Search Results (670)

To address the issues of low accuracy, high false positives, and missed detections in hot-rolled strip steel surface defect inspection, this paper proposes an improved detection model named DFEM-NET based on YOLOv8n. First, an efficient feature extraction module (DSC2f) based on Dynamic Snake Convolution is designed to enhance the model’s capability in capturing features of irregular and elongated defects. Second, a Feature Pyramid Shared Convolution module (FPSC) is constructed to expand the model’s receptive field and effectively suppress interference from complex backgrounds. Third, an Enhanced Feature Correction (EFC) strategy is adopted during the feature fusion stage to help the model better learn the detailed features of small defect targets. Finally, a Multi-Scale Attention Aggregation module (MSAA) is introduced before the detection head, enabling the network to focus on critical feature information and thereby comprehensively improve detection accuracy for target defects. Experimental results demonstrate that, compared to the baseline model YOLOv8n, DFEM-NET achieves a detection accuracy (mAP@0.5) of 83.5%, representing an increase of 4.8%; a recall rate of 76.4%, an increase of 3.3%; and a precision of 84.7%, an increase of 3.1%, without a significant increase in model complexity. Furthermore, generalization experiments conducted on the GC10-DET dataset confirm that the proposed algorithm exhibits exceptional generalization capability. Full article

Laser-based Powder Bed Fusion (LPBF) enables the fabrication of complex metal components but often results in high porosity and microdefect densities, compromising fatigue performance despite acceptable static properties. Standard fatigue characterisation methods are time-consuming and costly and yield scattered results due to defect-induced brittleness and residual stresses. This study investigates the application of thermographic techniques as a rapid alternative for evaluating the intrinsic fatigue behaviour of tensile coupons fabricated by LPBF employing AISI 316L steel. By monitoring surface temperature during stepwise static monotone and fatigue loading, thermographic methods aim to detect early hints of heat dissipation associated with microdamage initiation. Approaches based on temperature harmonic analysis have been implemented, allowing near-real-time and full-field mapping of stress distribution and damage development. Results show that harmonic metrics correlate with the material state and effectively track the thermoelastic effect-induced temperature changes. Some evidence is found regarding the onset of intrinsic heat dissipation, which needs to be confirmed by more focused and extensive experimental tests. Full article

This study investigates the causes and mechanisms of a corrosion-induced perforation failure in P110 tubing from a nitrogen injection well in the Tahe Oilfield. A comprehensive analysis was performed using macroscopic examination, mechanical and chemical property testing, characterization of corrosion product morphology and composition, and electrochemical measurements. The results show that the tubing material met all relevant standard requirements, ruling out intrinsic material defects as a contributing factor. The primary cause of failure was the breakdown of the internal coating. Poor coating adhesion in the older tubing from the shallow section, combined with the tensile stress from the tubing’s suspended weight and the acidic service environment, led to coating blistering and disbondment, thereby exposing the underlying steel. In the presence of H₂S, CO₂, and O₂, severe electrochemical corrosion developed on the exposed metal surface. The process was further accelerated by a high concentration of Cl⁻, which promoted rapid localized corrosion and ultimately resulted in perforation. Based on these findings, several targeted mitigation strategies are proposed. These include optimizing the coating process to improve adhesion and modifying the corrosive environment. The recommendations provide practical guidance for corrosion control in similar oil and gas well applications. Full article

Surface defects in high-temperature continuous cast billets are critical factors affecting the quality of steel products. Owing to high-temperature radiation, heavy dust contamination, varying billet specifications, and background interference from oxide scales and water stains, existing online surface defect detection technologies for high-temperature continuous cast billets still suffer from limitations including high false-positive rates, inefficient identification of pseudo-defects, and the inability to simultaneously detect three-dimensional (3D) depth information alongside two-dimensional (2D) features. To solve these problems, this paper proposes a multi-dimensional online detection technology for surface defects in high-temperature continuous cast billets based on multi-information fusion. A four-channel multispectral image sensor and a corresponding three-light-source imaging system were developed. Furthermore, a defect sample augmentation method, a deep learning-based 2D recognition method, and a photometric stereo-based 3D reconstruction method were designed to mitigate problems of low detection accuracy and poor robustness caused by sample imbalance among different defect types. Finally, industrial applications were conducted on large-section continuous cast billets, beam blanks, and billets during the grinding process. According to the surface defect detection requirements of different continuous cast billets, multispectral multi-information fusion and traditional 2D defect imaging methods were adopted respectively. The results demonstrate high-precision online detection of surface defects in continuous cast billets, with favorable practical application effects. Full article

