International Journal of Pressure Vessels and Piping最新文献

{"title":"Fatigue fracture of last stage X20Cr13 low pressure turbine (LPT) blade from 600 MW thermal power station","authors":"Chidambaram Subramanian ,&nbsp;Swarup Kr Laha ,&nbsp;Sourav Kansabanik ,&nbsp;Biplab Swarnakar ,&nbsp;Debashis Ghosh","doi":"10.1016/j.ijpvp.2026.105751","DOIUrl":"10.1016/j.ijpvp.2026.105751","url":null,"abstract":"<div><div>The last stage low pressure LP steam turbine blade operated for 3000 rpm was failed after 42000 equivalent hours of operation from 600 MW thermo electric plant. The fractured blade was investigated and compared with virgin blade to determine the failure mode. Visual examination, chemical analysis, uni-axial tensile, V-notch impact tests, bulk hardness, EDX, fractography and microstructural characterization were conducted on the fractured blade. Further, wet fluorescent magnetic particle inspection and surface roughness measurement conducted on virgin blade as well. Initial visual analysis suggested that chevron cracking accompanied with several ratchet marks. Moreover, dynamic analysis of last stage virgin blade was performed and evidenced that natural frequency was stable. Modal analysis had predicted using Finite Element Analysis. Both experimental and theoretical frequencies had been closely matched, and natural frequencies were well below the resonant frequency, thus, vibration had not induced fatigue fracture. Moreover, fractured blade was fractographic and metallographic analyzed for fatigue fracture characterization. An engineering failure analysis suggested that several non-metallic inclusions have been de-bonded at crack origin zone. Multiple source of fatigue cracks have been initiated adjacent to material anomalies and fatigue fracture propagated by alternating centrifugal induced tensile stress. Fine curved striations have been evidenced on fatigue crack initiation and propagation zones. The blade exhibited tempered martensite and tensile properties including hardness were within the specifications. The presence of anomalies including non-metallic inclusions and internal volumetric material defects has been linked with poor blade toughness which had reduced the fatigue resistance of last stage blade. Interaction of manganese sulfide inclusions with complex alternating centrifugal and bending stress had induced fatigue fracture. Several recommendations including blade manufacturing by clean steel technology are suggested based on various obtained evidences to prevent LPT blade failures in power plants.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105751"},"PeriodicalIF":3.5,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analytical and experimental determination of the failure-critical pressure of pipe structures manufactured by PBF-LB/M","authors":"T. Koers ,&nbsp;B. Magyar ,&nbsp;C. Bödger ,&nbsp;T. Tröster","doi":"10.1016/j.ijpvp.2026.105753","DOIUrl":"10.1016/j.ijpvp.2026.105753","url":null,"abstract":"<div><div>The state of the art shows that PBF-LB/M offers great potential for pressure-loaded parts, with significant weight reductions and simultaneous optimization of flow resistance. This study is aimed at applying existing calculation methods for pressure-loaded parts to additively manufactured pipe structures, considering the two materials EN AC-43000 (3.2381, AlSi10Mg) and AISI 316L (1.4404, X2CrNiMo17-12-2). For this purpose, systematic tensile tests are carried out for both materials. In addition, a statistical evaluation is performed to determine the design-relevant strength characteristics with a survival probability <em>P</em>_s of 97.5 % for both materials in the as-built and heat-treated condition.</div><div>Pipe specimens are manufactured, half of which are heat treated, geometrically measured and then subjected to a burst pressure test to experimentally determine the failure-critical internal pressure. These results are compared with calculated burst pressures. The calculations are based on the application-relevant methods identified in this study, considering the strength values determined for the respective material condition. This comparison is used to assess the suitability of the calculation methods for additively manufactured pipe structures, based on the materials investigated.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105753"},"PeriodicalIF":3.5,"publicationDate":"2026-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ball indentation test: A versatile small-scale testing method for evaluating mechanical properties of materials","authors":"M.D. Mathew ,&nbsp;J. Ganesh Kumar ,&nbsp;K. Linga Murty","doi":"10.1016/j.ijpvp.2025.105740","DOIUrl":"10.1016/j.ijpvp.2025.105740","url":null,"abstract":"<div><div>The ball indentation (BI) technique is a versatile and efficient small-scale testing method employed to assess the mechanical properties of metallic materials. In this method, a compressive force is gradually applied to a spherical indenter, which is pressed onto the material’s surface until a predetermined indentation depth is achieved. The indenter is then partially unloaded and reloaded. This loading-unloading cycle is repeated several times at incrementally increasing depths. Throughout the test, the indentation depth and the corresponding load are measured. This data is used to generate a load-depth curve. By combining semi-empirical relationships with elasticity and plasticity theories, this analysis yields the stress-strain curve that is characteristic of the material’s response to multiaxial indentation loading.</div><div>Key mechanical properties derived from the BI tests include hardness, flow curve, yield strength, ultimate tensile strength, and indentation energy to fracture. This testing method facilitates localized, point-to-point assessment of the mechanical properties of metallic materials. The technique is advantageous in evaluating narrow microstructural zones within weldments. The test method is minimally invasive as well. This makes ball indentation testing attractive for assessing the mechanical properties of structural components in service and for extending their life without compromising component integrity. The paper discusses a range of BI applications. Theoretical models, AI-assisted data analysis, portable in-situ BI system, and other critical issues, as well as future scenarios, are also discussed.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105740"},"PeriodicalIF":3.5,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928127","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental investigation on full-scale fracture behavior and dynamic response of supercritical CO2 pipelines with N2 impurities","authors":"Lei Chen ,&nbsp;Wenjing Yang ,&nbsp;Jianping Zhou ,&nbsp;Zhenxi Liu ,&nbsp;Zhanshu Lv ,&nbsp;Yanwei Hu ,&nbsp;Jian Li ,&nbsp;Xingqing Yan ,&nbsp;Jianliang Yu ,&nbsp;Shaoyun Chen","doi":"10.1016/j.ijpvp.2025.105741","DOIUrl":"10.1016/j.ijpvp.2025.105741","url":null,"abstract":"<div><div>To address the safety risks associated with pipeline fractures in carbon capture, utilization, and storage (CCUS) systems, this study constructed a full-scale experimental platform for supercritical CO₂ pipelines containing impurities and conducted systematic fracture tests under three sets of conditions with varying initial pressures (9.8–11.6 MPa) and N₂ molar concentrations (2 %–4 %). A self-developed data acquisition system, integrated with high-frequency pressure transducers, T-type armored thermocouples, and a high-speed camera (capturing crack propagation processes), was employed to monitor the dynamic evolutions of pressure, temperature, decompression wave propagation, and crack tip behavior during pipeline fracture. The results indicated that pipeline fracture induced four distinct pressure change stages: rapid decline (Stage Ⅰ), pressure oscillation (Stage Ⅱ), negative exponential decline (Stage Ⅲ), and static leakage (Stage Ⅳ). Axially, the internal temperature decreased first near the fracture and later at locations farther from it; vertically, the minimum temperature at all measuring points predominantly occurred at the pipeline bottom. The decompression wave velocity exhibited a linear decrease in Stage Ⅰ, formed a “pressure plateau” in Stage Ⅱ, and decreased irregularly in Stages Ⅲ–Ⅳ due to subcooled and superheated states caused by pressure instability. Higher initial pressure and N₂ molar concentration both contributed to an increase in the initial decompression wave velocity and the “pressure plateau” value. Additionally, the self-designed fracture recording system successfully captured the complete process of pipeline failure, crack initiation, ductile propagation, and arrest. The crack tip opening angle (<em>CTOA</em>) fluctuated within 14.3°–21.2° along the propagation path and showed a gradual decreasing trend, while the crack propagation velocity first increased, maintained a stable phase, and then decreased. Notably, a higher N₂ molar concentration led to a higher stable fracture velocity. This research provides critical experimental data and theoretical support for the safety design and fracture control of supercritical CO₂ pipelines in CCUS projects.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105741"},"PeriodicalIF":3.5,"publicationDate":"2026-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent prediction of crack stress intensity factors for nuclear-grade pressure vessels based on XFEM-PSONN collaboration","authors":"Kai Liu,&nbsp;WeiWei Liu,&nbsp;ShaoWei Wu,&nbsp;BoQun Xie,&nbsp;Xin Liu","doi":"10.1016/j.ijpvp.2025.105744","DOIUrl":"10.1016/j.ijpvp.2025.105744","url":null,"abstract":"<div><div>The reactor pressure vessels (RPVs) are key components in nuclear power plants, and their structural integrity assessment is of great significance for the safe and stable operation of nuclear power plants. To address issues such as low computational efficiency and limited applicability of existing assessment methods, this study proposes an innovative collaborative prediction method based on the extended finite element method (XFEM) and the particle swarm optimization neural network (PSONN). This method enables rapid and accurate prediction of stress intensity factors (SIFs) under the combined influence of multiple parameters including crack geometric parameters, container structure dimensions and internal pressure. Firstly, a parametric model including typical crack configurations such as beltline shells and nozzle corners is established using XFEM, and a comprehensive database of SIFs is constructed. By systematically comparing the predictive performance of eight machine learning (ML) algorithms, a neural network model based on Particle Swarm Optimization is developed. And K-fold cross-validation and grid search techniques are adopted to optimize the model's hyperparameters. The interpretability analysis of SHAP indicates that internal pressure and crack inclination Angle are the most critical parameters affecting the prediction accuracy. By effectively integrating the physical accuracy of XFEM with the computational efficiency of PSONN, the proposed method provides a practical tool for rapid and accurate safety assessment upon crack detection in in-service inspections.