Jet Engine Health Monitoring System using ML for Predictive Maintenance — a university group project.

IEEE Published | ML model for Aircraft Engine RUL prediction using XGBoost & Random Forest on NASA C-MAPSS dataset. RMSE: 23.8, R²: 0.67. Flask web app + PostgreSQL. ICMCSI 2025 (Paper ID: ICMCSI-472)

End-to-end predictive maintenance system: XGBoost RUL prediction (RMSE 16.7 cycles on NASA CMAPSS) + FastAPI + Streamlit + LangGraph agentic AI, deployed on Google Cloud Run.

LSTM-based Remaining Useful Life prediction for turbofan engines using NASA CMAPSS dataset

✈️ NASA Predictive Maintenance System >> 🚀 End-to-end predictive maintenance system for turbofan engines — detects failure 122 cycles early using LSTM, PCA, and explainable AI (XAI), deployed as a production-grade Streamlit dashboard.

Real-time rocket telemetry anomaly detection — Isolation Forest + Autoencoder ensemble, 95% accuracy. Built for ISRO PSLV PS3 stage failure prevention.

Predictive maintenance for turbofan engines - RUL prediction on NASA CMAPSS using Random Forest, XGBoost, sklearn Pipelines & MLflow

End-to-end predictive maintenance system using NASA CMAPSS dataset with XGBoost, Streamlit dashboard, and Docker deployment.

HPC-optimized RUL prediction on NASA C-MAPSS FD001 dataset using XGBoost

High-performance ETL pipeline for predictive maintenance using NASA CMAPSS data (Vectorized/Clean Code)

Repair-Aware Survival Analysis: Multi-domain maintenance optimization with NASA CMAPSS & SECOM validation.

Predictive maintenance for aircraft turbofan engines, RUL prediction using ML & LSTM on NASA CMAPSS dataset

End-to-end ML platform for turbofan engine RUL forecasting, failure classification, and anomaly detection using NASA CMAPSS FD001 dataset

End-to-end predictive maintenance ML system — RUL prediction, anomaly detection, FastAPI, Docker

Predictive maintenance of aircraft engines using NASA CMAPSS data with Random Forest, XGBoost, SHAP explainability, and Remaining Useful Life (RUL) prediction.

Predicts remaining useful life of turbofan engines from NASA CMAPSS sensor data (Gradient Boosting, RMSE ≈ 18.87); model exported as deployment-ready artifacts for a real-time inference API.

Production-grade AI Predictive Maintenance Copilot using NASA CMAPSS data, combining classical ML, deep learning (LSTM/GRU), unified inference, FastAPI, Streamlit, GenAI (RAG), Docker, and Google Cloud Run deployment.

Predictive maintenance platform with SHAP explainability, KS drift detection, OEE benchmarking, and interactive what-if scenarios. NASA C-MAPSS benchmark recast as mining ops, deployed on Streamlit Cloud.

Aircraft engine failure prediction · CatBoost · FastAPI + Docker · NASA CMAPSS · ROC-AUC 0.991

NASA C-MAPSS 터보팬 엔진 LSTM 기반 잔존수명(RUL) 예측 | Phase 3 예지보전 프로젝트