Continuous fiber-reinforced composite manufactured by additive manufacturing (CFRC-AM) offers opportunities for printing lightweight materials with high specific strength. However, their performance is sensitive to the interaction of process and material parameters, making exhaustive experimental testing impractical. In this study, we introduce a data-efficient, multi-input, multi-target learning approach that integrates Latin Hypercube Sampling (LHS)-guided experimentation with a squeeze-and-excitation wide and deep neural network (SE-WDNN) to jointly predict multiple mechanical and manufacturing properties of CFRC-AMs based on different manufacturing parameters. We printed and tested 155 specimens selected from a design space of 4, 320 combinations using a Markforged Mark Two 3D printer. The processed data formed the input-output set for our proposed model. We compared the results with those from commonly used machine learning models, including feedforward neural networks, Kolmogorov-Arnold networks, XGBoost, CatBoost, and random forests. Our model achieved the lowest overall test error (MAPE = 12.33%) and showed statistically significant improvements over the baseline wide and deep neural network for several target variables (paired t-tests, p ≤ 0.05). SHapley Additive exPlanations (SHAP) analysis revealed that reinforcement strategy was the major influence on mechanical performance. Overall, this study demonstrates that the integration of LHS and SE-WDNN enables interpretable and sample-efficient multi-target predictions, guiding parameter selection in CFRC-AM with a balance between mechanical behavior and manufacturing metrics.

Foreign Objects (FO) within an aircraft fuel tank present a serious risk of damage and possible catastrophic loss of the aircraft. As such, aircraft manufacturers place great emphasis on the thorough inspection of fuel tanks before they are closed and sealed. If a FO was left undetected in the tank then it could migrate throughout the fuel system due to phenomenon such as aircraft maneuvers and fuel sloshing and could potentially clog filters and pumps, block fuel tubes, or create structural damage which could harm the integrity of the aircraft. While industry carefully develops the physical inspection techniques for the fuel tank and implements preventive actions to mitigate the entry of FO into the tank during manufacture, there is no documented analysis about how the FO could move throughout the fuel system. In fact, current computational fluid dynamic (CFD) analysis of fuel systems is built on the assumption of FO-free fluid, and finite element methods (FEM) treat the fuel system as a solid body. This paper will propose a representative aircraft fuel tank design and create a methodology for evaluation of FO migration within that fuel tank. The methodology will include physical experimentation of a fuel tank prototype and documentation of FO migration characteristics for distinct types of FO and present the FO migration results expressed in terms of risk. Additionally, a simulation approach will be created to analyze not only fluid flow, but also the movement of a FO within that fluid flow. These results will enable a new understanding of how FO impacts an aircraft fuel system which can be useful for future FO-resilient fuel tank design and safer aircraft operation.