Application of Tiny Machine Learning in Predicative Maintenance in Industries

Abstract

The advancements in the Internet of Things (IoT) and Machine Learning (ML) have enabled significant improvements in Predictive Maintenance (PdM) in industries, providing economic benefits by reducing equipment downtime and maintenance costs. Traditional ML approaches, however, re-quire more computational resources and are often limited to cloud-based processing, leading to in-creased costs and high latencies. Tiny Machine Learning (TinyML) offers a novel solution by enabling ML models to run on low-power, resource-constrained devices at the edge, facilitating real-time, on-device inference. This review analyzesTinyML applications in PdM, highlighting the technology's po-tential to transform industrial maintenance practices. We explore the differences between TinyML and standard ML, discuss the economic and operational advantages of adopting PdM, and present practical case studies where TinyML has been successfully implemented. In addition, we address the challenges facing TinyML, including hardware limitations and the need for specialized algorithms. Our findings indicate that while TinyML is a promising technology for PdM, further research is needed to overcome these challenges and fully realize its potential. This review contributes to understandingTinyML's role in industrial PdM and outlines a roadmap for future research and development in this emerging field.