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

s-X-AIPI – self-X Künstliche Intelligenz für die digitale Transformation der Prozessindustrie

Das übergeordnete Ziel von s-X-AIPI ist die Erforschung, Entwicklung und Erprobung eines innovativen Toolsets von maßgeschneiderten, vertrauenswürdigen Self-X-KI-Technologien (autonome KI, […]

CheckSIS –
Performance assessment
for automatic surface
inspection systems

Initial situation In modern steel production, automatic surface inspection systems (ASIS) are commonly used to detect and classify surface defects […]

stackMonitor – Online Blast Furnace Stack Status Monitoring

Initial situation: The decreasing and fluctuating quality of raw materials and the aim to maximise PCI and decrease coke rates […]

I2MSteel – Softwareagenten für ein neues Automatisierungsparadigma

I2MSteel – Entwicklung eines neuen Informations- und Automatisierungsparadigmas für die intelligente und integrierte Fertigung in der Prozessindustrie basierend auf holonischen […]