Ferramenta computacional para análise de capacidade de processo utilizando a linguagem phyton

• Ano de defesa: 2019
• Autor(a) principal: Miura, Flávia Sayuri
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Tecnológica Federal do Paraná; Medianeira; Brasil; Programa de Pós-Graduação em Tecnologias Computacionais para o Agronegócio; UTFPR
• Palavras-chave em Português: Controle de processo - Métodos estatísticos; Python (Linguagem de programação de computador); Processos de fabricação - Automação; Process control - Statistical methods; Python (Computer program language); Manufacturing processes - Automation; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO; Engenharia/Tecnologia/Gestão
• Link de acesso: http://repositorio.utfpr.edu.br/jspui/handle/1/25457

Statistical Process Control (SPC) is a technique widely used to analyze, monitor, manage and recover the performance of manufacturing processes. Control Charts are powerful Statistical ProcessControl tools. These charts allow, through sample information, to identify problems in industrial processes. Many commercial software for building these charts are available in the market. However, they can be expensive and present license and usage restrictions. In this context, this work aimed to develop a Python application, called CECad,as an option for the development of these charts for use in small and medium enterprises. Currently, this application presents the control charts̅-R e ̅̅-S and calculation of process capacity indices. It also includes the confidence interval calculation using the bootstrap resampling technique. Results of the capacity analysis of two production processes are presented: a plastic bottle production process and a process of production of tilapia packaging. In the industries, 160 plastic bottles of 100 milliliters and 200 packages of 400 grams of tilapia were weighed. It has been found that the capacity indices Cpkare below one, which classifies the processes as incapable.