HiMAP: Hidden Markov models for Advanced Prognostics

HiMAP is a Python package for implementing hidden Markov Models (HMMs) and hidden semi-Markov Models (HSMMs) tailored for prognostic applications. It provides a probabilistic framework for predicting Remaining Useful Life (RUL) and modeling complex degradation processes without requiring labeled datasets.

Link  

Dataset: Composite Specimens under Fatigue and Impact Loading 

The dataset consists of condition monitoring data collected from open-hole composite specimens subjected to fatigue and impact loading. Specimens were tested under constant amplitude fatigue loading until failure. To introduce variability and simulate realistic operational conditions, some specimens included in-situ impact events during loading, while others contained manufacturing-induced imperfections.  

Acoustic Emission (AE) and Digital Image Correlation (DIC) techniques were used to capture real-time structural responses and surface strain fields. The dataset includes both standard fatigue cases and cases with unexpected behavior due to impact or imperfections, offering a diverse representation of structural performance under different loading and damage scenarios.  

In total, data from 12 specimens are included:  

• 8 specimens subjected solely to fatigue loading.  

• 4 specimens with additional conditions:  

  • 3 with in-situ impacts.  

  • 1 with a manufacturing imperfection.

Link