12th International Conference on Zinc & Zinc Alloy Coated Steel Sheet - GALVATECH 2021

In industrial electro galvanizing lines, the performance of the dimensionally stable anodes (Ti + IrOx) is a crucial factor for product quality. Ageing of the anodes causes worsened zinc coating distribution on the steel strip and a significant increase in production costs due to a higher resistivity of the anodes. Up to now, the end of the anode lifetime has been detected by visual inspection every several weeks. The voltage of the rectifiers increases much earlier, indicating the deterioration of anode performance. Therefore monitoring rectifier voltage has the potential for a premature determination of the end of anode lifetime.
Anode condition is only one of many parameters affecting the rectifier voltage. In this work we employed machine learning to predict expected baseline rectifier voltages for a variety of steel strips and operating conditions at an industrial electro galvanizing line. In the plating section the strip passes twelve “Gravitel” cells and zinc from the electrolyte is deposited on the surface at high current densities.
Data, collected on one exemplary rectifier unit equipped with two anodes, have been studied for a period of two years. The dataset consists of one target variable (rectifier voltage) and nine predictive variables describing electrolyte, current and steel strip characteristics. For predictive modelling, we used selected Random Forest Regression. Training was conducted on intervals after the plating cell was equipped with new anodes. Our results show a Normalized Root Mean Square Error of Prediction (NRMSEP) of 1.4 % for baseline rectifier voltage during good anode condition. When anode condition was estimated as bad (by manual inspection), we observe a large distinctive deviation in regard to the predicted baseline voltage. The gained information about the observed deviation can be used for early detection resp. classification of anode ageing to recognize the onset of damage and reduce total operation cost.