Yazar "Savas, Sertac" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    DESIGN OF INTELLIGENT CRUISE CONTROLLER OF MOTOR VEHICLES
    (Cefin Publishing House, 2023) Yildirim, Sahin; Bingol, Mehmet Safa; Savas, Sertac
    Nowadays, due to traffic jam and many cars on traffic, it is very necessary to control the distance between cars and obstacle. Many car producers have been designed and manufacture Cruise Control Systems for cars. Reinforcement learning, one of the popular artificial intelligence techniques, is a method used to train autonomous systems in many different fields. In this simulation study, the adaptive cruise control (ACC) of a ring bus serving in the campus area is controlled with Deep Deterministic Policy Gradient, which is one of the reinforcement learning methods. This simulation study is carried out considering the speed limit in the campus area and the acceleration values required for a comfortable journey of the passengers. Acceleration, velocity and distance values are given with graphs. Consequently; the proposal neural predictor has superior performance to adapt and predict the distance, velocity and acceleration of ego vehicle (bus). © 2023, Cefin Publishing House. All rights reserved.
  • Küçük Resim Yok
    Öğe
    Tuning PID controller parameters of the DC motor with PSO algorithm
    (Akademiai Kiado ZRt., 2024) Ylldlrlm, Sahin; Bingol, Mehmet Safa; Savas, Sertac
    Direct current (DC) motors have superior features such as operating at different speeds, being affordable and easily controllable. Therefore, DC motors have many uses, such as machine tools and robotic systems in many factories up to the textile industry. The PID controller is one of the most common methods used to control DC motors. PID is a feedback controller with the terms Proportional, Integral, and Derivative. The proper selection of P, I, and D parameters is critical for achieving the desired control in the PID controller. In this study, the transfer function of a DC motor is first obtained, and the speed of the DC motor is controlled by the PID controller using this transfer function. Then, Particle Swarm Optimization (PSO), an optimization method based on swarm intelligence, is used to adjust the P, I, and D parameters. By using the obtained P, I, and D coefficients, the speed of the DC motor is tried to be controlled, and the effect of the filter coefficient on the system output is examined. The performance of the proposed PSO-PID controller with successful results is given in tables and graphics. Control and optimization studies are carried out with MATLAB Simulink. © 2023 The Author(s).
  • Küçük Resim Yok
    Öğe
    Tuning the Proportional-Integral-Derivative Control Parameters of Unmanned Aerial Vehicles Using Artificial Neural Networks for Point-to-Point Trajectory Approach
    (Mdpi, 2024) Ulu, Burak; Savas, Sertac; Ergin, Oemer Faruk; Ulu, Banu; Kirnap, Ahmet; Bingoel, Mehmet Safa; Yildirim, Sahin
    Nowadays, trajectory control is a significant issue for unmanned micro aerial vehicles (MAVs) due to large disturbances such as wind and storms. Trajectory control is typically implemented using a proportional-integral-derivative (PID) controller. In order to achieve high accuracy in trajectory tracking, it is essential to set the PID gain parameters to optimum values. For this reason, separate gain values are set for roll, pitch and yaw movements before autonomous flight in quadrotor systems. Traditionally, this adjustment is performed manually or automatically in autotune mode. Given the constraints of narrow orchard corridors, the use of manual or autotune mode is neither practical nor effective, as the quadrotor system has to fly in narrow apple orchard corridors covered with hail nets. These reasons require the development of an innovative solution specific to quadrotor vehicles designed for constrained areas such as apple orchards. This paper recognizes the need for effective trajectory control in quadrotors and proposes a novel neural network-based approach to tuning the optimal PID control parameters. This new approach not only improves trajectory control efficiency but also addresses the unique challenges posed by environments with constrained locational characteristics. Flight simulations using the proposed neural network models have demonstrated successful trajectory tracking performance and highlighted the superiority of the feed-forward back propagation network (FFBPN), especially in latitude tracking within 7.52745 x 10-5 RMSE trajectory error. Simulation results support the high performance of the proposed approach for the development of automatic flight capabilities in challenging environments.