A carregar...
Publicação
A influência das tecnologias de IA na gestão de processos e da qualidade no setor industrial
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 712.19 KB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
A presente dissertação analisa a influência das tecnologias de Inteligência Artificial (IA) na gestão de processos e da qualidade nas organizações, evidenciando o seu papel estratégico na transformação digital e na criação de vantagens competitivas sustentáveis. Neste enquadramento, a presente dissertação tem como objetivo analisar criticamente o contributo da IA para a gestão de processos e da qualidade em ambientes industriais, identificando impactos, benefícios, riscos e limitações, com base na evidência da literatura científica recente. A metodologia adotada assenta numa revisão sistematizada da literatura e na análise comparativa de estudos de caso reais, selecionados segundo critérios de relevância científica e aplicabilidade industrial. Os casos analisados abrangem diferentes domínios de aplicação da IA, nomeadamente o controlo e previsão da qualidade, a monitorização e otimização de processos através de gémeos digitais e a automatização da inspeção visual, recorrendo a técnicas de machine learning e deep learning. A análise incide sobre a integração destas soluções nos processos produtivos, os dados utilizados, os métodos de validação e os resultados reportados. Os resultados mostram o potencial da IA para apoiar a tomada de decisão, reforçar a capacidade de previsão e deteção de desvios de qualidade e reduzir a dependência de inspeções manuais. Contudo, demonstram também que os benefícios obtidos dependem fortemente da qualidade dos dados, da maturidade tecnológica das organizações e da integração efetiva das soluções nos sistemas existentes, sendo ainda identificadas limitações relacionadas com a interpretabilidade, escalabilidade e competências necessárias. Conclui-se que a IA constitui um instrumento relevante para a gestão de processos e da qualidade na indústria, desde que a sua adoção seja orientada por uma abordagem estruturada e crítica, alinhada com os objetivos organizacionais.
Abstract This dissertation analyzes the influence of Artificial Intelligence (AI) technologies on process and quality management in organizations, highlighting their strategic role in digital transformation and the creation of sustainable competitive advantages. Within this framework, this dissertation aims to critically analyze the contribution of AI to process and quality management in industrial environments, identifying impacts, benefits, risks, and limitations, based on evidence from recent scientific literature. The methodology adopted is based on a systematic literature review and a comparative analysis of real case studies, selected according to criteria of scientific relevance and industrial applicability. The cases analyzed cover different application domains of AI, namely quality control and prediction, process monitoring and optimization through digital twins, and the automation of visual inspection using machine learning and deep learning techniques. The analysis focuses on the integration of these solutions into production processes, the data used, the validation methods, and the results reported. The results show the potential of AI to support decision-making, strengthen the ability to predict and detect quality deviations, and reduce dependence on manual inspections. However, they also demonstrate that the benefits obtained depend heavily on data quality, the technological maturity of organizations, and the effective integration of solutions into existing systems, while limitations related to interpretability, scalability, and necessary skills are also identified. It is concluded that AI is a relevant tool for process and quality management in industry, provided that its adoption is guided by a structured and critical approach, aligned with organizational objectives.
Abstract This dissertation analyzes the influence of Artificial Intelligence (AI) technologies on process and quality management in organizations, highlighting their strategic role in digital transformation and the creation of sustainable competitive advantages. Within this framework, this dissertation aims to critically analyze the contribution of AI to process and quality management in industrial environments, identifying impacts, benefits, risks, and limitations, based on evidence from recent scientific literature. The methodology adopted is based on a systematic literature review and a comparative analysis of real case studies, selected according to criteria of scientific relevance and industrial applicability. The cases analyzed cover different application domains of AI, namely quality control and prediction, process monitoring and optimization through digital twins, and the automation of visual inspection using machine learning and deep learning techniques. The analysis focuses on the integration of these solutions into production processes, the data used, the validation methods, and the results reported. The results show the potential of AI to support decision-making, strengthen the ability to predict and detect quality deviations, and reduce dependence on manual inspections. However, they also demonstrate that the benefits obtained depend heavily on data quality, the technological maturity of organizations, and the effective integration of solutions into existing systems, while limitations related to interpretability, scalability, and necessary skills are also identified. It is concluded that AI is a relevant tool for process and quality management in industry, provided that its adoption is guided by a structured and critical approach, aligned with organizational objectives.
Descrição
Palavras-chave
Inteligência artificial Indústria 4.0 Gestão de processos Gestão da qualidade Machine learning Deep learning Controlo e previsão da qualidade Gémeo digital Inspeção visual automatizada Estudos de caso Artificial intelligence Industry 4.0 Process management Quality management Machine learning Deep learning Quality control and prediction Digital twin Automated visual inspection Case studies