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

ELOTOP – Influences of the electro-galvanizing process on the surface topography alterations

Situation: The roughness of zinc coated steel flat products is a very important regarding the deep drawing properties and the […]

NEBS – Use of waste heat for electricity generation using ORC

Initial situation: In the iron and steel industry as well as other energy-intensive industries, a variety of different thermal process […]

ROLLOILFREE – Cold rollers with oil-free lubricants

Situation: Oil-based lubricants are state-of-the-art in cold rolling of steel and hot rolling of aluminium. 2-phase character of emulsions and […]

MACO Pilot – Optimisation of the mixed-acid online monitoring and control in stainless steel pickling plants

Initial situation Economic pressure on European steel sector demands high flexible and favourable production Especially the pickling step is of […]