LAUSR

A coating collapse occurs when large parts of coating break away from the refractory of a rotary kiln in a cement plant. If the collapse is more conspicuous, the cooler may become filled with excessive material, causing the clinker transport systems to overload and the temperature in the cooler outlet to rise excessively. An unstable coating quickly causes problems with the refractory material, resulting in a loss of energy that disturbs the stable operation of the kiln. Variable amounts of coating in the burning zone also influence the kiln torque. A coating collapse is normally detected by the operator through the trend curve of kiln drive amps. This paper explains the application of empirical mode decomposition with a fuzzy inference system and a fuzzy neural network to identify a kiln coating collapse and predict refractory failure in the cement process. The results show that the proposed method improved considerably upon the original.