This review systematically examined the transformative role of machine learning in predicting polymer aging lifetime, addressing critical limitations of conventional methods such as the Arrhenius model, time–temperature superposition principle, and numerical fitting approaches. The primary objective was to establish a comprehensive framework that integrates multi-mechanism coupling with dynamic data-driven modeling to enhance prediction accuracy across complex aging scenarios. Four key machine learning categories demonstrate distinct advantages: support vector machines effectively capture nonlinear interactions in multi-stress environments; neural networks enable cross-scale modeling from molecular dynamics to macroscopic failure; decision tree models provide interpretable feature importance quantification; and hybrid approaches synergistically combine complementary strengths. These methodologies have shown significant success in critical industrial applications, including building trades, photovoltaic systems, and aerospace composites, creating an integrated predictive system that bridges molecular-level dynamics with service-life performance. By transforming life prediction from empirical extrapolation to mechanism-based simulation, this machine-learning-driven paradigm offers robust methodological support for engineering safety design in diverse polymer applications through its capacity to model complex environmental interactions, adapt to real-time monitoring data, and elucidate underlying degradation mechanisms.

To investigate the static performance of precast segmental hollow piers, two precast segmental hollow pier specimens were designed for static loading tests on the top of piers. The finite element model of precast segmental hollow piers was established by the finite element software Abaqus and verified based on the test results. Based on the experimental and finite element models, three optimal design solutions were proposed, and the calculation results of each solution were analyzed. The results show that precast segmental hollow pier mechanical behavior is similar to that of cantilevered bending members. The specimens present brittle damage characteristics after the destruction of the structure at the bottom of the pier pressure edge as the axis of the rigid body rotation. Following the test loading process, the bonding between the segments is good, except for the pier bottom damage surface of the rest of the bonding surface, which has no relative displacement. The calculation results of the finite element model are in good agreement with the test results and can effectively predict the load–displacement response of precast piers. Three optimized design solutions are proposed. The finite element simulation proves all three optimized design solutions show better overall ductility than the original solution and can effectively improve the performance of segmental precast hollow piers.

In civil engineering, with the increasing demand for structural reinforcement and renovation projects, polymer-rich anchoring adhesives have attracted much attention due to their performance advantage of having high strength and have become a key factor in ensuring the safety and durability of buildings. In this study, polymer-rich anchoring adhesives underwent three artificial aging treatments (alkali medium, hygrothermal, and water bath) to evaluate their aging performance. Alkali treatment reduced bending strength by up to 70% (sample 5#) within 500 h before stabilizing, while hygrothermal and water-curing treatments caused reductions of 16–51% and 15–77%, respectively, depending on adhesive composition. Dynamic thermomechanical analysis revealed significant loss factor decreases (e.g., epoxy adhesives dropped from >1.0 to stable lower values after 500 h aging), indicating increased rigidity. Infrared spectroscopy confirmed chemical degradation, including ester group breakage in vinyl ester resins (peak shifts at 1700 cm⁻¹ and 1100 cm⁻¹) and molecular chain scission in unsaturated polyesters. The three test methods consistently demonstrated that 500 h of aging sufficiently captured performance trends, with alkali exposure causing the most severe degradation in sensitive formulations (e.g., samples 5# and 6#). These results can be used to establish quantitative benchmarks for adhesive durability assessment in structural applications.

By applying the Schmidt hammer rebound (SHR) method and the Leeb hardness method for nondestructive testing (NDT) and localized sampling analysis of stone materials, this study carefully selected suitable experimental parameters to assess the mechanical properties of the stone materials. Based on these findings, a bridge was established between field testing and laboratory analysis, leading to a comprehensive set of on‐site NDT techniques for evaluating the strength of stone materials. Under simulated real‐world conditions, the load‐bearing capacity of the simulated components in the dry‐hanging stone system was assessed and compared with the technical specifications outlined in current standards by analyzing the bending test results of the stone materials, the flexural and shear strengths were determined, thus validating the intrinsic link between the hardness of the stone materials and the load‐bearing capacity of the dry‐hanging stone system. Consequently, a systematic approach for inspecting and assessing the load‐bearing capacity of the dry‐hanging stone system was formulated.