Year-end Sale % OFF 
Abstract
This paper proposes a reliable fault diagnosis model for a spherical storage tank. The proposed method first used a blind source separation (BSS) technique to de-noise the input signals so that the signals acquired from a spherical tank under two types of conditions (i.e., normal and crack conditions) were easily distinguishable. BSS split the signals into different sources that provided information about the noise and useful components of the signals. Therefore, an unimpaired signal could be restored from the useful components. From the de-noised signals, wavelet-based fault features, i.e., the relative energy (REWPN) and entropy (EWPN) of a wavelet packet node, were extracted. Finally, these features were used to train one-against-all multiclass support vector machines (OAA MCSVMs), which classified the instances of normal and faulty states of the tank. The efficiency of the proposed fault diagnosis model was examined by visualizing the de-noised signals obtained from the BSS method and its classification performance. The proposed fault diagnostic model was also compared to existing techniques. Experimental results showed that the proposed method outperformed conventional techniques, yielding average classification accuracies of 97.25% and 98.48% for the two datasets used in this study.
Highlights
Spherical storage tanks contain fluids, such as liquids and compressed gases, and are widely used in different industries [1,2]
The proposed method indications in a storage tank is illustrated in Figure 3, WSα) for detecting faultResonant frequency: 650 kHz which consists of the following fundamental steps
This paper proposed a new approach to effectively discriminate between two different types of signals taken from a spherical tank based on a blind source separation (BSS) technique
Summary
Spherical storage tanks contain fluids, such as liquids and compressed gases, and are widely used in different industries (e.g., the petrochemical, chemical, and aerospace industries) [1,2]. Bayesian inference to find the optimal wavelet transform In addition to these methods, which try to find an optimal filtering band in order to extract short-time transient properties from the signal, there is another acclaimed approach which extracts features from wavelet coefficients of the wavelet packet transform (WPT). Such features were proved to be sensitive to fault occurrence and robust to different operating conditions. To validate the performance of the developed diagnosis model for the storage tank, we sampled the acquired AE signals at 1 MHz to capture very detailed information related to the storage tank condition Two-channel AE PCI board (5 M samples/s as two channels are used simultaneously)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
