Dissertação PPG.EGPSA

URI permanente para esta coleçãohttps://rigalileo.itegam.org.br/handle/123456789/3

Navegar

Filtros

2024 - 20252

Configurações

Data inicial: 2024Assunto: search.filters.subject.Placas de Circuito Impresso

Resultados da Pesquisa

Agora exibindo 1 - 2 de 2
  • Imagem de Miniatura
    Item
    Uso da Ferramenta OEE para Otimizar o Processo de Fabricação de Placas de Circuito Impresso no Processo SMT
    (Instituto de Tecnologia e Educação Galileo da Amazônia, 2025) MEDEIROS, Gelson Ricardo Martins; SANTOS, Eliton Smith dos; ALMEIDA, Luiz Fernando Correia de Almeida
    This dissertation addresses the application of the Overall Equipment Effectiveness (OEE) metric in the Surface Mount Technology (SMT) process to optimize production efficiency in a company located in the Manaus Industrial Hub. The study identifies the main losses affecting the printed circuit board assembly line, classifies these losses, and proposes improvement actions based on the Total Productive Maintenance (TPM) methodology. The methodology includes a case study, data collection from production lines, expert interviews, and practical application of performance indicators. The results demonstrate that the use of the OEE tool, combined with corrective and preventive measures, can enhance SMT line efficiency and significantly reduce losses related to downtime, speed, and quality.
  • Imagem de Miniatura
    Item
    Utilização de Inteligência Artificial e IoT para Inspeção e Detecção de Defeitos em Placas de Circuito Impresso
    (Instituto de Tecnologia e Educação Galileo da Amazônia, 2024) SOARES, Karen Kettelen Souza; GUIMARÃES, Gil Eduardo
    The increasing complexity in the manufacturing of printed circuit boards (PCBs) has posed significant challenges for industries, particularly in the inspection and detection of defects. This study proposes the use of Artificial Intelligence (AI) and the Internet of Things (IoT) as tools to optimize fault detection in PCBs, focusing on reducing human errors and improving operational efficiency. The research is based on the implementation of an automated inspection system, utilizing neural networks for defect classification and IoT sensors for real-time monitoring of manufacturing conditions. The main goal of the dissertation is to develop an efficient analysis model to identify early faults, enhance product quality, and reduce operational costs. The study involved building a functional prototype that integrates AI and IoT, validated in a real production environment. The results showed that the proposed approach could detect defects with higher accuracy, leading to significant improvements in the efficiency of the PCB production line.