Crack fault diagnosis of rotating machine in nuclear power plant based on ensemble learning

Zhong, Xianping; Ban, Heng

doi:10.1016/j.anucene.2021.108909

Cited by 27 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The loads on a pipeline include weight, internal pressure, thermal expansion, thermal stratification and earthquakes, etc (Zhong and Ban, 2022a;Zhong and Ban, 2022b;Zhong et al, 2022). These loads produce axial forces and bending moments along the pipeline.…”

Section: Loading Strategymentioning

confidence: 99%

Role of welding residual stress in stainless steel piping with application of the leak-before-break technology

Liu

Zhang

Mao³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

The predicted leakage rate of piping circumferential through-wall cracks (CTWC) under various loading levels is a critical factor for the application of leak-before-break (LBB) technology. In current engineering approaches, the effect of welding residual stress has not been carefully taken into account. In this paper, both numerical analyses and comparative verification are adopted to examine the influence of typical welding residual stress field on the crack opening displacement for austenitic stainless steel piping with representative geometric dimensions and in situ measured material performance curves. An in-depth investigation is carried out to reveal the effect of the residual stress on morphological parameters of the CTWC flow channel. In the case where the residual internal stress of welding has the greatest effect, the Henry-Fauske model is employed to analyze the flow medium passing through the CTWC and the corresponding leak rate for a typical nuclear power plant. The results indicate that the welding residual stress leads to a substantial change in the crack opening displacement and crack morphology parameters. Both the current GE/EPRI method and the NUREG/CR-6837 modification recommended by the American Electric Power Research Institute underestimate the effect of this phenomenon, resulting in a higher prediction of the medium leakage rate. A similar situation is most likely to occur for the cases of short cracks in thin-walled piping and long cracks in thick-walled piping. Additionally, the obtained results reveal that the welding residual stress causes the whole crack surface to open negatively, and the axial line of the long crack on the thick-walled piping is close to a conic curve under specific conditions.

show abstract

Section: Loading Strategymentioning

confidence: 99%

Role of welding residual stress in stainless steel piping with application of the leak-before-break technology

Liu

Zhang

Mao³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…Statistical-feature-based detectors first extract statistical features from time-domain signals or frequency-domain signals, such as the maximum value of amplitude, mean value of amplitude, and Kurtosis factor. These features are then used to detect the fault type [1][2][3][4][5][6][7]. However, the efficiency of statistical features may vary based on datasets and detection models, and it requires manual feature extraction for each specific case.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Feature-Construction-Based Motor Fault Diagnosis

Amarbayasgalan,

Ryu

2024

Sensors

View full text Add to dashboard Cite

Any bearing faults are a leading cause of motor damage and bring economic losses. Fast and accurate identification of bearing faults is valuable for preventing damaging the whole equipment and continuously running industrial processes without interruption. Vibration signals from a running motor can be utilized to diagnose a bearing health condition. This study proposes a detection method for bearing faults based on two types of neural networks from motor vibration data. The proposed method uses an autoencoder neural network for constructing a new motor vibration feature and a feed-forward neural network for the final detection. The constructed signal feature enhances the prediction performance by focusing more on a fault type that is difficult to detect. We conducted experiments on the CWRU bearing datasets. The experimental study shows that the proposed method improves the performance of the feed-forward neural network and outperforms the other machine learning algorithms.

show abstract

“…For nuclear technology, artificial intelligence methods are mainly used in equipment fault diagnosis and have achieved good results (Zhong and Ban, 2022a;Zhong and Ban, 2022b;Zhong et al, 2022). However, few studies have been performed on artificial intelligence (AI)-based reverse reconstruction methods.…”

Section: Introductionmentioning

confidence: 99%

Validation of the neural network for 3D photon radiation field reconstruction under various source distributions

Hao

Yanheng

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Introduction: This paper proposes a five-layer fully connected neural network for predicting radiation parameters in a radiation space based on detector readings.Methods: The network is trained and tested using gamma flux values from individual detector positions as input, and is used to predict the gamma radiation field in 3D space under different source term distributions. The method is evaluated using the mean percentage change error (PCT) for the test set under different source term distributions.Results: The results show that the neural network method can accurately predict radiation parameters with an average PCT error range of 0.53% to 3.11%, within the given measurement input error range of ± 10%. The method also demonstrates its ability to directly reconstruct the 3D radiation field with some simple source terms.Discussion: The proposed method has practical value in real operations within radiation spaces, and can be used to improve the accuracy and efficiency of predicting radiation parameters. Further research could explore the use of more complex source term distributions and the integration of other types of sensors for improved accuracy.

show abstract

Crack fault diagnosis of rotating machine in nuclear power plant based on ensemble learning

Cited by 27 publications

References 13 publications

Role of welding residual stress in stainless steel piping with application of the leak-before-break technology

Role of welding residual stress in stainless steel piping with application of the leak-before-break technology

Unsupervised Feature-Construction-Based Motor Fault Diagnosis

Validation of the neural network for 3D photon radiation field reconstruction under various source distributions

Contact Info

Product

Resources

About