Answers are grounded in this paper and cite their sources.
Investigates valve leakage detection in liquid-filled pipelines, suggesting kernel PCA enhances signal processing.
To detect internal valve leakage in liquid‐filled pipelines, a method using kernel principal component analysis (KPCA) is proposed to analyze acoustic emission (AE) signals for leakage detection. Time‐frequency analysis and root mean square (RMS) values of AE signals across various frequency bands reveal that the dominant frequency band for valve leakage signals consistently falls within 160–180 kHz across the tested pressure and leakage rate ranges. Using these findings, key feature parameters were selected and subjected to dimensionality reduction via principal component analysis (PCA). A kernel function was integrated to enhance the efficacy of feature extraction for leakage detection. The results show that KPCA effectively distinguishes background noise from leakage signals when appropriate feature parameters are selected. The integration of the kernel function increased the explained variance ratio of the first principal component from 77.84% to 88.75% compared to conventional PCA. Evaluation of multiple metrics confirms that the KPCA method with a sigmoid kernel achieves optimal performance in processing AE signal feature parameters.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: