Inline Measurement of Particle Concentrations in Multicomponent Suspensions using Ultrasonic Sensor and Least Squares Support Vector Machines.

Xiaobin Zhan,Shulan Jiang,Tielin Shi,Yili Yang,Xiwen Li,Jian Liang

doi:10.3390/s150924109

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.

Highlights

Inline measurement of the component concentrations is an important approach to supervise industrial processes
This paper is aimed to develop a new inline measurement system for simultaneous measurement of two particle concentrations in ternary suspensions based on ultrasonic sensor and the least squares support vector machines (LS-SVM) model
This paper proposes an alternative methodology for inline measurement of particle concentrations in multicomponent suspensions based on a combination of ultrasonic sensor and LS-SVM model

Summary

Introduction

Inline measurement of the component concentrations is an important approach to supervise industrial processes. The measurement of component concentrations in multicomponent mixtures cannot be achieved through a low-cost and inline technique. Ultrasonic sensor can satisfy the requirements of good robustness, high accuracy, inline measurement, safety and low maintenance in industrial processes [5]. The ultrasonic features (e.g., ultrasonic attenuation and velocity) are directly correlated with concentrations [6,7]. It is very difficult or even impossible to derive a physical model to characterize the relationship between ultrasonic features and component concentrations in multicomponent mixtures [8]

Objectives

Methods

Results

Conclusion