Journal of Nondestructive Evaluation最新文献

Reliable detection of aero-engine blade surface defects is hindered by weak defect saliency, long-tailed category imbalance, and strong geometric priors from curved surfaces. This paper proposes MSFF-YOLO, a multi-scale feature fusion framework built upon YOLOv11. The method integrates a Multi-scale Efficient Aggregation Module (MEAM) for enhancing subtle and edge-attached defects, a multi-scale FMSIoU loss for improving regression robustness under long-tailed distributions, and a Manhattan Self-Attention (MaSA) mechanism for modeling curvature-related spatial dependencies. Evaluated on the high-resolution AeBSDD dataset, MSFF-YOLO achieves an mAP₅₀ of 89.1%, surpassing YOLOv11 especially on nick, bent, and dent defects. Real-world illumination-disturbance tests and zero-shot evaluation on NEU-DET further verify its strong cross-scene and cross-domain generalization, demonstrating its robustness for industrial blade inspection.

Detection of defects in diverse domains requires a specialized object detection system capable of identifying various types of flaws of different sizes and shapes. This research addresses detection challenges across six critical domains: saline bottle level monitoring, screw defect detection, magnetic tile inspection, road crack analysis, fabric flaw identification, and potato leaf disease recognition. These applications exhibit unique visual characteristics, including variable defect morphologies, subtle texture variations, and domain-specific features, which conventional detection models often fail to adequately address. Standard Faster R-CNN implementations with ResNet-50 and VGG-16 backbones offer general feature extraction but lack domain-specific optimization for these specialized applications. We propose LightDefectNet-18, a custom CNN backbone for Faster R-CNN featuring dual residual blocks with skip connections, strategic kernel sizing, and progressive channel expansion, integrated with a Feature Pyramid Network (FPN) architecture. The FPN component creates a multi-scale feature hierarchy through top-down pathways and lateral connections, effectively detecting defects across scales. The architecture incorporates batch normalization layers, calibrated dropout, and proper weight initialization to enhance feature preservation and gradient flow. When integrated with Faster R-CNN, we implement refined anchor configurations optimized for multi-scale defect detection across our target applications, with tailored anchor sizes and aspect ratios for each pyramid level. The detection pipeline employs an adaptive optimization strategy with learning rate scheduling and early stopping mechanisms. The quantitative evaluation demonstrates superior detection performance across all target applications compared to standard backbones, with significant improvements in Average Precision using a relaxed IoU threshold specifically calibrated for industrial defect detection scenarios. The model's FPN-enhanced architecture effectively addresses the challenges of capturing fine-grained visual features essential for distinguishing subtle anomalies at multiple scales in specialized materials while maintaining computational efficiency suitable for deployment in real-world industrial and agricultural monitoring systems, even with limited training data.

The prediction of fracture and progressive damage in solid materials can be assessed with acoustic emission (AE) monitoring, yet most quantitative AE-stress/strain relationships remain largely empirical. In this work, we present a unified stochastic framework that derives and generalizes these relationships from a microfailure distribution. By modeling the temporal occurrence of microfailures as a stochastic Poisson process, we establish direct statistical connections between AE activity and macroscopic mechanical variables such as stress and strain. This perspective allows us to reinterpret proposed empirical AE laws as particular statistical regimes, while also advancing a generalized formulation capable of capturing more complex behaviors often observed under dynamic loading. Extensive stochastic simulations further reveal that simple assumptions about internal deterioration rates naturally lead to heuristic quantitative laws for the number of AE events, thereby grounding empirical observations in probabilistic reasoning. The framework is validated against experimental datasets from cortical bone and collagenous soft tissue, confirming its robustness and predictive capacity. Beyond providing a rigorous theoretical foundation for empirical AE laws, our results demonstrate how microlevel statistical assumptions can explain macroscopic fracture signatures, offering new tools for structural health monitoring and prediction of fractures.

Steel defects can significantly diminish the corrosion resistance, wear resistance, and load-bearing capacity of the steel, leading to substantial financial losses. To effectively identify and locate steel surface defects, we propose a cross-scale feature fusion network. The process begins with the pre-processing of the input image through gray transformation and histogram equalization, followed by feature extraction using an enhanced backbone feature extraction network. Subsequently, a feature fusion network incorporating a gather-and-distribute (GD) structure is introduced to merge multi-scale feature maps, improving the robustness of information fusion across different scales. In the final stage, three detection heads of varying sizes undergo processing by a convolution module with a coordinate attention mechanism. The efficacy of the proposed method is validated using the Northeastern University surface defect database (NEU-DET) dataset, with experimental results demonstrating that the network achieves an 84.7% mean average precision (mAP) at an intersection over union (IoU) threshold of 0.5. Noteworthy contributors to the mAP of the proposed network include the image pre-processing module, the improved feature extraction network, the gather-and-distribute feature fusion network, and the detection network, contributing 4.1%, 2.9%, 2.6%, and 0.2%, respectively. The comparative experiments based on the attention mechanisms illustrate that the Squeeze-and-Excitation (SE) mechanism is the most suitable mechanism for the model proposed in this paper compared to other mainstream attention mechanisms. In comparison with other deep learning networks, our network demonstrates a significant enhancement in detection capability, showcasing superior performance in the identification of steel surface defects.

