Machine fault detection during transient operation using measurement denoising

Zhang, Yu, Bingham, Chris, Gallimore, Michael , Yang, Zhijing and Chen, Jun (2013) Machine fault detection during transient operation using measurement denoising. In: IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), 15-17 July 2013, Milan, Italy.

Full content URL:

[img] PDF
Restricted to Repository staff only

Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive


The paper reports and demonstrates a computationally efficient method for machine fault detection in industrial turbine systems. Empirical mode decomposition (EMD) and Savitzky–Golay smoothing filters are used for signal denoising, with a resulting noise index being developed. By comparing the noise index with a power index (also derived in the paper), obtained from the detection of transients using a spectral analysis of the rate-of-change of unit power, three operational conditions are identifiable viz. normal operation, transient operation and operation when subject to emerging machine faults. The accommodation of transient operational conditions of the unit, so as not to create excessive ‘false alerts’, provides a valuable alternative to more traditional techniques, based on PCA for instance, that can only provide reliable information during steady-state operation. The efficacy of the proposed approaches is demonstrated through the use of experimental trials on sub-15MW gas turbines.

Keywords:machine fault detection, empirical mode decomposition, spectrogram, spectral energy, Savitzky–Golay smoothing filter
Subjects:G Mathematical and Computer Sciences > G160 Engineering/Industrial Mathematics
Divisions:College of Science > School of Engineering
Related URLs:
ID Code:12552
Deposited On:20 Nov 2013 11:29

Repository Staff Only: item control page