International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | NASA Turbofan Predictive Maintenance System |
|---|---|
| ABSTRACT | Predicting the Remaining Useful Life (RUL) of aircraft turbofan engines helps reduce unscheduled maintenance and improves operational safety. This paper presents a comparative study and end-to-end predictive maintenance pipeline developed using multiple machine learning approaches, including a feed-forward Neural Network (NN), a Convolutional Neural Network (CNN) adapted for time-series data, a Long Short-Term Memory (LSTM) model, a classical time-series regression baseline, and an Ensemble Data-Adaptive Linear Regressor (EDALR). The models were trained and evaluated using NASA’s C-MAPSS turbofan engine degradation dataset. Performance comparison is carried out using RMSE, MAE, and R² metrics, along with visual analysis of predicted RUL and health index curves. Experimental results indicate that the NN model achieves higher short-term prediction accuracy, while the EDALR ensemble provides more stable and reliable long-horizon predictions. The proposed system is integrated with a FastAPI backend and a React-based frontend for real-time RUL prediction and engine health monitoring. |
| AUTHOR | HIMASHREE S, LAVANYA J S, SPOORTHI N, TEJASWINI R, PUSHPALATHA S S Department of Computer Science and Engineering, GSSS Institute of Engineering and Technology for Women, Mysuru, Affiliated to VTU, Belagavi, Karnataka, India Assistant Professor, Department of Computer Science and Engineering, GSSS Institute of Engineering and Technology for Women, Mysuru, Affiliated to VTU, Belagavi, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312036 |
| pdf/36_NASA Turbofan Predictive Maintenance System.pdf | |
| KEYWORDS |
