Physical and chemically changes in limestone intruded by trachytic dyke: implications for cement raw material

Limestone samples intruded by trachyte dike from the Tonasa Formation in Bantimurung, Indonesia have been investigated for their suitability for cement manufacturing. The objective of this study is to analyze the physical and chemical characteristics of the limestone surround an intrusion with the petrographic and XRF methods. Field observation shows a gradation of color (reddish to grey) away from intrusion contacts. Petrographic analysis shows metasomatic indication by the presence of garnet and wollastonite within the limestone at 0 - 20 meters from the intrusion contact. The geochemical analysis shows a decreasing degree trend of CaO2, and Fe2O3, however SiO2, Al2O3, and MgO increase towards the intrusion contact. According to the petrographic and geochemical characteristics indicate the limestone fulfills requirements as raw material for cement, even though the ideal composition for the cement industry is the limestone which is located between 20 - 70 meters from the intrusion contact.

Prediction of raw meal fineness in the grinding process of cement raw material: A two-dimensional convolutional neural network prediction method

Raw meal fineness is the percentage content of 80 µm sieving residue after the cement raw material is ground. The accurate prediction of raw meal fineness in the vertical mill system is very helpful for the operator to control the vertical mill. However, due to the complexity of the industrial environment, the process variables have coupling, time-varying delay and nonlinear characteristics in the grinding process of cement raw material. At present, few people pay attention to the coupling characteristics among variables, thus solving this problem is particularly important in raw meal fineness prediction. In this article, we propose a two-dimensional convolutional neural network method that is used to predict raw meal fineness during the grinding process of raw material. Convolutional neural network has strong feature extraction capabilities and does not require manual feature selection. The two-dimensional convolution kernels are used to extract the coupling, time-varying delay and nonlinear features among variables, especially the coupling features. In addition, two important parameters P and L of two-dimensional convolutional neural network model are optimized, respectively. The optimized model solves the problems of coupling, time-varying delay and nonlinearity among variables. Our two-dimensional convolutional neural network model is proved to be very effective by comparing with the state-of-the-art methods.

Simulation of cement raw material deposits using plurigaussian technique

Plurigaussian simulation is a powerful and very effective technique for modelling subsurface rock type domain distribution and in-situ mining reserve analysis. Modelling of subsurface to reveal the rock type distribution plays a key role for raw material extraction planning and plant operations such as extraction, transportation and comminution strategies. Because, the raw material distribution defines the plant operations and final product quality (cement modulus). This study addresses the application of plurigaussian simulation technique to reveal the subsurface rock type distribution of a cement raw material deposit in Turkey. The rock type domains include the limestone, clayey limestone, marl and sandstone which are the basic four rock type classes effecting the cement modulus in the field. The simulation process is carried out using these four rock type data on a determined grid system. A series of tests are made for the validation of the plurigaussian simulation. As a result, the rock type distributions are presented as both 2D-3D graphics and tabulated. The limestone is found as a dominant rock type in the deposit. The marl – a natural clinker - is another widespread raw material in the field and is found interbedded with limestone across the study field. The unwanted sandstone existence exhibited a sparse distribution in reserve body. The results indicated that, the deposit can provide the required raw material for the plant, showing the localised rock type distribution. A detailed raw material extraction planning and scheduling may be made using the results of this study.