Condition Monitoring and Diagnostic Technologies

Instructor information

  • Name: Roozbeh Razavi-Far 

  • Office: CEI 2134

  • Office Hours: Fridays from 14:30 until 16:00

 

Class and lab information

  • Location: University of Windsor, CEI, Room 1102

  • Time: Mondays from 7:00 PM - 9:50 PM  

Course Description:

There have been an increasing interest in condition monitoring, diagnostic and prognostic systems in recent years, as a result of the increased degree of automation and the growing demand for higher performance, efficiency, reliability and safety in mechanical systems and industrial equipment. To maintain a high level of performance and reliability in these systems, errors, component faults and abnormal system operation must be detected quickly. The source and severity of each fault must be diagnosed so that corrective action can be taken promptly. Faults in process equipment can result in off-specification production, increased operating costs, the chance of line shutdown and the possibility of detrimental environmental impact. Therefore, proper condition monitoring, early detection and diagnosis of process malfunctions are strategically essential to enhance system availability, safety, reduce maintenance costs, catch potentially catastrophic failures and reduce system downtime.

The aim of the course is to provide students with the methodological competences and the computational tools necessary to tackle critical problems in the areas of condition monitoring, diagnostics, prognostics and health management of machine, mechanical systems and industrial equipment. To this purpose, the course presents proven methods to improve safety, increase efficiency, manage equipment ageing and obsolescence and reduce maintenance costs of mechanical systems and industrial equipment. In this course, various computational techniques at the intersection of signal processing, computational intelligence, and machine learning for condition monitoring, fault diagnosis and prognosis will be introduced and considerable efforts will also be given on their implementation, strengths and weaknesses for different applications in mechanical systems, machine, rotating machinery: gearbox and bearings, power generation and wind turbines, mechatronic devices, electric motors and drives.

Required Resources:

[1] Course BLACKBOARD site: By registering in this course, you will automatically gain access to the course BLACKBOARD site.  BLACKBORAD.uwindsor.ca

Primary Text:

[2] Lecture slides provided by the instructor

The following books are strongly recommended:

           [3] Intelligent Fault Diagnosis and Prognosis for Engineering Systems, by Vachtsevanos

           [4] Vibration-based Condition Monitoring: Industrial, Aerospace and Automotive Applications, by Randall

           [5] Fault-Diagnosis Systems: An introduction from fault detection to fault tolerance, by Isermann

           [6] The Elements of Statistical Learning, by Hastie, Tibshirani and Friedman

Course Schedule

The following course schedule is approximate. 

  • Week 01:

    • Teaching subjects: introduction to condition monitoring, fault diagnosis, prognosis and health management.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 02:

    • Teaching subjects: condition monitoring, destructive/non-destructive tests.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 03:

    •  Teaching subjects: fault detection and diagnosis.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 04:

    • Teaching subjects: fault prognosis and prediction.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 05:

    • Teaching subjects: related technologies, computational intelligence, machine learning, statistical learning, signal processing, control theory.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 06:

    • Teaching subjects: related technologies, computational intelligence, machine learning, statistical learning, signal processing, control theory.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 07: Study week

  • Week 08:

    • Teaching subjects: detection and diagnosis goals, steps of fault diagnosis, detection techniques, diagnosis techniques, prognostic techniques, CBM, RUL, Fleetwide CBM/PHM.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 09:

    • Teaching subjects: practical exercises: mechanical systems, machine condition monitoring, mechatronic devices, electric motors and drives, rotating machinery: gearbox and bearings, power generation and wind condition monitoring.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 10:

    • Teaching subjects: signal processing techniques, measuring and analyzing condition monitoring signals, vibration analysis and diagnostics, time domain, frequency domain, time-frequency domain.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 11:

    • Teaching subjects: data-driven techniques, data acquisition, data cleaning, data processing, multivariate data analysis, unsupervised techniques.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 12:

    • Teaching subjects: fault classification, prediction.

    • Textbook Chapter or Readings: Lectures notes and slides

  • Week 13:

    • Teaching subjects: dynamic environments.

    • Textbook Chapter or Readings: Lectures notes and slides

There will be a course project which involves developing a monitoring and diagnostic tool for given case studies. The students can choose their own specific case studies and methodologies which need the instructor’s approval.    

The students can work in groups of two or three (no more than three). The projects will have to be demonstrated during the semester (you must check the upcoming schedule).

 

Evaluation Methods

The course grade will be evaluated as follows:

  • Participation: 5%

  • Class presentation: 5%

  • Course project (group): 35%

  • Final report: 25%

  • Exam: 30%

Teaching Assistants:

  • TBD

CONTACT ME

Roozbeh Razavi-Far

PH.D., Lecturer, academic adviser,

Coordinator of Master of Engineering Programs

Faculty of Engineering, University of Windsor

 

 

 

Email:

roozbeh@uwindsor.ca

 

  • Black LinkedIn Icon