Application of Deep Reinforcement Learning to Predict Shaft Deformation Considering Hull Deformation of Medium-Sized Oil/Chemical Tanker

The enlargement of ships has increased the relative hull deformation owing to draft changes. Moreover, design changes such as an increased propeller diameter and pitch changes have occurred to compensate for the reduction in the engine revolution and consequent ship speed. In terms of propulsion shaft alignment, as the load of the stern tube support bearing increases, an uneven load distribution occurs between the shaft support bearings, leading to stern accidents. To prevent such accidents and to ensure shaft system stability, a shaft system design technique is required in which the shaft deformation resulting from the hull deformation is considered. Based on the measurement data of a medium-sized oil/chemical tanker, this study presents a novel approach to predicting the shaft deformation following stern hull deformation through inverse analysis using deep reinforcement learning, as opposed to traditional prediction techniques. The main bearing reaction force, which was difficult to reflect in previous studies, was predicted with high accuracy by comparing it with the measured value, and reasonable shaft deformation could be derived according to the hull deformation. The deep reinforcement learning technique in this study is expected to be expandable for predicting the dynamic behavior of the shaft of an operating vessel.

Time-Varying Dynamic Analysis of a Helical-Geared Rotor-Bearing System with Three-Dimensional Motion Due to Shaft Deformation

The rotordynamics of a helical-geared rotor-bearing system were investigated. A new dynamic model for a helical-geared rotor-bearing system, which takes into account three-dimensional (3-D) motion due to rotating shaft deformation, was proposed. The proposed model considers the time-varying effect, which in other models, is considered constant. The system equations of motion were obtained by applying Lagrange’s equation, and the dynamic responses were computed by the fourth-order Runge–Kutta method. The time-varying dynamic responses of the helix angle, transverse pressure angle, gear pair center distance, and total contact ratio were investigated. The numerical results show that the time-varying effect is an important factor in gear vibration analysis and cannot be neglected when the helical geared rotor-bearing system has a lower stiffness.

A new concept of a device for crankshaft crank shoulder deformations measurements by means of the symmetrical method

The patent pending design of the crank shaft deformation measuring device by means of the symmetric method, was presented. The new solution eliminates imperfections and inaccuracies resulting from the method currently used for this purpose, and enables correct assessment of the crankshaft positioning in main bearings.

The Effect of Compressor Shaft Geometry on Shaft Thermal Bow due to Natural Convection

This study builds upon previous work by the authors, using a combination of 3D conjugate heat transfer (CHT) computational fluid dynamics (CFD) and finite element analysis (FEA) to characterise the thermal bow behaviour of a simple compressor shaft and case model under natural cooling. As with previous studies by the authors, body temperatures obtained from 3D CHT CFD solutions at set time intervals are transferred to FEA, where the physical distortion associated with the asymmetric thermal load is measured. The current study examines the influence of a range of shaft design parameters on the severity and duration of the shaft deformation. The parameters of interest include shaft length, annulus geometry, degree of shaft ventilation, and shaft internal cavity geometry. Each time the baseline model is modified to analyse the contribution of a parameter, the model is allowed to cool down from representative operational temperatures for a period of 180 minutes, over which time the shaft thermal bow, and shaft-to-case clearance, are measured. The results of this study indicate that the shaft’s thermal bow response and shaft-to-case clearance over time are highly sensitive to changes to its geometry, whereas the change in 180-degree out-of-phase shaft-to-case clearance is more sensitive to the case geometry, rather than the shaft. These results indicate that increasing the length of the shaft, reducing its wall thickness, or introducing a rising-line annulus, will increase the severity of the shaft thermal bow phenomenon; whereas introducing disc geometry inside the shaft will reduce the severity of the bow.