This paper investigates the use of advance signal processing techniques for the classification of four common reciprocating compressor conditions. Non-stationary vibration signals from the compressor are decomposed based on two emerging techniques: WPT (Wavelet Packet Transform) and EMD (Empirical Mode Decomposition) and harmonic changes of the optimal components of each technique are used for condition monitoring and diagnostics of the machine. Performance comparison of WPT and EMD is done for the envelope analysis of the optimal wavelet packet and the IMF (Intrinsic Mode Function) component that can extract salient features of the four compressor conditions including one normal and three fault conditions (intercooler leakage, discharge valve leakage and the combination of intercooler and discharge valve leakage). Harmonic changes produced after envelope analysis of the best packet and IMF component are used for classification and results show that WPT technique is more robust and effective in fault classification compared to EMD.
|Title of host publication
|Proceedings of the 23rd International Conference on Automation & Computing, (University of Huddersfield, 7-8 September 2017)
|Institute of Electrical and Electronics Engineers Inc.
|Number of pages
|Published - 26 Oct 2017
|23rd International Conference on Automation and Computing: Addressing Global Challenges through Automation and Computing - University of Huddersfield, Huddersfield, United Kingdom
Duration: 7 Sep 2017 → 8 Sep 2017
Conference number: 23
https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=41042 (Link to Conference Website)
|23rd International Conference on Automation and Computing
|7/09/17 → 8/09/17
|The scope of the conference covers a broad spectrum of areas with multi-disciplinary interests in the fields of automation, control engineering, computing and information systems, ranging from fundamental research to real-world applications.