Self-updating inverse model for magnetorheological dampers

Deng, Huaxia; Yue, Rui; Lian, Xinyu; Deng, Jialei; Zhang, Jin; Ma, Mengchao; Zhong, Xiaoming

doi:10.1088/1361-665x/ab473b

Cited by 8 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MJL Boada used the network inversion method to establish the inverse model of an MR damper [43]. The principle for applying the technique to this research is shown in Fig.…”

Section: Establishment Of the General Inverse Model A Network Inversion Based On The Gradient Descent Methodsmentioning

confidence: 99%

“…However, this research did not update the model itself, only updated other input variables in the inversion process, and the proposed forward model could not capture the damping force behavior close to the peak values in low frequency excitations. Huaxia Deng et al proposed a self-updating forward model that could be adjusted to describe the dynamic characteristics of MR dampers as external incentives changes [43]. Nevertheless, the inverse model was obtained by directly inverting the hyperbolic tangent function based model in this research, causing errors.…”

Section: Introductionmentioning

confidence: 94%

“…Deng [43] proposed an Self-updating inverse model for MR dampers, which can be adjusted to describe the dynamic characteristics of MR dampers under changes in the external incentives. The dynamic characteristics of MR dampers are tracked by constantly changing the parameters of the damper forward model, which means that the damper model can adapt to changeable excitations.…”

Section: ) Sigmoid Function Damper Controllermentioning

confidence: 99%

See 2 more Smart Citations

A New High-Precision General Inverse Model Based on Deep Learning for Magnetorheological Damper

2021

View full text Add to dashboard Cite

There are several main factors affect damping characteristics of a magnetorheological damper, the influence laws of some ones are eager to change with varying working conditions. Therefore, it is challengable to establish the relationship between the two: influence factors and damping characteristics of the magnetorheological damper. This paper proposed a new deep learning-based general inverse model to predict the required current value of a magnetorheological damper under changing complex working conditions. Specifically, a fully-connected multilayer perceptron was chosen to train the general forward model. The complex and time-varying relationships between the main factors and damping characteristics were accurately characterized on use of the high nonlinear mapping ability of the multilayer perceptron. Compared to most of general forward models, the proposed model was more excellent with an accuracy of 99.73% based on ensuring generality. Besides, the network inversion method was used in the inverse solution of the multilayer perceptron general forward model, which simplified the process of inverse solution without requiring a mass of training data. Furthermore, a genetic algorithm was used to replace the gradient descent method which was commonly used in network inversion, with the benefit of solving the problem of selecting the initial value and step size, as well as improving the accuracy. Simultaneously, the experiments were conducted on the proposed general inverse model, the experimental results, being consistent with the simulation results, demonstrated that the proposed model can accurately predict the control current value and track the required damping force in changing complex working conditions.INDEX TERMS General forward model, general inverse model, genetic algorithm, multilayer perceptron, network inversion.

show abstract

“…MJL Boada used the network inversion method to establish the inverse model of an MR damper [43]. The principle for applying the technique to this research is shown in Fig.…”

Section: Establishment Of the General Inverse Model A Network Inversion Based On The Gradient Descent Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 94%

Section: ) Sigmoid Function Damper Controllermentioning

confidence: 99%

See 1 more Smart Citation

A New High-Precision General Inverse Model Based on Deep Learning for Magnetorheological Damper

2021

View full text Add to dashboard Cite

show abstract

“…The dynamic characteristics of variable stiffness MRF dampers vary with excitations including current and displacement amplitude. The improvement structures of dampers bring friction and other problems which affect damper characteristics [6,7]. Hence, the variable stiffness MRF dampers inherently have nonlinearity characteristics like non-symmetrical hysteresis and so on.…”

Section: Introductionmentioning

confidence: 99%

Self-adapting model for variable stiffness magnetorheological dampers

Lian¹,

Deng²,

Han³

et al. 2021

Smart Mater. Struct.

Self Cite

View full text Add to dashboard Cite

Variable stiffness magnetorheological fluid (MRF) dampers inherently have special nonlinear characteristics and complex structures. An accurate model describing the nonlinearity is the key for the damper to operate under variable conditions. This paper proposes a self-adapting model to characterize the variable stiffness MRF dampers through corresponding optimized algorithm. The experimental results verify the capability of the self-adapting of the model parameters. The model can describe the nonlinear characteristics of the variable stiffness MRF damper when conditions are changed. The proposed self-adaptive model improves the model accuracy which provide an approach for modeling complex dampers under variable working conditions.

show abstract

“…The rheological properties such as viscosity or yield stress value rapidly and reversibly rise in the increasing value of an applied magnetic field because of the bonding among the magnetic particles. Due to their behavior, MR suspensions have attracted much interest in the last two decades, such as automotive suspensions, brakes, torque transfer devices, and seals systems [2][3][4]. The devices are usually designed based on the required working range translated into the MR suspension rheological properties, such as yield stress.…”

Section: Introductionmentioning

confidence: 99%

A machine learning approach to estimate magnetorheological suspension composition based on magnetic field dependent-rheological properties

Bahiuddin¹,

Imaduddin²,

Mazlan³

et al. 2021

Smart Mater. Struct.

View full text Add to dashboard Cite

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.

show abstract

Self-updating inverse model for magnetorheological dampers

Cited by 8 publications

References 33 publications

A New High-Precision General Inverse Model Based on Deep Learning for Magnetorheological Damper

A New High-Precision General Inverse Model Based on Deep Learning for Magnetorheological Damper

Self-adapting model for variable stiffness magnetorheological dampers

A machine learning approach to estimate magnetorheological suspension composition based on magnetic field dependent-rheological properties

Contact Info

Product

Resources

About