Machine learning-based performance analysis of two-axial-groove hydrodynamic journal bearings

Abstract

The precise prediction of a rotor against instability is needed for avoiding the degradation or failure of the system’s performance due to the parametric variabilities of a bearing system. In general, the design of the journal bearing is framed based on the deterministic theoretical analysis. To map the precise prediction of hydrodynamic performance, it is needed to include the uncertain effect of input parameters on the output behavior of the journal bearing. This paper presents the uncertain hydrodynamic analysis of a two-axial-groove journal bearing including randomness in bearing oil viscosity and supply pressure. To simulate the uncertainty in the input parameters, the Monte Carlo simulation is carried out. A support vector machine is employed as a metamodel to increase the computational efficiency. Both individual and compound effects of uncertainties in the input parameters are studied to quantify their effect on the steady-state and dynamic characteristics of the bearing.

The Effects of Interval Uncertainties on Dynamic Characteristics of a Rotor System Supported by Oil-Film Bearings

“…For such complex simulation cases, the traditional scanning method introduces an overwhelming computational burden aroused by the massive parameter sampling. For instance, there will be 100 4 samples in total if we use 100 samples for an individual interval uncertainty in the scanning process. Indeed, a parameter sample requires a complete execution of solving the original rotor-bearing system.…”

“…Moreover, the fluid-lubricated bearings are recognized to have a large load-carrying capacity, which is beneficial to large-sized heavy-duty machinery. Although many variants, such as tilting pad journal bearings [3], are available in modern industry, the lubrication characteristics of plain oil-film bearings and the corresponding rotordynamics are still the core research interests of many investigators [4][5][6]. It has been identified that uncertain factors in rotor systems supported by oil-film bearings play crucial roles in design and dynamic studies [7][8][9][10][11][12].…”

Probing asymmetric uncertain effect on symmetric three-lobe journal bearing

“…It was only in the last few years that uncertainties called the attention of Engineers and Researchers. Some recent studies [29][30][31][32][33][34][35] have considered the input uncertainty in the hydrodynamic analysis of journal bearings. da Silva et al 29 considered stochastic variation in bearing clearance and Griffini et al 30 considered the stochastic variation in bearing clearance as well as fluid viscosity to study the dynamic response of tilting pad bearings.…”

“…Cavalini et al 32 and Maharshi et al 33 performed the dynamic analysis of plain journal bearing wherein, Cavalini et al considered the variation of the input parameters based on fuzzy logic whereas, Maharshi et al used the stochastic variation of the input parameters. Roy and Dey 34 quantified the uncertain behavior of a circular bearing with two axial grooves considering supply pressure and oil viscosity as stochastic variables. Recently, Roy et al 35 presented an investigation on the probabilistic response of two-lobe journal bearing considering polynomial neural network-based surrogate model.…”