İlgi alanları

Sürdürülebilir Kalkınma Amaçları

• 2

• MakaleAçık Erişim2026/r/gumushane/19459
  Enhanced control of a two-wheeled gyroscopic combat robot with variable CMG disk speeds using LQR-Based neural network

  Oğuz, Yasin; Ünker, Faruk; Cetin, Gokhan

  This study proposes a hybrid control approach to improve the stability and adaptability of a two-wheeled gyroscopic combat robot by integrating deep learning with Linear Quadratic Regulator (LQR) control. Due to their inherently unstable nature, two-wheeled robots face challenges maintaining balance, especially when Control Moment Gyroscope (CMG) disk speeds vary, which significantly affect system dynamics. While LQR provides effective stabilization by minimizing a cost function, its performance degrades when disk speeds change. To overcome this limitation, a Neural Network (NN) was trained on 42001 precomputed LQR gain sets optimized for CMG disk speeds ranging from 800 to 5000 rad/s. The trained NN predicts appropriate coefficients in real time, enabling adaptive control under dynamic operating conditions. Simulation results demonstrate that the hybrid NN-LQR controller maintains stability under recoil forces up to 3000 N, where the conventional LQR loses balance about 4–6 seconds. Furthermore, the proposed controller reduces energy consumption by 21.6% during steady-state operation within the first 5 seconds and 10.6% under recoil conditions within the first 3 seconds compared to classical LQR. Although developed for a combat robot, the proposed framework offers a scalable solution for broader robotic applications such as search and rescue, surveillance, and autonomous navigation in complex environments, contributing to the advancement of intelligent control in robotics.

  İncele
• MakaleAçık Erişim2026/r/gumushane/13855
  Regression-Based Controller Design Using LQR Data for a Two-Wheeled Gyroscopic Combat Robot

  Oğuz, Yasin; Çetin, Gökhan; Ünker, Faruk

  Two-wheeled gyroscopic robots are challenging to balance due to their intrinsic instability and sensitivity to external disturbances. This study proposes a hybrid control approach that combines a linear quadratic regulator (LQR) and a regression-based machine learning model to increase stability and adaptability. The regression model is trained with data collected from an LQR-controlled system to predict the optimal control responses under different conditions. The proposed approach utilizes state-space representation and the Jacobian linearization technique to design and simulate the robot’s performance under both controlled and random disturbance profiles. Simulation results indicate that the proposed method ensures steady motion even in dynamic, uncertain environments and increases resistance to external disturbances. Compared to the conventional LQR control method, the regression-enhanced model dynamically adjusts the control parameters, effectively reducing oscillations throughout the robot’s motion and achieving an average energy saving of approximately 80 %. These results demonstrate that robust, adaptive control in autonomous two-wheeled robotic systems can be achieved by fusing data-driven models with classical control techniques.

  İncele
• MakaleAçık Erişim2025/r/gumushane/19525
  Advanced adaptive control strategies application for speed regulation of a 12V small dc geared motor

  Cetin, Gokhan

  This paper investigates the implementation and performance of adaptive control techniques for a 12V small geared DC motor characterized by modeling errors and input disturbances. This paper discusses the following two primary approaches: Adaptive Radial Basis Function Neural Network (ARBFNN) Controllers and Model Reference Adaptive Control (MRAC). In model uncertainty, MRAC and ARBFNN outperformed the simple Proportional-Integral (PI) controller. The study is further expanded to involve Robust MRAC and Adaptive Sliding Mode Radial Basis Function Neural Network (ASRBFNN) Controllers to counter the compounded effects of model uncertainty and input disturbances. The versions of the robust controllers performed better than the conventional PI controller in cases involving both uncertainties and disturbances. Implementations were done on a 12V geared DC motor testbed with an Arduino microcontroller and MATLAB's System Identification Toolbox. The results from simulations and experimental applications highlight the greater flexibility and disturbance rejection capability of the developed advanced adaptive control schemes, making them perform better than standard PI controllers under challenging conditions.

  • 
  İncele
• MakaleYayıncıda açık erişim2024/r/gumushane/13996
  Gyroscopic precession control for maneuvering two-wheeled robot recoil stabilization

  Çetin, Gökhan; Ünker, Faruk

  A two-wheeled robot has high maneuverability and can spin around with a high velocity but is prone to roll over under a recoil force. Because the wheels are only used to control the maneuver speed of the robot. However, a two-wheeled robot using a gyroscope does not need the control of the wheels and can maintain the stability of the robot under a recoil force during maneuvers even if the gimbal of the gyroscope is not controlled by a torque. In this study, the equations of motion of the gyroscopic robot are derived via Lagrangian equations, and the balancing performance of the uncontrolled gyroscope is simulated via Matlab to determine a desired configuration for mechatronics system design. Then, a linear-quadratic regulator (LQR) is implemented to the chosen control moment gyroscope (CMG) configuration and compared in simulations of RecurDyn. LQR controller was used to prevent oscillating motions of double CMGs under the recoil force of a weapon. The simulation results showed that the gyroscopic two-wheeled robot is improved using an LQR controller and powerfully balanced in static with excellent performance.