We present a note on the implementation and efficacy of a box-constrained (L_1/L_2) regularization in numerical optimization-based approaches to performing tomographic reconstruction from a single projection view. The constrained (L_1/L_2) minimization problem is constructed and solved using the Alternating Direction Method of Multipliers (ADMM). We include brief discussions of parameter selection, as well as detailed numerical comparisons with relevant alternative methods. In particular, we benchmark against a box-constrained TVmin and an unconstrained Filtered Backprojection in both cone-beam and parallel-beam (Abel) forward models. We consider both a fully synthetic benchmark and reconstructions from X-ray radiographic image data.

This paper presents an integrated non-destructive evaluation method for monitoring thermal aging in P91 steel by analyzing magneto-acoustic emission (MAE) signals through wavelet packet transform (WPT). Samples were thermally aged for 0–600 h at 780 °C and tested under controlled excitation conditions of 30 V and 30 Hz. The resulting MAE signals were processed using level-3 WPT decomposition to obtain energy distribution ratio (EDR%) features across multiple frequency bands. These frequency-domain features were compared with changes in hardness, tensile properties, and impact energy, as well as metallographic observations showing a transition from fine-lath martensitic to coarsened ferritic structures. Lower-frequency energy (Node 0, 0–125 kHz) increased during early aging and then declined due to precipitate coarsening and boundary pinning, while mid-frequency energy (Node 1) showed complementary trends associated with evolving domain-wall interactions. Although the dataset is limited (n = 4), Pearson correlation and linear regression further confirmed that Node-specific EDR% tracks progression of mechanical degradation. Overall, the findings demonstrate that WPT-based MAE analysis offers a sensitive and practical approach for non-destructive condition monitoring of thermally aged P91 steel components.

As critical sealing components in well control equipment, the preload uniformity of flange bolt connections significantly influences the reliability of metal seals under high-pressure dynamic service conditions. However, non-uniform stress distributions in bolt groups caused by complex external loads can compromise sealing contact stress, thereby affecting the sealing performance. Existing detection methods have difficulties in accurately characterizing bolt stress states under coupled complex loads such as eccentric loading. This paper develops a combined magnetic-acoustic bolt stress detection system based on magnetic stress measurement and acoustoelastic effects. Laboratory experiments were conducted to validate an integrated methodology for identifying complex bolt stress states. Field tests under eccentric loading conditions show that the relative error between magnetic and acoustic axial stress measurements is below 6%. Under non-uniform preload and bending loads, magnetic stress measurements were used to identify linear axial stress evolution during elastic-stage pressurization, stress variation disparities, and tensile-compressive stress asymmetry on individual bolts.

X-ray computed tomography (CT) is a non-invasive diagnostic technology that has been widely used for various clinical applications. However, CT image quality becomes severely degraded when the X-ray dose is reduced. To reconstruct high-quality low-dose CT image, we present a sub-pixel anisotropic diffusion (SAD) for statistical iterative reconstruction (SIR), based on the penalized weighted least-squares (PWLS) model, termed as PWLS-SAD. Specifically, the SAD uses sub-pixel difference as a generalized form of the first-order derivative, replacing the original first-order derivative in anisotropic diffusion. An alternative minimization algorithm is used to solve the associated objective function. XCAT phantom simulations, anthropomorphic torso phantom measurements, and clinical data were used for the experiment. Experimental results show that PWLS-SAD technique achieves superior performance compared to competing methods, particularly in terms of suppressing image noise, enhancing the visibility of low-contrast structures, and maintaining edge detail.

Lightweight expanded vermiculite (EV) mortars based on calcium sulfoaluminate (CSA) cement are promising for high temperature applications. However, predicting their residual strength after moderate thermal exposure (70–100℃) remains challenging. This study employs advanced acoustic emission (AE) monitoring and machine learning (ML) to address this. The key contributions are twofold: First, a novel Radial Basis Function (RBF) kernel-based approach has been introduced to dynamically classify failure modes in RA-AF analysis, overcoming the limitations of fixed threshold approaches. Second, a newly developed grouped Gaussian noise (GGN) technique has been used to augment the dataset, which has improved the performance of the LightGBM (LGBM) regression model. Experimental results indicate that while EV content reduces flexural strength, heating at 100℃ restores it by up to 48%, likely due to the formation of crack-filling hydration products. The RBF-refined AE analysis reveals a distinct transition from tensile to shear-dominated failure with accumulating damage. The optimized LGBM model, trained on GGN-augmented data, achieved high prediction accuracy (R² = 0.99, MAE = 0.18, MSE = 0.06), outperforming other mainstream models. This work proposes a combined diagnostic-predictive framework for assessing lightweight EV mortars under moderate thermal stress.