Interior Void Classification in Liquid Metal Using Multi-Frequency Magnetic Induction Tomography With a Machine Learning Approach

Abstract

Identification of gas bubble, void detection and porosity estimation are important factors in many liquid metal processes. In steel casting, the importance of flow condition and phase distribution in crucial parts, such as submerged entry nozzle (SEN) and mould raises the needs to observe the phenomena. Cross-section of flow shapes can be visualised using the magnetic induction tomography (MIT) technique. However, the inversion procedure in the image reconstruction has either limited resolution or postprocessing stages. Additionally, in some cases, the displayed image may not be essential when quantifying the void fraction or porosity. This work proposes an interior void classifier based on multi-frequency mutual induction measurements with eutectic alloy GaInSn as a cold liquid metal model contained in a 3D printed plastic miniature of an SEN. The sensors consist of eight coils arranged in a circle encapsulating the column, providing combinatorial detection on conductive surface and depth. The datasets are induced voltage collections of several non-metallic inclusions (NMI) patterns in liquid metal static test and used to train a machine learning model. The model architectures are a fully connected neural network (FCNN) for 1D; and a convolutional neural network (CNN) for 2D data. The classifier using 1D data has been trained providing 98% accuracy on this dataset. On the other hand, CNN classification using multi-dimensional data produces 96% of test accuracy. Refined with representative flow scenarios, the trained model could be deployed for an intelligent online control system of the liquid metal process.

Recent Progress in the Preparation Technologies for Micro Metal Coils

“…The liquid metal flows through the interconnected layer, then through the lead-out channel back to another PCB contact pad, and finally out through the outlet drilled in the PCB. The large contact area between the liquid metal and the PCB contact pad ensures a good electrical connection with the external equipment, and the liquid metal is cooled to form a three-dimensional coil [120], which completes the preparation process of the liquid metal micro coil.…”

Design of soft-magnetic shield in electromagnetic tomography

“…It has been applied in industry (e.g. the monitoring of the melting process [1,2], the testing of metal/non-metal components [3][4][5], and the visualization of the multiphase flow processes in fluidized beds [6][7][8][9]) and in biomedicine [10][11][12][13].…”

Laboratory Investigation of Tomography-Controlled Continuous Steel Casting

“…Small distributed inner bubbles are difficult to detect and reconstruct. The multifrequency method, bypassing reconstruction and using just raw data, or data-driven approaches for quantification are the future directions that could be investigated for continuous casting [ 25 ].…”