With developing technology, robot arms are used in more areas, and this is directly proportional to the work done for its development. Studies on robot arms are generally focused on control. The controllability of robot arms generally provides speed and precision. Within the scope of this study, the control optimization of a two-arm robot arm with an optimized proportional integral differential controller (PID) was carried out using a microcontroller. The kinematic operations required to control a two-arm robot arm have been developed by the MATLAB Support Package for Arduino Hardware. The transfer function required for the control system was used for a direct current (DC) brushed motor, using the values given in the motor data sheet. Feedback is provided for the control system thanks to the Hall effect encoder. The gripper end of the two-limbed robot arm follows the specified square-shaped reference. In this study, where PID controller was used, controller parameters were obtained with particle swarm, artificial bee colony and chaos game metaheuristic optimization algorithms for square orbit and these parameters were used on the produced robot arm. Many methods have been used in the literature to determine PID parameters. In this study, the chaos game metaheuristic optimization algorithm, which has become popular in recent years, was used to determine the parameters of the PID controller.

Purpose: Rotating functionally graded (FG) disks of variable thickness generates vibration. This study aims to analyze the vibration generated by the rotating disks using a finite element program and compare the results obtained with the regression methods.Design/methodology/approach: Transverse vibration values of rotating FG disks with variable thickness were modeled using different regression methods. The accuracies of the obtained models are compared. In the context of comparing regression methods, multiple linear regression (MLR), extreme learning machine (ELM), artificial neural networks (ANNs) and radial basis function (RBF) were used in this study. The error graph between the observed value and the predicted value of each regression method was obtained. The error values of the regression methods used with scientific error measures were calculated.Findings: The analysis of the transverse vibration of rotating FG disks with the finite element program is consistent with the studies in the literature. When the variables and vibration value determined on the disk are modeled with ELM, MLR, ANN and RBF regression methods, it is concluded that the most accurate model order is RBF, ANN, MLR and ELM.Originality/value: There are studies on the vibration value of rotating discs in the literature, but there are very few studies on modeling. This study shows that ELM, MLR, ANN and RBF, which are machine learning methods, can be used in modeling the vibration value of rotating discs.

Purpose: The discs used in many fields of engineering can have dangerous consequences in terms of vibration value and temporal wear. This research aims to model the lateral vibrations of disks with different boundary conditions and Forward (FW) and Backward (BW) frequencies using a deep neural network (DNN). Methods: The transverse vibration analysis of rotating (Functionally graded) FG discs with different geometries was carried out using finite element software. The material properties of FG discs were calculated by the combination of the mixing rule and power law function obtained from the mixture of metallic and ceramic components. The material properties of FG discs are calculated by the combination of the rule of mixtures and power law function obtained from the mixture of metallic and ceramic components. This approach provides an important reference for material design in engineering applications. Modelling is provided by DNN tool with the determined hyperparameters. Results: The vibration responses of annular discs are obtained for Free-free (F-F), (Clumped-free) C-F and Clumped—Clumped (C–C) boundary conditions on the inner and outer surfaces and Campbell plots are drawn to show the effect of velocities on frequencies. The velocity dependent frequencies of FG discs are obtained for FW and BW waves. Different modelling results are obtained with DNN as the forward and backward wave boundary conditions. Conclusion: It is shown that the damped vibration responses of functionally graded rotating discs with variable geometry can be modelled in the range of hyperparameters determined by DNN.

Background: In this study, the relationship between the arrangement of centrally located elliptical holes on Functional Graded Plates (FGPs) and their free vibration behavior was analyzed using the finite element method, while the performance of the hybrid GWMTR algorithm for multivariate regression problems was also evaluated. In the vibration analysis, the effects of material index, hole size, arrangement angle, boundary conditions, and plate aspect ratio on the natural frequencies were investigated. Methods: In the field of regression analysis, a Multi-Task Regression Neural Network (MTRN) architecture optimized using the Grey Wolf Optimizer (GWO) was configured with hyperparameters determined via Particle Swarm Optimization (PSO). Results: It has been observed that FGP with circular holes produce higher frequencies compared to those with elliptical holes, and that the arrangement angle and plate ratio significantly affect the frequencies. This configuration provided superior accuracy (Coefficient of Determination, R ² ) and lower Root Mean Square Error (RMSE) for all outputs compared to the classical artificial neural network (ANN) architecture. Specifically, Root Mean Square Error (RMSE) values decreased by over 35% for outputs 1, 3, and 7, thereby significantly reducing the model’s error tolerance. Conclusion: The findings indicate that the GWMTR algorithm is more effective for multi-output regression problems and offers reliable and accurate modeling capabilities for complex engineering problems.

Today, solar energy is a standout option for meeting the increasing energy demand, as it is both renewable and environmentally friendly. The efficiency of photovoltaic (PV) systems, which convert light into electricity, depends on the amount of light that falls on the panel. Therefore, it is important to clean the panels regularly to remove dust and dirt, and to detect and repair broken panels. This study presents a solar panel cleaning robot designed according to current mobile robotic system technology. The robot moves along a designed trajectory to clean the factors affecting the efficiency of the solar panel, such as dust and bird droppings, which prevent the passage of solar rays. Another factor affecting solar panel efficiency is damage to the panels, such as cracks and breaks. These are detected during the cleaning process by the orbital movement of the mobile robot. The broken areas on the panel are visualized in real time on the designed interface with simulation in the ROS2 environment. Fracture detection using YOLOv8 produced successful results, and the mobile robot was simulated in the ROS2 environment. Three solar panels with a varying number of fractured and cracked regions were tested in the ROS2 environment, and successful results were observed. These results demonstrate that the YOLOv8 algorithm in the ROS2 environment can detect broken areas on the panel and provide users with information on the PyQt interface.