A methodology for designing a Sugeno type Fuzzy Logic Controller (FLC) for accurate position control of a pneumatic servo system is presented. Adaptive Neuro Fuzzy Inference System technique is employed to construct a fuzzy inference system whose membership function parameters are tuned using a training data set comprising of input/output signal of the pneumatic servo system with proportional control. Hybrid backpropogation-least square algorithm is used for training of the Fuzzy Inference System (FIS). The resulting FIS optimally projected the behavior of training data set. To obtain the desired steady-state response, the fuzzy inference system is further tuned using the expert knowledge of the input/output response of the system. The system response for various reference inputs is compared quantitatively with that of the system without fuzzy logic controller, and excellent improvement in steady-state response is observed.

This content is only available via PDF.
You do not currently have access to this content.