Incorporating coarse aggregates into ultra-high-performance concrete (UHPC-CA) can reduce material costs, yet reliably predicting its strength-related behavior and overall performance remains challenging. This study examines UHPC-CA through a two-stage orthogonal experimental program comprising 18 mixtures with coarse aggregate, fly ash, and hybrid fiber reinforcements (steel, polypropylene, and composite fibers). Microstructural characterization using scanning electron microscope (SEM) and X-ray computed tomography (X-CT) was conducted to assess interfacial features and crack evolution and to link these observations to the measured mechanical response. Experimentally, fiber reinforcement markedly enhanced post-cracking performance. Compared with the fiber-free control mixture, the optimal hybrid configuration increased flexural strength from 6.9 to 23.5 MPa and compressive strength from 60.1 to 90.5 MPa. The steel–composite fiber system outperformed the steel–polypropylene system, which is consistent with the tighter composite-fiber interfacial bonding observed by SEM/X-CT and supports the feasibility of partially substituting steel fibers. An artificial neural network (ANN) model trained on 50 mixtures and evaluated on 10 unseen mixtures achieved an R2 of 0.9703, an MAE of 1.22 MPa, and an RMSE of 2.11 MPa for compressive strength prediction, enabling sensitivity assessment under multi-factor coupling. Overall, the proposed experiment–characterization–modeling framework provides a data-driven basis for performance-oriented mix design and rapid screening of UHPC-CA.
The clevis-grip tensile test is usually employed to evaluate the mechanical properties of textile reinforced concrete (TRC) composites, which is actually a bond test and is unsuitable for determining reliable design parameters. Thus, the clevis-grip tensile test needs further improvement to obtain foreseeable results concerning TRC tensile behavior. This paper presents the experimental results of twenty-one tension tests performed on basalt TRC (BTRC) thin plates with different test setups, i.e., clevis-grip and improved clevis-grip, and with different textile ratios. The influences of test setups and textile ratios on crack patterns, failure mode, and tensile stress-strain curves with characteristic parameters were analyzed in depth to judge the feasibility of the new test setup. The results indicated that with the new test setup, BTRC composites exhibited textile rupture at failure; in addition, multi-cracks occurred to the BTRC composites as the textile ratio exceeded 1.44%. In this case, the obtained results relied on textile properties, which can be considered reliable for design purposes. The modified ACK model with a textile utilization rate of 50% provided accurate predictions for the tensile stress-strain behavior of the BTRC composite derived from the improved test setup. The proposed test setup enables the adequate utilization of BTRC composite and the reliability of obtained results related to the occurrence of textile rupture; nevertheless, further work is required to better understand the key parameters affecting the textile utilization rate, such as the strength of the concrete matrix.