Lime is a major material in many industrial processes, including steelmaking by blast furnace. Lime production through rotary kilns is a common method in industries, yet it has depreciation, high energy consumption, and environmental pollution. Recognizing and modeling this process can help reduce its disadvantages. This paper presents a black-box model by Artificial Neural Network (ANN) for the lime production process considering pre-heater, rotary kiln, and cooler parameters. To this end, actual data are collected from Isfahan Steel Company, including 23 input variables and one output variable. Then, various characteristics of the ANN such as number of hidden layers, number of neurons in each layer, activation functions, and training algorithm are optimized. Process sensitivity to input variables is explored using the optimum model. Top-three input variables are selected on the basis of one-group sensitivity analysis and their interactions are studied. Finally, an ANN model is developed considering the top-three most effective input variables. Model validation shows that predicted values greatly matched experimental data.
