Search Results (464)

Automated surface defect detection in steel manufacturing is pivotal for ensuring product quality, yet it remains an open challenge owing to the extreme heterogeneity of defect morphologies—ranging from hairline cracks and microscopic pores to elongated scratches and shallow dents. Existing approaches, whether classical vision pipelines or recent deep-learning paradigms, struggle to simultaneously satisfy the stringent demands of industrial scenarios: high accuracy on sub-millimeter flaws, insensitivity to texture-rich backgrounds, and real-time throughput on resource-constrained hardware. Although contemporary detectors have narrowed the gap, they still exhibit pronounced sensitivity–robustness trade-offs, particularly in the presence of scale-varying defects and cluttered surfaces. To address these limitations, we introduce MBY (MBDNet-Attention-YOLO), a lightweight yet powerful framework that synergistically couples the MBDNet backbone with the YOLO detection head. Specifically, the backbone embeds three novel components: (1) HGStem, a hierarchical stem block that enriches low-level representations while suppressing redundant activations; (2) Dynamic Align Fusion (DAF), an adaptive cross-scale fusion mechanism that dynamically re-weights feature contributions according to defect saliency; and (3) C2f-DWR, a depth-wise residual variant that progressively expands receptive fields without incurring prohibitive computational costs. Building upon this enriched feature hierarchy, the neck employs our proposed MultiSEAM module—a cascaded squeeze-and-excitation attention mechanism operating at multiple granularities—to harmonize fine-grained and semantic cues, thereby amplifying weak defect signals against complex textures. Finally, we integrate the Inner-SIoU loss, which refines the geometric alignment between predicted and ground-truth boxes by jointly optimizing center distance, aspect ratio consistency, and IoU overlap, leading to faster convergence and tighter localization. Extensive experiments on two publicly available steel-defect benchmarks—NEU-DET and PVEL-AD—demonstrate the superiority of MBY. Without bells and whistles, our model achieves 85.8% mAP@0.5 on NEU-DET and 75.9% mAP@0.5 on PVEL-AD, surpassing the best-reported results by significant margins while maintaining real-time inference on an NVIDIA Jetson Xavier. Ablation studies corroborate the complementary roles of each component, underscoring MBY’s robustness across defect scales and surface conditions. These results suggest that MBY strikes an appealing balance between accuracy, efficiency, and deployability, offering a pragmatic solution for next-generation industrial quality-control systems. Full article

The object of this study is welded joints of AISI 321 and Ti-6Al-4V, obtained by diffusion welding on developed conical surfaces. The problem of creating bimetallic joints of AISI 321 and Ti-6Al-4V with developed conical contact surfaces, using diffusion welding through an intermediate Electrolytic Tough Pitch Copper (Cu-ETP) copper layer, was solved. The joints were studied using micro-X-ray spectral analysis, microstructural analysis, and mechanical tests. High mutual diffusion of copper and titanium, along with increased concentrations of Cr and V in copper, was detected. The shear strength of the obtained welded joints is 250 MPa and 235 MPa at 30 min and 15 min, respectively, which is higher than the copper layer’s strength (180 MPa). The obtained results are explained by the dislocation diffusion mechanism in the volume of grains and beyond, due to thermal deformations during welding. Under operating conditions of internal pressure and cryogenic temperatures, the strength of the connection is ensured by the entire two-layer structure, and tightness is ensured by a vacuum-tight diffusion connection. The obtained strength of the connection (250 MPa) is sufficient under the specified operating conditions. Analysis of existing solutions in the literature review indicates that industrial application of technology for manufacturing bimetallic adapters from AISI 321 stainless steel and Ti-6Al-4V titanium alloy is limited to butt joints with small geometric dimensions. Studies of the transition zone structure and diffusion processes in bimetallic joints with developed conical contact surfaces enabled determination of factors affecting joint structure and diffusion coefficients. The obtained bimetallic adapters, made of Ti-6Al-4V titanium alloy and AISI 321 stainless steel, can be used to connect titanium high-pressure vessels with stainless steel pipelines. Full article