Quench–polish–quench (QPQ) of 40Cr steel was performed to improve its tribological properties and corrosion resistance, thereby enhancing the service performance of components such as gears and bearings. The 40Cr steel was treated by QPQ at 580 °C and 620 °C for 90 or 120 min. Optical microscopy (OM, Sunny Group, Ningbo, China), scanning electron microscopy (SEM, Hitachi, Tokyo, Japan), and X-ray diffraction (XRD Rigaku Corporation, Tokyo, Japan) were used to characterise the microstructure and phase constitution. Ball-on-disk tribometry, electrochemical tests, and salt spray tests in 3.5 wt.% NaCl evaluated surface performance. At 580 °C, a composite structure of Fe₃O₄ and ε-Fe₂₋₃N formed on the surface. When the temperature rose to 620 °C, ε-Fe_2–3N gradually transformed into γ′-Fe₄N. Within the scope of this study, the diffusion layer depth exhibits an approximately linear relationship with increasing processing temperature and holding time, and the surface hardness is 67–112% higher than that of the untreated sample. After QPQ treatment, the wear mechanism changed from adhesive wear to abrasive wear. However, under the treatment conditions of 620 °C × 120 min, brittle surface spalling increased roughness, thereby increasing the coefficient of friction. As treatment time increases, nitrogen atoms continue to diffuse outward as Fe₂N transforms to the γ′ phase. This increases the composite layer’s porosity and decreases its corrosion resistance. The best corrosion resistance was observed at 580 °C for 120 min, with a corrosion potential of −0.4325 V, corrosion current density of 1.80 × 10⁻⁶ A·cm⁻², and polarisation resistance of 24,500 Ω. Corrosion performance depends on overall surface integrity. Porosity morphology strongly influences this property. For 40Cr steel, the results show that surface properties are primarily determined by the quality of the compound layer’s microstructure. Specifically, density, phase-composition stability, and defect control are more important than the commonly held view of layer thickness. Full article

Accurate surface defect detection is essential for ensuring the measurement accuracy and assembly reliability of aero-engine components during manufacturing and assembly processes. Bearings, as critical rotating components in aero-engines, are highly sensitive to surface defects that may lead to stress concentration and premature failure. However, complex defect types, low-contrast textures, and multi-scale characteristics pose significant challenges for existing lightweight visual inspection models. To address these issues, this paper proposes an improved lightweight detection model, termed DMR-YOLO, based on YOLOv8n. A Diverse Branch Block (DBB) is introduced to enhance multi-scale feature extraction and improve the representation of complex defect patterns. A Multi-Level Channel Attention (MLCA) mechanism is embedded to strengthen discriminative feature channels and suppress background interference caused by low-contrast textures. In addition, a ResidualADown module is designed to preserve critical feature information during downsampling, improving the detection of subtle defects. Experimental results on a bearing surface defect dataset show that the proposed model achieves an mAP of 89.3%, representing a 2.8% improvement over YOLOv8n while maintaining real-time inference at 138.6 FPS. Moreover, generalization tests conducted on a steel surface defect dataset demonstrate the robustness and transferability of the proposed method across different datasets. Full article

