Análise do uso da Inteligência Artificial na área de Engenharia da Qualidade

• Autor(a) principal: SARAH LOPES DE ALBUQUERQUE
• Data de Publicação: 2023
• Tipo de documento: Trabalho de conclusão de curso
• Idioma: por
• Título da fonte: Repositório Institucional da UFMS
• Texto Completo: https://repositorio.ufms.br/handle/123456789/6793
• topic: engenharia da qualidade; inteligência artificial; engenharia de produção.; Engenharia / Tecnologia

Artificial Intelligence (AI) finds applications in various industrial and service sectors, including the enhancement of production process quality. In light of this, this research aims to analyze the use of AI techniques applied in the field of Quality Engineering. To achieve this, the research employed the Systematic Literature Review (SLR) as its primary research method and supplemented it with textual analysis of abstracts using the Iramuteq software. The research utilized Engineering Village, SCOPUS, and Web of Science databases due to their relevance in the study area. By analyzing 44 articles, the results demonstrated an increasing number of publications on the topic in recent years, with a 38% increase compared to the previous two full years. Furthermore, the key findings revealed that 77% of the research is applied in the industry, with the subarea of quality planning and control being the most prevalent, featured in approximately 66% of the analyzed articles. Regarding the technical procedures used in AI applications, the data predominantly consisted of product and equipment data, with artificial neural networks being the most frequently used technique, representing approximately 50% of the analyzed articles. It was also noted that the primary advantage of AI application is the improvement of product or service quality, albeit with the challenge of collecting and processing a large volume of data. Additionally, to complement the results, the analyses conducted through the Iramuteq software underscore the significance of AI in enhancing quality in manufacturing and industrial processes, confirming the two main subareas identified in the SLR and highlighting that the research topics analyzed are subject to variations over the years. Thus, this research contributes to identifying promising areas for the adoption of this technology, directing investments more efficiently towards the required data types and equipment, thereby addressing a gap in the literature concerning the use of AI in Quality Engineering subareas.