Machine learning in industrial systems

This unit introduces you to the principles and applications of machine learning in industrial systems, with a focus on solving real-world engineering problems using data-driven approaches. As modern industries increasingly adopt intelligent and automated systems, machine learning has become a core enabling technology for enhancing efficiency, reliability, safety, and decision-making across manufacturing, infrastructure, energy, and process industries. You will explore the integration of fundamental industrial and machinery systems knowledge with introductory machine learning (ML) techniques. You will develop a foundational understanding of key machine learning methods, including supervised and unsupervised learning, feature extraction, model training, and performance evaluation. Through industry-motivated case studies, you will examine applications such as predictive maintenance, fault detection and diagnosis, quality inspection, condition monitoring, and process optimisation. By the end of the unit, you will be equipped with the skills to critically evaluate machine learning solutions and apply them effectively within industrial engineering contexts.

Problem-based learning - This unit adopts problem-based learning approaches. You will integrate theory and practice by applying your knowledge and skills to develop viable solutions to authentic industrial problems.

Active learning - The workshops will be organised based on an active learning approach where you will be engaged to actively apply your knowledge, skills and attributes in interactive, collaborative and reflective activities

Case-based teaching - This unit adopts a case-based teaching approach, where you apply your technical knowledge and engage in analytical and reflective thinking to address complex, real-world scenarios in industrial systems. Through industry-inspired case studies, you will examine how machine learning techniques can be used to support tasks such as machinery monitoring, fault diagnosis, and operational decision-making.

The minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of 3-6 hours of scheduled learning activities and 6-9 hours of independent study per week. Scheduled activities may include a combination of teacher-directed learning, peer-directed learning and online engagement. Independent study may include associated readings, assessment and preparation for scheduled activities.