| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 2.43 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
Este trabalho tem por objetivo identificar os custos de produção críticos, relativos à ma-téria-prima e mão de obra, de produtos por encomenda sem padronização, e assim desen-volver um modelo quantitativo para realizar predições precisas destes custos na etapa inicial do projeto de uma empresa, no âmbito do processo de orçamento. Para alcançar o objetivo proposto, buscou-se, em primeiro lugar, o entendimento dos processos produti-vos e matérias-primas da empresa, assim como o estudo dos principais aspectos teóricos relacionados a técnicas e métodos para estimativa de custos, criação de modelos para estimativa de custos, seleção de modelos e validação destes. Visto isso, pretende-se de-senvolver um modelo de regressão linear múltipla (RLM), aplicada a um histórico de dados quantitativos da empresa, utilizando o software RStudio, a fim de estimar cada va-riável crítica relativa à quantidade de matéria-prima principal e aos tempos de mão de obra para processos críticos. Seis modelos foram analisados, dois para cada variável crí-tica definida, sendo estas o valor dos metros lineares (VML) de matéria-prima principal utilizado no produto, o tempo de corte da matéria-prima principal envolvido no produto e o tempo de costura ligado ao produto. Os modelos foram avaliados, selecionados e va-lidados, definindo um melhor modelo para cada variável crítica. Os parâmetros dos mo-delos foram obtidos utilizando dados de treino e posteriormente os resultados dos mode-los selecionados foram validados utilizando dados de teste. Os resultados obtidos, medi-ante a utilização da metodologia proposta, foram avaliados pela empresa e se mostraram confiáveis para utilização na fase inicial de desenvolvimento do produto. Após estes pas-sos, foi possível utilizar estes modelos para criar uma ferramenta simples e útil para a empresa.
This work aims to identify the critical production costs, related to raw materials and labor, of ordered products without standardization in order to develop a quantitative model to predict accurately these costs in the early project stage of a company, within the budget step. In order to achieve this goal, it was necessary to understand the production processes and the raw materials of the company, as well as to study the principal theoretical aspects related to cost estimating techniques and methods, cost estimating models, model selec-tion and validation. Therefore, it is intended to develop a multiple linear regression model, applied to an historical quantitative data of the company, using the R software to estimate each critical variable concerning the quantity of the main raw material and the labor times to critical processes. Six models were analyzed, in which two models are identified for each critical variable such as the linear meters value of the main raw material used in the product, the main raw-material cut time involved in the product and the sew time required by the product. The models were evaluated, selected, and validated, defining the best model for each critical variable. The model parameters were obtained using a train dataset and, afterwards, the results of the selected models were validated using a test dataset. The obtained results, through the proposed methodology, were evaluated by the company and they show to be reliable for use in the early stage of product development within the budget step. After these steps, it was possible to use these models to create a simple and useful tool to the company.
This work aims to identify the critical production costs, related to raw materials and labor, of ordered products without standardization in order to develop a quantitative model to predict accurately these costs in the early project stage of a company, within the budget step. In order to achieve this goal, it was necessary to understand the production processes and the raw materials of the company, as well as to study the principal theoretical aspects related to cost estimating techniques and methods, cost estimating models, model selec-tion and validation. Therefore, it is intended to develop a multiple linear regression model, applied to an historical quantitative data of the company, using the R software to estimate each critical variable concerning the quantity of the main raw material and the labor times to critical processes. Six models were analyzed, in which two models are identified for each critical variable such as the linear meters value of the main raw material used in the product, the main raw-material cut time involved in the product and the sew time required by the product. The models were evaluated, selected, and validated, defining the best model for each critical variable. The model parameters were obtained using a train dataset and, afterwards, the results of the selected models were validated using a test dataset. The obtained results, through the proposed methodology, were evaluated by the company and they show to be reliable for use in the early stage of product development within the budget step. After these steps, it was possible to use these models to create a simple and useful tool to the company.
Description
Mestrado de dupla diplomação com a UTFPR - Universidade Tecnológica Federal do Paraná
Keywords
Orçamentação de produtos Custos de produção Estimativa de custos Regressão linear múltipla