Classificador Fuzzy para Estimação de Parâmetros de Corte em Serras Feixe Circulares

Abstract

In industrial environments, the correct definition of operating parameters is essential to ensure the productive cadence and conservation of assets. The equipment in this study consists of 4 circular saws, which had an outdated operational standard. Thus, in new product scenarios, operators set the cutting speed and feed values based on their own experience. This situation led to forced deterioration, increasing the occurrence of breakages and wear of the cutting blades. This work proposed to use the existing historical data in the PIMS - Plant Information Management System, evaluating through supervised learning, which combinations of cutting speed and feed are the most suitable for new products, thus reviewing the current procedure. For data classification, the c-means algorithms were used to group steels of similar hardness and Fuzzy c-means to evaluate the performance of the cuts. After the revision of the operational standard, the MTBF (Mean Time to Failure) and MTTR (Mean Time to Repair) indicators improve substantially, which can be translated into reduced operating costs.