c-mapss

N-CMAPSS data preparation for Machine Learning and Deep Learning models. (Python source code for new CMAPSS dataset)

PyTorch implementation of CNN for remaining useful life prediction. Inspired by Babu, G. S., Zhao, P., & Li, X. L. (2016, April). Deep convolutional neural network-based regression approach for estimation of remaining useful life. In International conference on database systems for advanced applications (pp. 214-228). Springer, Cham.

Remaining Useful Life estimation and sensor data generation by VAE and diffusion model on C-MAPSS dataset.

Bayesian deep learning for remaining useful life estimation via Stein variational gradient descent

Evolutionary Neural Architecture Search for Remaining Useful Life Prediction

Bayesian Deep Learning for Remaining Useful Life Estimation of Machine Tool Components

Multi-Objective Optimization of ELM for RUL Prediction

Feature clustering and XIA for RUL estimation

Remaining Useful Life estimation for turbofan engines on NASA C-MAPSS: XGBoost RUL model with NASA asymmetric scoring, Flask edge-inference service (Docker) and a LangGraph maintenance copilot with RAG.

Fleet health intelligence on an aviation ontology. It ranks which engines to inspect first, explains why, and shows what happens if you wait. Includes data pipelines, RUL prediction with uncertainty, real ADS-B flight cycles, a planner app and an AI copilot that cites its sources. Built in Python and on Palantir Technologies Foundry.

PyTorch implementation of an LSTM-based deep learning model for predicting Remaining Useful Life (RUL) of turbofan engines using the NASA C-MAPSS dataset. Achieves 16.78 RMSE on FD001.

ML-based remaining useful life estimation and maintenance alerting for aircraft turbofan engines (C-MAPSS, TE7483)

Operational Regime-Aware Degradation Simulation for Mission Planning Support – IEEE IRAI 2026

CNN-LSTM based Remaining Useful Life prediction on NASA C-MAPSS with multi-scale feature engineering, feature selection, and blind-test evaluation.

Excel predictive maintenance, RUL modelling & reliability analysis using NASA C-MAPSS, Power Query, Power Pivot/DAX and Solver.

Fault Detection Of JET Engine with Reccurent Neural networks

Confirmatory, label-free test of bearing alarm findings on 709 NASA C-MAPSS turbofan engines: hysteresis transfers; filtering and tuning depend on failure dynamics and fleet type

Closed-loop MLOps system that predicts engine Remaining Useful Life and auto-recovers from sensor distribution shift. On-prem, air-gap-capable, fully reproducible via Ansible. Master's thesis artifact.

Predicts remaining useful life of turbofan engines from sensor telemetry using LightGBM + Optuna. Includes SHAP attributions and a Flask inference API.

A C library that makes managing and using dynamic maps much easier.