In-Line Monitoring and Control of Rheological Properties through Data-Driven Ultrasound Soft-Sensors.

Stefania Tronci,Daniele Piras,Massimiliano Grosso,Paul Van Neer,Erwin Giling,Roberto Mei,Uilke Stelwagen,Francesc Corominas

doi:10.3390/s19225009

Abstract

The use of continuous processing is replacing batch modes because of their capabilities to address issues of agility, flexibility, cost, and robustness. Continuous processes can be operated at more extreme conditions, resulting in higher speed and efficiency. The issue when using a continuous process is to maintain the satisfaction of quality indices even in the presence of perturbations. For this reason, it is important to evaluate in-line key performance indicators. Rheology is a critical parameter when dealing with the production of complex fluids obtained by mixing and filling. In this work, a tomographic ultrasonic velocity meter is applied to obtain the rheological curve of a non-Newtonian fluid. Raw ultrasound signals are processed using a data-driven approach based on principal component analysis (PCA) and feedforward neural networks (FNN). The obtained sensor has been associated with a data-driven decision support system for conducting the process.

Highlights

The competitiveness of the chemical industry depends on its ability to deliver high quality and high-value products at competitive prices in a sustainable fashion and to adapt quickly to changing customer needs
The Principal Component Analysis (PCA) has been used [23], that allows representing the variation present in many variables using a smaller number of abstract factors number next to the points is the number of replicates of that setting
The viscosity values calculated by the neural network and the off-line measured values are reported in Figure 7 for the training set and in Figure 8 for the test set

Summary

Introduction

The competitiveness of the chemical industry depends on its ability to deliver high quality and high-value products at competitive prices in a sustainable fashion and to adapt quickly to changing customer needs. In continuous flow processes, identifying the cause of specific deviations during production is more difficult when the product continuously flows through the different unit operations. This implies that the effects of process fluctuations can significantly affect the performance of the process [2], with a significant risk of producing large amounts of off-spec product that needs rework or even must be treated as waste, causing high cost and high consumption of energy and of raw materials. The use of continuous in-line measurements and control of the product quality are mandatory

Methods

Results

Conclusion