Akademik Veri Yönetim Sistemi
6th International Conference on Frontiers in Academic Research, Konya, Türkiye, 16 - 17 Aralık 2025, (Yayınlanmadı)
Spacecraft's attitude determination
and control systems (ADCS) need high-performance controllers since they need to
be able to move very precisely and because the actuators don't have a lot of
power. This research examines the attitude control problem of a rigid
spacecraft, comparing the numerical performance metrics of a traditional
Proportional-Integral-Derivative (PID) controller with those of an Artificial
Neural Network (ANN)-based intelligent controller. We used Euler angles and
angular velocities to make the spacecraft's dynamic model, and we used a rigid
body dynamics approach to simulate moments of inertia. The PID controller is
set up to work with reference moves, while the ANN-based controller is taught
to learn how the system behaves in a nonlinear way.The simulation findings show
that when using a PID controller, the settling time for the orientation error
is about 8–10 seconds. However, when utilizing an ANN-based controller, this
time is cut down to 4–5 seconds. The greatest overshoot with a PID controller
is about 12–15%, however with an ANN-based controller, this number has dropped
to less than 5%. Also, adopting an ANN-based controller cut steady-state
inaccuracy by about 40–50%. When looking at the control torque needs, it was
found that the PID controller needed greater instantaneous torque, while the
ANN-based controller made a smoother and more energy-efficient control signal.
The results clearly reveal that the PID controller is better since it is easier
to use and works in more situations. The ANN-based controller, on the other
hand, works better when there are nonlinearities and parameter uncertainties.