Presed – Predictive Sensor Data mining

Initial situation:

  • Some steelworks experiences problems with product deficiencies like slivers and cracks.
  • Several pre-studies indicated a relationship between the time dependence of a set of measured values and the occurrence frequency of the defect.
  • Methods for predicting, detecting and reducing the defect early in the process are desired.

Working topics:

  • Highly resolved time-series process data is analysed with respect to the root causes for these defects.
  • Influential key factors are derived from the time-series data to quantify the probability of the defects.
  • An event-detection for time-series data will be developed.
  • The know-how about the interdependencies is conserved in an ontological knowledge base.

Results:

  • A prediction system for the defect probability is developed to assist the plant personnel.
  • Novel results on defect appearance and root causes are expected.
  • Reduction of slivers and cracks by operating the processes at optimum working points.

Siehe auch

PSP-BOF – Removal of Phosphorus from BOF-slag

Initial situation Increased cost for raw materials and for landfilling have forced European steelmakers to look for new ways to […]

INSPIREWATER – Innovative und zukunftsorientierte Lösungen für ein effizientes Wassermanagement in Prozessindustrien

Ausgangssituation Prozessbedingter Eintrag von Zunder sowie Aufkonzentrierung von Härtebildern und Salzen in Walzwerkswasser bzw. Metallen in Beizsäuren und Spülwassern Hohes […]

TempKorroSchu

Situation: Bildung von 1 bis 2 % Zunder bei der Wiedererwärmung von Vormaterial für die Herstellung von Schrauben und Sonderprofilen. […]

CoolCut – Entwicklung einer innovativen industriellen Schneidtechnik für hochverschleißendes Bahnenmaterial

Situation: Hohe tribologische Beanspruchungen von Kreismessern führen zu einem sehr hohen Verschleiß. Verschleiß der Messer erfolgt durch unterschiedliche Mechanismen, abhängig […]