Bu çalışmada, türbülanslı akışta boru içerisine cidardan ayrık olarak yerleştirilen 3D/4 genişliğe sahip sinüzoidal ondüle şerit elemanların, farklı Reynolds sayılarında, sürtünme ve ısıl performans katsayılarında ve D/8, D/4, 3D/16 olmak üzere 3 farklı genlikte ısı transferine etkilerinin deneysel sonuçları kullanılarak, yapay sinir ağı tabanlı bulanık mantık (YSATBM) yaklaşımı ile aynı girdilerin ve çıktıların modellemesi gerçekleştirilmiştir. Deneysel ısı transferinde elde edilen minimum ve maksimum Nusselt sayılarının oluşturulan iki ayrı YSATBM yaklaşımı ile tahmin edilmesi sağlanmıştır. Elde edilen simülasyon sonuçları deneysel sonuçlar ile karşılaştırılmış ve min. Nusselt sayılarının tahmininde ortalama %0.1378, maks. Nusselt sayılarının tahmininde ise %0.0141 hata değerleri elde edilmiştir.

Inverse kinematics is a fundamental problem in robotic manipulator control, especially when the joint variables must be determined from a desired end-effector pose. In this study, an artificial neural network-based regression model is developed for the inverse kinematics prediction of a 3-DOF planar robotic manipulator. The model uses the end-effector position and orientation as input variables and predicts the corresponding three joint angles as output variables. The training data set was generated by considering the robot link lengths, joint constraints, reachable workspace and valid inverse kinematic solutions. A multilayer feedforward artificial neural network was trained and tested using separate training, validation and test data sets. The performance of the model was evaluated using error metrics, regression scatter diagrams, workspace-based visualization and selected target configuration tests. The results obtained indicate that the proposed ANN model can approximate the inverse kinematics mapping within the feasible workspace of the manipulator. This approach provides a simple and effective learning-based solution for joint angle estimation in planar robotic systems.

The value of wheelbase preview in half-car active suspension depends on how reliably preview information can be reconstructed as road excitation changes. A confidence-aware wheelbase-preview model predictive control strategy is formulated for a four-degree-of-freedom half-car active suspension system subjected to random-road and impact-road inputs. The framework combines augmented state-road estimation with shift-register-based rear-preview generation. Preview usage is then adjusted online through an innovation-based confidence measure, while control increments are regularized within a constrained MPC formulation. Reconstruction quality differs clearly between the two simulated scenarios: road-estimation correlation falls from 0.9652 in the random-road case to 0.6935 in the impact-road case, and the mean confidence drops from 0.968 to 0.919. Preview is therefore useful, but its reliability is not stable enough for fixed use across operating conditions. In random-road simulations, rear acceleration root-mean-square (RMS) falls from 1.594 to 1.159 m/s², rear suspension deflection RMS from 7.82 to 5.93 mm, and rear relative dynamic load RMS from 0.235 to 0.203 relative to the passive baseline. For impact-road excitation, the controller provides the strongest improvements in rear-axle acceleration and dynamic-load response, attaining a rear acceleration RMS of 1.213 m/s², a rear acceleration P2P value of 13.269 m/s², and a rear relative dynamic load P2P value of 2.059 among the compared controllers. Changes at the front axle remain modest, whereas the clearest benefit appears at the rear, where preview is most directly relevant. Ablation results show that warm-up, confidence gating, and control-increment regularization improve different aspects of the response, leaving the full configuration as the most balanced overall trade-off rather than the best result in every metric. Mean solve times remain at 0.16 ms for the random-road case and 0.22 ms for the impact-road case, both below the selected 0.01 s sampling interval. Taken together, these results show that wheelbase preview is most effective when its contribution is adjusted according to estimation reliability rather than treated as uniformly trustworthy information.

Nonlinear aeroelasticity with pitch freeplay can generate finite-amplitude limit cycle oscillation below or near the linear flutter boundary. This study examines flutter suppression in a two-degree-of-freedom pitch-plunge airfoil benchmark with quasi-steady aerodynamic coupling, freeplay nonlinearity, and trailing-edge flap actuation. A conservative linear quadratic regulator is designed as the stabilizing baseline and augmented with a model reference adaptive control layer whose regressor explicitly includes the piecewise freeplay restoring function. This structure allows the adaptive input to compensate the nonlinear torsional contribution rather than treating it only as an unmodeled disturbance. Closed-loop simulations are conducted for inflow velocities from 11.2 to 12.0 m/s, covering limit-cycle and post-flutter cases, with controller activation tested both initially and after an uncontrolled oscillation has developed. At 11.6 m/s with delayed activation, the combined controller reduces the residual pitch amplitude from approximately 1.05×10−3 rad for the linear quadratic regulator baseline to 3.49×10−5 rad, corresponding to a 96.7% reduction relative to the selected non-aggressive baseline, while maintaining bounded flap motion below the imposed saturation limit. Additional numerical checks under measurement noise, bounded external disturbances, and deterministic parameter perturbations support a practical boundedness interpretation within the tested quasi-steady benchmark envelope.