Integrated AI-Driven Aircraft Maintenance System with Real-Time Crack Detection, Battery Life Estimation, Jet Engine Predictive Maintenance

DOI

10.2991/978-94-6463-858-5_32How to use a DOI?

Keywords

AI-driven maintenance; Aircraft Monitor; Battery Life Estimation; Jet Cycles Prediction; YOLOv5; Streamlit dashboard; Remaining Useful Life (RUL); Battery predictive analytics; Webcam-based defect detection; Jet engine predictive maintenance; Deep learning; Machine learning

Abstract

Deep learning and machine learning techniques enable the AI system described in this research to enhance aircraft predictive maintenance operates. The program integrates three main components that function as Aircraft Monitor and support Battery Life Estimation and Jet Cycles Prediction. The Aircraft Monitor module employs YOLOv5 for real-time defect detection in aircraft fuselage images, with a user-friendly interface supporting image uploads and realtime webcam capture for inspections. The Battery Life Estimation module works with Random Forest Regressor to foretell aircraft battery Remaining Useful Life (RUL) after the system processes discharge cycle inputs together with voltage and charging time information provided by users. The Jet Cycles Prediction module utilizes a neural network developed with PyTorch to forecast jet engine Remaining Useful Life through engine sensors that allows proactive maintenance executions. Users can obtain access through a simple interface with Streamlit which brings together three predictive tools on a single dashboard. The detection accuracy of YOLOv5 stands at 92% while the battery life prediction exhibits an MSE value of 0.18 and the engine RUL forecasting achieves an R² effect of 88.7% in its predictive outcomes.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Netaji Gandi
AU  - Bandi Mounika
AU  - Gajjana Joshna
AU  - Rittapalli Sruthi
AU  - Sundarapu Prathima
PY  - 2025
DA  - 2025/11/04
TI  - Integrated AI-Driven Aircraft Maintenance System with Real-Time Crack Detection, Battery Life Estimation, Jet Engine Predictive Maintenance
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 365
EP  - 376
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_32
DO  - 10.2991/978-94-6463-858-5_32
ID  - Gandi2025
ER  -