Impeller fault detection under variable flow conditions based on three feature extraction methods and artificial neural networks

Jami, AminHeyns, P.S. (Philippus Stephanus)2018-10-092018-09Jami, A. & Heyns, P.S. Impeller fault detection under variable flow conditions based on three feature extraction methods and artificial neural networks. Journal of Mechanical Science and Technology (2018) 32: 4079-4087. https://doi.org/10.1007/s12206-018-0807-3.1738-494X (print)1976-3824 (online)10.1007/s12206-018-0807-3http://hdl.handle.net/2263/66791Nonstationary flow conditions can introduce complexities and nonlinear characteristics to pumping systems. This paper presents comparative studies of impeller fault detection techniques combined with artificial neural networks (ANNs) to propose the most appropriate diagnosis system. An experimental study, including seven impeller conditions, is performed to further explore the phenomena. Statistical parameters, frequency peaks, and wavelet packet energy present data feature sets, and a three-layer back-propagation ANN is used for fault recognition. The verification of the results proves that the detectability of the wavelet packet transform (WPT)-ANN model is considerably improved by using the energy of the decomposed vibration from WPT. This model can save computational time and provide superior diagnostic information. This study provides two key contributions. First, the feasibility and effectiveness of common monitoring techniques are compared. Second, the results demonstrate the accuracy of the proposed models for impellers operating under variable working conditions, which has not been previously addressed in the literature.en© The Korean Society of Mechanical Engineers and Springer-Verlag GmbH Germany, part of Springer Nature 2018. The original publication is available at : http://link.springer.comjournal/12206.Artificial neural network (ANN)Wavelet packet transform (WPT)Time domain analysis (TDA)Centrifugal pumpsImpeller faultsNonstationary flow conditionsVibration signal processingCondition-based maintenance (CBM)Fault detectionVibration signalNonlinear characteristicsBackpropagationFeature extractionWavelet analysisNeural networksImpellersEngineering, built environment and information technology articles SDG-09SDG-09: Industry, innovation and infrastructureEngineering, built environment and information technology articles SDG-12SDG-12: Responsible consumption and productionImpeller fault detection under variable flow conditions based on three feature extraction methods and artificial neural networksPostprint Article