My rotating machine fault detection research
I've created this page as a way to share PDF copies of my published rotating machine fault detection research papers that from my understanding fits within their publication licenses. It's pretty cool that Elsevier lets you share your papers published with them on your personal blogs. I guess I should talk a little bit about myself in case anyone is interested. I took Electrical Engineering with a BSc at the University of Calgary Canada, then pursued a MSc in Electrical Engineering under Dr. Qing Zhao at the Advanced Control Systems laboratory at the University of Alberta, Canada. During my research I became fascinated with deconvolution techniques to extract faults from the vibration, and was really inspired by Hiro Endo's application of Minimum Entropy Deconvolution (MED). I graduated in 2011, but have had some hobby interest in the field since on the occasional weekend/weeknight.

This fascination with MED led me to begin experimenting with different filter design optimization cost functions that were better-designed for rotating machine faults. If anyone else is exploring new deconvolution techniques - I recommend using the non-linear optimization Matlab toolkit to solve any cost functions you come up with iteratively. Using this method, you can try out any cost function you can dream up without solving any of the math. Save the math until you have good results here first. Anyways, this led to the papers below for Maximum Correlated Kurtosis Deconvolution (MCKD) and Multipoint Optimal Minimum Entropy Deconvolution (MOMEDA), as well as the convolution region fix for MED (MEDA). Generally, I feel the deconvolution methods make more sense than most other vibration fault detection methods. For example, with the Wavelet Transform then selecting a band that has maximum Kurtosis can be thought of generally as just applying a bandpass filter - it is taking a frequency range of the signal and discarding the rest of the information + spectrum. A lot of information is lost here.

Although the deconvolution techniques have come a long way in rotating machine fault detection, there is a lot more work to be done and discovered. Here are a few brainstorming bullets for inspiration:
  • The deconvolution methods solve for the inverse filter yielding the fault impulses. What does this filter describe? Can you solve for the original fault path system?
  • How does MOMEDA normalized MKurt change as a fault progresses?
  • MOMEDA is better than MED and MCKD. Focus on this instead I think.
  • Multiple accelerometers mounted on the same machine grading the same fault? I can't think how, and maybe that's fine.
  • Can you separate the fault period from multiples of the fault period?
  • With MOMEDA you seem to be able to accurately track the rotational speed of elements in a machine from just the acceleration. Is this valuable to any applications?
  • Maybe you can pose deconvolution problems with different MOMEDA target goals, such as goals based on fault dynamics associated with rotor imbalance?
  • Fault detection on a machine with changing speeds should be possible MOMEDA, something like a pathfinding approach for the impulses for this?
  • A description of the MOMEDA spectrum peaks and amplitudes as a feature set for machine learning classification?
  • Bearing fault detections? Inner outer race failures should work, right?

As I was getting close to graduating from my MSc, I happened to come across a job position where I was lucky enough to turn a hobby passion of mine (reverse-engineering/computer hacking/security/vulnerabilities) into a career. I worked for Symantec for a couple years fighting and researching targeted attacks, and now work as an Anti-Virus Researcher for Microsoft working on Windows Defender. I've been here since 2013, and work a lot in machine learning to fight and detect malware. I work on developing hobby reverse-engineering tools and hobby vulnerability fuzzing tools in this field on the side as well.

Feel free to reach out to me or even to meet up if you are ever passing through Vancouver Canada and up for catching me up on latest in fault detection,

Geoff McDonald, glmcdona@gmail.com
Linked In
https://github.com/glmcdona
Multipoint Optimal Minimum Entropy Deconvolution and Convolution Fix: Application to Vibration Fault Detection
McDonald, Geoff L., and Qing Zhao. "Multipoint Optimal Minimum Entropy Deconvolution and Convolution Fix: Application to vibration fault detection." Mechanical Systems and Signal Processing 82 (2017): 461-477.
Download as PDF (accepted manuscript version)
MATLAB Code
Elsevier Official Published Version Link

I've got a few thoughts on this in retrospect after publishing this paper. I still think this is the best deconvolution problem for our problem rotating machine fault extraction - MCKD and MED aren't as good IMO. It solves directly for the solution (no iteration), and uses an infinite impulse train as the goal. What I figured out afterwards is that I derived a known equation from a different angle, look here at page 441 for more context on what the MOMEDA solution is:
Least squares and psuedo inverses
Maximum correlated Kurtosis deconvolution and application on gear tooth chip fault detection
McDonald, Geoff L., Qing Zhao, and Ming J. Zuo. "Maximum correlated Kurtosis deconvolution and application on gear tooth chip fault detection." Mechanical Systems and Signal Processing 33 (2012): 237-255.
Download as PDF (accepted manuscript version)
MATLAB Code
Elsevier Official Published Version Link
Model-based adaptive frequency estimator for gear crack fault detection
McDonald, Geoff, and Qing Zhao. "Model-based adaptive frequency estimator for gear crack fault detection." American Control Conference (ACC), 2011. IEEE, 2011.
Download as PDF

I was never a huge fan of this research direction for rotating machine fault detection. I think it's neat, but I don't think it will be superior or will meet other approaches. Gang Li has done some cool research down this line afterwards.
Thesis: Vibration Signal-Based Fault Detection for Rotating Machines
McDonald, Geoffrey Lyall. Vibration Signal-Based Fault Detection for Rotating Machines. Diss. University of Alberta, 2011.
Download as PDF University Page

This main content of the thesis is the MCKD and adaptive sinusoidal modelling content. There is an extra chapter on applying the data to long-term monitoring of industrial steam turbines.