No abstract

Abstract-This paper characterises vibration signals using modulation signal bispectrum method in order to develop an effective and reliable feature sets for detecting and diagnosing faults from both the bearings and impellers in a centrifugal pump. As vibration signals contain high level background noises due to inevitable flow cavitation and turbulences, effective noise reduction and reliable feature extraction are critical procedures in vibration signal analysis. Considering the modulation effect between rotating shaft and vane passing components, a modulation signal bispectrum (MSB) method is employed to extract these deterministic characteristics of modulating components in a low frequency band for diagnosing both the bearing defects and impeller blockages. Experimental results show that the diagnostic features developed by MSB allow impellers with inlet vane damages and bearing outer-race faults to be identified under different operating conditions. Not only does this new method produces reliable diagnostic results but also it needs a bandwidth about 1000Hz, rather than the high frequency bands around 10kHz used by conventional envelope analysis.

Abstract-Centrifugal pumps are widely used in various manufacturing processes, such as power plants, and chemistry. However, pump problems are responsible for large amount of the maintenance budget. An early detection of such problems would provide timely information to take appropriate preventive actions. This paper investigates the application of Machine Learning Techniques (MLT) in monitoring and diagnosing fault in centrifugal pump. In particular, the focus is on utilising motor current signals since they can be measured remotely for easy and low-cost deployment. Moreover, because the signals are usually produced by a nonlinear process and contaminated by various noises, it is difficult to obtain accurate diagnostic features with conventional signal processing methods such as Fourier spectrum and wavelet transforms as they rely heavily on standard basis functions and often capture limited nonlinear weak fault signatures. Therefore, a datadriven method: Intrinsic Time-scale Decomposition (ITD) is adopted in this study to process motor current signals from different pump fault cases. The results indicate that the proposed ITD technique is an effective method for extracting useful diagnostic information, leading to accurate diagnosis by combining the RMS values of the first Proper Rotation Component (PRC) with the raw signal RMS values.

No abstract

No abstract