Upcycling cement kiln dust for manufacturing clay bricks fired at different temperatures: RSM and ANN-GA hybrid-optimization

Abstract

The present research examines the utilization of cement kiln dust (CKD) in the manufacturing of low temperatures clay bricks (CB) adopting two types of clay, Remila (CR) and Ajiba (CA). The primary goal is to examine how the proportion of CKD and firing temperature interact to affect the bricks' mechanical and thermal characteristics. The effects of these substances on the regulated parameters were assessed using artificial neural network (ANN) techniques and response surface methodology (RSM) in a two-variable process that included curing temperature and CKD %. A factorial design was used for this objective, with CKD rates set at 0 %, 10 %, 20 %, and 25 % at temperatures ranging from 600 �C to 900 �C. The statistical research findings show that these parameters have a major impact on brick performance. According to the desirability function RSM, genetic algorithm ANN, and Multi-Criteria Decision-Making (MCDM) using the TOPSIS method optimization, the optimal circumstances were identified as 896.51 �C and 29.61 %, 870.24 �C and 29.79 %, 800 �C and 30% of temperature and CKD content, respectively. These findings allow for the determination of the best parameters to design bricks that optimally balance strength and thermal insulation, thereby optimizing production conditions through this experimental approach.