Abstract

Although having structural system models which determine system behaviours is critical to plan, control and manage many complex systems (e.g. manufacturing and production systems), we often do not have pre-defined structural system models. We need to perform reverse engineering which is to collect and mine observable system data in order to discover structural system models. This paper presents a reverse engineering algorithm that can be used to discover a causal system model which is one kind of structural system model and represents causal relations of system factors. In a causal relation, the presence of one system factor causes the presence of another system factor. The paper also shows the computational complexity of the algorithm. The paper presents the application and performance of the reverse engineering algorithms to data in two application fields.

Original languageEnglish (US)
Pages (from-to)1-17
Number of pages17
JournalInternational Journal of Production Research
DOIs
Publication statusAccepted/In press - Jul 28 2016

    Fingerprint

Keywords

  • causal relations
  • data mining
  • manufacturing information systems
  • reverse engineering
  • structural system models

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Management Science and Operations Research
  • Strategy and Management

Cite this