An artificial neural network-based prediction model for utilization of coal ash in production of fired clay bricks: A review

This study analyzed the last 20 years` data available on power plant coal ashes used in clay brick production. The statistical analysis has been carried out for a total of 302 cases based relevant parameters reported literature. chemical composition clays and ashes, percentage incorporation maximum particle size ash, fired samples, peak firing temperature, corresponding soaking time were selected as inputs modeling. product characteristics i.e. open porosity, water absorption, compressive strength was taken output parameters. An artificial neural network model developed showed satisfactory fit to experimental predicted observed variables with overall coefficient determination (r2) 0.972 during training period. Besides, reduced chi-square, mean bias error, root square error utilized check correctness obtained model, which proved generalization capability. sensitivity suggested that quantity Na2O coming from clays, percentages SiO2 K2O MgO most influential descending order ash-clay composite bricks` quality, mostly owing influence fluxes firing.