2017

Predicting Product Quality as Early as Possible in the Production Process

Predicting Product Quality as Early as Possible in the Production Process Speaker: Dr. Gabriel Fricout, Arcelor Mittal Data mining processes have proven to be very valuable for addressing industrial issues such as understanding defect crisis. In classical data mining procedures, only “single value” variables are considered, meaning that one individual, in the steel industry typi- cally one coil, is characterized by average values of many process parameters (composition, temperature, speed, strengths, tractions, composition, etc.

Continue reading

Quality Prediction in a Rolling Mill from Sensor Data Streams

Quality Prediction in a Rolling Mill from Sensor Data Streams Speaker: Daniel Lieber, DEW - Deutsche Edelstahlwerke Specialty Steel GmbH & Co. KG Daniel Lieber, deputy operations manager of the rolling mill and forging shop at Deutsche Edelstahlwerke Specialty Steel GmbH & Co. KG in Witten, presents results of the Collaborative Research Center SFB 876 - “Providing Information by Resource- Constrained Data Analysis”, Project B3 “Data Mining on Sensor Data of Automated Processes”.

Continue reading