This paper presents a machine learning neural network capable of approximating pressure as the distributive result of elastohydrodynamic (EHD) effects for a journal bearing at steady state. Design of efficient, reliable fluid power pumps and motors requires accurate models of lubricating interfaces; however, many state-of-the-art simulation models are structured around numerical solutions to the Reynolds equation which involve nested iterative loops, leading to long simulation durations and limiting the ability to use such models in optimization studies. This study presents a machine learning model capable of approximating the pressure solution of the Reynolds equation for a journal bearing with given distributive geometric boundary conditions and considering cavitation and elastic deformation at steady-state operating conditions. A 1024-sample training set was generated using an in-house multiphysics simulator. A hyperparameter optimization study was conducted, leading to the six-layer U-Net convolutional neural network architecture proposed. After training, the neural network accurately predicted pressure distributions for test samples with different geometric inputs from the training data, and accurately estimated resultant journal bearing loads, showing the feasibility of post-processing the machine learning output for integration into other fluid power models. Additionally, the neural network showed promise in analyzing geometric inputs outside the space of the training data, approximating the pressure in a grooved journal bearing with reasonable accuracy. These results demonstrate the potential of a machine learning model to be integrated into fluid power pump and motor simulations for faster performance evaluation and optimization.

The cylinder block/valve plate interface is one of the major power loss sources and main failure points in axial piston pumps and motors. Surface micro-texture has been proven to be an effective approach to reduce friction and wear in many tribological applications. In the present paper, the effect of micro-texture on the tribological and lubricating performance of the important cylinder block/valve plate interface is studied experimentally and numerically. The experimental investigation was conducted on a disk-on-disk tribometer with similar geometry, operating speed, material, and working fluid to the cylinder block/valve plate interface in the axial piston pump. The tribological test results confirmed the chevron micro-texture's potential to reduce frictional loss in such lubricating interface. Furthermore, a novel numerical method coupling the dynamic loading, squeeze motion, analytical pressure deformation, mixed friction, and cavitation was proposed to study the lubricating performance of micro-textured valve plate/cylinder block interface. This model was then validated comparing to the tribometer experimental results and was used to study the effect of depths, widths, and distances of chevron micro-textures on the lubrication performance of cylinder block/valve plate interface. The results found that the depth of the chevron micro-textures affected whether the cavitation occurred inside the micro-texture, the width of the chevron micro-texture affected the size of the cavitation area that occurred in the micro-textures, and the chevron micro-texture distance affected the size of the convergence zone where positive pressure generated.

The authors propose a temperature adaptive piston design for axial piston machines of swash plate type. The proposed piston helps to keep the film thickness between piston and cylinder close to optimal with respect to energy dissipation while operating temperature can change in a wide range. The authors utilize the thermal deformation of piston and cylinder, which varies with temperature, to design the interface that adapt the gap height to compensate the change of the fluid viscosity with the temperature. An in-house developed fluid-structure and thermal interaction model together with recently developed port and case temperature prediction model are used to analyze the piston/cylinder interface and to predict resulting part temperatures, deformations, the fluid film properties and resulting energy dissipation, friction and leakage of the proposed novel design. The results show a reduction of energy dissipation over a large range of operating temperature for the proposed design compared to the baseline design.

In lieu of reliable scaling rules, hydraulic pump and motor manufacturers pay a high monetary and temporal price for attempting to expand their production lines by scaling their existing units to other sizes. The challenge is that the lubricating interfaces, which are the key elements in determining the performance of a positive displacement machine, are not easily scalable. This article includes an analysis of the size-dependence of these units with regard to the significant physical phenomena describing the behavior of their three most critical lubricating interfaces. These phenomena include the non-isothermal elastohydrodynamic effects in the fluid domain, and the heat transfer and thermal elastic deflection in the solid domain. The performance change due to size variation is found to be unavoidable and explained through fundamental physics. The results are demonstrated using a numerical fluid–structure–thermal interaction model over a wide range of unit sizes. Based on the findings, a guide to scaling swashplate-type axial piston machines such as to uphold their efficiency is proposed.

The slipper/swashplate interface, as one of the three main lubricating interfaces in swashplate type axial piston machine, serves both a sealing function and a bearing function while dissipating energy into heat due to viscous friction. The sealing function prevents the fluid in the displacement chamber from leaking out through the gap to the case, and the bearing function prevents the slipper from contacting to the swashplate. The challenge of the conventional slipper/swashplate lubricating interface design is to rely on the tribological pairing self-adaptive wearing process to find a slipper surface profile that fulfills the bearing function. However, the resulted slipper surface profile from uncontrollable wearing process is not necessarily able to achieve good energy efficiency. This article proposes a novel slipper design approach that overcomes this challenge by adding a quadratic spline curvature to the slipper running surface which eliminates the wear while keeping good efficiency. A fully-coupled fluid-structure and thermal interaction model is used to simulate the performance of the slipper/swashplate interface. A computationally inexpensive optimization scheme is used to find the desired slipper design. This article presents the simulation methodology, the optimization scheme, the full factorial simulation study results, and the optimized slipper running surface.