Extended Approach of ANFIS in Cascade Control

this paper discusses extended approaches of Adaptive Network Based Fuzzy Inference System (ANFIS) using Self Tuning Regulator (STR) via Fuzzy logic to be implemented in cascade control. Plant used is Pressure RIG 38-714 which supports cascade configuration. The controlled variable in the outer loop is pressure, in the inner loop's flow. The proposed method's used to improve the performance of ANFIS which has been commonly implemented to accomplish control task. Comparison has been conducted between ANFIS using STR and without STR, from experiment could be concluded that controller ANFIS using STR acquired better performance than only used ANFIS. It's derived from the transient response of those. For ANFIS using STR is obtained rise time and settling time are 9 ms and 12 ms respectively. In the other hand, ANFIS without STR resulted 21 ms and 29 ms for rise time and settling time respectively. Cascade control's one of example in the complex architecture of control system. Indeed, it has two control loops, one's used to control main variable (outer loop) and another's used to reject the disturbance (inner loop). An advantage of this structure's if there's a disturbance on the inner loop might be immediately detected and undertaken self correcting, because process on the inner loop has to be much faster than on the outer loop, thereby such structure like that's also able to prevent a stability of the plant simultaneously. Although has an advantage, cascade control's relatively expensive due to utilizing more sensor. Because, there are two control variable to solve one main control variable. Fuzzy logic invented by Zadeh has been widely used in the many applications. In the area of control engineering, fuzzy logic controller with many varieties and structures have been practically developed in the many areas such as: control, forecasting, identification, and etc. The strongest thing of fuzzy logic's can adopt intuition of human feeling mapped in the membership function of fuzzy logic. Such thing like that might replace on-off logic which only understands 2 values as ON and OFF. However, the weakness of fuzzy logic's it does not has a