: Sources are listed at the end of the document in the numerical order they were first cited, not alphabetically.
Two primary AI approaches dominate the field: traditional Machine Learning (ML) and Deep Learning (DL). asme format citation
The evolution of manufacturing maintenance strategies has shifted from a reactive approach—fixing equipment only after it fails—to a proactive approach. In the context of Industry 4.0, the advent of the Industrial Internet of Things (IIoT) has facilitated the collection of massive datasets from industrial machinery [1]. This data influx has paved the way for Predictive Maintenance (PdM), a technique that predicts when machine failure will occur, allowing for maintenance to be planned just before the failure happens. : Sources are listed at the end of
The "black box" nature of complex neural networks poses a significant barrier. Maintenance engineers often hesitate to trust a model's prediction if the reasoning behind it is opaque. For safety-critical systems, explainability is not just a feature but a requirement. Current research focuses on Explainable AI (XAI) methods to bridge this trust gap [2]. In the context of Industry 4
[2] Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., and Beghi, A., 2015, "Machine Learning for Predictive Maintenance: A Multiple Classifier Approach," IEEE Transactions on Industrial Informatics , 11(3), pp. 812–820.
Use a dash for more than two consecutive references: .