Using knowledge-informed machine learning on the PRONOSTIA (FEMTO) and IMS bearing data sets. Predict remaining-useful-life (RUL).

The NASA Prognostic Model Package is a Python framework focused on defining and building models for prognostics (computation of remaining useful life) of engineering systems, and provides a set of prognostics models for select components developed within this framework, suitable for use in prognostics applications for these components.

The NASA Prognostic Python Packages is a Python framework focused on defining and building models and algorit for prognostics (computation of remaining useful life) of engineering systems, and provides a set of models and algorithms for select components developed within this framework, suitable for use in prognostic applications.

The Prognostic Algorithm Package is a python framework for model-based prognostics (computation of remaining useful life) of engineering systems, and provides a set of algorithms for state estimation and prediction, including uncertainty propagation. The algorithms take as inputs prognostic models (from NASA's Prognostics Model Package), and per…

A Unified Framework for Prognostics and Health Management (PHM) Tasks, enabling streamlined execution of key tasks such as Remaining Useful Life prediction (RUL prediction), fault diagnosis, and anomaly detection.

Evolutionary Neural Architecture Search on Transformers for RUL Prediction

ML Approaches for RUL Prediction, Anomaly Detection, Survival Analysis and Failure Classification

remaining useful life, residual useful life, remaining life estimation, survival analysis, degradation models, run-to-failure models, condition-based maintenance, CBM, predictive maintenance, PdM, prognostics health management, PHM

An awesome list of papers on remaining useful life (RUL) prediction from arXiv

The NASA Prognostics As-A-Service (PaaS) Sandbox is a simplified implementation of a Software Oriented Architecture (SOA) for performing prognostics (estimation of time until events and future system states) of engineering systems. The PaaS Sandbox is a wrapper around the Prognostics Algorithms Package and Prognostics Models Package, allowing on…

Tools to test BNN inference algorithms and techniques to predict RUL on aeronautical systems.

A deep reinforcement learning system for optimizing bridge maintenance decisions across municipal infrastructure fleets, implementing cross-subsidy budget sharing and cooperative multi-agent learning.

This project aims to enhance Prognostics and Health Management (PHM) technologies for spacecraft propulsion systems. Developed as part of the JAXA Challenge. This study uses telemetry data and a numerical simulator to predict the dynamic response of spacecraft propulsion systems, focusing on fault detecti

Machine Data Hub Web App

Deep Q-Network implementation for optimal bridge maintenance planning using Markov Decision Process formulation with vectorized parallel training. Based on Phase 3 (Vectorized DQN) from dql-maintenance-faster project.

Deep Q-Network (DQN) implementation for optimal maintenance planning of 100-bridge fleet infrastructure using advanced reinforcement learning techniques and vectorized parallel training.

Semi-supervised and unsupervised health indicator construction for aeronautical composite structures: Diversity-DeepSAD vs. DTC-VAE

A curated collection of papers, articles and datasets to keep modern industrial engineer up-to-date on new strategies for anticipating failures using sensors historical data.

This project utilizes signal processing and machine learning techniques to analyze vibration data for detecting mechanical faults in rotating machinery. It includes the application of Fast Fourier Transform (FFT) for frequency analysis, feature extraction in both time and frequency domains, and classification using Support Vector Machines (SVM).

C51 Distributional DQN (v0.8) for bridge fleet maintenance optimization. Implements categorical return distributions (Bellemare et al., PMLR 2017) with 300x speedup via vectorized projection. Combines Noisy Networks, Dueling DQN, Double DQN, PER, and n-step learning. Validated on 200-bridge fleet: +3,173 reward in 83 min (25k episodes).