Kumari, Amrita and Das, Suchandan K and Srivastava, P K (2017) Data-driven modeling of ﬁreside corrosion rate. Anti-corrosion methods and materials, 64(4) (IF-0.364). pp. 397-404.
Restricted to NML users only. Others may use ->
Purpose – This paper aims to propose an efﬁcient artiﬁcial neural network (ANN) model using multi-layer perceptron philosophy to predict the ﬁreside corrosion rate of superheater tubes in coal ﬁre boiler assembly using operational data of an Indian typical thermal power plant. Design/methodology/approach – An efﬁcient gradient-based network training algorithm has been used to minimize the network training errors. The input parameters comprise of coal chemistry, namely, coal ash and sulfur contents, ﬂue gas temperature, SOX concentrations in ﬂue gas, ﬂy ash chemistry (Wt.% Na2O and K2O). Findings – Effects of coal ash and sulfur contents, Wt.% of Na2O and K2O in ﬂy ash and operating variables such as ﬂue gas temperature and percentage excess air intake for coal combustion on the ﬁreside corrosion behavior of superheater boiler tubes have been computationally investigated and parametric sensitivity analysis has been undertaken. Originality/value – Quite good agreement between ANN model predictions and the measured values of ﬁreside corrosion rate has been observed which is corroborated by the regression ﬁt between these values.
|Uncontrolled Keywords:||Artiﬁcial neural network, Coal composition, Fireside corrosion, Flue gas, Fly ash, Superheater tubes|
|Divisions:||Material Science and Technology|
|Deposited By:||Sahu A K|
|Deposited On:||13 Sep 2017 14:35|
|Last Modified:||18 Sep 2017 14:50|
Repository Staff Only: item control page