Dynamic Adaption to Permanent Memory Faults in Industrial Control Systems

Johannes Iber*, Michael Krisper, Jürgen Dobaj, Christian Kreiner

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

Industrial control systems are making increased use of commercial off-the-shelf hardware components. One such component is memory based on DRAM technology. As pointed out by others, DRAM memory can experience permanent hardware errors, e.g. a memory cell can be permanently stuck-at zero or one. In the worst case, such a fault may have serious safety-related consequences. In this work, we present the application of a self-adaptive software system named Scari that detects erroneous datapoints, analyzes them concerning permanent stuck-at faults, and adapts to them by masking defect memory areas. Crucial for this to work is a hot-standby device that takes over the control loop during the detection and adaption phases. The goal of the mechanism presented here is automatic self-repair of a faulty control device to increase its service life and to strengthen overall resilience. The industrial setting of the presented approach is that of control devices for hydropower plant units.

Original languageEnglish
Pages (from-to)392-399
Number of pages8
JournalProcedia Computer Science
Volume130
DOIs
Publication statusPublished - 24 Apr 2018
EventANT 2018: The 9th International Converence on Ambient Systems, Networks and Technologies - Porto, Portugal
Duration: 8 May 201811 May 2018
http://cs-conferences.acadiau.ca/ant-18/

Keywords

  • industrial control systems
  • permanent memory faults
  • self-adaptive software system

ASJC Scopus subject areas

  • Computer Science(all)

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Application

Fingerprint

Dive into the research topics of 'Dynamic Adaption to Permanent Memory Faults in Industrial Control Systems'. Together they form a unique fingerprint.

Cite this