This paper proposes a method for the detection and depth assessment of tiny defects in or near surfaces by combining laser ultrasonics with convolutional neural networks (CNNs). The innovation in this study lies in several key aspects. Firstly, a comprehensive analysis of changes in ultrasonic signal characteristics caused by variations in defect depth is conducted in both the time and frequency domains, based on discrete frequency spectra and original A—scan signals. Continuous wavelet transform (CWT) is employed to obtain wavelet time–frequency maps, demonstrating the consistent characteristics of this image with crack depth variations. A crucial innovation in this research involves the targeted design and optimization of the model based on the characteristics of ultrasonic signals and dataset size. This includes aspects such as data preparation, CNN architecture construction, and hyperparameter selection. The model is tested using a random validation set, which effectively demonstrates the CNN model’s validity and high precision. The proposed method enables the recognition and depth assessment of tiny defects on or near surfaces.

A CoCrNi-AlTi medium-entropy alloy was fabricated via laser powder bed fusion (L-PBF), and its microstructural evolution and mechanical response during aging at 500–900 °C for 1 h were systematically investigated. The as-built alloy exhibits a hierarchical microstructure consisting of elongated columnar grains and dislocation-rich cellular substructures, which is associated with an excellent strength–ductility combination (YS: 848 MPa, UTS: 1136 MPa, EF: 32.6%). Upon aging, a pronounced precipitation-hardening response is observed, with a peak hardness of 501 ± 7 HV and an ultimate tensile strength of 1429 MPa achieved at 800 °C. TEM and STEM-EDS analyses indicate that Ti preferentially segregates along dislocation networks and grain boundaries at early aging stages, promoting the heterogeneous nucleation of nanoscale Ni–Al–Ti–rich precipitates that effectively impede dislocation motion. At elevated aging temperatures, additional Cr-enriched regions with diffuse compositional partitioning are observed within the FCC matrix, occurring concurrently with the peak mechanical performance. Further aging at 900 °C leads to strength degradation, which is attributed to precipitate coarsening and recovery-induced dislocation annihilation. These results highlight the critical role of L-PBF-induced defect structures in governing precipitation behavior and the resulting strength–ductility trade-off during post-build heat treatment of CoCrNi-AlTi medium-entropy alloys.