ML enhanced measurement of the electrostatic charge distribution of powder conveyed through a duct

TL;DR

This paper introduces a machine learning method using shallow neural networks to estimate the full 2D electrostatic charge distribution of powders in a duct from 1D optical measurements, enhancing process safety analysis.

Contribution

It presents a novel ML approach trained on simulation data to reconstruct 2D charge distributions from limited 1D measurements in duct flows.

Findings

Average $L^1$-error of 1.63% in charge distribution reconstruction

ML model trained on four different simulation scenarios

Method enables estimation of critical safety parameters from limited data

Abstract

The electrostatic charge acquired by powders during transport through ducts can cause devastating dust explosions. Our recently developed laser-optical measurement technique can resolve the powder charge along a one-dimensional (1D) path. However, the charge across the duct's complete two-dimensional (2D) cross-section, which is the critical parameter for process safety, is generally unavailable due to limited optical access. To estimate the complete powder charge distribution in a conveying duct, we propose a machine learning (ML) approach using a shallow neural network (SNN). The ML algorithm is trained with cross-sectional data extracted from four different three-dimensional direct numerical simulations of a turbulent duct flow with varying particle size. Through this training with simulation data, the ML algorithm can estimate the powder charge distribution in the duct's cross-section based on only 1D measurements. The results reveal an average $L^1$-error of the reconstructed 2D cross-section of 1.63 %.