HUMS2023 Data Challenge
Result Submission
Team Name: DSRS
Team Members: Dr Rick Morgans, Dr Mike Kidner, Alexandra Begg
Institutions: Dedicated Systems Pty Ltd, Resonate Systems Pty Ltd
Publishable: Yes
1. Summary of Findings
A fault metric based on the variance of a modified squared-kurtosis (nd
6
) of the vibration signal
corresponding to a planetary gear tooth has been developed. It is shown that the aggregate of this metric
across all 4 channels shows a strong indication of fault emergence.
A definite shift in the fault metric can be seen from file 50 onwards, although an exponential trend is only
evident from file 400.
A parallel method based on a subspace distance between the singular spectra of the signal (called Mutual
Singular Spectrum Analysis) was also investigated and results reported in an addendum. A deviation from
baseline MSSA derived metric shows broad agreement with the nd
6
metric with consistent detection after
file 180, although the derived fault metric was quite intermittent. An inter tooth comparison method
using MSSA shows some promise although a convincing fault metric could not be derived.
Table 1 Summary of Analysis Results
Consistent detection on at least one signal
channel; i.e. the fault indicators remain
consistently above the threshold.
Deviation of the variance of
toothwise kurtosis from
baseline across all signals.
Confirmed detection on at least two signal
channels; i.e. the fault indicators remain
consistently above the threshold.
Clear multi-channel indication of the
characteristic fault features; i.e. faulty planet gear
meshing with both the ring and sun gears.
Confirmed trend of fault progression; i.e. a
consistent increasing trend started from which file
number/name.
Confirmed trend of accelerated fault progression;
i.e. a consistent exponential increasing trend
started from which file number/name
