Integration of Adaptive Neuro Fuzzy Inference Systems and principal component analysis for the control of tertiary scale formation on tinplate at a hot mill

• Merger of principal components, Poisson processes, likelihoods and fuzzy networks.
• Three PC inputs to an ANFIS identified conditions leading to small scale counts.
• Minimum scale occurred when the PC’s were less than −0.1, 0.81 and 0.48 respectively.
• These PC’s corresponded to specific hot mill temperatures and slab chemistries.

Scale is highly detrimental to surface quality for tinplate products. There are a large number of process variables at a typical hot mill and principal component analysis is a well-known technique for reducing the number of process variables. This paper estimates the principal components associated with the hot mill process variables and puts these through an Adaptive Neuro Fuzzy Inference System (ANFIS) to find those hot mill running conditions that will minimise the amount of scale observed on the bottom of the rolled strip. It was found that the variation observed in all the hot mill process variables could be captured through the use of just six principal components, and that using just three of these in an ANFIS was sufficient to identify those operating conditions leading to coils being produced with a consistently low scale count. Specifically, it was found that the best operating conditions for the hot mill were when the first component was lower than −0.098 the second lower than 0.8058 and the third higher than −0.482. These ranges in turn corresponded to certain hot mill temperatures that depended to some extent on the base chemistry of the incoming slab.