ABSTRACT
The manufacturing industry is currently witnessing a huge revolution in terms of the Industry 4.0 paradigm, aiming to automate most manufacturing processes from condition monitoring of machinery to optimising production efficiency with automated robots and digital twins. One such valuable contribution to the Industry 4.0 paradigm is the concept of predictive maintenance (PdM), which aims to explore the contributions of artificial intelligence (AI) to gain meaningful insights into the health data of the machinery and enable timely maintenance. Machinery fault detection under the umbrella of PdM helps to monitor the operation of the machinery via integrated sensors, generates alerts on observing noticeable deviations in sensor readings, and predicts machine failure ahead of time. Such insights can help the manufacturer plan maintenance activities in advance without risking the machine’s unplanned downtime due to failure. Further, machinery fault detection provides sustainable solutions in energy conservation during manufacturing processes and ensures optimised utilisation of maintenance resources. This chapter delves into the concept of artificial intelligence–enabled machinery fault detection and provides an in-depth review of traditional and modern approaches used for fault detection. It further explores the recent advancements in terms of sensors used and extracted for fault detection in case studies. This work would be resourceful literature for researchers and practitioners planning to explore the impact of artificial intelligence in smart manufacturing.
