A novel balanced Aquila optimizer using random learning and Nelder-Mead simplex search mechanisms for air-fuel ratio system control

An air-fuel ratio system has a crucial role in helping protect the environment from the harmful emissions of the lean combustion spark-ignition engines and regulating fuel consumption. Due to such importance, an efficient control mechanism poses an utmost necessity for this system. However, the air-fuel ratio system has a time-delayed structure with nonlinear nature making its control difficult. This paper considers the last challenge and proposes a novel method to effectively control the air-fuel ratio system. In this regard, a feedforward proportional-integral controller based on a novel balanced Aquila optimizer (bAO) is proposed with this work to achieve adequate control of the respective system. The proposed bAO algorithm is constructed via the integration of the random learning mechanism and the Nelder-Mead simplex search method for better exploration and exploitation tasks. A novel objective function is also proposed for the first time in the literature for such a system in order to achieve the optimal parameters of the employed controller via the proposed bAO algorithm. Different recent and good performing metaheuristic algorithms are employed to comparatively assess the performance of the proposed method in terms of statistical, transient, input signal tracking, and robustness analyses. The related evaluations demonstrate that the proposed method has more excellent air-fuel ratio system control ability as performance improvement of more than 64% is reached for overshoot, whereas around 9 and 7% are achieved for rise time and settling time, respectively. Similar figures are achieved for robustness and input signal tracking. To further demonstrate the capability of the proposed bAO algorithm, well-known performance indices are also employed in this study as objective functions which also shows a performance improvement of up to 12% for the proposed method.