The increasing rotational speed and temperature levels in modern aeroengines impose higher demands on the lubrication and cooling design of the roller bearings supporting the main shaft. To design a compact and efficient under-race lubrication system, a comprehensive understanding of the characteristics of oil–air two-phase flow and the variations in oil capture efficiency is necessary. This study experimentally investigated the oil capture efficiency and employed numerical simulations to elucidate the mechanisms of oil–air two-phase flow. The results reveal a favorable consistency between the numerical simulations and experimental findings, both in terms of the oil capture efficiency and the oil–air distribution. The decreasing trend of oil capture efficiency gradually stabilizes when the jet distance exceeds 10 mm. To ensure stable and effective testing results for oil capture efficiency, the jet distance should be maintained within the range of 10–14 mm during experiments. Under different operating conditions, there exists an optimal jet angle that maximizes the oil capture efficiency. The corresponding optimal jet angle becomes smaller with lower oil supply pressure and higher rotational speed of the radial oil scoop. Within a momentum flux ratio range of 5–870, an innovative predictive correlation for the optimal jet angle is derived, with a maximum relative error between predicted and experimental values being 4.0%. The proposed correlation provides theoretical support and methodological basis for refining the design of radial under-race lubrication in aeroengines.

To study the influence of orifice spacing on the oil–air two-phase flow and the oil capture efficiency of an oil scoop in an under-race lubrication system, an experimental platform for under-race lubrication was built, and a calculation model for the oil–air two-phase flow field was established. The rationality of the experiment and the validity of the numerical model were verified by comparing the experimental and numerical results. The results showed that under the same oil supply pressure, the captured oil mass flow rate of the double-orifice structure was much higher than that of the single-orifice structure, though it was still less than twice that of the single-orifice structure. When applying a tandem layout structure of double orifices to an under-race lubrication system, the orifice spacing of the tandem layout structure should be determined based on a full evaluation of the influence of the orifice spacing and working condition parameters on the oil capture performance. Otherwise, it may lead to a decrease in oil capture efficiency, with the maximum reduction even reaching 12%.

In response to the limitations regarding applicable pipe diameters and media in the study of two-phase flow in aviation engine scavenge pipe, a flow pattern identification method that integrates image features with neural networks has been proposed, offering an innovative solution for the analysis of intricate oil–gas flow states. A small-diameter oil–gas two-phase flow experimental system was developed, utilizing high-speed imaging technology to capture 1104 sets of images representing four distinct flow patterns. Following the feature selection criteria delineated in this study, 12 multidimensional feature parameters encompassing color, texture, and shape were extracted through various image processing techniques. Comparative validation revealed that the Elman neural network significantly outperforms the back propagation neural network in flow pattern identification, achieving an impressive accuracy of 97.06%. This research elucidates the mechanisms by which oil–gas media influence flow morphology through image analysis, effectively addressing the adaptability limitations of conventional water–gas models. The intelligent flow pattern identification framework constructed herein provides substantial data support for the structural optimization of aviation engine scavenge pipes, and its non-intrusive analytical characteristics hold considerable practical value in monitoring the flow states of lubrication systems.