Programa del congreso

The automation of industrial processes has given rise to innovative solutions that combine robotics and artificial vision to optimize the sorting of parts. In this context, the development of a SCARA robot capable of selecting and sorting parts using an artificial vision system based on an ESP32 as the main camera is presented.
After analyzing the images, the SCARA robot controller executes precise trajectories that allow parts to be sorted according to predefined criteria. This type of approach ensures efficient and repetitive handling, optimizing operation times in production lines. The mechanical structure of the SCARA has been designed to offer high speed and accuracy, essential characteristics in industrial environments where reliability is a priority.
The ESP32 as a camera offers good resolution, a powerful processor, and high connectivity, making it a compact and cost-effective solution that facilitates its implementation in applications where cost reduction is essential. Additionally, an intuitive graphical interface was designed, allowing the user to configure classification parameters and monitor system performance in real time, enhancing its flexibility and adaptability.
This proposal integrates areas such as computer vision, robotic control, and mechatronic design, standing out for its ability to efficiently solve complex tasks, as well as for its functionality and accessibility. In this way, the prototype is consolidated as a practical and versatile tool for automated piece classification. This work demonstrates the potential of accessible technologies in developing advanced solutions for the industry, positioning the system as a promising alternative in the field of industrial automation.

Proper management of reactive power constitutes a fundamental aspect in ensuring energy efficiency and operational stability in electric power systems. A poor power factor is associated with increased conduction losses and may lead to additional costs or financial penalties imposed by the utility operator. Therefore, this article proposes a reactive power compensation system aimed at reducing losses and improving the power factor in low-cost residential single-phase networks. The control strategy is based on the application of Park and Clarke transformations, which enable a convenient representation of electrical variables for controller design. The system’s performance is validated through simulations carried out in the Matlab/Simulink environment, demonstrating its effectiveness for low-cost applications in residential single-phase grids.

Modern wireless communication systems face increasing challenges in efficiently managing radio frequency spectrum in highly dynamic and congested environments. Cognitive radios play a pivotal role by utilizing advanced spectrum sensing techniques to identify available frequency bands and avoid interference. This study introduces a novel model that integrates Recurrent Neural Networks (RNN) and Gated Recurrent Units (GRU), addressing the limitations of traditional spectrum sensing methods. RNNs excel at capturing temporal patterns in signal data, while GRUs enhance learning efficiency and adaptability to rapidly changing signal characteristics. Unlike previous approaches, this hybrid model demonstrates superior performance in complex and noisy environments. Evaluated using the RadioML 2016.10a dataset and key metrics such as F1 score, MCC, and CKC, the proposed technique outperforms both traditional and recent methods in accuracy and efficiency. These findings highlight the potential of this innovative approach to significantly enhance spectrum utilization and reliability in wireless sensor networks (WSNs).