基于多传感器数据融合的喷水推进泵空化分类识别

PDF(1291 KB)

振动与冲击 ›› 2012, Vol. 31 ›› Issue (18) : 93-95.

论文

基于多传感器数据融合的喷水推进泵空化分类识别

苏永生 , 王永生 , 段向阳

作者信息 +

Classification of Cavitation in Waterjet Pump Based on Multi-Sensor Data Fusion

SU Yong-sheng；WANG Yong-sheng；DUAN Xiang-yang

Author information +

文章历史 +

摘要

采用基于奇异值分解和人工神经网络的多传感器数据融合方法对喷水推进泵的空化状态进行了分类识别研究。首先利用基于奇异值分解的权值估计算法分别对水声信号和振动信号在时间上进行数据级融合，提取出各自的特征，然后将所有特征组合起来作为神经网络的输入，利用BP网络和RBF网络进行特征级融合和分类识别。分析结果表明：基于多传感器数据融合的分类识别结果优于单传感器分类识别结果；采用基于奇异值分解的数据融合方法后，分类识别率显著提高，对空化初生微弱特征的识别效果尤佳。

Abstract

The classification of cavitation in waterjet pump was researched by multi-sensor data fusion method based on singular value decomposition (SVD) and artificial neural networks (ANN). Time data fusion was used to fuse the acoustic and vibration signals based on SVD firstly, then the respective features were extracted, which were composed and used as entries of the ANN, the BP network and RBF network were applied to fuse the features for classification. The results show that the classification performance based on multi-sensor data fusion is better than single sensor, and the recognition rates are obviously improved after data fusing based on SVD, which is superior for weak feature detection and recognition of cavitation inception

导出引用

苏永生;王永生;段向阳. 基于多传感器数据融合的喷水推进泵空化分类识别[J]. 振动与冲击, 2012, 31(18): 93-95

SU Yong-sheng;WANG Yong-sheng;DUAN Xiang-yang. Classification of Cavitation in Waterjet Pump Based on Multi-Sensor Data Fusion[J]. Journal of Vibration and Shock, 2012, 31(18): 93-95