Module Details

Module Code: MECH9007
Title: Machine Prognostics
Long Title: Machine Prognostics
NFQ Level: Expert
Valid From: Semester 1 - 2019/20 ( September 2019 )
Duration: 1 Semester
Credits: 10
Field of Study: 5211 - Mechanical Engineering
Module Delivered in: 1 programme(s)
Module Description: The aim of this module is to identify and select the relevant strategies and techniques for Prognostics and Health Management (PHM) and apply them to data sets to better predict the future performance of machines and systems to estimate remaining useful life. The module will investigate both physics and data based PHM methodologies and maintenance implications of life cycle assessment of components and systems in an industrial context.
 
Learning Outcomes
On successful completion of this module the learner will be able to:
# Learning Outcome Description
LO1 Appraise and critically assess methods for damage estimation of components and systems.
LO2 Implement using appropriate software a lifetime or accelerated model and benchmark its performance.
LO3 Critically assess PHM techniques on component and system level maintenance and lifetime prognostics.
LO4 Implement suitable physics and/or data based numerical techniques in PHM to a relevant data set and critically assess outcomes.
LO5 Select and apply the most appropriate PHM methodology to a real world dataset.
LO6 Assess appropriateness of chosen PHM methodology.
Dependencies
Module Recommendations

This is prior learning (or a practical skill) that is strongly recommended before enrolment in this module. You may enrol in this module if you have not acquired the recommended learning but you will have considerable difficulty in passing (i.e. achieving the learning outcomes of) the module. While the prior learning is expressed as named MTU module(s) it also allows for learning (in another module or modules) which is equivalent to the learning specified in the named module(s).
Incompatible Modules
These are modules which have learning outcomes that are too similar to the learning outcomes of this module. You may not earn additional credit for the same learning and therefore you may not enrol in this module if you have successfully completed any modules in the incompatible list.
No incompatible modules listed
Co-requisite Modules
No Co-requisite modules listed
Requirements

This is prior learning (or a practical skill) that is mandatory before enrolment in this module is allowed. You may not enrol on this module if you have not acquired the learning specified in this section.
No requirements listed
 
Indicative Content
Approaches to Maintenance and Reliability
Review of damage/degradation mechanisms such as wear, corrosion, crack growth, deformation and estimation. Component level and system level reliability modelling, employing functional diagrams, lifetime and accelerated testing such as Arhenius, Coffin-Mason, Eyring Model, statistical process control (SPC). Evolution of maintenance strategies from corrective and preventative to condition based monitoring (CBM). Influence of maintenance and reliability on overall equipment effectiveness (OEE).
Prognostics and Health Management (PHM)
Introduction to prognostics and health monitoring (PHM) techniques and methodologies - including data acquisition, data pre-processing, detection, diagnostics and prognostics and decision making, key challenges. Prediction of remaining useful life (RUL).
Implementation of Model based Prognostics
Introductions and applications, physics based models, data based models, hybrid based models, RUL prediction, Matlab implementation, model adequacy and uncertainty, parameter extraction, data quality and uncertainty, conditional probability, digital twin. Prognostic algorithms - Bayesian methods including kalman filter (KF), Particle Filter (PF), method of least squares (LS), Non Linear least Squares (NLS), Neural Networks, Gaussian Process Regression (GPR).
Applications to published data sets
Review and application of PHM to published data sets e,g, NASA, PHM, Kaggle. Assess appropriateness of chosen PHM methodology.
Module Content & Assessment
Assessment Breakdown%
Coursework100.00%

Assessments

Coursework
Assessment Type Project % of Total Mark 20
Timing Week 3 Learning Outcomes 1,4
Assessment Description
Demonstrate using Matlab suitable numerical techniques and their application to a relevant data subset
Assessment Type Project % of Total Mark 30
Timing Week 8 Learning Outcomes 1,2,3
Assessment Description
Using prescribed numerical techniques generate a component lifetime model based on reliability data for in service components.Critically asses to predict future failure rates.
Assessment Type Presentation % of Total Mark 10
Timing Week 13 Learning Outcomes 3,6
Assessment Description
Disseminate findings from end of semester project regarding the application of PHM techniques
Assessment Type Project % of Total Mark 40
Timing Sem End Learning Outcomes 1,3,4,5,6
Assessment Description
Implement relevant PHM techniques to a large published data set. Define identify and extract relevant usable parameters. Critically assess suitability for PHM
No End of Module Formal Examination
Reassessment Requirement
Coursework Only
This module is reassessed solely on the basis of re-submitted coursework. There is no repeat written examination.

The University reserves the right to alter the nature and timings of assessment

 

Module Workload

Workload: Full Time
Workload Type Contact Type Workload Description Frequency Average Weekly Learner Workload Hours
Lecture Contact Lectures on Machine Prognostics Every Week 3.00 3
Lab Contact Practical Implementation of Numerical methods Every Second Week 1.50 3
Lab Contact Published dataset interrogation Every Second Week 1.50 3
Independent & Directed Learning (Non-contact) Non Contact Machine Prognostics Every Week 8.00 8
Total Hours 17.00
Total Weekly Learner Workload 14.00
Total Weekly Contact Hours 6.00
Workload: Part Time
Workload Type Contact Type Workload Description Frequency Average Weekly Learner Workload Hours
Lecture Contact Lectures on Machine Prognostics Every Week 3.00 3
Lab Contact Practical Implementation of Numerical methods Every Second Week 1.50 3
Lab Contact Published dataset interrogation Every Second Week 1.50 3
Independent & Directed Learning (Non-contact) Non Contact Machine Prognostics Every Week 8.00 8
Total Hours 17.00
Total Weekly Learner Workload 14.00
Total Weekly Contact Hours 6.00
 
Module Resources
Recommended Book Resources
  • Nam-Ho Kim, Dawn An, Joo-Ho Choi. (2016), Prognostics and Health Management of Engineering Systems, Springer Nature, Gewerbestrasse 11, 6330 Cham, Switzerland, [ISBN: 9783319447].
Supplementary Book Resources
  • Jihong Yan. (2015), Machinery Prognostics and Prognosis Oriented Maintenance Management, Wiley, p.375, [ISBN: 9781118638].
Supplementary Article/Paper Resources
  • Yaguo Lei, Naipeng Li, Liang Guo, Ningbo Li, Tao Yan, Jing Lin. (2017), Machinery health prognostics: A systematic review from data acquisition to RUL prediction, Mechanical Systems and Signal Processing, Vol 104, May 2018, p.799-8.
  • Abhinav Saxena, Kai Goebel, Don Simon. (2008), Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation, International Conference on Prognostics and Health Management, pages 1-9.
Other Resources
 
Module Delivered in
Programme Code Programme Semester Delivery
CR_EINMS_9 Postgraduate Certificate in Intelligent Manufacturing Systems 2 Mandatory