Ensuring the structural safety of steel trusses in escalators is critical for the reliable operation of vertical transportation systems. While manual inspection remains widely used, its dependence on human judgment leads to extended cycle times and variable defect-recognition rates, making it less reliable for identifying subtle surface imperfections. To address these limitations, a novel context-aware, multi-scale deep learning framework based on the YOLOv5 architecture is proposed, which is specifically designed for automated structural defect detection in escalator steel trusses. Firstly, a method called GIES is proposed to synthesize pseudo-multi-channel representations from single-channel grayscale images, which enhances the network’s channel-wise representation and mitigates issues arising from image noise and defocused blur. To further improve detection performance, a context enhancement pipeline is developed, consisting of a local feature module (LFM) for capturing fine-grained surface details and a global context module (GCM) for modeling large-scale structural deformations. In addition, a multi-scale feature fusion module (MSFM) is employed to effectively integrate spatial features across various resolutions, enabling the detection of defects with diverse sizes and complexities. Comprehensive testing on the NEU-DET and GC10-DET datasets reveals that the proposed method achieves 79.8% mAP on NEU-DET and 68.1% mAP on GC10-DET, outperforming the baseline YOLOv5s by 8.0% and 2.7%, respectively. Although challenges remain in identifying extremely fine defects such as crazing, the proposed approach offers improved accuracy while maintaining real-time inference speed. These results indicate the potential of the method for intelligent visual inspection in structural health monitoring and industrial safety applications. Full article

This study systematically investigated the corrosion evolution and protective mechanisms of X80 pipeline steel in Xinjiang’s saline soil environments under freeze–thaw cycling conditions. Combining regional soil characterization with laboratory-constructed corrosion systems, we employed electrochemical impedance spectroscopy, potentiodynamic polarization, and surface analytical techniques to quantify temporal–spatial corrosion behavior across 30 freeze–thaw cycles. Experimental results revealed a distinctive corrosion resistance pattern: initial improvement (cycles 1–10) attributed to protective oxide layer formation, followed by accelerated degradation (cycles 10–30) due to microcrack propagation and chloride accumulation. Synchrotron X-ray diffraction analyses identified sulfate–chloride ion synergism as the primary driver of localized corrosion disparities in heterogeneous soil matrices. A comparative evaluation of asphalt-coated specimens demonstrated a 62%–89% corrosion rate reduction, with effectiveness directly correlating with coating integrity and thickness (200–500 μm range). Molecular dynamics simulations using Materials Studio revealed atomic-scale ion transport dynamics at coating–substrate interfaces, showing preferential Cl⁻ permeation through coating defects. These multiscale findings establish quantitative relationships between environmental stressors, coating parameters, and corrosion kinetics, providing a mechanistic framework for optimizing protective coatings in cold-region pipeline applications. Full article

This study systematically evaluates the influence of copper (Cu) addition in gas-shielded solid wires on the microstructure and cryogenic toughness of X80 pipeline steel welds. Welds were fabricated using solid wires with varying Cu contents (0.13–0.34 wt.%) under identical gas metal arc welding (GMAW) parameters. The mechanical capacities were assessed via tensile testing, Charpy V-notch impact tests at −20 °C and Vickers hardness measurements. Microstructural evolution was characterized through optical microscopy (OM), scanning electron microscopy (SEM) and electron backscatter diffraction (EBSD). Key findings reveal that increasing the Cu content from 0.13 wt.% to 0.34 wt.% reduces the volume percentage of acicular ferrite (AF) in the weld metal by approximately 20%, accompanied by a significant decline in cryogenic toughness, with the average impact energy decreasing from 221.08 J to 151.59 J. Mechanistic analysis demonstrates that the trace increase in the Cu element. The phase transition temperature and inclusions is not significant but can refine the prior austenite grain size of the weld, so that the total surface area of the grain boundary increases, and the surface area of the inclusions within the grain is relatively small, resulting in the nucleation of acicular ferrite within the grain being weak. This microstructural transition lowers the critical crack size and diminishes the density for high-angle grain boundaries (HAGBs > 45°), which weakens crack deflection capability. Consequently, the crack propagation angle decreases from 54.73° to 45°, substantially reducing the energy required for stable crack growth and deteriorating low-temperature toughness. Full article

