ML-Class-Project

Project Title:

Probabilistic structural health monitoring of composite structures under impact testing

Project Description:

The aerospace industry's safety and cost concerns drive the investigation of damage detection and progression in carbon-fiber-reinforced plastics (CFRP) from low-energy impacts. Leveraging machine learning, specifically Auto-Regressive models, offers a promising avenue for Structural Health Monitoring (SHM). By tailoring these models to the unique characteristics of composite materials and impact-induced damage, the aim is to enhance safety and reduce maintenance costs. This project aims to develop efficient detection techniques.

Folder Structure

• data/
• code/
• notebooks/
• literature/
• references/
  • Shabbir Ahmed and Fotis Kopsaftopoulos (2022): “Statistical Active-Sensing Structural Health Monitoring via Stochastic Time-Varying Time Series Models.”
  • Nardi et al.: "Detection of low-velocity impact-induced delaminations in composite laminates using Auto-Regressive models." Link
  • Ahmed and Kopsaftopoulos (2023): "Active Sensing Acousto-Ultrasound SHM via Stochastic Non-stationary Time Series Models."

To access the repository, click here