Conference Agenda

The accelerated growth of cities and communities has created the need to develop efficient systems for managing distributed infrastructures, facing significant challenges such as the prevalence of manual processes, understood as non-digitalized tasks that require physical intervention for data collection, equipment operation, or condition verification, as well as limited connectivity and low availability of real-time information, especially in rural areas [1]. This paper presents the AURA system (Unified Action for
Tracking and Analysis), a modular and scalable technological platform based on IoT technologies including FIWARE, LoRaWAN, and MQTT [2], [3] [4], [5], designed for real-time monitoring, tracking, and data analysis in [1]. To support deployments across heterogeneous urban–rural contexts, we rely on evidence from field trials and evaluations of LoRaWAN performance in both scenarios[1], [6]. AURA’s architecture integrates heterogeneous devices through specialized IoT agents, supporting multiple communication protocols to ensure interoperability and flexibility across diverse implementation contexts. Furthermore, it provides dynamic data visualization to facilitate process automation and remote management of critical services. Its hybrid storage scheme, combining traditional and graph-oriented databases along with advanced analytical tools, enables the execution of complex queries and supports predictive capabilities for evidence-based decision-making. Experimental and comparative results demonstrate that AURA outperforms traditional IoT architectures in terms of scalability, interoperability, and functionality, establishing itself as a comprehensive solution for implementing intelligent connected systems, with a clear projection toward more complex scenarios and broader territorial reach.

This article presents the design and implementation of an automated remote reading system for analog electricity meters, based on computer vision and artificial neural networks. The ESP32-CAM module is used as the capture unit, evaluating three optical configurations of the OV2640 sensor (66°, 120°, and 120° adjustable) to identify the most suitable in terms of sharpness and coverage. The obtained images are processed using binarization, segmentation, and normalization techniques and input into a neural network trained with the MNIST dataset for automatic digit recognition. The results show that the 120° adjustable variant at a distance of 5 cm offers greater capture accuracy. The neural model achieved an accuracy of 96.18% when evaluated with external images, demonstrating its generalization capabilities in real-world conditions. This proposal represents a low-cost, replicable, and technically viable solution for environments where analog meters are still used, contributing to energy automation in contexts with limited infrastructure.

This research proposes the design of a climate-adaptive photovoltaic pumping and irrigation system (PV-PIS) for a 7-hectare sugarcane plot in Chimbote, Ancash, aiming to improve water and energy efficiency within the Peruvian agricultural context. The study addresses the sector’s high-water demand, dependence on fossil fuels, and increasing climate uncertainty. The methodology followed an applied and quantitative approach with a descriptive-propositional design. Historical meteorological data from NASA Power and SENAMHI were used to determine the crop’s water requirement, estimated at 370.3 m³ per day, as well as the optimal solar resource availability. Based on these parameters, a 7.06 kWp photovoltaic system composed of thirteen 575 W monocrystalline panels was dimensioned, managed by an 8 kW hybrid inverter and integrated with an automation system using a Siemens S7-1200 PLC and environmental sensors. Technical validation was performed through SISIFO software simulation, yielding an estimated annual energy generation of 12,217 kWh. The economic analysis determined an initial investment of S/. 56,586.09, a levelized cost of energy (LCOE) of S/. 0.781/kWh, a positive Net Present Value (NPV) of S/. 7,955.03, and an Internal Rate of Return (IRR) of 12.00%, with a payback period of 7.46 years. The results confirm that the proposal is technically and financially viable, representing a sustainable alternative to conventional irrigation systems

The research aimed to study a three-bladed horizontal-axis wind turbine from the Renewable Energy Laboratory (RENOVA) at Metropolitan University using Computational Fluid Dynamics (CFD), contributing to the development of sustainable energy solutions in line with SDG 7 (Affordable and Clean Energy). A reverse engineering methodology was applied, beginning with 3D scanning to digitize the turbine geometry, followed by the creation of a CAD model based on the scan, measurements, and images. This model was used to conduct CFD simulations to determine the aerodynamic performance of the turbine, generating its characteristic curves. The simulation results were validated against literature, showing good agreement. The study revealed that while the aerodynamic design is capable of capturing power above the rated value, the actual system capacity is limited by the generator’s power, which is protected by the power controller. The work concludes by providing a documented foundation of the turbine’s behavior, identifying the generator as the system’s limiting factor, and establishing a replicable methodology for future studies at the university.

The reliability of rolling bearings in mining machinery is essential for maintaining operational continuity in extreme environments such as Cerro de Pasco, Peru, where abrasive particles, humidity, and cyclic loads accelerate mechanical degradation. To address the limitations of conventional maintenance approaches, this study proposes a hybrid methodology for predicting the Remaining Useful Life (RUL) of industrial bearings by integrating Finite Element Modeling (FEM), IoT-based monitoring, and machine learning techniques.

The analysis focuses on the SKF 22244 CC/W33 spherical roller bearing, widely used in rotating equipment such as crushers and grinding mills. FEM simulations were performed under realistic loads to identify stress concentration zones, while real-time data from vibration, temperature, and pressure sensors were used to train XGBoost and Random Forest models for RUL estimation. Additionally, a Convolutional Neural Network (CNN) classified wear severity from bearing images with accuracy above 93%.

Results show that actual bearing lifespan in abrasive environments may decrease by up to 15% compared with theoretical ISO 281 predictions, highlighting the need for predictive models adapted to real operating conditions. Cross-validation between simulations, sensed data, and intelligent algorithms confirms the robustness of the proposed approach for early fault detection, maintenance optimization, and reliability improvement in mining systems. This methodology also demonstrates scalability to other industrial sectors aligned with Industry 4.0 and Industry 5.0 frameworks.

This work presents the design and analysis of a tendon-driven underactuated robotic finger capable of adaptive grasping without individual joint control. The mechanism is actuated by a single input force while joint motion emerges from the interaction between stiffness distribution, inertia, and tendon transmission geometry. A dynamic model based on second-order rotational systems was developed to describe the behavior of each passive joint and predict the closing sequence. The finger was designed using CAD tools and fabricated through additive manufacturing using carbon fiber PLA and TPU materials. Experimental tests were performed to evaluate the closing behavior under constant actuation. Results show that the joints reach equilibrium at different settling times, producing a progressive grasping motion consistent with the dynamic model. The study demonstrates that adaptive grasping can be achieved through passive mechanical dynamics, reducing sensing and control requirements in robotic and prosthetic applications.