Advertisement

Adaptable Realization of Industrial Analytics Functions on Edge-Devices using Reconfigurable Architectures

  • Carlos Paiz GaticaEmail author
  • Marco Platzner
Conference paper
Part of the Technologien für die intelligente Automation book series (TIA, volume 11)

Abstract

Machine learning algorithms play a significant role for the realization of industrial analytics functions, such as predictive maintenance. This paper first outlines the workflow and topology variants for industrial analytics, and then focuses on the efficient realization of machine learning algorithms on edge devices using reconfigurable System-on-Chip architectures, showing the benefits of an optimized application-specific realization.

Keywords

Predictive Maintenance Machine Learning Reconfigurable System on Chip ReconOS k-NN Support Vector Machine 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Reference

  1. 1. A. Agne, M. Happe, A. Keller, E. Lübbers, B. Plattner, M. Platzner, and C. Plessl. “ReconOS – An Operating System Approach for Reconfigurable Computing”, IEEE Micro, 34(1):60–71, IEEE Computer Society, 2014.Google Scholar
  2. 2. U. Riaz. “Acceleration of Industrial Analytics Functions on a Platform FPGA”, Master’s Thesis, Paderborn University, 2017.Google Scholar
  3. 3. P. Santos, L. F. Villa, A. Renones, A. Bustillo, and J. Maudes. “An svm-based solution for fault detection in wind turbines”, Sensors, vol. 15, no. 3, pp. 5627–5648, 2015. Available: http://www.mdpi.com/1424-8220/15/3/5627Google Scholar
  4. 4. C. Bayer, O. Enge-Rosenblatt, M. Bator, and U. Moenks. “Sensorless drive diagnosis using automated feature extraction, significance ranking and reduction”, in 2013 IEEE 18th Conference on Emerging Technologies Factory Automation (ETFA), Sept 2013, pp. 1–4.Google Scholar
  5. 5. G. A. Susto, A. Schirru, S. Pampuri, S. McLoone, and A. Beghi. “Machine learning for predictive maintenance: A multiple classifier approach”, IEEE Transactions on Industrial Informatics, vol. 11, no. 3, pp. 812–820, 2015.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Authors and Affiliations

  1. 1.Weidmüller Interface GmbH & Co. KGDetmoldGermany
  2. 2.Paderborn UniversityPaderbornGermany

Personalised recommendations