DeepQuality

DeepQuality – Use of robust deep learning methods for the automatic quality assessment of steel products

Deep Learning aims to improve the automatic quality assessment of steel products by means of a holistic approach combining deep learning technology with sophisticated management of underlying training data to enable the optimal use of all available data sources and simultaneously simplify the configurability and maintainability of previous decision support system.

This project combines deep learning technology with sophisticated management of underlying training data and consists of the following concepts realizing a human-centered lifecycle for the robust industrial application of deep learning quality models.

  • Production data pipelines
  • Industrial Training Data Management
  • Robust Application of Deep Learning techniques
  • Online application of Deep Learning quality models

Recommendation

Rolloilfree – Steel cold rolling with aqueous oilfree 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 […]

IConSys – Improved quality management in flat steel production

Initial situation DSS developed during DECFLAQ project is successful running since 2007 at ThyssenKrupp Rasselstein Operators are supported to check […]

InnoKon – Innovative non-stick surface to increase the service life of oxygen lances on the converter

In the converter process, pig iron is converted into crude steel with the addition of oxygen. This is done using […]

AdaptEAF – Adaptive EAF on-line control for improved energetic efficiency

Initial situation: Properties of scrap used as charge material for EAF steelmaking are changing with time regarding composition, yield, energy […]