Predicting atmospheric corrosion rates of copper in Taiwan industrial zones using artificial neural network

Abstract

This study employed artificial neural network (ANN) to develop a regional forecasting model to predict atmospheric corrosion rates of copper within general industrial zones and coastal industrial zones in Taiwan. Analyzed data are based on the results of metal atmospheric corrosion rates monitoring project executed by The Institute of Harbor & Marine Technology Center in Taiwan. The results reveal that among the different models utilized in this study, the winter and annual corrosion rates predicted by ANN have the most accurate performance. For the corrosion predictions of C5 and CX levels, all of the models have better performance for the winter and annual corrosions than other seasons. But for C3 and C4 levels, none of the models can obtain accurate corrosion predictions. The performance of different models will also be compared, and the results may provide useful information for reference of design and maintenance of copper objects in Taiwan.