Brief: Predicting quality and performance of oilfield cements with artificial neural networks and FTIR spectroscopy

Portland cement is used almost exclusively for primary and secondary cementing despite the fact that its performance is variable and not understood completely. Cement variability makes slurry performance testing difficult and is often a major factor in operational failure. This paper shows that the Fourier transform infrared (FTIR) spectrum of cements yields information on the factors that control hydration and cement variability, which establishes the infrared spectrum as a ``signature`` of cement composition and performance. Statistical models, based on linear statistics and artificial neural networks, that allow prediction of cement composition, extent of aging, particle-size distribution, and limited slurry performance from cement spectra have been constructed. In addition, the technique can be used to detect and to quantify the presence of contaminants, such as barite, clay or silica. Case studies demonstrate that spectra can be used to predict the nature and condition of the cement in a way not given by API measurements.