  İncele
• MakaleYayıncıda açık erişim2024/r/gumushane/12555
  Control moment gyroscope recoil stabiliser including LQR controller for two-wheeled robot

  Çetin, Gökhan; Ünker, Faruk

  The control moment gyroscope’s (CMG) success in emerging damping control under impact load is of great interest for new technical applications. This paper explores the potential use of a two-wheeled robot with an independent weapon, such as an automatic cannon robot, and considers employing CMG with LQR control as a weapon recoil stabiliser for the robot. Cannon turret firing accuracy is crucial for optimising LQR control parameters and enhancing weapon-robot performance. CMG with LQR control effectively reduces the recoil impact loads of the overhead weapon while compensating angular momentum to ensure safety for robot in firing. The precession motion of the gimbal from several milliradians to tens of milliradians is one of some contradictions for describing the effect of the recoil force on robot–gyroscope performance. This paper uses computational methods, combined with CAE software, to study the impact of increasing angular momentum on recoil-induced weapon vibrations.

  İncele
• BildiriYalnız künye2023/r/gumushane/12773
  Pedestrian Inertial Navigation with Multi-Head CNN

  Cetin, Gokhan; Kucuk, Mehmet Ali; Koroglu, Muhammed Taha

  Traditional pedestrian dead-reckoning (DR) methods utilizing inertial measurement units (IMU) have been successfully employed in GPS-denied environments over the past two decades. However, despite continuous advancements in wearable IMU technology, the long-term solution still suffers from the issue of drift. In light of this, Deep Learning (DL) has emerged as a potential candidate for inertial navigation solutions, leveraging its powerful non-linear regression capabilities. Recent research has demonstrated that DL models trained on public datasets can effectively serve as end-to-end solutions. Most studies focus on smartphones, where the IMU is typically situated at the torso, and generally work with transformed data represented in the navigation coordinate frame to estimate pedestrian velocity and heading change at rates lower than the IMU sampling rate. In contrast, this study uses raw foot-mounted IMU data as input to a multi-headed structure consisting of independent convolutional neural networks (CNNs) and targets displacement directly and heading change. The proposed model is trained on a publicly available foot-mounted IMU dataset where pseudo ground-truth (GT) data is generated heuristically to provide supervision for the learning process. The results indicate that the Multi-Head CNN (MHCNN) model is capable of producing pedestrian trajectories at the IMU sampling rate, with positioning errors of less than 2m throughout the duration of the walks. The code for the trained network can be accessed in the associated repository, i.e., github.com/mtkoroglu/PIN-MHCNN.

  İncele
• MakaleYalnız künye2022/r/gumushane/12915
  Resilient active seismic response control of structural systems

  Çetin, Gökhan; Fadali, Mohammed S; Pekcan, Gökhan

  This paper proposes a dissipative resilient observer and controller (DROC) design for a network controlled system (NCS) that handles faults, implementation errors, or cyberattacks that can be modeled as bounded controller or observer gain perturbations. It presents linear matrix inequality (LMI) conditions for the robust stability of the system in the presence of bounded perturbations in the observer and controller. Furthermore, a new LMI-based time-delay control (TDC) algorithm that mitigates the effects of perturbations due to time-delays in the NCS is introduced. The robust methodology is applied to active control of a scaled model of a structural system equipped with an active mass driver system. The results demonstrate that the proposed methodology is robust and ensures stable system response due to various types of earthquake base excitations.

  • 
  İncele
• MakaleAçık Erişim2021/r/gumushane/14857
  Security system with RFID control using E-KTP and internet of things

  Çetin, Gökhan; Fadali, M. Sami

  This paper presents an optimal bandwidth allocation method for a networked control system (NCS) which includes time-driven sensor, event-driven controller and random channels. A hidden markov model (HMM) with a discretized state space is formulated for the random traffic to predict the network states using a suitable data window. Network bandwidth is allocated based on the predicted traffic state subject to bounds on the deterministic traffic that guarantee acceptable NCS performance and do not exceed hardware limitations. Bandwidth allocation uses l1 minimization of unmet bandwidth demand. A stability condition is derived for a variable but bounded sampling period interval. Computer simulation results show the effect of varying the number of discrete states for the HMM and the window width on bandwidth allocation. The results compare favorably with a published approach based on fuzzy logic.

  İncele