Parameter Tuning for a Fuzzy Logic Controller using the Ant Colony Optimization Algorithm
The Ant Colony Optimization (ACO) algorithm can be applied in tuning parameters in a Fuzzy Logic Controller (FLC) to control the water level of the process tank. Fuzzy input and output consists of seven membership functions, namely large positive (PB), medium positive (PM) and small positive (PS), zero (Z), small negative (NS), medium negative (NM) and large negative (NB) ). First, the initial FLC parameter is searched, then a graph is generated where the values â€‹â€‹of the FLC parameter are determined in the range of values â€‹â€‹between 0 and 1.5 times the initial parameter value. ACO algorithm is used to improve the value of the FLC parameter in order to obtain better performance. The expected controller performance is to minimize the maximum surge (overshoot) and rise time. This system is implemented using the LabVIEW program. Water level data is obtained using a potentiometer sensor. The output from the FLC is connected to the stepper motor to regulate the discharge of water input to the process tank. The test results obtained overshoot and a small rise time, for example, for setpoint 8, the system output performance has an overshoot of 2.5% and a rise time of 8909 ms. ACO algorithm succeeded in increasing system performance compared to system performance if using initial parameters. This increase in performance is due to the ACO algorithm acting as a local search algorithm which will look for better system performance around its initial parameter values. This research successfully demonstrated that the ACO algorithm can be used to do tuning from FLC parameters.