Optimizing the Sulfates Content of Cement Using Neural Networks and Uncertainty Analysis

Abstract

This study aims to approximate the optimum sulfate content of cement, applying maximization of compressive strength as a criterion for cement produced in industrial mills. The design includes tests on four types of cement containing up to three main components and belonging to three strength classes. We developed relationships correlating to 7- and 28-day strength with the sulfate and clinker content of the cement (CL), as well as the clinker mineral composition (tricalcium silicate, C3S, tricalcium aluminate, C3A). We correlated strength with the ratio %SO3/CL and the molecular ratios MSO3/C3S and MSO3/C3A. The data processing stage proved that artificial neural networks (ANNs) fit the results’ distribution better than a parabolic function, providing reliable models. The optimal %SO3/CL value for 7- and 28-day strength was 2.85 and 3.00, respectively. Concerning the ratios of SO3 at the mineral phases for 28-day strength, the best values were MSO3/C3S = 0.132–0.135 and MSO3/C3A = 1.55. We implemented some of the ANNs to gain a wide interval of input variables’ values. Thus, the approximations of SO3 optimum using ANNs had a relatively broad application in daily plant quality control, at least as a guide for experimental design. Finally, we investigated the impact of SO3 uncertainty on the 28-day strength variance using the error propagation method.

Keywords

• sulfates
• cement
• strength
• clinker
• optimization
• artificial neural networks