Adaptive Data Analysis for Fatigue Studies of Additively Manufactured 17-4 PH Stainless Steel

Abstract

In this report, principal component analysis (PCA) is used to investigate quasi-static and tension-tension fatigue stress and strain data sets of modified ASTM E8 subsized dog-bone-shaped samples manufactured by a Markforged Metal X additive manufacturing printer. These large data sets were made using the strain field data created using digital image correlation (DIC) imaging technology. Using PCA unsupervised learning algorithms, we investigated if these machine learning techniques can provide various trends and patterns of these materials that DIC and other traditional material characterization techniques cannot show us. Although a simple PCA of images did not show a trend or unique pattern within the data, it did, however, show that reducing the data size and processing via DIC does not cause a large reduction in the DIC strain output.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 2022
Accession Number
AD1180904

Entities

People

  • Michael D . Coatney
  • Mulugeta Haile
  • Natasha C. Bradley
  • Todd Henry

Organizations

  • United States Army Research Laboratory

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Additive Manufacturing
  • Algorithms
  • Artificial Intelligence
  • Data Analysis
  • Data Mining
  • Data Science
  • Data Sets
  • Digital Images
  • Dimensionality Reduction
  • Fabrication
  • Factor Analysis
  • Information Science
  • Machine Learning
  • Manufacturing
  • Materials
  • Materials Science
  • Test And Evaluation
  • Three Dimensional
  • Two Dimensional
  • Unsupervised Machine Learning

Readers

  • Manufacturing Engineering.
  • Materials Science (Mechanical Engineering).
  • Regression Analysis.

Technology Areas

  • AI & ML