
| dc.description.abstract | There is a high demand and interest in considering the social and environmental effects of the component’s lifespan. Aircraft are one of the most high-priced businesses that require the highest reliability and safety constraints. The complexity of aircraft systems designs also has advanced rapidly in the last decade. Consequently, fault detection, diagnosis and modification/ repair procedures are becoming more challenging. The presence of a fault within an aircraft system can result in changes to system performances and cause operational downtime or accidents in a worst-case scenario. The CBM method that predicts the state of the equipment based on data collected is widely used in aircraft MROs. CBM uses diagnostics and prognostics models to make decisions on appropriate maintenance actions based on the Remaining Useful Life (RUL) of the components. The aircraft fuel system is a crucial system of aircraft, even a minor failure in the fuel system can affect the aircraft's safety greatly. A failure in the fuel system that impacts the ability to deliver fuel to the engine will have an immediate effect on system performance and safety. There are very few diagnostic systems that monitor the health of the fuel system and even fewer that can contain detected faults. The fuel system is crucial for the operation of the aircraft, in case of failure, the fuel in the aircraft will become unusable/unavailable to reach the destination. It is necessary to develop fault detection of the aircraft fuel system. The future aircraft fuel system must have the function of fault detection. Through the information of sensors and Machine Learning Techniques, the aircraft fuel system’s fault type can be detected in a timely manner. This thesis discusses the application of a Data-driven technique to analyse the healthy and faulty data collected using the aircraft fuel system model, which is similar to Boeing-777. The data is collected is processed through Machine learning Techniques and the results are compared | en_UK |
| dc.description.coursename | PhD in Manufacturing | en_UK |
| dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/19376 | |
| dc.language.iso | en | en_UK |
| dc.rights | © Cranfield University, 2015. All rights reserved. No part of this publication may be reproduced without the written permission of the copyright holder. | |
| dc.subject | Machine learning | en_UK |
| dc.subject | diagnosis | en_UK |
| dc.subject | PHM | en_UK |
| dc.subject | CBM | en_UK |
| dc.subject | aircraft fuel system | en_UK |
| dc.subject | component level | en_UK |
| dc.title | Fault diagnosis in aircraft fuel system components with machine learning algorithms | en_UK |
| dc.type | Thesis | en_UK |