This paper presents an experimental investigation of the shear behavior of steel beam-to-column connections with unequal depth of outer annular stiffener. The depth-to-thickness ratio ($D:t$ ) of the hollow structural section (HSS) column, the beam depth ratio ($D_{b2}:D_{b1}$ ), and two sizes of outer annular stiffener are considered. This test involves seven cruciform connections subjected to lateral cyclic loading with vertical displacements imposed at the end of beams. The failure modes, hysteretic performance, strength and stiffness degradation, shear deformation, and energy dissipation of panel zone are estimated. The experimental results indicated that the whole panel exhibited large hysteretic loops, excellent ductility, and energy dissipating capacity. Due to the effect of the beam depth ratio, the tested specimens formed two types of failure modes: shear buckling of the whole panel and shear buckling of the primary panel at the column web between two beams.

Multiaxial fatigue failure of metals, a common issue in industrial production, often leads to significant losses. Recently, many researchers have applied deep learning methods to predict the multiaxial fatigue life of metals, achieving promising results. Due to the high costs of fatigue testing, training data for deep learning is scarce and labor-intensive to collect. This study meets this need by creating a large-scale, high-quality dataset for multiaxial fatigue life prediction, consisting of 1167 samples from 40 materials collected from literature. The dataset includes key mechanical properties (elastic modulus, yield strength, tensile strength, Poisson’s ratio) and 48 loading paths, along with additional relevant information (composition ratios, processing conditions). Common deep learning models validated the dataset’s effectiveness. This dataset aims to support researchers applying deep learning to fatigue life prediction, addressing the long-standing issue of data scarcity, thereby advancing the intersection of artificial intelligence and metal fatigue research.