In cement mills, ventilation is a critical key for maintaining temperature and material transportation. However, relationships between operational variables and ventilation factors for an industrial cement ball mill were not addressed until today. This investigation is going to fill this gap based on a newly developed concept named “conscious laboratory (CL)”. For constructing the CL, a boosted neural network (BNN), as a recently developed comprehensive artificial intelligence model, was applied through over 35 different variables, with more than 2000 records monitored for an industrial cement ball mill. BNN could assess multivariable nonlinear relationships among this vast dataset, and indicated mill outlet pressure and the ampere of the separator fan had the highest rank for the ventilation prediction. BNN could accurately model ventilation factors based on the operational variables with a root mean square error (RMSE) of 0.6. BNN showed a lower error than other traditional machine learning models (RMSE: random forest 0.71, support vector regression: 0.76). Since improving the milling efficiency has an essential role in machine development and energy utilization, these results can open a new window to the optimal designing of comminution units for the material technologies.

Since last two decades, several investigations in various countries have been started to discover new rare earth element (REE) resources. It was reported that coal can be considered as a possible source of them. REE of coal occur in low concentrations, and their detection is a complicated process; therefore, their predictions based on conventional coal properties (proximate, ultimate and major elements (ME)) may have several advantages. However, few studies have been conducted in this area. This study examined relationships between coal properties and REE (HREE and LREE) for a wide range of coal samples (708 samples). Variable importance measure (VIM) by Mutual information (MI) as a new feature selection method was applied to consider the heterogeneous structure of coal and assess the individual relation between coal parameters and REE to select the compact subsets as input variables for modeling and improve the performance of prediction. VIM by MI showed that Si- Carbon, and Al-Hydrogen are the best subsets for the prediction of HREE and LREE concentrations, respectively. A boosted neural network (BNN) model as a new predictive tool was used for REE prediction. BNN can significantly reduce generalization of error. Results of BNN models showed that the HREE and LREE concentrations can satisfactory estimate (R²: 0.83 and 0.89, respectively). Results of this investigation were approved that MI-BNN can be used as a potential tool for prediction of other complex problems in energy and fuel areas.