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.

Recommendation

EvalHD – High resolution process data for quality assessment

Initial situation Plant-wide quality databases exist at many steel producers Data-warehouses are optimized for per-coil data access For statistical analysis […]

TopTemp – Shaft furnace analysis with acoustic gas temperature measurement

Initial situation: Shaft furnaces such as blast furnaces for pig iron production are highly effective aggregates, but very complex physico-chemical […]

H2BF – CO2-Mitigation through Injection of H2 into the Blast Furnace – Project Phase 1

This project is funded from the State of NRW and aims to technically investigate a new, modified blast furnace process. […]

S5 – Integrated thickness and flatness control

Initial situation: The regulations of the strip thickness and the strip planarity influence each other. The planarity controller is artificially […]