A Comparative study between Support Vector Machine (SVM) and Extreme Learning Machine (ELM) for Fault Detection in Pumps
Background/Objectives: To apply Support Vector Machine and Extreme Learning Machine for fault diagnosis of centrifugal pump and to compare them with respect to classification accuracy and learning time. The overall best one is reported.
Methods/Statistical Analysis: The vibration signals are extracted from the experimental setup. Then signals are then filtered and trimmed for ease of processing. The wavelet features are extracted in its discrete form thus it forms the feature set. The set of features are then fed as an input and classified using Extreme Learning Machine and Support Vector Machine. These two algorithms are state of the art techniques for classification of different conditions of the setup. The results are compared with respect to classification accuracy and learning rate. Finally, it is concluded that the ELM could achieve 99.2% classification accuracy at a very faster rate than SVM.
Application/Improvements: Extreme Learning Machine has been used for the first time for fault diagnosis applications. Discrete wavelet transform features in combination with ELM have been attempted for the first time. To conclude, ELM could act as a better alternate for machine learning approach.
- Jeng JJ, Wei CY. An on-line condition monitoring and diagnosis system for feed rolls in the plate mill. Journal of Manufacturing Science and Engineering. 2002 Feb 1;124(1):52–7.
- Changfeng YA, Zhang H, Lixiao WU, A novel real-time fault diagnostic system for steam turbine generator set by using strata hierarchical artificial neural network. Energy and Power Engineering. 2009 Aug 18;1(01):1–7.
- DePold HR, Gass FD, The application of expert systems and neural networks to gas turbine prognostics and diagnostics. InASME International Gas Turbine and Aeroengine Congress and Exhibition 1998 American Society of Mechanical Engineers.1998.p. 5–9.
- Xue W, Shuzi Y. A parallel distributed knowledge-based system for turbine generator fault diagnosis. Artificial Intelligence in Engineering. 1996 Nov 30;10(4):335–41.
- Todd M, McArthur SD, McDonald JR, Shaw SJ, A semiautomatic approach to deriving turbine generator diagnostic knowledge. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on Systems. 2007 Sep;37(5): 979–92.
- Sugumaran V, Muralidharan V, Ramachandran KI. Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing. Mechanical systems and signal processing. 2007 Feb 28;21(2):930–42.
- Huang GB, Siew CK, Extreme learning machine with randomly assigned RBF kernels. International Journal of Information Technology. 2005;11(1):16–24.
- Jiang L, Liu Y, Li X, Tang S. Using bispectral distribution as a feature for rotating machinery fault diagnosis. Measurement. 2011 Aug 31;44(7):1284–92.
- Kubrusly CS, Levan N, Orthogonal decompositions for wavelets. Applied Mathematics Letters. 2009 Aug 31;22(8):1286–91.
- Le TH, Tamura Y, Matsumoto M. Spanwise pressure coherence on prisms using wavelet transform and spectral proper orthogonal decomposition based tools. Journal of Wind Engineering and Industrial Aerodynamics. 2011 Apr 30; 99(4): 99–508.
- Lhermitte S, Verbesselt J, Verstraeten WW, Coppin P. A comparison of time series similarity measures for classification and change detection of ecosystem dynamics. Remote Sensing of Environment. 2011 Dec 15;115(12):3129–52.
- Liu L, McLernon D, Ghogho M, Hu W, Huang J. Ballistic missile detection via micro-Doppler frequency estimation from radar return. Digital Signal Processing. 2012 Jan 31;22(1):87–95.
- Article title:?Matlab 7.0.0, MATLAB Company, 2011.
- Nejad FM, Zakeri H. An expert system based on wavelet transform and radon neural network for pavement distress classification. Expert Systems with Applications. 2011 Jun 30;38(6):7088–70101.
- Nelson DE, Starzyk JA, Ensley DD, Iterated wavelet transformation and signal discrimination for HRR radar target recognition. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans.. 2003 Jan;33(1);52–7.
- Tabib MV, Sathe MJ, Deshpande SS, Joshi JB. A hybridized snapshot proper orthogonal decomposition-discrete wavelet transform technique for the analysis of flow structures and their time evolution. Chemical Engineering Science. 2009 Nov 1;64(21):4319–340.
- Tang X, Sun T, Tang Z, Zhou Z, Wei B, Geological disaster survey based on Curvelet transform with borehole Ground Penetrating Radar in Tonglushan old mine site. Journal of Environmental Sciences. 2011 Jun 30;23(4):S78–83.
- Wang Y, Cao F, Yuan Y. A study on effectiveness of extreme learning machine. Neurocomputing. 2011 Sep 30;74(16):2483–90.
- Wink AM, Roerdink JB. Polyphase decompositions and shift-invariant discrete wavelet transforms in the frequency domain. Signal Processing. 2010 Jun 30;90(6):1779–87.
- Muralidharan V, Sugumaran V. Feature extraction using wavelets and classification through decision tree algorithm for fault diagnosis of mono-block centrifugal pump. Measurement. 2013 Jan 31;46(1):353–59.
- Muralidharan V, Sugumaran V. Rough set based rule learning and fuzzy classification of wavelet features for fault diagnosis of monoblock centrifugal pump. Measurement. 2013 Nov 30;46(9):3057–63.
- Muralidharan V, Sugumaran V, Sakthivel NR. Fault Diagnosis of Monoblock Centrifugal Pump Using Stationary Wavelet Features and Bayes Algorithm. Asian Journal of Science and Applied Technology. 2014;3(2):1–4.
- Muralidharan V, Sugumaran V, Indira V. Fault diagnosis of monoblock centrifugal pump using SVM. Engineering Science and Technology, an International Journal. 2014 Sep 30;17(3):152–7.
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.