engleski

PREDICTION OF ANODE LIFETIME IN ELECTRO GALVANIZING LINES BY BIG DATA ANALYSIS

Anode conditions can cause an increase in production cost and quality in industrial electro galvanizing lines. We employ machine learning to predict expected rectifier voltages for a variety of steel strip types 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. The data was 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 Random Forest Regression. The model training was conducted on intervals where anodes were freshly exchanged. Our results show a Normalized Root Mean Square Error of Prediction (%RMSEP) of 1.4 % for baseline rectifier voltage during good anode condition. When the anode condition was estimated as bad (by manual inspection), at the same time 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.

machine learning, big data, electro-galvanization, voltage

nije evidentirano