The relief groove is the most effective measure to alleviate oil trapping of gear pumps; therefore, its design directly affects the working efficiency and service life of the gear pump. This paper presents a performance analysis method for relief grooves based on computational fluid dynamics. A comparative study was conducted to evaluate the performance of different structural forms of relief grooves, focusing on technical indicators such as trapped oil pressure, gas volume fraction, outlet flow rate, and the flow rate non-uniformity coefficient. The results show that the relief groove F, with a flow non-uniformity of only 5.25% and a trapped oil pressure peak of 18 MPa, outperforms the rectangular, circular, and unloading slot E in terms of overall performance, exhibiting advantages of low trapped oil pressure, high volumetric efficiency, and high flow quality. These characteristics make it well-suited for the design of high-speed and high-pressure fuel gear pumps. In addition, increasing the size of the relief groove and positioning it towards the low-pressure chamber can reduce cavitation, oil entrapment, and flow pulsation. Designing the new unloading slot F with these factors in mind can improve its overall performance.

As a typical thin-walled part of aviation, blade is prone to elastic deformation and machining residual stress deformation in the process of milling, which affects the machining accuracy and quality of blade. To address the deformation mechanism modeling problem of complex machining process of blade and the data-driven model prediction problem relying on limited collected samples, a mechanism-guided Sparrow optimized Extreme Learning Machine (SSA-ELM) thin-walled blade machining deformation prediction model is established. Firstly, the machining deformation mechanism model of thin-walled blade considering elastic deformation and machining residual stress deformation is established. Secondly, the Extreme Learning Machine Neural Network (ELMNN) is designed, and the Sparrow Search Algorithm (SSA) is used to optimize the parameters of the ELMNN hidden layer network. Then, the dataset of the data-driven model is constructed, and the Monte Carlo simulation is used to enhance the processed deformation data samples to establish the data-driven model. Finally, the mechanism-guided SSA-ELM is used to predict the thin-walled blade machining deformation, and the root mean square error and correlation coefficient of the machining deformation are used as the model accuracy evaluation index. The results show that the root mean square error of the mechanism guided and SSA optimized machining deformation prediction model is reduced by 77.25% and 30.5% respectively, which proves that the model has good prediction performance.