Alagoz, Baris BaykantTepljakov, AlekseiKavuran, GurkanAlisoy, Hafiz2024-08-042024-08-042018978-1-5386-6878-8https://hdl.handle.net/11616/98679International Conference on Artificial Intelligence and Data Processing (IDAP) -- SEP 28-30, 2018 -- Inonu Univ, Malatya, TURKEYThis study demonstrates an application of direct gradient descent control for adaptively control of a nonlinear stable system models. The approach is based on utilization of gradient descent optimization techniques for the synthesis of control signals to control a specific plant model. In a former work, gradient descent optimizers were designed by considering a first degree instant input-output relation model assumption of the controlled system and this can allow model independent adaptive control of a class of plant models that can approximate to first order stable plant dynamics. The current study is an extension of this scheme for the purpose of nonlinear adaptive control. Here, we consider a higher degree polynomial assumption of instant input-output relations of the controlled system to obtain gradient descent optimizers that can be applied for adaptive control of a class of nonlinear systems. For evaluation of control performance of gradient descent optimizers, it is applied for the control of nonlinear TRMS model and the results are compared with performance of conventional PID control.eninfo:eu-repo/semantics/closedAccessGradient descent methodcontrolnonlinear systemsTRMSConference Object2-s2.0-85062496936N/AWOS:000458717400085N/A