Seawater sea sand-engineered cementitious composites (SS-ECCs) provide a potential solution to the shortage of freshwater and sand resources for coastal and offshore construction. However, systematic studies on the combined effects of fiber parameters in SS-ECC systems remain limited. This study examines the effects of polyethylene (PE) fiber content (0%, 1%, 1.5%, and 2%) and length (12 mm, 18 mm, and 24 mm) on the mechanical properties of SS-ECC via compressive, tensile, and bending tests. The results indicate that increasing the volume fraction of PE fibers effectively enhances the tensile strength, flexural strength, and flexural toughness of SS-ECC. SS-ECC attained its highest tensile strength with a 24 mm PE fiber length, showing increases of 41.1% and 44.2% over specimens with 12 mm and 18 mm fibers, respectively. Furthermore, based on 28-day curing, the utilization of seawater and sea sand led to increases in tensile and flexural strengths by 12.3% and 17.2%, respectively, relative to ECC prepared with freshwater and river sand, though it resulted in a reduction in toughness. A predictive model for tensile strength is established considering the characteristic value of PE fiber with an R² of 0.8461, indicating reasonable correlation within the tested range. Results from this paper can help to develop a favorable PE fiber-reinforced SS-ECC for ocean engineering.

This study investigates the compressive performance of fiber-reinforced polymer (FRP) rebar-reinforced Seawater and Sea Sand Concrete (SSC) columns through an integrated approach combining finite element analysis, theoretical derivation, and machine learning. Finite element models were developed to quantify the influence of key parameters on the ultimate bearing capacity and lateral deflection. The results indicate that the compressive capacity decreases significantly with increasing eccentricity and slenderness ratio. Columns reinforced with steel rebars demonstrated superior load-bearing and anti-lateral displacement capabilities compared to their FRP-reinforced counterparts. A theoretical formula for predicting the compressive capacity was derived; however, it systematically overpredicted the experimental measurements by approximately 36%. To develop data-driven predictive models for the ultimate load capacity of FRP–SSC columns, four machine learning models, backpropagation neural network (BPNN), bootstrap aggregating BPNN (Bagging-BP), genetic algorithm-optimized BPNN (GA-BP), and gradient boosting regression trees (GBRT), were employed. Using sectional dimension, concrete strength, reinforcement parameters, eccentricity, and slenderness ratio as inputs, the validation sets of the models achieved R-values of 0.942, 0.918, 0.933, and 0.990, respectively. Feature importance analysis based on SHAP identified eccentricity as the most influential parameter. Results from this work can help to understand the behavior of FRP–SSC columns under compression.

The strengthening of intermediate-length concrete-filled steel tubular (CFST) columns using CFRP has attracted growing attention, but the effect of fibre orientation on the axial compressive behaviour—particularly for members where stability rather than strength governs—has not been fully clarified. This study therefore addressed the issue through a combined experimental, numerical, and analytical approach. Specimens were divided into four groups: unstrengthened controls, those with four longitudinal CFRP layers, those with four hoop layers, and a hybrid group with two longitudinal plus two hoop layers. All were tested under monotonic axial compression. The ultimate load-carrying capacity was enhanced by 23.0%, 20.5%, and 8.4% for the longitudinal, hybrid, and hoop-only CFRP wrapping schemes, respectively. These findings indicate that the strengthening efficiency is likely governed by the wrapping configuration under the conditions examined in the present test programme. Unstrengthened columns exhibited local buckling of the steel tube and crushing of the concrete core, a brittle failure mode. Longitudinal CFRP participated directly in load resistance and raised the flexural stiffness, thus effectively suppressing global buckling—the critical mode for intermediate-length columns. The hybrid configuration provided a reasonable strength gain and exhibited a relatively gentle descending branch together with favourable deformation compatibility. Hoop-only confinement, however, contributed little to stability improvement because it only provided lateral restraint without affecting bending resistance. A three-dimensional finite element model was constructed in ABAQUS, and its predictions of failure modes, load–displacement curves, and ultimate loads agreed well with the experimental data, confirming its reliability. Parametric studies using this model further revealed that the axial capacity decreased markedly with increasing slenderness ratio, whereas higher concrete and steel strengths both led to steady improvements. Finally, a simplified design formula was derived for the axial compressive capacity of CFRP-confined circular CFST intermediate-length columns. This formula includes a confinement efficiency coefficient that reflects the wrapping pattern and a stability coefficient suitable for intermediate-length members. Comparisons with both experimental and numerical results demonstrated that the proposed formula yields predictions within ±5% of the present dataset. The formula is applicable to circular CFST intermediate-length columns with 40 ≤ λ ≤ 80, concrete grades of C30–C50, steel grades of Q235–Q460, and the three wrapping configurations examined herein. Extension to slenderness ratios below 40 requires further validation, since the present tests and parametric study did not cover this range. Further independent validation is warranted prior to its adoption in general design.

This study investigates the time-dependent compressive behavior of seawater sea-sand concrete (SSC) and establishes intelligent prediction models for its evaluation. SSC samples with three strength grades (C30, C40, and C60) were fabricated and tested at curing ages of up to 720 d, accompanied by microstructural characterization. A database containing 344 compressive-strength records was compiled from the present experiments and published literature. Four models were developed and compared, including a back-propagation (BP) neural network, a genetic algorithm-optimized BP (GA-BP) network, a Bagging-BP ensemble model, and a gradient boosting regression tree (GBRT) model. Model interpretability was further examined using SHapley Additive exPlanations (SHAP). The results indicate that SSC exhibits rapid early-age strength gain, while moderate fluctuations may occur during middle and later curing periods. Strength–elastic modulus relationships were established for SSC and showed satisfactory fitting accuracy, with R² values exceeding 0.80. Among the investigated models, GA-BP demonstrated favorable predictive performance under the adopted data split, achieving the lowest root mean square error with R = 0.9413. SHAP interpretation highlighted curing duration and water-to-cement ratio as the dominant factors governing compressive strength. Overall, the proposed GA-BP model can serve as a useful reference for SSC strength prediction and mix-design optimization within the current dataset.