Advanced optical measurement techniques for simultaneous fibre orientation and flow analysis complemented by machine learning

TL;DR

This paper introduces a new optical method combined with machine learning to measure fiber orientation and flow in transparent fluids, helping to better understand how fibers align during fluid movement.

Contribution

The novel contribution is a PIV-based measurement system with machine learning for quasi-simultaneous fiber orientation and flow analysis.

Findings

Fibers show strong orientation effects near interfering bodies.

Machine learning enables accurate fiber detection with minimal training data.

Velocity vector fields and fiber motion are successfully combined and analyzed.

Abstract

A new measuring method is presented that allows time-resolved quasi-simultaneous measurement of fibre orientation and flow velocity of a transparent fluid such as a substitute fluid for fresh concrete or polymer melt, thus enabling the flow-related fibre orientation process to be visualised and thus better understood. In order to study individual fibres and their orientation in detail a PIV-based measurement stand was built, which is capable of analysing the flow and the fibre orientation in the suspension quasi-simultaneously. To measure the fibre orientation, black light can be switched on so that the fibres are stimulated by phosphorescence and become visible in the fluid. A random forest algorithm is used to detect the fibres in the images. This machine learning method allows the fibres to be accurately detected with little training data and a short training and processing time. The results show that there is a strong orientation effect on the fibres the closer they are to the orbit in the vicinity of the interfering body. In addition, a rapidly occurring orientation can be determined in detail. This allows the velocity vector fields and the actual fibre motion to be combined and analysed in this work.

Figures