Automated pixel-level detection of steel surface defects is a critical challenge in manufacturing quality control, complicated by the variation in defect size and shape, low contrast with background textures, and the diversity of defect patterns. This paper proposes ID-MSNet, an enhanced version of the UNet3+ architecture, designed specifically for the segmentation of three common steel surface defect types: inclusions, patches, and scratches. The proposed architecture introduces three targeted modifications: (1) a multi-scale feature learning module (MSFLM) in the encoder that uses dilated convolutions at multiple rates to capture contextual features across different scales, combined with DropBlock regularization and batch normalization to improve generalization; (2) an improved down-sampling (IDS) module that replaces standard max-pooling with learnable strided convolutions fused via 1 × 1 convolution, preserving richer feature representations; and (3) a convolutional block attention module (CBAM) integrated into the skip connections to selectively focus the model on spatially and channel-wise relevant defect regions. Experiments on the publicly available SD-saliency-900 dataset demonstrate that ID-MSNet achieved an 86.19% mIoU, outperforming all compared state-of-the-art segmentation models while using only 6.7 million parameters—approximately 75% fewer than the original UNet3+. These results establish ID-MSNet as a strong and efficient baseline for steel surface defect segmentation, with potential applicability to automated quality inspection in broader manufacturing contexts. Full article

Detecting surface defects on steel products is crucial for maintaining quality standards in industrial manufacturing. However, existing detection algorithms face several challenges, including the difficulty of capturing multi-scale defect characteristics with fixed receptive fields, insufficient utilization of defect edge and frequency domain features, and simplistic feature fusion strategies. In response to the above challenges, this paper proposed the Multi-Scale Frequency-Enhanced YOLO (MSFE-YOLO) algorithm that integrates multi-scale frequency domain enhancement with defect-aware attention mechanisms. First, a Multi-Scale Frequency-Enhanced Convolution (MSFC) module was constructed, which extracted multi-scale spatial features in parallel through depth-adaptive dilated convolutions, explicitly modeled high-frequency edge information using the Laplacian operator, and achieved adaptive fusion of multi-branch features via learnable weights. Second, a Cross-Stage Partial with Multi-Scale Defect-Aware Attention (C2MSDA) module was designed, integrating Sobel operator-based edge perception, multi-scale spatial attention, and adaptive channel attention to collaboratively enhance features across spatial, channel, and edge domains through a gated fusion strategy. Finally, an Adaptive Feature Fusion Enhancement (AFFE) module was proposed to achieve adaptive aggregation of multi-level features through a data-driven weight generation network and cross-scale feature interaction mechanism. Experimental results on the NEU-DET and GC10-DET datasets demonstrated that MSFE-YOLO achieved the mAP@0.5 of 79.8% and 66.7%, respectively, which were 1.7% and 2.1% higher than the benchmark model YOLOv11s respectively, while maintaining an inference speed of 89.3 FPS, which satisfied the real-time detection requirements in industrial scenarios. Full article

Although 45 steel is widely used in the manufacture of mechanical parts, its application in harsh working conditions is limited owing to its low hardness, poor wear resistance, and corrosion resistance. Laser cladding can enhance the performance of the working surface without sacrificing substrate toughness. CoCuNiTi HEACs with different cBN additions were successfully prepared on a 45-steel substrate. The phase structure, microstructure, elemental composition, wear, and corrosion behavior of CoCuNiTi + x cBN (x = 0.0, 0.5, and 1.0 wt.%) HEACs were investigated using XRD, OM, SEM, EDS, friction and wear tester, and electrochemical workstation, respectively. The results show that all three coatings exhibit a dual-phase structure composed of FCC and BCC phases. The addition of cBN transforms the alloy phase structure from the original FCC main phase to the BCC main phase. The incorporation of cBN significantly reduces the lattice constant and cell volume of the alloy phase. The change in the alloy phase density is negatively correlated with the cell volume. CoCuNiTi + x cBN (x = 0.0, 0.5, and 1.0 wt.%) alloys have a dendritic structure. No pores were observed in the cBN-containing sample. The content of Ti in the primary phase is the highest. Co is enriched in the dendrite region, and Cu is enriched in the interdendrite region. The significant reduction in the average segregation coefficient for cBN-containing samples is attributed to the heterogeneous nucleation of the alloy melt at lower undercooling levels and the significant increase in the diffusion rate. The friction coefficient of the alloy decreases significantly with increasing cBN content. The sample with 1.0 wt.% cBN shows the best wear resistance, mainly due to the combined effects of hard particle support, solid solution strengthening, phase interface reduction, and high thermal conductivity of cBN. The sample with 1.0 wt.% cBN has the largest capacitive arc radius and charge-transfer resistance, along with the lowest annual corrosion rate, indicating optimal corrosion resistance. This is primarily related to the reduction in pore defects caused by cBN addition, hindrance of uniform penetration of the corrosive medium by dispersed cBN particles, and increased complexity of the anodic dissolution process. CoCuNiTi HEACs reinforced by cBN can simultaneously improve the wear and corrosion resistance of the surface of the 45-steel substrate, providing a feasible strategy for the design of high-performance protective coatings. Full article

