Non-parametric multiple inputs prediction model for magnetic field dependent complex modulus of magnetorheological elastomer

Abstract

This study introduces a novel platform to predict complex modulus variables as a function of the applied magnetic field and other imperative variables using machine learning. The complex modulus prediction of magnetorheological (MR) elastomers is a challenging process, attributable to the material’s highly nonlinear nature. This problem becomes apparent when considering various possible fabrication parameters. Furthermore, traditional parametric modeling methods are limited when applied to solve larger-scale cases involving large databases. Consequently, the application of non-parametric modeling such as machine learning has gained increasing attraction in recent years. Therefore, this work proposes a data-driven approach for predicting multiple input-dependent complex moduli using feedforward neural networks. Besides excitation frequency and magnetic flux density as operating conditions, the inputs consider compositions and curing conditions represented by magnetic particle weight percentage and the curing magnetic field, respectively. Extreme learning machines and artificial neural networks were used to train the models. The simulation results obtained at various curing conditions and other inputs confirm that the predicted complex modulus has high accuracy with an R2 of about 0.997, as compared to the experimental results. Furthermore, the predicted complex modulus pattern and magnetorheological effect agree with the experimental data using both the learned and unlearned data.

A Comparative Study on Various ANN Optimization Algorithms for Magnetorheological Elastomer Carbonyl Iron Particle Concentration Estimation

“…Hence, modelling and simulation model is needed to accurately anticipate particle composition under certain conditions. Prediction model for estimating viscoelastic properties (forward model) such as stress relaxation and creep behaviour [15] or particle composition such as particle concentration and size [16] (inverse model) involved with mathematical derivation-based model [17,18] and also machine learning based model [19][20][21].…”

Magnetodielectric Properties of Ordered Microstructured Polydimethylsiloxane-Based Magnetorheological Elastomer with Fe3O4@rGO Nanoparticles

“…Magnetorheological elastomer (MRE) is an emerging magneto-functional intelligent material that consists of a composite of magnetic particles and a polymer matrix [ 1 , 2 ]. The magnetic filler inside MRE undergoes displacement changes under the action of an external magnetic field, which is macroscopically manifested as a rapid, continuous, and reversible change in the mechanical and electrical properties of MRE controlled by the magnetic field, such as magnetorheological effect [ 3 ], magnetoresistance effect [ 4 ], and magnetic properties [ 5 , 6 ].…”

Controllable Damping Magnetorheological Elastomer Meniscus

“…In this paper, the feasibility of using controllable damping magnetorheological elastomer as a natural meniscus replacement material was researched . The MRI data of the human knee joint was obtained by CT scanning, and a three-dimensional finite element model of the meniscus was established.…”

“…19−22 In this paper, the feasibility of using controllable damping magnetorheological elastomer as a natural meniscus replacement material was researched. 23 The MRI data of the human knee joint was obtained by CT scanning, and a threedimensional finite element model of the meniscus was established. The compressive loads of 400 N, 600 N, 800 N, and 1000 N were applied to the model, and the stress and displacement distribution of the meniscus was analyzed by ANSYS simulation.…”