A predictive analytics methodology is presented, utilizing machine learning algorithms to identify the performance state of marine journal bearings in terms of maximum pressure, minimum film thickness, Sommerfeld number, load and shaft speed. A dataset of different bearing operation states has been generated by solving numerically the Reynolds equation in the hydrodynamic lubrication regime, for steady-state loading conditions and assuming isothermal and isoviscous lubricant flow. The shaft has been modelled with four different values of misalignment angle, lying within the acceptable operating range, as defined in the existing regulatory framework. The journal bearing was modelled parametrically using generic geometric parameters of a marine stern tube bearing. The lift-off speed was estimated for each loading scenario to ensure operation in the hydrodynamic lubrication regime and the effect of shaft misalignment on lift-off speed has been evaluated. The generated dataset was utilised for training, testing and validation of several machine learning algorithms, as well as feature selection analysis, in order to solve several classification problems and identify the various bearing operational states.

Journal and thrust bearings utilise hydrodynamic lubrication to reduce friction and wear between the shaft and the bearing. The process to determine the lubricant film thickness or the actual applied load is vital to ensure proper and trouble-free operation. However, taking accurate measurements of the oil film thickness or load in bearings of operating engines is very difficult and requires specialised equipment and extensive experience. In the present work, the performance parameters of journal bearings of the same principal dimensions are measured experimentally, aiming at training a Machine Learning (ML) algorithm capable of predicting the loading condition of any similar bearing. To this end, an experimental procedure using the Bently Nevada Rotor Kit 4 is set up, combined with sound and vibration measurements in the vicinity of the journal bearing structure. First, sound and acceleration measurements for different values of bearing load and rotational speed are collected and post-processed utilising 1/3 octave band analysis techniques, for parametrisation of the input datasets of the ML algorithms. Next, several ML algorithms are trained and tested. Comparison of the results produced by each algorithm determines the fittest one for each application. The results of this work demonstrate that, in a laboratory environment, the operational parameters of journal bearings can be efficiently identified utilising non-intrusive sound and vibration measurements. The presented approach may substantially improve bearing condition identification and monitoring, which is an imperative step to prevent journal bearing failures and conduct condition-based maintenance.

This paper presents two novel artificial intelligence-based approaches for evaluating the performance of heavily loaded marine journal bearings including shaft misalignment. Traditionally, the Sommerfeld number has been used as a key parameter to evaluate the performance similarity between different bearings. However, this method has limitations, particularly when dealing with complex elastic geometries, heavily loaded journal bearings and shaft misalignment. The first proposed approach leverages neural networks to analyze key bearing performance parameters and provide a more accurate and comprehensive assessment of bearing performance similarity, including additional parameters beyond the Sommerfeld number limitations. The second method utilizes artificial intelligence convolutional networks to assess the bearing similarity based on their simulated pressure profiles under isoviscous and isothermal hydrodynamic lubrication regime. The effectiveness of the proposed methods is demonstrated and compared to the traditional Sommerfeld number method, discussing various potential applications and extensions of this concept.

This paper introduces a rigorous and comprehensive approach to the assessment of marine shafting systems through the utilization of an advanced π-Theorem-based scaling methodology. Integrating journal-bearing similarity assessment and shaft-line scaling methodology with advanced dimensional analysis, the study aims to provide a methodology foundation for systematic replication and analysis of marine shafting systems through scaled models. The proposed scaling methodology ensures geometric and mechanical similarity in terms of shaft-line deflection, considering key scaling parameters such as shaft length, diameter, weight, loads, rotational speed, material properties, bearing locations, and offsets. The advanced dimensional analysis computes specific non-dimensional ratios to guarantee a close resemblance between a real-size system and a scaled lab model. The methodology is analytically derived and validated with numerical simulations for a case study, conducting comparative analysis, evaluating discrepancies, and utilizing the integrated framework for experimentation.

This article explores the elastohydrodynamic analysis of journal bearings with deformable surface. An iterative solver is developed, coupling the Reynolds equation for hydrodynamic lubrication with the open-source FEM software, CalculiX. The steady-state Reynolds equation is solved using FDM with Reynolds boundary conditions, while the displacement field of the bearing bush is obtained via FEM and compared to the Winkler model. Both oil and water-lubricated bearings are examined, and the validity of the Winkler model is investigated, pointing out the circumstances under which it provides satisfactory results. While fluid-solid interaction and EHD analysis of journal bearings are well-documented in the literature, few studies offer a cross-domain comparison between FEM and Winkler models. This study aims at assessing the bearing performance over a range of operational conditions, including different loads, values of bush thickness, and shaft misalignment conditions. The model results are compared and validated against existing literature results. Furthermore, in water-lubricated bearing bush materials, a phenomenon occurs where negative values of radial displacements (opposite to the applied pressure) are observed in the divergent region of the fluid film. This effect is closely linked to the poisson ratio and the incompressibility of the material, and it is thoroughly illustrated and discussed in detail.

This paper introduces a rigorous and comprehensive approach for the assessment of marine shafting systems through the utilization of an advanced Pi-Theorem based scaling methodology. Integrating journal bearing similarity assessment and shaft-line scaling methodology with advanced dimensional analysis, the study aims to provide a methodology foundation for systematic replication and analysis of marine shafting systems through scaled models. The proposed scaling methodology ensures geometric and mechanical similarity in terms of shaft-line deflection, considering key scaling parameters such as shaft length, diameter, weight, loads, rotational speed, material properties, bearing locations, and offsets. The advanced dimensional analysis computes specific non-dimensional ratios to guarantee a close resemblance between a real-size system and a scaled lab model, enabling meaningful experimentation. The methodology is analytically derived and validated with numerical simulations for a case study, conducting comparative analysis, evaluating discrepancies, and utilizing the integrated framework for experimentation.