Aplicação de sensores na manutenção preditiva: desafios e benefícios em empresas de usinagem de Panambi

Abstract

This study analyzes the application of sensor technologies in predictive maintenance within companies in the metal machining sector in Panambi, focusing on the types of sensors used, practical challenges, and observed benefits in operational efficiency. The research combines a literature review on sensors and predictive maintenance with a qualitative case study, including interviews and meetings with managers from machining companies (Kepler Weber and Bruning Tecnometal) and sensor suppliers (Acoem and Dynamox). The results reveal that despite the specific challenges of the machining environment, such as rotation variations and interference, the implementation of vibration and temperature sensors provides significant benefits, including reduced unplanned downtime and protection of critical equipment. The case study of Kepler Weber demonstrates a significant cost avoidance, equivalent to approximately 1,174% of the invested amount, highlighting the effectiveness of predictive maintenance based on sensors. The time to achieve this saving was 180 days, which demonstrates the rapid recovery of the investment and the financial benefits resulting from the reduction of unplanned downtime, repairs, and equipment damage. A comparative analysis of sensors available on the market (Tractian Smart Trac Ultra, WEG WEGscan 100, Acoem Eagle, and Dynamox DynaLogger HF+) provides guidance for appropriate selection according to the specific needs of each industry. It is concluded that, despite the initial implementation challenges, predictive maintenance with sensors represents a necessary evolution for machining companies seeking greater competitiveness through reduced operational costs and increased equipment availability.