The weight loss of raw materials during cement clinker production is often used as an indicator of final product quality. The raw materials are usually limestone mixed with a sand, clay and iron ore. The weight loss is influenced by essentials parameters such as the correct composition, particle size, temperature and duration of burning of the raw materials. It is difficult to determine experimentally the weight loss with high accuracy due to the interaction of its several parameters. Moreover, the determination of the weight loss is expensive, time-consuming, risk associated. Consequently, various intelligent models such as artificial neural network optimized by genetic algorithm (GA-ANN), regression tree ensembles (RTE), least squares support vector machines (LS-SVM), adaptive neuro-fuzzy inference system (ANFIS) are proposed in the present paper to predict the weight loss. The performance of these models is also compared. The results show that all models have great ability as feasible tools and as good alternatives to predict the weight loss quickly, efficiently and less expensive compared to experiment measurements. According to the values of adjusted R 2 there are 99.31%, 99.06%, 98.01% and 97.17% of data can explained by GA-ANN, RTE, LS-SVM, ANFIS respectively with error less than 3.1%.
The purpose of this work is to predict the mass loss of cement raw materials during the decarbonation process. The mass loss is influenced by the interaction of several parameters such as chemical composition of raw material, particle size, temperature range of decarbonation and time exposed. Therefore, predicting mass loss based on experimental parameters data is often challenging. For this reason, various machine learning algorithms such as deep networks using autoencoder DN-AE, artificial neural networks optimized by particle swarm optimization PSO-ANN, ANN optimized by ant colony optimization ACO-ANN and ANN are proposed to predict the mass loss. In this research, all models have been applied successfully to predict the mass loss with high accuracy. The results obtained have shown the superiority of DN-AE compared to PSO-ANN, ACO-ANN and ANN. In addition, PSO-ANN and ACO-ANN have a better performance than the individual use of ANN. The values of adjusted R2 indicate that 99.11%, 98.66%, 98.27% and 97.03% of data are explained by DN-AE, ACO-ANN, PSO-ANN and ANN respectively with scatter index (SI) less than 0.1 and maximum error less than 3.32%. Finally, the results justify that all models proposed can be employed to predict the mass loss as alternative tools.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.