Abstract: A carbon black process control system measures input variables such as feedstock flow rate, feedstock quality, air flow rate, air humidity, air temperature, fuel flow rate, fuel quality, and/or potassium additive solution flow rate at spaced intervals while the carbon black reactor is operating. Then, at spaced intervals in time one or more output variables of the carbon black, such as iodine number and/or DBP, are predicted in accordance with a prediction algorithm based on the values of the measured input variables. Then, at spaced intervals in time the predicted values of the output variables, such as iodine number and/or DBP, are averaged. Based on the average values of the predicted output variables, one or more input variables are then adjusted to achieve goal values of the predicted output variables, and thus obtain carbon black of substantially consistent quality.