The existing studies mainly focus on the coarse-grained heat-affected zone and the inter-critically reheated coarse-grained heat-affected zone, while the studies on other sub-zones are relatively low. Meanwhile, the studies on the Cr element in steel mainly focus on the influence of the Cr element on strength and hardness; however, its mechanism is not very clear. Therefore, three kinds of X80 experimental steels with different Cr contents (0 wt.%, 0.13 wt.%, and 0.40 wt.%) were designed in this paper. The thermal simulation experiments on the supercritically coarse-grained heat-affected zone (SCCGHAZ) were carried out using a Gleeble-3500 thermal simulator. The effects of Cr on the microstructure and toughness of SCCGHAZ were systematically investigated through Charpy impact tests and microstructural characterization techniques. The results indicate that the microstructures of the three Cr-containing X80 experimental steels in SCCGHAZ are predominantly composed of fine granular bainite. However, impact tests at −10 °C show that the SCCGHAZs of 0 wt.% and 0.13 wt.% Cr steel exhibit higher impact energy, while that of the 0.40 wt.% Cr steel demonstrates significantly reduced energy impact (<100 J). Microstructural characterization reveals that the impact toughness of the SCCGHAZ in X80 steel is correlated with microstructural features, including effective grain size, grain boundary angles, and the volume fraction and shape of martensite–austenite (M-A) constituents. Among these factors, the volume fraction of M-A constituents substantially influences toughness. It was found that island-shaped M-A constituents inhibit crack propagation, whereas blocky M-A constituents impair toughness. Full article

Deep-sea oil and gas pipelines undergo significant plastic strain during reel-lay installation. Additionally, the static strain aging phenomenon that occurs during service can further deteriorate the mechanical properties of the pipelines. This study investigates the plastic deformation mechanism of reel-lay pipeline steel by subjecting the test steel to 5% pre-strain followed by aging treatment at 250 °C for 1 h. The present study systematically correlates the evolution of mechanical properties with microstructural changes through microstructural characterization techniques such as EBSD, TEM, and XRD. The results demonstrate that after pre-straining, the yield strength of the experimental steel increases due to dislocation strengthening and residual stress generation, while its uniform elongation decreases. Although no significant changes in grain size are observed macroscopically, microstructural characterization reveals a substantial increase in dislocation density within the matrix, forming dislocation cells and walls. These substructures lead to a deterioration of the material’s work hardening capacity. Following aging treatment, the tested steel exhibits further increased yield strength and reduced uniform elongation. After aging treatment, although the dislocation density in the matrix slightly decreases and dislocation tangles are somewhat reduced, the Cottrell atmosphere pinning effect leads to a further decline in work hardening capability, ultimately resulting in the deterioration of plasticity in reel-lay pipeline steel. The instantaneous hardening exponent curve shows that the work hardening phenomenon becomes more pronounced in the tested steel after strain aging as the tempering temperature increases. Full article

The operational efficiency of the main steam pipelines at thermal power plants is reduced due to several factors, including operating temperature, pressure, service life, and the frequency of process shutdowns, which contribute to the degradation of heat-resistant steels. The study aims to identify the features of changes in the sizes of grains and carbides along their boundaries, as well as mechanical properties (hardness, strength, plasticity and fracture toughness) along the wall thickness of both pipes in the initial state and after operation with block shutdowns. Preliminary electrolytic hydrogenation of specimens (before tensile tests in air) showed even more clearly the negative consequences of operational degradation of steel. The degradation of steel was also assessed using fracture toughness (J_IC). The value of J_IC for operated steel with a smaller number of shutdowns decreased by 32–33%, whereas with a larger number of shutdowns, its decrease in the vicinity of the outer and inner surfaces of the pipe reached 65 and 61%, respectively. Fractographic signs of more intense degradation of steel after a greater number of shutdowns were manifested at the stage of spontaneous fracture of specimens by changing the mechanism from transgranular cleavage to intergranular, which indicated a decrease in the cohesive strength of grain boundaries. Full article

This study investigates the mechanical behavior of X52 steel pipes and their weld regions under pure hydrogen transport conditions, with a focus on assessing potential hydrogen embrittlement risks. Through experimental analysis, the research evaluates how different pipeline regions—including the base metal, weld metal, and heat-affected zones—respond to varying hydrogen pressures. Key mechanical properties such as elongation, fracture toughness, and crack growth resistance are analyzed to determine their implications for structural integrity and safety. Based on the findings, this study proposes criteria for the safety evaluation of X52 pipelines operating in hydrogen service environments. The results are intended to inform decisions regarding the repurposing of existing pipelines or the design of new infrastructure dedicated to pure hydrogen transport, offering insights into material performance and critical safety considerations for hydrogen pipeline applications. Full article

