Artificial Neural Network Model for Fault Diagnosis of Rotating Machine in ETRR-2 Research Reactor | ||
| Arab Journal of Nuclear Sciences and Applications | ||
| Article 7, Volume 55, Issue 3, July 2022, Pages 55-61 PDF (741.56 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/ajnsa.2022.106437.1526 | ||
| Authors | ||
| Said Shaban Haggag1; Ahmed Ramadan Adly* 2; Magdy Mahmoud Zaky3 | ||
| 1Atomic Energy Authority of Egypt, Reactors Department | ||
| 2ETTR-2, EAEA | ||
| 3ETRR-2, EAEA, Egypt | ||
| Abstract | ||
| This article characterizes vibration signals using Artificial Neural Network (ANN) method to develop an effective and reliable feature sets for detecting and diagnosing faults in a centrifugal pump (ETRR-2 research reactor core coolant pumps). In this paper, a modular ANN are used for modeling the ETRR-2 research reactor core coolant pumps vibration monitoring. The input and the output signals of the vibration transducer are used as input source data for the ANN model. The amplitudes and frequency domain are inputted to the ANN separately from the vibration data. It is noted that the features statistical have good results based on frequency and amplitudes domains. The ANNs are used to detect the misalignment, unbalance severity, looseness bearing, and anti-fraction. The results are very useful for maintenance making decision. This methodology can be used for the research reactor coolant pumps. Hence, it may turn out to be a powerful tool for early detection of pump fault. | ||
| Keywords | ||
| Neural Network; vibration analysis; Misalignment; Anti-fraction bearing | ||
|
Statistics Article View: 1,257 PDF Download: 498 |
||
