Program Overview

Fault Detection and Prognosis

This CPD course aims to provide production operators/junior engineers/safety managers with a robust foundation in machinery fault diagnosis and prognosis (FDP) tailored for advanced manufacturing environments. After this course, students will gain an essential but significant understanding of machinery FDP, failure modes in rotating machinery, data acquisition techniques, and MATLAB applications. The curriculum includes basic signal processing techniques, such as time and frequency domain analysis, and incorporates fundamental artificial intelligence (AI) methods for fault diagnosis and prognosis. Students will be shown demonstrations of machinery health and condition monitoring. Learners will also have the opportunity to consolidate their knowledge through real-world case studies, highlighting practical applications and collaborative problem-solving.

Learning Outcomes

• Understand the significance, terminology, and core concepts of machinery FDP, supported by video examples.
• Apply data acquisition techniques, and conduct fundamental time and frequency domain signal processing techniques for machinery FDP.
• Apply AI methods, including feature extraction and learning-based approaches, to conduct machinery FDP.
• Assess the performance using a variety of real-world case studies.

Course Agenda

The CPD course is structured to span two full days, with four sessions each day: two in the morning and two in the afternoon. On the first day, students will learn about the fundamentals of FDP, followed by hands-on hardware experiments. The second day will cover traditional signal processing techniques and AI-based FDP methods. The course will conclude with a group project, where students will work on real-world case studies.

Course Sessions

• First Day:
  • Introduction to machinery fault diagnosis and prognosis (FDP)
  • Introduction to faults in machines
  • Data acquisition techniques
  • Signal processing fundamental concepts
• Second Day:
  • Signal processing frequency domain analysis
  • Signal processing fault diagnosis
  • AI-based method for fault diagnosis
  • Case studies