Cement roller press control by fuzzy logic reasoning

An application of fuzzy logic inference technique on cement grinding roller control is proposed. The control of cement grinding roller is that the oil-pressure is commanded to follow a desired setting pressure. The original method of determining the setting pressure in terms of driving current is a PI-like method. But by this method, the grinding roller control will result in large fluctuation of pressure and current caused by variation of feedstocks. According to the previous operation record data, we apply the back-propagation neural network to identify the system model for establishing the simulation program for evaluating the derived control algorithm and propose the fuzzy rules to infer the desired setting pressure to replace the original PI-like method. This improvement has been practically applied in a Taiwan cement manufacturing plant, it can show that the fluctuation of pressure and current has been reduced, i.e. the manufacturing plant on-line works confirm the improvement