To address the challenges of steel surface defect detection—characterized by fine-grained textures, substantial scale variations, and complex background interference—conventional lightweight detectors often struggle to balance real-time navigation requirements with high-precision spatial localization on mobile inspection platforms. In this work, we propose KDM-YOLO, a lightweight visual localization and detection method built upon YOLOv10n, designed to provide an efficient perception engine for autonomous inspection robots. The proposed approach enhances the baseline through three key perspectives: feature extraction, context modeling, and multi-scale fusion. Specifically, KWConv is introduced to strengthen the representation of fine-grained texture and edge cues; C2f-DRB is employed to enlarge the effective receptive field and improve long-range dependency perception to reduce missed detections; and a multi-scale attention fusion (MSAF) module is inserted before the detection head to adaptively integrate spatial details with semantic context while suppressing redundant background responses. Ablation studies confirm that each module contributes to performance gains, and their combination yields the best overall results. Comparative experiments further demonstrate that KDM-YOLO significantly improves detection performance while retaining a compact model size and high inference speed. Compared with the YOLOv10n baseline, Precision, Recall and mAP@50 are increased to 91.0%, 93.9%, and 95.4%, respectively, with a parameter count of 3.29 M and an inference speed of 155.6 f/s. These results indicate that KDM-YOLO achieves an ideal balance between the accuracy and computational efficiency required for embedded navigation platforms, providing an effective solution for online autonomous inspection and real-time localization of steel surface defects. Full article

Identifying microscopic textural anomalies and filtering out complicated industrial background noise remain significant hurdles in inspecting metallic surfaces. To tackle these operational bottlenecks, our research introduces a refined multi-scale detection framework built upon the YOLOv8l architecture. Specifically, we engineer a fine-grained detection pathway utilizing the P2 layer, which aims to preserve critical details of miniature flaws that are otherwise discarded during feature extraction. Furthermore, a Bi-directional Feature Pyramid Network model is embedded to reconstruct the feature fusion path, balancing the preservation of shallow geometric textures with enhanced multi-scale representation capabilities. To bolster anti-interference performance, a Convolutional Block Attention Module (CBAM) is integrated prior to the detection head, employing adaptive channel and spatial weighting to suppress unstructured background noise. Experimental results utilizing TTA demonstrate that the mAP@0.5 reached 76.3%. Detection accuracies for patches and inclusions reached 93.1% and 85.3%. Full article

The fatigue pitting model based on the minimum oil film thickness does not consider the influence of tooth surface roughness and residual stress, which limits the accuracy of predicting the fatigue pitting of the model. Micro pitting often initiates on the surface due to large external loads. Therefore, it is urgent to propose a new-micro pitting bearing capacity model based on gear surface integrity parameters. This paper studied a new fatigue pitting model considering surface integrity subjected to polishing processes. This model thoroughly analyzes the effects of teeth surface roughness dynamically on the oil film pressure and explores the complex mechanism of residual stress in the near-surface stress field of the gear teeth. The new model can more accurately simulate the micro-pitting bearing capacity under actual operating conditions by introducing teeth surface roughness and residual stress, and the prediction reliability of gear steel is greatly improved. This improved model provides a solid theoretical basis and technical support for optimizing gear transmission systems, accurate diagnosis of micro-pitting defects, and in-depth theoretical research in related fields. Full article