Steel lazy wave risers (SLWRs) are critical in offshore hydrocarbon transport for linking subsea wells to floating production facilities in deep-water environments. The incorporation of buoyancy modules reduces curvature-induced stress concentrations in the touchdown zone (TDZ); however, extended operational exposure under cyclic environmental and operational loads results in repeated seabed contact. This repeated interaction modifies the seabed soil over time, gradually forming a trench and altering the riser configuration, which significantly impacts stress patterns and contributes to fatigue degradation. Accurately reconstructing the riser’s evolving profile in the TDZ is essential for reliable fatigue life estimation and structural integrity evaluation. This study proposes a simulation-based framework for the autonomous tracking of SLWRs using a fin-actuated autonomous underwater vehicle (AUV) equipped with a monocular camera and multibeam echosounder. By fusing visual and acoustic data, the system continuously estimates the AUV’s relative position concerning the riser. A dedicated image processing pipeline, comprising bilateral filtering, edge detection, Hough transform, and K-means clustering, facilitates the extraction of the riser’s centerline and measures its displacement from nearby objects and seabed variations. The framework was developed and validated in the underwater unmanned vehicle (UUV) Simulator, a high-fidelity underwater robotics and pipeline inspection environment. Simulated scenarios included the riser’s dynamic lateral and vertical oscillations, in which the system demonstrated robust performance in capturing complex three-dimensional trajectories. The resulting riser profiles can be integrated into numerical models incorporating riser–soil interaction and non-linear hysteretic behavior, ultimately enhancing fatigue prediction accuracy and informing long-term infrastructure maintenance strategies. Full article

It is important to accurately characterize the plane-stress state of pipe walls for evaluating the bearing capacity of the pipe and ensuring the structural safety. This paper describes a novel ultrasonic technique for evaluating anisotropic pipe-wall plane stresses using three-directional longitudinal critical refracted (LCR) wave time-of-flight (TOF) measurements. The connection between plane stress and ultrasonic TOF is confirmed by examining how the anisotropy of rolled steel plates affects the speed of ultrasonic wave propagation, which is a finding not previously documented in spiral-welded pipes. Then based on this relationship, an ultrasonic stress coefficient calibration experiment for spiral-welded pipes is designed. The results show that the principal stress obtained by the ultrasonic method is closer to the engineering stress than that obtained from the coercivity method. And, as a nondestructive testing technique, the ultrasonic method is more suitable for in-service pipelines. It also elucidates the effects of probe pressure and steel plate surface roughness on the ultrasonic TOF, obtains a threshold for probe pressure, and reveals a linear relationship between roughness and TOF. This study provides a feasible technique for nondestructive measurement of plane stress in anisotropic spiral-welded pipelines, which has potential application prospects in the health monitoring of in-service pipelines. Full article

Stainless steel, due to its exceptional comprehensive properties, has been widely adopted as the primary material for liquid cargo tank containment systems and pipelines in liquefied natural gas (LNG) carriers. However, challenges such as hot cracking, excessive deformation, and the deterioration of welded joint performance during stainless steel welding significantly constrain the construction quality and safety of LNG carriers. While conventional tungsten inert gas (TIG) welding can produce high-integrity welds, it is inherently limited by shallow penetration depth and low efficiency. Magnetic field-assisted TIG welding technology addresses these limitations by introducing an external magnetic field, which effectively modifies arc morphology, refines grain structure, enhances penetration depth, and improves corrosion resistance. In this study, TIG bead-on-plate welding was performed on 304 stainless steel plates, with a systematic investigation into the dynamic arc behavior during welding, as well as the microstructure and anti-corrosion properties of the deposited metal. The experimental results demonstrate that, in the absence of a magnetic field, the welding arc remains stable without deflection. As the intensity of the alternating magnetic field intensity increases, the arc exhibits pronounced periodic oscillations. At an applied magnetic field intensity of 30 mT, the maximum arc deflection angle reaches 76°. With increasing alternating magnetic field intensity, the weld penetration depth gradually decreases, while the weld width progressively expands. Specifically, at 30 mT, the penetration depth reaches a minimum value of 1.8 mm, representing a 44% reduction compared to the non-magnetic condition, whereas the weld width peaks at 9.3 mm, corresponding to a 9.4% increase. Furthermore, the ferrite grains in the weld metal are significantly refined at higher alternating magnetic field intensities. The weld metal subjected to a 30 mT alternating magnetic field exhibits the highest breakdown potential, the lowest corrosion rate, and the most protective passive film, indicating superior corrosion resistance compared to other tested conditions. Full article

