Data-driven modeling of corrosion and scale deposition rate in economizer

Abstract

Purpose - The aim of this paper is to study the effect of the parametric sensitivity of all critical parameters of feed water and other operating variables on the corrosion rate and oxide scale deposition on economizer tubes of a typical coal-fired 250-MW boiler. Design/methodology/approach - In this paper, a multilayer perceptron-based artificial neural network ( ANN) model has been developed to envisage the corrosion rate and oxide scale deposition rate in economizer tubes of a coal-fired boiler. The neural network architecture has been optimized using an efficient gradient-based network optimization algorithm to minimize the training and testing errors rapidly during simulation runs. Findings - The parametric sensitivity of all critical parameters of feed water and other operating variables on the corrosion rate and oxide scale deposition activities has been investigated. It has been observed that dissolved oxygen, dissolved copper content, residual hydrazine content and pH of the feed water have a relatively predominant influence on the corrosion rate, whereas dissolved iron content, silica content, pH and temperature of the feed water have a moderately major influence on oxide scale deposition phenomenon. There has been very good agreement between ANN model predictions and the measured values of corrosion rate and oxide scale deposition rate substantiated by the regression fit between these values. Originality/value - This paper details the development of an alternative model to accurately predict corrosion rate and deposition rate on the inner surface of economizer tubes of a boiler over first principle-based kinetic model.