Single-step prediction method of burning zone temperature based on LSSVM

摘要

The single-step prediction of burning zone temperature plays an important role in the safety and stability control of cement rotary kiln. In this paper, the burning zone temperature prediction method based on least squares support vector machine is studied. First, the visual inspection device is used to detect the burning zone temperature. And then, the moving average filtering process is performed to obtain a relatively smooth temperature data. On the basis of this, the temperature prediction model based on least squares support vector machine is constructed by taking the current value of the burning zone temperature and the previous time value as the input and the next time value as the output. At last, the burning zone temperature prediction method is validated. The result shows that this paper provides a feasible method for the single-step prediction of burning zone temperature.