Identification of cement rotary kiln using type 2 Takagi- Sugeno neuro-fuzzy system considering the effect of different noisy condition

A Cement rotary kiln is the main part of the cement production process, which has always attracted many researchers’ attention. However, this complex nonlinear system has not been modeled efficiently, which can make an appropriate performance, especially in noisy condition. In this work, the type 2 Takagi-Sugeno neuro-fuzzy system (T2TSNFS) is used to identify the cement rotary kiln, and the gradient descent (GD) algorithm is applied for tuning the parameters of antecedent and consequent parts of fuzzy rules. In addition, the optimal inputs of the system are selected by the genetic algorithm (GA) to achieve less complexity in the fuzzy system. The data relating to the Saveh White Cement (SWC) factory is used in the simulations. The Results demonstrate that the proposed identifier has an appropriate performance in noisy conditions. Furthermore, in this work, T2TSNFS is evaluated in noisy conditions, which had not been worked out before in related research works. Also, T2TSNFS and type 1 Takagi-Sugeno neuro-fuzzy system (T1TSNFS) are compared. The simulations show that T2TSNFS has more proper performance when the standard deviation of noise increases.