With a higher operation temperature, the conventional aero-turbine single web disk (SWD) has reached its limits. The twin-web disk (TWD) has been designed as a breakthrough, which has an expected performance in weight loss, strength and heat transfer efficiency. However, the lack of investigation on the position of the cooling air inlet is slowing down further application of TWD. Therefore, for a further study, inlet position optimization with maximum average Nusselt number is conducted for TWD flow structure study. The average Nusselt number result shows that the TWD has a better performance in heat transfer. All the works, including modeling and analyzing, can be referred for engineering design. And the conclusions obtained in this paper could be valuable for the future improvement of the TWD.

Kinship verification using facial information determines whether two faces share a familial relationship. Existing methods improve verification by leveraging negative sample information and addressing distribution differences but often extract independent features from parent and child images separately, ignoring variations in pairwise similarity. To overcome this, we propose CI3Former, a Swin-Transformer-based model that enables cross-image information interaction for joint feature extraction. By incorporating a Self-Attention based Interaction (SAI) module within each Swin-Transformer block, our method allows mutual querying between parent and child features, dynamically guiding region-level feature extraction and adaptively focusing on similar regions. Additionally, we introduce a Multi-metric Similarity based Interaction (MSI) module for feature fusion, which processes paired features through similarity measurements before final prediction. The model is trained with contrastive and binary cross-entropy losses to enhance coupled feature learning. Extensive experiments on four kinship verification datasets and a signature verification dataset demonstrate that CI3Former outperforms state-of-the-art methods, showcasing its effectiveness, robustness, and strong cross-task generalization.