Steel surface defects significantly impact product quality and safety in industrial settings. Traditional defect detection methods suffer from inefficiencies and limitations. This study introduces an innovative deep learning architecture, CTG-YOLO, designed to enhance multi-scale defect detection accuracy on steel surfaces. By integrating a CBY parallel network structure, a TFF-PANet neck network, and a GS-Head detection head, our model achieves superior feature extraction and fusion capabilities. Experimental results on the NEU-DET and GC10-DET datasets demonstrate significant improvements, with mean Average Precision (mAP) scores of 76.55% and 69.94%, respectively, outperforming the original YOLOv8s by 3.72% and 3.14%. This research provides a robust foundation for industrial defect detection applications. Full article

To address the issues of poor adaptability to complex scenarios, high computational complexity, and difficulties in terminal deployment of existing steel surface defect detection models, a novel lightweight detection network named LHO-net is proposed, with the Lightweight Multi-Backbone (LM Backbone), the Hierarchical Scale-based Pyramid Attention Network (HSPAN), and the Occlusion-aware Detection Head (OAHead). The LM Backbone adopts a dual-branch structure with shared HGStem and a dynamic feature fusion mechanism, effectively capturing multi-dimensional features of irregular defects while extremely compressing model parameters. The HSPAN module realizes efficient fusion of multi-scale features through dynamic feature selection and adaptive upsampling strategies, balancing background noise suppression and defect detail preservation. The OAHead completes adaptive compensation of features in occluded regions by means of deep feature aggregation and exponential normalization technology, significantly enhancing the ability to recognize complex defects. On the NEU-DET dataset, LHO-net achieves a mAP@0.5 of 75.0%, a mAP@0.5:0.95 of 44.0%, and a recall of 73.6%, with a computational complexity of only 2.3 GFLOPS. Compared with the baseline model YOLOv12, it reduces parameters by 64% and computational cost by 60.3%. On the GC-10 dataset, its mAP@0.5 reaches 67.2%, and its detection stability for complex defects such as slender creases and low-contrast water spots is superior to that of mainstream lightweight YOLO variants. Visualization results confirm that the model can effectively avoid common problems such as redundant annotations and false detections and maintains stable recognition performance for various defects. It solves the core contradiction between detection accuracy and lightweight deployment in industrial scenarios, providing an efficient and practical technical solution for real-time steel surface defect detection on resource-constrained terminal devices. Full article

This study investigates how torch standoff distance influences the microstructure, surface topography, and progressive-load scratch response of air plasma-sprayed 8YSZ and rare-earth co-doped GdYbYSZ thermal barrier coatings on an St-52 grade carbon steel substrate. Three nozzle-to-substrate spraying distances were examined: 80, 100, and 120 mm. X-ray diffraction revealed that the 8YSZ coatings possessed a predominantly tetragonal (t′) structure, with minor monoclinic fractions detected in the coatings obtained with the 80 mm and 100 mm distance parameters. The GdYbYSZ coatings, in contrast, exhibited a single-phase cubic defect-fluorite structure; their diffraction peaks appeared at lower 2θ angles relative to undoped cubic ZrO₂, consistent with lattice expansion caused by the substitution of Zr⁴⁺ by the larger Gd³⁺ and Yb³⁺ cations. Surface topography was quantified by non-contact laser profilometry, providing areal (Sa) and profile (Ra) roughness parameters for the as-sprayed condition as well as three-dimensional scratch-damage morphology after testing. Progressive-load scratch tests were performed using a Rockwell diamond indenter over a 2 mm track with the normal load ramped from 0.03 N to 30 N. Penetration depth, residual depth, tangential force, and acoustic emission were recorded continuously to identify critical damage transitions. Across all spraying distances, 8YSZ exhibited systematically shallower scratch grooves than GdYbYSZ; end-of-track maximum groove depths remained below 37 µm for 8YSZ, whereas GdYbYSZ reached up to 72 µm under identical loading conditions. The novelty of this study lies in combining torch standoff distance as a processing variable with multi-channel progressive-load scratch diagnostics, including in situ acoustic emission, depth profiling, and friction monitoring, to comparatively assess the scratch wear performance of 8YSZ and rare-earth co-doped zirconia TBCs for the first time. Full article