An acoustic signal cavitation detection framework based on XGBoost with adaptive selection feature engineering

TL;DR

This paper introduces a novel cavitation detection framework using XGBoost with adaptive feature engineering, addressing small-sample issues and achieving state-of-the-art accuracy in classifying valve acoustic signals.

Contribution

The paper proposes an innovative framework combining data augmentation, FFT-based feature extraction, and adaptive feature selection to improve cavitation detection accuracy.

Findings

Achieved 4.67% higher accuracy in binary classification

Achieved 11.11% higher accuracy in four-class classification

Outperformed traditional XGBoost methods

Abstract

Valves are widely used in industrial and domestic pipeline systems. However, during their operation, they may suffer from the occurrence of the cavitation, which can cause loud noise, vibration and damage to the internal components of the valve. Therefore, monitoring the flow status inside valves is significantly beneficial to prevent the additional cost induced by cavitation. In this paper, a novel acoustic signal cavitation detection framework--based on XGBoost with adaptive selection feature engineering--is proposed. Firstly, a data augmentation method with non-overlapping sliding window (NOSW) is developed to solve small-sample problem involved in this study. Then, the each segmented piece of time-domain acoustic signal is transformed by fast Fourier transform (FFT) and its statistical features are extracted to be the input to the adaptive selection feature engineering (ASFE) procedure, where the adaptive feature aggregation and feature crosses are performed. Finally, with the selected features the XGBoost algorithm is trained for cavitation detection and tested on valve acoustic signal data provided by Samson AG (Frankfurt). Our method has achieved state-of-the-art results. The prediction performance on the binary classification (cavitation and no-cavitation) and the four-class classification (cavitation choked flow, constant cavitation, incipient cavitation and no-cavitation) are satisfactory and outperform the traditional XGBoost by 4.67% and 11.11% increase of the accuracy.