https://repositorio.unifei.edu.br/jspui/handle/123456789/65 2026-06-03T12:03:01Z https://repositorio.unifei.edu.br/jspui/handle/123456789/3173 Título: Aquisição e validação de sinal de ruído eletroquímico Abstract: Corrosion is a global problem, which implies costs in industrialized countries of up to 4.5% of GDP, with either economic, but also social and environmental impacts. In the case of Brazil, the waste of water supply networks due to leaks loss is quite significant and much of it is caused by network degradation, indicating that corrosion control should be promoted whenever possible. This study proposes a corrosion monitoring system, in system subject to the use of inhibitor, with the approach of passive technique for monitoring corrosion by electrochemical noise (EN), in which the classification of events in a corrosion sensor by EN is part of methodological study for structural integrity (or “health”) monitoring system (SHM). Due to very dynamic and stochastic nature of the signal, this study and analysis of EN measurements (ENM) considers numerical and graphic characteristics of two corrosion systems both in saline aqueous solution: carbon steel and stainless steel. These experiments are repeated for accumulating data, which allow the generation of several graphs in time and frequency domains, from which at least one characteristic is extracted, which has a good correlation with data from corrosion processes. Then, based on a supervised machine learning system, the training data allows the model to be calibrated. From the test data, the correctness rate of the model above 50% is verified. Tipo: Dissertação 2022-02-17T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4422 Título: Sistemas de informação e aprendizagem de máquina na gestão da produtividade de equipes de campo de telecomunicações Abstract: The appliance of information systems in managing the productivity of field teams is a natural way to solve the various challenges for the evolution of management practices in service companies particularly in sectors that use field teams such as telecommunications, energy, logistics, sanitation, or maintenance. Field teams are responsible for much of the operational work and have a significant impact on customer satisfaction, directly affecting the company's financial performance. A system to replace the coercive control of dispatch supervision teams needs to have the intelligence to cross data from different monitoring mechanisms, learning from the behavior of the teams and encouraging people to collaborate naturally with information. The question to be answered in the research is how to monitor activities productivity of people in autonomous and remote work. The main objective of this work is to develop a model, using machine learning in image recognition, to the implementation of an information system for monitoring the service provision process of telecommunications companies. To this end, it presents a most important processes of telecommunications field service mapping and a detailed description of collecting useful data opportunities. The research methodology adopted was CRISP-DM in its six phases that include: understanding the problem, understanding the data, data preparation, modeling, assessment, and application. As a result, the research contributes to an automatic productivity monitoring approach, with minimal operator requirements and team adherence in an organic and systemic way. In addition, the research presents the implementation models for the proposed system. Tipo: Dissertação 2025-05-28T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4421 Título: Projeto, prototipagem e avaliação do ciclo de vida de metamateriais mecânicos usados no controle de vibrações de um canote de bicicleta Abstract: Metamaterials (MMs) are artificial structures designed to exhibit unique properties not available in nature. The aim of this study is to develop a chiral mechanical metamaterial (MM) to attenuate vibrations in a bicycle seatpost, using computational modeling, fabrication of a prototype by 3D printing, and life cycle assessment (LCA). Two types of seatposts damping systems were examined. The first one corresponds to a conventional model (CC) with integrated damping, already available on the market. The second one refers to a MM design (CMM), developed with the same functionality. Additionally, an optimized model of the CMM (CMMot) was proposed with a reduction in the total mass of the component, in order to evaluate any advantages associated with the reduced use of material and energy for manufacturing. The geometry of the CMM has a central arch-type unit cell (CACs), i.e., it has straight sections at the ends and concave curvature in the intermediate section, allowing the concentration of deformation in this region. Through computer modeling, the three geometries were designed, and then the CMM was constructed using 3D printing in selective laser melting (SLM) with 316L steel. Next, a comparative LCA was performed on the inputs derived from the manufacturing processes of the seatposts. The results of the numerical simulation indicated that, while the CC obtained a maximum displacement in Z of 20.47 mm, the CMM responded with a significantly lower value of 2.55×10-4 mm and the CMMot of 2.41×10-4 mm, indicating the promising potential of MMs in vibration mitigation. With regard to LCA, CMMot performed better than the original CMM, with reductions of approximately 32% in all impact categories evaluated. However, CC still has a lower total environmental impact, even with the use of renewable energy sources. The negative effects of CMM are mainly related to the electricity consumed during additive manufacturing. From an environmental and structural point of view, CMM represents a significant technical advance, but it still depends on improvements in the process to increase its sustainable viability. The research contributes to the literature by addressing the integration between MMs and LCA, an area that has been little explored, and reinforces the need for future studies involving a cradle-to-grave approach, experimental validations, and production scaling strategies. Tipo: Dissertação 2026-01-28T00:00:00Z https://repositorio.unifei.edu.br/jspui/handle/123456789/4420 Título: Proposta de um sistema baseado em inteligência de negócios aplicado ao gerenciamento de projetos na área de exportação Abstract: Efficient project management in Engineer to Order (ETO) companies is a constant challenge due to the need for high flexibility, cross-departmental collaboration, and extended lead times resulting from the customization of each order. In this context, increasing organizational complexity, driven by globalization and technological advancements, requires tools that enable fast, assertive, and data-driven decision-making. This study aims to propose and develop a conceptual model for strategic decision-making by integrating Business Intelligence (BI) concepts into project management, with practical application in the export sector of a power equipment manufacturing company. The research adopted the CRISP-DM method, providing a structured approach to building a BI environment tailored to support international project management. As a result, an interactive dashboard was implemented to consolidate data from different departments (commercial, logistics, and financial), enhancing transparency, integration, and real-time control. The main benefits observed include the reduction of rework and errors from manual spreadsheets, monitoring of costs and performance indicators, predictive analysis of lead times and bottlenecks, support in negotiations with freight forwarders, and significant productivity gains (estimated at 59.84% per year). In conclusion, the integration of BI into project management represents a strategic advancement, transforming raw data into actionable intelligence, improving operational efficiency, and supporting complex decision-making in the dynamic environment of international trade. Tipo: Dissertação 2025-10-22T00:00:00Z