Utilizing Data Analytics for Predictive Maintenance in Manufacturing: A Systematic Review on Achieving Operational Excellence

Abstract

Predictive maintenance (PdM) has emerged as a key strategy for enhancing operational efficiency in manufacturing by leveraging data analytics to forecast equipment failures and optimize maintenance activities. This paper systematically reviews the current state of predictive maintenance in manufacturing, with a particular focus on the integration of data-driven techniques, including machine learning and Internet of Things (IoT) technologies, for improved maintenance management. The review highlights the effectiveness of various predictive models, such as random forests, support vector machines, and artificial neural networks, in predicting machine failures and reducing downtime. It also explores the role of IoT sensors in real-time monitoring of equipment and the challenges associated with data quality, sensor reliability, and the integration of legacy systems. The paper examines the cost-benefit considerations of adopting predictive maintenance systems, revealing that while the initial investment can be significant, the long-term savings from reduced unplanned downtime, extended equipment lifespan, and optimized maintenance operations often justify the expenditure. Additionally, it discusses the barriers to PdM adoption, including the need for skilled labor, organizational resistance to change, and challenges related to data management. Looking ahead, the review identifies key emerging technologies, such as artificial intelligence (AI), digital twins, and edge computing, as critical enablers for the future of predictive maintenance. These technologies are expected to enhance the accuracy and real-time capabilities of predictive models, further driving efficiency in manufacturing operations. The paper concludes that while challenges remain, the continued advancement of predictive maintenance, underpinned by data analytics, will play a pivotal role in driving operational excellence and competitiveness within the manufacturing sector.