A machine learning approach to estimate magnetorheological suspension composition based on magnetic field dependent-rheological properties. (31st August 2021)

• Record Type: Journal Article
• Authors: Bahiuddin, Irfan; Imaduddin, Fitrian; Mazlan, Saiful Amri; Shapiai, Mohd Ibrahim; Ubaidillah, ; Nazmi, Nurhazimah; Mohamad, Norzilawati
• Is Part Of: Smart materials and structures. Volume 30:Number 10(2021)
• Publication Date: 2021-08-31
• Subjects: magnetorheological fluids -- rheology -- yield stress -- machine learning -- neural networks -- inverse model; Smart materials -- Periodicals; Strucural design -- Periodicals; 620.11
• DOI: 10.1088/1361-665X/ac1d92
• Languages: English
• ISSNs: 0964-1726

Abstract

Abstract: This paper presents an inverse model of magnetorheological (MR) suspensions to predict the compositions as a function of magnetic field-dependent rheological properties using the feedforward neural network (FFNN) model. Although many variations of MR suspension compositions have been published, the composition of the MR suspensions needs to be chosen manually by considering the required rheological properties. Therefore, this paper proposed a systematic method to predict MR suspension composition based on the rheological properties by employing extreme learning machine (ELM) and backpropagation (BP) techniques to build FFNN models. The model is built based on three experimental datasets representing particle shapes, sizes, and weight percentages. Three input topologies are proposed involving yield stress at the on-state condition, yield stress at the off-state condition τ y, 0, yield stress slope m, and magnetic fields B . The outputs are the particle weight percentages, milling time of magnetic particles representing the particle shapes, and particle sizes for each dataset model. FFNN models trained by ELM and BP have shown comparable accuracy. The simulations have also shown that the inclusion of the slope as one of the model inputs can produce R 2 of more than 0.80 for training and testing data. The off-state condition of yield stress can also improve the model performances if the off-state yield stress has a high correlation with the output. Finally, from the results, it can be concluded that the proposed machine learning approaches and topologies have successfully predicted the compositions in good agreement with the experimental data.