Application of artificial neural networks in modeling limestone–SO2 reaction

摘要: Four varieties of limestone distinguished on the basis pore-size distributions were exposed in dynamic 10-, 20- and 50-ppm SO{sub 2} atmospheres for up to 500 h at 25 C 100% rh. The resulting conversion was measured as a function reaction product formed change porosity. These conversions could be predicted correctly using either shrinking unreacted core model or distributed pore model. An artificial neural network (ANN) also trained purpose. All three approaches that fitted well with observed data; however, those by ANN most accurate. Further, weights determined accurately fourth variety which no information supplied training phase, showing can used successfully estimate gas-solid noncatalytic reactions.