Additive manufacturing (AM) is widely used in industries such as aerospace, medical, and automotive. Within this domain, defect detection technology has emerged as a critical area of research focus in the quality inspection phase of AM. The main challenge lies in that under extreme lighting conditions, strong reflected light obscures defect feature information, leading to a significant decrease in the defect detection rate. This paper introduces a novel methodology for intelligent defect detection in AM components with reflective surfaces, leveraging virtual polarization filtering (IEVPF) and an improved YOLO V5-W model. The IEVPF algorithm is designed to enhance image quality through the virtual manipulation of light polarization, thereby improving defect visibility. The YOLO V5-W model, integrated with CBAM attention, DenseNet connections, and an EIoU loss function, demonstrates superior performance in defect identification across various lighting conditions. Experiments show a 40.3% reduction in loss, a 10.8% improvement in precision, a 10.3% improvement in recall, and a 13.7% improvement in mAP compared to the original YOLO V5 model. Our findings highlight the potential of combining virtual polarization filtering with advanced deep learning models for enhanced AM surface defect detection.

Aiming at the key technology of defect detection in precision additive manufacturing of highly reflective metal materials, this study proposes an enhanced SCK-YOLOV5 framework, which combines polarization imaging and deep learning methods to significantly improve the intelligent identification ability of small metal micro and nano defects. This framework introduces the SNWD (Selective Network with attention for Defect and Weathering Degradation) Loss function, which combines the SIOU Angle Loss with the NWD distribution sensing characteristics. It is specially designed for automatic positioning and identification of micrometer hole defects. At the same time, we employ global space construction with a dual-attention mechanism and multi-scale feature refining technique with selection kernel convolution to extract multi-scale defect information from highly reflective surfaces stably. Combined with the polarization imaging preprocessing and the comparison of enhancement defects under high reflectivity, the experimental results show that the proposed method significantly improves the precision, recall rate, and mAP50 index compared with the YOLOv5 baseline (increased by 0.5%, 1.2%, and 1.8%, respectively). It is the first time that this improvement has been achieved among the existing methods based on the YOLO framework. It creates a new paradigm for intelligent defect detection in additive manufacturing of high-precision metal materials and provides more reliable technical support for quality control in industrial manufacturing.

Calcium fluoride (CaF₂) crystals are widely utilized in deep-ultraviolet (DUV) lithography due to their excellent optical properties. The laser-induced degradation and damage of CaF₂ crystals is a critical concern that restricts its extended application. Impurities of CaF₂ crystal are considered a key factor affecting its laser resistance. Establishing the quantitative relationship and mechanism of impurity content impacting the degradation and damage characteristics of CaF₂ crystal is essential. This study investigated the characteristics of different impurity contents affecting the degradation and laser-induced damage thresholds (LIDTs) of CaF₂ crystals under X-ray and 193 nm pulsed laser irradiations, and quantitatively analyzed the degradation process and mechanism. Our findings demonstrate that impurities at ppm levels significantly diminish the transmittance of CaF₂ crystals across various wavelengths following X-ray irradiation. In contrast, these impurities have a negligible effect on the LIDT test results, suggesting distinct damage mechanisms between X-ray and laser irradiation. This study provides valuable insights for optimizing the CaF₂ crystal fabrication process and enhancing irradiation resistance.

In this study, we examine the characteristics of laser-induced periodic surface structures (LIPSSs) fabricated on N-doped 4H-SiC (N-SiC) and high-purity 4H-SiC (HP-SiC) crystals using femtosecond–picosecond lasers. The effects of various laser parameters on the orientation, size, and morphology of the LIPSS are systematically investigated. The results reveal that, under identical laser irradiation conditions, the area of LIPSS on both N-SiC and HP-SiC increases linearly with the number of pulses, with N-SiC exhibiting a higher growth coefficient. Furthermore, analysis of differences in photothermal weak absorption and electric field modulation during the LIPSS fabrication process indicates that distinct SiC crystals yield varied LIPSS formation outcomes. This work not only elucidates the underlying physical mechanisms governing LIPSS formation on different silicon carbide crystal surfaces but also provides valuable guidance for precisely controlling the size and orientation of LIPSS regions on various 4H-SiC substrates.

Silicon carbide (SiC) single crystals are extensively utilized in various fields due to their exceptional properties, such as a wide bandgap and a high breakdown threshold. Nevertheless, the intrinsic high hardness of SiC creates significant challenges for contact machining. This study investigates the surface damage characteristics and underlying mechanisms involved in processing both high-purity silicon carbide (HP-SiC) and nitrogen-doped silicon carbide (N-SiC) crystals using fundamental-frequency nanosecond pulsed lasers. This study establishes a laser-induced damage threshold (LIDT) testing platform and employs the internationally standardized 1-ON-1 test method to evaluate the damage characteristics of HP-SiC and N-SiC crystals under single-pulse laser irradiation. Experimental results indicate that N-SiC crystals exhibit superior absorption characteristics and a lower LIDT compared with HP-SiC crystals. Subsequently, a defect analysis model was established to conduct a theoretical examination of defect information across various types of SiC. Under fundamental-frequency nanosecond pulsed laser irradiation, N-SiC crystals demonstrate a lower average damage threshold and a broader defect damage threshold distribution than their HP-SiC counterparts. By integrating multi-dimensional analytical methods—including photothermal weak absorption mechanisms and damage morphology analysis—the underlying damage mechanisms of the distinct SiC forms were comprehensively elucidated. Moreover, although N-SiC crystals show weaker photothermal absorption properties, they exhibit more pronounced absorption and damage response processes. These factors collectively account for the different laser damage resistances observed in the two types of silicon carbide crystals, implying that distinct processing methodologies should be employed for nanosecond pulsed laser treatment of different SiC crystals. This paper elucidates the damage characteristics of various SiC materials induced by near-infrared nanosecond pulsed lasers and explores their underlying physical mechanisms. Additionally, it provides reliable data and a comprehensive mechanistic explanation for the efficient removal of these materials in practical applications.