Elevating Manufacturing Excellence: A Data-Driven Approach to Optimize Overall Equipment Effectiveness (OEE) for a Single Machine

In the intensely competitive landscape of global manufacturing,
achieving operational excellence is paramount for survival and success. Central to this endeavor is the optimization of Overall Equipment Effectiveness (OEE), a key metric that directly influences resource efficiency and product quality. Manufacturing companies face numerous challenges, including maintenance inefficiencies, unplanned downtimes, and product quality variations, which hinder the achievement of optimal OEE levels. The research explores the valuable role of machine learning in OEE enhancement, with a specific focus on bolstering availability, a critical key performance indicator in this context. This paper delves into a comprehensive numerical experiment, elucidating the machinery under scrutiny, data collection intricacies, machine learning model construction, and meticulous
validation processes. The chosen machine learning model is Random Forest, selected for its top-notch accuracy and F1 score. The model’s deployment and real-world application are delineated, demonstrating a notable OEE improvement
from 49% to 52% between July 2023 and September 2023. This paper provides a structured path for manufacturing optimization, fortified by machine learning, to address the challenges of enhancing OEE. It underscores the critical role of OEE in the manufacturing domain and offers a holistic framework for addressing its complexities.