This study systematically investigates the degradation and failure prediction of pipeline materials in sulfur-containing environments, with a particular focus on X52 pipeline steel exposed to high-sulfur environments. Through uniaxial tensile tests to assess mechanical properties, it was found that despite surface corrosion and a reduction in overall structural load-bearing capacity, the intrinsic mechanical properties of X52 steel did not exhibit significant degradation and remained within standard ranges. The Johnson–Cook constitutive model was developed to accurately capture the material’s plastic behavior. Subsequently, a genetic algorithm-optimized backpropagation (GABP) neural network was employed to predict the failure pressure of defective pipelines and the corrosion rate in acidic environments, with prediction errors controlled within 5%. By integrating the GABP model with NACE standard methods, a framework for predicting the remaining service life for in-service pipelines operating in sour environments was established. This method provides a novel and reliable approach for pipeline integrity assessment, demonstrating significantly higher accuracy than traditional empirical models and finite element analysis. Full article

Microbiologically influenced corrosion (MIC) poses significant challenges in oilfield water injection environments, leading to substantial socioeconomic losses. L245 steel, a low-alloy steel widely used in oil and gas pipelines due to its excellent mechanical properties and cost-effectiveness, remains highly vulnerable to MIC during long-term service. This study uses surface characterization and electrochemical techniques to investigate the corrosion behavior of L245 pipeline steel under short-cycle conditions in a symbiotic environment of iron-oxidizing bacteria (IOB) and Shewanella algae (S. algae). Key findings revealed that localized corrosion of L245 steel was markedly exacerbated under coexisting IOB and S. algae conditions compared to monoculture systems. However, the uniform corrosion rate under symbiosis fell between the rates observed in the individual IOB and S. algae systems. Mechanistically, the enhanced corrosion under symbiotic conditions was attributed to the synergistic electron transfer interaction: IOB exploited electron carriers secreted by S. algae during extracellular electron transfer (EET), which amplified the microbial consortium’s capacity to harvest electrons from the steel substrate. These results emphasize the critical role of interspecies electron exchange in accelerating localized degradation of carbon steel under complex microbial consortia, with implications for developing targeted mitigation strategies in industrial pipelines exposed to similar microbiological environments. Full article

For over five decades, blending hydrogen into existing natural gas pipelines has been explored as a potential solution to reduce greenhouse gas emissions. Despite its promise, implementing this approach has been slow due to concerns about hydrogen embrittlement (HE) and its interactions with various metals. Stainless steel alloys like 316L are commonly used in hydrogen service due to their superior resistance to HE. However, the impact of additive manufacturing (AM) on 316L’s susceptibility to HE when subjected to gas charging has not been thoroughly investigated. To fill this knowledge gap, we created conventionally manufactured and AM 316L tensile bars and solubility specimens, which were then exposed to hydrogen-blended natural gas at 10 MPa with a 50% blend and 100% pure H₂. Both conventionally manufactured and additively manufactured specimens had as-received/printed samples that were used as controls. The samples underwent mechanical evaluation through tensile testing and hot chemical extraction to assess hydrogen solubility. Further analysis revealed significant changes in the microstructure near the fracture area of the soaked samples using scanning electron microscope fractography and metallography. These findings were compared with our previous work on traditionally produced 316L bar stock, which demonstrated that AM processing conditions can yield superior performance in terms of resistance to HE. Notably, this study provides valuable insights into the effects of AM on 316L’s susceptibility to HE when subjected to gas charging. The results have significant implications for the development and implementation of AM 316L for hydrogen/natural gas applications in pressure regulators when AM processing conditions are well-controlled. This article is a revised and expanded version of a paper entitled “Effect of Hydrogen-Blended Natural Gas on Additive Manufactured 316L Stainless Steel in Pressure Regulator Environments”, which was presented at TMS in Las Vegas, March 2025. Full article