Monoblock centrifugal pumps play an important role in a variety of engineering applications such as in the food industry, in wastewater treatment plants, in agriculture, in the oil and gas industry, in the paper and pulp industry, and others. Condition monitoring of the various mechanical components of centrifugal pumps becomes essential for increasing productivity and reducing the number of breakdowns. Vibration-based continuous monitoring and analysis using machine learning approaches are gaining momentum. Particularly, artificial neural networks and fuzzy logic have been employed for continuous monitoring and fault diagnosis. This article presents the use of the J48 algorithm for fault diagnosis through discrete wavelet features extracted from vibration signals of good and faulty conditions of the components of a centrifugal pump. The classification accuracies of different discrete wavelet families were calculated and compared in order to find the best wavelet for the fault diagnosis of the centrifugal pump. © 2013 Copyright Taylor and Francis Group, LLC.