Striving for Zero Defect Production: Intelligent Manufacturing Control Through Data Mining in Continuous Rolling Mill Processes

摘要

Steel production processes are renowned for being energy and material demanding. Moreover, due to organizational and technological restrictions in flow production processes, the intermediate product's internal quality features cannot be assessed within the process chain. This lack of knowledge causes waste of energy and material resources, unnecessary machine wear as well as reworking and rejection costs, when defective products are passed through the entire process chain without being labeled defective. The process control approach presented in this paper provides the opportunity of gaining transparency on quality properties of intermediate products. This aim is achieved by predicting intermediate product's quality by means of data mining techniques. This approach can be applied in a wide field of production environments, ranging from steel and rolling mills to automated assembly operations. Concerning this concept, the authors derive a methodology for representing different quality properties in a way that it can be applied in the process control. Beyond that, first results of statistical analyses on the quality-related significance of process parameters are disclosed.