Machine learning assisted mechanism modeling for gas phase electrohydrodynamic system
Authors:
- Wen ChenWCWen Chen
- Ru-Xian CaiRCRu-Xian Cai
- Le WangLWLe Wang
- Zhi-Zhou YangZYZhi-Zhou Yang
- Ran WeiRWRan Wei
- Wei-Cheng YanWei-Cheng Yan
- 1 September 2024
- journal article
- research article
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (9)
Abstract
In this paper, a hybrid physics-data driven model for electrohydrodynamic gas system (EHDGS) was developed by combining artificial neural network (ANN) with mechanism modeling method. ANN was used to correlate the relationship between the variables (electrode distance, diameter of grounding cylinder, applied voltage, electric field gradient, etc.) in a needle-cylinder EHDGS and the initial space charge density. The results showed that the ANN model of nine neurons can well predict the initial space charge density. The coefficient of determination (R2) reaches 0.9874, and the mean absolute error is as low as 0.0067. Subsequently, a hybrid mechanism model where the initial space charge density was predicted from the ANN model was constructed to simulate the needle-cylinder EHDGS. The experiment with the needle-cylinder EHDGS was carried out. The simulation results were in good agreement with the experimental data, demonstrating the reliability of the proposed hybrid model. The electric field distribution, space charge distribution, and flow field distribution behavior of the EHDGS were then analyzed in detail. The effects of key parameters on the flow characteristics of EHDGS were systematically studied, showing that higher voltage and shorter distance give higher flow rate up to 2.5 m/s. The diameter of the cylinder also significantly influences the breakdown voltage. Three dimensionless groups were defined and their effects on spatial charge density distribution were investigated. This study provides both insights and an efficient tool for the design and optimization of EHDGS.Keywords
Funding Information
- National Natural Science Foundation of China (22378171)
- Innovation and Entrepreneurship Talents of Jiangsu Province ((2020)10545)
This publication has 53 references indexed in Scilit:
- Development of machine learning based droplet diameter prediction model for electrohydrodynamic atomization systemsChemical Engineering Science, 2022
- Prediction of nuclear charge density distribution with feedback neural networkNuclear Science and Techniques, 2022
- Enhancement of Ion Acceleration Efficiency by Multi-stage and Accelerating Electrodes CouplingJournal of Electrical Engineering & Technology, 2021
- Prediction of polycarbonate degradation in natural atmospheric environment of China based on BP-ANN model with screened environmental factorsChemical Engineering Journal, 2020
- Characteristics of ionic wind in needle-to-ring corona dischargeJournal of Electrostatics, 2015
- An empirical model for ionic wind generation by a needle-to-cylinder dc corona dischargeJournal of Electrostatics, 2015
- Parallel integration of ionic wind generators on PCBs for enhancing flow rateMicrosystem Technologies, 2014
- Use of artificial neural networks to determine parameters controlling the nanofibers diameter in electrospinning of nylon‐6,6Journal of Applied Polymer Science, 2011
- Numerical simulation of cone‐jet formation in electrohydrodynamic atomizationAIChE Journal, 2010
- Prediction of corrosion behavior using neural network as a data mining toolCorrosion Science, 2010