Fault detection and diagnosis in monitoring a hot dip galvanizing line using multivariate statistical process control

Fault detection and diagnosis is an important problem in continuous hot dip galvanizing and the increasingly stringent quality requirements in automotive industry has also demanded ongoing efforts in process control to make the process more robust. Multivariate monitoring and diagnosis techniques have the power to detect unusual events while their impact is too small to cause a significant deviation in any single process variable. Robust methods for outlier detection in process control are a tool for the comprehensive monitoring of the performance of a manufacturing process. The present paper reports a comparative evaluation of robust multivariate statistical process control techniques for process fault detection and diagnosis in the zinc-pot section of hot dip galvanizing line.