Support Vector Machines for characterising Whipple shield performance

S. Ryan, S. Kandanaarachchi, K. Smith-Miles

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

Support Vector Machines (SVMs) are a classification technique used in data mining and machine learning that are particularly well suited for application with sparse data sets. A database of over 1100 hypervelocity impact tests using spherical aluminium projectiles against spaced aluminium armour (i.e. Whipple shield) was compiled and used to train four different SVMs. The SVMs were developed using a variety of input-attributes and Principal Component Analysis (PCA). Initially, a maximum accuracy of 75% was obtained for an SVM when applied to predict the perforated/not-perforated outcome of impact events not included in the training process. A number of tests were identified which were inconsistent with the pattern observed for other training data. By removing this conflicting data (<5% of the total number of entries), significant increases in the training and generalization accuracy (83%) were achieved. The qualitative outputs of the SVMs were investigated through comparison with classical ballistic limit curves and test data. Within a velocity range of ∼3-8 km/s the SVMs demonstrated a good level of agreement with the classical ballistic limit curves and test data. The application of machine learning methods, including SVM, to predict impact outcomes is limited by the statistical quality of the training dataset. A broader and more homogenous distribution of test conditions, target geometries, materials, and outcomes (i.e. from well above to well below the ballistic limit) is required for machine learning to provide a high level of quantitative accuracy with consistent qualitatively output. Improvements to the training data set may be best achieved via a process in which the current SVMs are applied to identify the most valuable test conditions for future analysis.

Original languageEnglish
Title of host publicationProceedings of the 2015 Hypervelocity Impact Symposium (HVIS 2015)
EditorsWilliam P. Schonberg
PublisherElsevier
Pages522-529
Number of pages8
DOIs
Publication statusPublished - 2015
EventHypervelocity Impact Symposium (HVIS) 2015 - St. Julien Hotel & Spa, Boulder, United States of America
Duration: 26 Apr 201530 Apr 2015
Conference number: 13th
http://hvis2015.mst.edu/
https://www.sciencedirect.com/journal/procedia-engineering/vol/103/suppl/C (Proceedings)

Publication series

NameProcedia Engineering
PublisherElsevier
Volume103
ISSN (Electronic)1877-7058

Conference

ConferenceHypervelocity Impact Symposium (HVIS) 2015
Abbreviated titleHVIS 2015
CountryUnited States of America
CityBoulder
Period26/04/1530/04/15
Internet address

Keywords

  • Artificial Neural Network
  • Hypervelocity impact
  • Machine Learning
  • Support Vector Machine
  • Whipple shield

Cite this