Nonlinear Blind Source Separation of Multi-Sensor signals for Marine Diesel Engine Fault Diagnosis

Marine diesel engines are the heart of the ships. They provide the power for the normal propulsion of the vessels. Any unexpected failures occurred in the marine diesel engines may lead to terrible accident. It is therefore imperative to monitor the marine diesel engines to prevent impending faults. In the present work, a new defect detection method for the marine diesel engines using the artificial intelligence has been proposed. The vibration signals of the marine diesel engine were recorded by the multi-channel sensors. The nonlinear independent component analysis (NICA) was adopted as the data fusion approach to find the characteristic vibration signals of the marine diesel engine fault from the multiply sensor collections. Then the Empirical Mode Decomposition (EMD) was employed to extract the feature vector of the fused vibration signals. Lastly, the Genetic Algorithm-Chaos and RBF neural network was used to recognize the fault patterns of the marine diesel engine. The experimental tests were implemented in a real ship to evaluate the effectiveness of the proposed diagnosis approach. The diagnosis results have showed that distinguished fault features have been extracted and the fault identification accuracy is satisfactory. In addition, the classification rate of the proposed method is superior to the traditional linear ICA based methods. Streszczenie. Wykorzystano nieliniową niezalezną analize skladnikow NICA do diagnostyki wibracji silnika Diesla. Zastosowano metode empirycznej dekompozycji EMD do separacji sygnalow. Nastepnie wykorzystano sieci neuronowe i algorytm genetyczny do identyfikacji uszkodzen. (Wykorzystanie nieliniowej ślepej separacja sygnalow wielu czujnikow do diagnostyki silnika Diesla w napedach okretowych)

[1]  Xinping Yan,et al.  A New Intelligent Fusion Method of Multi-Dimensional Sensors and Its Application to Tribo-System Fault Diagnosis of Marine Diesel Engines , 2012, Tribology Letters.

[2]  M. Cheng,et al.  GENETIC ALGORITHM-BASED CHAOS CLUSTERING APPROACH FOR NONLINEAR OPTIMIZATION , 2010 .

[3]  Gustavo Deco,et al.  Nonlinear higher-order statistical decorrelation by volume-conserving neural architectures , 1995, Neural Networks.

[4]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[5]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[6]  P. McFadden.  Examination of a technique for the early detection of failure in gears by signal processing of the time domain average of the meshing vibration , 1987 .

[7]  Pierre Comon,et al.  Blind separation of sources, part II: Problems statement , 1991, Signal Process..

[8]  Esfandiar Sorouchyari,et al.  Blind separation of sources, part III: Stability analysis , 1991, Signal Process..

[9]  Yang Jiangxin.  A new fault diagnosis method for a rotor of a steam turbine generator set based on instantaneous energy distribution characteristics , 2009 .

[10]  Yan Xinping.  Independent Component Analysis and Manifold Learning with Applications to Fault Diagnosis of VSC-HVDC Systems , 2011 .

[11]  Jacek M. Zurada,et al.  Nonlinear Blind Source Separation Using a Radial Basis Function Network , 2001 .

[12]  Gilles Burel,et al.  Blind separation of sources: A nonlinear neural algorithm , 1992, Neural Networks.

[13]  Christian Jutten,et al.  Source separation in post nonlinear mixtures: an entropy-based algorithm , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[14]  Li Li,et al.  Virtual prototype and experimental research on gear multi-fault diagnosis using wavelet-autoregressive model and principal component analysis method , 2011 .

[15]  Georgios B. Giannakis,et al.  New Results On State-Space And Input-Output Identification Of Non-Gaussian Processes Using Cumulants , 1988, Optics & Photonics.

[16]  Wojciech Grega.  Information Technologies Supporting Control and Monitoring of Power Systems , 2012 .

[17]  A. Hyvärinen,et al.  Nonlinear Blind Source Separation by Self-Organizing Maps , 1996 .