Use of harmony search algorithm to improve PID controller performance

The PID controller is the most commonly used industrial controller due to its good performance and ease of implementation. The controller performance mostly depends on tuning, which requires selecting appropriate values for the controller parameters: controller gain, integral time and derivative time to reach a trade-off between performance and reliability. The tuning process can be tedious and time consuming. In this study, we use the stochastic Harmony Search optimization algorithm to automatically select the controller parameters that minimize our predefined objective function. This is the first application of the Harmony Search to PID controller tuning. In addition, we are using a new modified four-term objective function. Unlike the commonly used objective functions for evaluating controller performance, both the controller output and settling time are put in the objective function to penalize possible over-control. In order to avoid over-tuning, the difference of system outputs between the current time and the previous sampling time is also a part of our modified objective function. The new results are compared with those obtained using conventional PID techniques to demonstrate the effectiveness of the new methods.