Condition Monitoring of a Nuclear Power Plant Check Valve Based on Acoustic Emission and a Neural Network

Lee, Min-Rae; Lee, Joon-Hyun; Kim, Jung-Teak

doi:10.1115/1.1991880

Cited by 19 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these experiments, different sizes of valves were tested in order to achieve the relationship between the leakage rate and the valve size. The leakage was generated by three ways: the artificial destruction of the valves [26], incomplete closure [27], or simulated leakage source [28].…”

Section: Methodsmentioning

confidence: 99%

“…Lee and Kim et al systematically studied the relations between AErms and failure modes such as disk wear and foreign object of check valves. In their study, an advanced condition monitoring technique based on AE detection and artificial neural networks was applied to the valve, which could successfully finish the evaluation of different types of failure modes [26,59,60]. The schematic diagram for condition monitoring test of the valve is shown in Figure 4.…”

Section: The Condition Monitoring Of Valvesmentioning

confidence: 99%

See 1 more Smart Citation

Nondestructive Detection of Valves Using Acoustic Emission Technique

Jin

Heng-hu

Hong

et al. 2015

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

The applications of acoustic emission (AE) technique in detection of valves are presented in this review, and the theoretical models and experimental results of nondestructive detection of valves using AE are provided. The generation of AE signals and the basic composition of AE detection system are briefly explained. The applications of AE technique in valves are focused on condition monitoring, failure, cavitation detection, and the development of portable measuring devices. All results prove that the AE technique works well in the detection of valves.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: The Condition Monitoring Of Valvesmentioning

confidence: 99%

Nondestructive Detection of Valves Using Acoustic Emission Technique

Jin

Heng-hu

Hong

et al. 2015

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…. , n}, and the mean of each decision tree {h(x, θ t )} is taken as the regression prediction value as equation (15):…”

Section: Extremely Randomized Trees(et)mentioning

confidence: 99%

“…In terms of internal leakage state recognition, Lee et al [15] conducted an experimental study on the internal leakage faults of nuclear power plant check valves using acoustic emission and neural network techniques, and could accurately distinguish between two internal leakage states of check valve grinding surface wear and external foreign body interference. Puttmer and Rajaraman [16] carried out a study of regulating valve leakage based on acoustic emission technique and found the relationship between the characteristic amount of acoustic emission signal of valve internal leakage and the magnitude of leakage.…”

Section: Introductionmentioning

confidence: 99%

Research on internal leakage detection of the ball valves based on stacking ensemble learning

Shi,

Deng,

Yang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Natural gas is an important clean energy source that is mainly transported through pipelines. The ball valve is a crucial piece of control equipment for the pipeline transportation system for natural gas, and the failure of internal leakage of the ball valve will seriously affect the natural gas transmission and increase the risk of sudden safety accidents. In response to the problems of the limitations of a single machine learning model in the traditional ball valve internal leakage rate prediction methods and failure to qualitatively analyze unilateral and bilateral internal leakage recognition of ball valve, a study of ball valve internal leakage detection based on Stacking ensemble learning is proposed. A total of 15 time and frequency domain feature parameters were obtained by feature extraction of 125 and 96 sets of raw acoustic emission signals from the ball valve; the parameters of a single machine learning model were adjusted by Bayesian optimization grid search. An internal leakage rate prediction model and an internal leakage recognition model are constructed, and the proposed model is compared and analyzed with a single model through a field ball valve internal leakage test. The results indicate that the Stacking ensemble learning model outperforms each single machine learning model in terms of SMAPE (17.2583), RMSE (1.1009), and MAE (0.9375) for internal leakage rate prediction. The Stacking ensemble learning model outperformed the single machine learning model in terms of accuracy (1.0000), recall (1.0000), precision (1.0000), FAR(0), and F1-score (1.0000) for internal leakage recognition. Stacking ensemble learning significantly enhances the model’s ability to detect internal ball valve leaks.

show abstract

“…opening and closing) and the detection of the wear or leakage in check valves [2,3]. Several research works studied the effects of AE parameters on valve and fluid variables such as pressure, types of gas and valve [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%