Periodic inspection of fatigue cracks in welded steel oil storage tanks is critical for structural integrity. Conventional techniques, such as Magnetic Particle Testing, often necessitate costly and time-consuming coating removal, which generates industrial waste and increases downtime. To address these challenges, this study proposes a novel "Virtual ACFM-type Butterfly Plot Analysis" using Uniform Eddy Current (UEC) probes to enable high-accuracy crack evaluation through coatings without complex hardware. The butterfly plot is a well-known technique associated with Alternating Current Field Measurement (ACFM) probes. The proposed method derives a synthesized horizontal magnetic field signal, denoted as V^'_H , by spatially integrating the vertical magnetic field component, denoted as V_V , measured by a single detection coil of the UEC probe. This mathematical transformation facilitates the generation of ACFM-type "butterfly plots" from UEC signals. The effectiveness of this methodology was validated through finite element method simulations and experimental benchmarks on welded steel plates containing fatigue cracks. A significant advantage is that the integration process functions as a digital spatial filter, effectively mitigating high-frequency noise arising from surface roughness and improving the signal-to-noise ratio in the presence of complex weld bead geometries. Consequently, the synthesized V^'_H signal demonstrated a superior signal-to-noise ratio in detecting fatigue cracks in welded joints compared to direct physical V_H measurements obtained from conventional ACFM probes. The proposed method is highly synergistic with automated measurement systems, where the integration of precise spatial data from a scanner maximizes its diagnostic potential. Furthermore, by utilizing a signal feature plane derived solely from the V_V signal, it is possible to determine whether a detected crack requires repair without performing complex calculations. This research demonstrates that sophisticated ACFM-level diagnostics can be achieved using the UEC probe. Ultimately, the combination of the UEC probe and the proposed virtual butterfly plot analysis offers a robust, efficient, and cost-effective solution for the non-destructive evaluation of coated welded structures in industrial environments.
Accurate tool wear monitoring is essential for maintaining machining quality, productivity, and tool life during the dry turning of Inconel 718. Conventional image-based approaches and standalone convolutional neural networks (CNNs) may have difficulty distinguishing different wear stages because of similarities in wear morphology. To address these limitations, this study proposes FT-CAT Net (Fine-Tuned CNN–Attention Transformer Network), a hybrid nondestructive image-based framework that integrates fine-tuned CNN feature extraction with Transformer-based contextual attention for automated tool wear classification. Microscopic flank-wear images were collected during controlled dry-turning experiments using a Taguchi L27 experimental design and categorized into early-stage, intermediate, and severe wear according to the ISO 3685 VB_MAX criterion. Following preprocessing and data augmentation, the final dataset comprised 1,572 images, including 515 early-stage, 554 intermediate, and 503 severe-wear images.Four pretrained CNN backbones, namely AlexNet, GoogleNet, ResNet50, and VGG19, were evaluated for spatial feature extraction. Among these architectures, VGG19 achieved the best standalone CNN performance with an accuracy of 97.5
Ball Grid Array (BGA) packages are widely adopted in modern electronic systems due to their excellent interconnect density, compact footprint, and superior electrical performance. However, detecting hidden solder connections and guaranteeing assembly reliability has become much more challenging due to the gradual reduction in solder joint pitch and standoff height. The detection of fine-scale internal defects, such as micro-voids, delamination, and early-stage cracking, is still a challenge for conventional non-destructive testing (NDT) methods including X-ray imaging and infrared thermography, especially in high-density fine-pitch Ball Grid Array (FBGA) assemblies. This review critically examines existing inspection techniques for BGA and FBGA solder joint defect detection, with emphasis on their capabilities, limitations, and applicability in production-like environments. This paper specifically highlighted acoustic-based inspection methods, including scanning acoustic microscopy and emerging acoustic mapping approaches such as laser ultrasonic inspection, which offer high sensitivity to subsurface discontinuities and potential for contactless, high-resolution inspection. Recent developments in acoustic imaging, coupling techniques, and scanning modalities are discussed to address significant drawbacks inherent in conventional inspection methods. The review identifies current research gaps and outlines future directions toward rapid, high-resolution, and manufacturing-compatible acoustic inspection solutions for advanced electronic packaging.
Laser Powder Bed Fusion of Metal is a key additive manufacturing technology, but its industrial adoption is limited by inherent process imperfections. While in-situ non-destructive testing is essential, current monitoring methods face limitations. In-line active thermography, as a promising testing approach, faces significant challenges with overpowering reflections from the high-energy process laser, which can saturate sensors and mask faint, defect-related thermal emissions. This paper introduces a novel stroboscopic active thermography methodology designed to overcome this limitation. The approach utilizes the Synchronized Path Infrared Thermography dual scanhead setup, which employs the processing laser as a modulated thermal excitation source. This system is based on precise temporal gating of the acquisition of the IR camera: it isolates the desired thermal emission signal from interfering laser reflections, and it ensures that the same, specific segment of the material cooling curve is consistently sampled for every measurement point. The stroboscopic approach was validated on specimens with artificial subsurface defects. It successfully eliminates sensor saturation, providing a high-fidelity thermal signal for analysis. The system identifies voids with actual mean diameters as small as 111 m at depths of down to 40 m. The study also quantifies the technical boundaries of the method, where signal attenuation from thermal diffusion limits detection at 120 m depth to the largest defect measuring 977 m.
Veneer constitutes a critical structural component in engineered wood products such as plywood, laminated veneer lumber (LVL), and cross-laminated timber (CLT), which are extensively utilized in modern civil engineering infrastructure. However, the inherent heterogeneity and rapid growth of raw timber frequently introduce structural defects, including knots, cracks, and voids, that severely compromise the mechanical integrity and load-bearing capacity of the final assembly. Traditional non-destructive evaluation (NDE) methods and standard convolutional neural networks (CNNs) often fail to distinguish these structural anomalies from complex natural grain patterns, leading to potential safety risks in construction applications. To address these challenges, this paper proposes a material-property-aware feature co-evolution network named Veneer-AEPNet (VAEPNet), specifically engineered for the high-precision non-destructive grading of structural veneers. The architecture explicitly integrates a dual-stage Transformer mechanism to establish a global texture baseline, effectively identifying macro-scale topological deformations. Simultaneously, we introduce the Adaptive Anisotropic Granular Pooling (AAGP) module to capture directional fiber perturbations and the Global-Contrastive Feature Refinement (GCFR) module to suppress natural background noise by modeling deviations from a global texture reference. The methodology was validated on a large-scale industrial dataset containing 25,000 high-resolution images. Experimental results demonstrate that VAEPNet achieves a test accuracy of 94.47
