In this Chapter, Petri-like net structure is used to develop an intelligent expert control system in order to achieve optimum wastage of the grinding material by regulating the parameters of the grinding mill. The work establishes an appropriate theoretical background that helps to predict dynamic breakage characteristics of the particle size distribution of materials, adequately supported by experimental data. A feed-forward neural network has been employed in this work to adapt the dynamic breakage characteristics of the mill by imparting training using the backpropagation learning algorithm. The mill has been tuned with the trained parameters and no further change in parameters is required so long the desired output remains the same, irrespective of the input particle size range. For reasoning the breakage characteristics of the mill, a rule base is designed using the recorded information of the acoustic signal and implemented using the Petri-like net structure. In real-time, the reasoning process generates inference in case there is any deviation from the recorded acoustic signal, which is subsequently converted to control action and achieving optimum wastage of grinding material. The time of reasoning is compatible with the particle residence time.