Implementation of Acoustic Emission technique in early detection of control valve seat leakage

Shukri, Intan Najiha binti Mohd; Rosdiazli, bin Ibrahim

doi:10.1109/sta.2014.7086680

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, L yy is called the sum of off-mean-squared deviations of y, referred to as the y-difference sum, and is calculated as equation (19):…”

Section: Extremely Randomized Trees(et)mentioning

confidence: 99%

“…Meland et al [18] conducted a joint time-frequency domain analysis of the signal using a valve with a broken seal failure as the study object. Shukri [19] built an acoustic emission detection bench for control valve seat leakage was carried out and the relationship between valve leakage rate and acoustic emission signal peak, standard deviation, and variance was analyzed, and the results of the study showed that acoustic emission is available for valve seat leakage detection. Li et al [20] proposed a leak recognition method with kernel principal component analysis and support vector machine (SVM) classifier for the ball valve leakage problem of natural gas, and the accuracy of their classification model could reach 96.5%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

“…Similarly, L yy is called the sum of off-mean-squared deviations of y, referred to as the y-difference sum, and is calculated as equation (19):…”

Section: Extremely Randomized Trees(et)mentioning

confidence: 99%