Paper Info
Title
Inline Measurement of Particle Concentrations in Multicomponent Suspensions using Ultrasonic Sensor and Least Squares Support Vector Machines
Abstract
This paper proposes an ultrasonic measurement system based on least squares support vector machines (LS-SVM) for inline measurement of particle concentrations in multicomponent suspensions. Firstly, the ultrasonic signals are analyzed and processed, and the optimal feature subset that contributes to the best model performance is selected based on the importance of features. Secondly, the LS-SVM model is tuned, trained and tested with different feature subsets to obtain the optimal model. In addition, a comparison is made between the partial least square (PLS) model and the LS-SVM model. Finally, the optimal LS-SVM model with the optimal feature subset is applied to inline measurement of particle concentrations in the mixing process. The results show that the proposed method is reliable and accurate for inline measuring the particle concentrations in multicomponent suspensions and the measurement accuracy is sufficiently high for industrial application. Furthermore, the proposed method is applicable to the modeling of the nonlinear system dynamically and provides a feasible way to monitor industrial processes.
Year
DOI
Venue
2015
10.3390/s150924109
SENSORS
Keywords
Field
DocType
ultrasonic sensor,particle concentration,multicomponent suspensions,inline measurement,LS-SVM
Least squares,Ultrasonic sensor,Data mining,Nonlinear system,System of measurement,Biological system,Support vector machine,Electronic engineering,Engineering,Accuracy and precision,Particle
Journal
Volume
Issue
Citations 
15
9.0
0
PageRank 
References 
Authors
0.34
3
6
Name
Order
Citations
PageRank
xiaobin zhan111.02
shulan jiang200.34
yili yang300.34
jian liang400.34
Tielin Shi59017.20
xiwen li651.81