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105744"},"PeriodicalIF":3.5,"publicationDate":"2025-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145877098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stress distribution characteristics and intelligent online monitoring methods for multilayer wound pressure vessel","authors":"Ruiyuan Xue ,&nbsp;Xuezong Zhang ,&nbsp;Juyin Zhang ,&nbsp;Xueping Wang ,&nbsp;Yongnan Zhang ,&nbsp;Linbin Li ,&nbsp;Yongzhi Luo","doi":"10.1016/j.ijpvp.2025.105742","DOIUrl":"10.1016/j.ijpvp.2025.105742","url":null,"abstract":"<div><div>A digital twin-driven online stress prediction method is proposed to address the stress monitoring requirements for multi-layer wrapped high-pressure hydrogen storage vessels. This method establishes a phased computational framework (offline/online): During the offline phase, the global stress field is computed using the Finite Element Method (FEM), and a random forest hybrid regression prediction model incorporating the whale optimization algorithm (WOA-RF) is trained to establish the mapping relationship between container load, structural features, node coordinates, and stress. During the online phase, the deviation between measured local stresses and offline-predicted stresses is first calculated. Subsequently, a K-Nearest Neighbors (KNN) algorithm constructs a surrogate model linking load-node coordinates to stress deviation. Ultimately, the KNN model is driven by locally acquired real-time measurement data, utilizing its output stress deviation to perform real-time corrections on WOA-RF prediction results, thereby achieving global twin stress prediction for the monitored vessel. To establish a more accurate finite element model during the offline phase, this paper innovatively derives a method for inverting interlayer preload in multilayer vessels based on measured data. Verification conducted on a multi-layer wrapped high-pressure reactor demonstrated that the proposed stress monitoring method achieved prediction errors ranging from 0.4 % to 10 %. Furthermore, the findings elucidate the random and non-uniform stress distribution characteristics exhibited by multi-layer wrapped vessels under loading, which stem from the complex interlayer preload generated during the manufacturing process.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105742"},"PeriodicalIF":3.5,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment of tensile properties and fracture toughness of ultra-high-strength oil casing steels via instrumented spherical indentation test","authors":"Feng Yu ,&nbsp;Jian Fang ,&nbsp;Mingcheng Sun ,&nbsp;Feng Zhang ,&nbsp;Jianwei Zhang ,&nbsp;Yingzhi Li","doi":"10.1016/j.ijpvp.2025.105739","DOIUrl":"10.1016/j.ijpvp.2025.105739","url":null,"abstract":"<div><div>To address the demand for rapid, non-destructive, and accurate characterization of ultra-high-strength oil casing steels in H₂S-containing environments, this study combined standard tests with the instrumented spherical indentation test (ISIT) to evaluate the tensile properties, fracture toughness, and post-hydrogen-induced cracking (HIC) performance of three XCoMo-series steels (Q125, Q140, Q165). Key findings: 1) The three steels broke the strength-toughness trade-off, with Q165 showing the best performance due to the synergy of grain refinement and alloy strengthening. 2) Validated against ISO standards, ISIT achieved prediction errors of ≤10 % for yield stress, ≤5 % for ultimate tensile stress, and ≤15 % for fracture toughness, enabling non-destructive, and rapid in-situ characterization. 3) After HIC exposure, all three steels showed an elastic modulus decrease of ≥25.4 % with grade-specific strength response characteristics, while Q165 maintained the smallest fracture toughness reduction (3.3 %). Notably, ISIT realized quantitative characterization of HIC-induced performance degradation, successfully filling the evaluation gap of traditional HIC tests and providing direct data support for performance degradation assessment.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105739"},"PeriodicalIF":3.5,"publicationDate":"2025-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145876934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Creep life prediction of 2.25Cr1Mo0.25V steel using cross-material transfer learning, automatic hyperparameter optimization, and Bagging ensemble","authors":"You Li ,&nbsp;Bieerlan Jianayihan ,&nbsp;Zhenyu Wang ,&nbsp;Peng Jiao ,&nbsp;Chaoxu Guan ,&nbsp;Hao Huang","doi":"10.1016/j.ijpvp.2025.105734","DOIUrl":"10.1016/j.ijpvp.2025.105734","url":null,"abstract":"<div><div>2.25Cr1Mo0.25V steel is widely adopted in critical high-temperature components across the petrochemical and power energy sectors. Owing to extended service under harsh conditions, creep rupture emerges as the primary failure mode encountered in this steel. However, the limited availability of creep data significantly constrains the efficacy of conventional empirical and data-driven techniques in accurately predicting the creep life of 2.25Cr1Mo0.25V steel. To address this issue, a novel methodology was introduced for predicting the creep life of 2.25Cr1Mo0.25V steel, utilizing cross-material transfer learning (TL), automatic hyperparameter optimization (auto-HPO), and Bagging ensemble techniques. Here, three TL strategies were developed and evaluated: a baseline network, a variant augmented with weight coefficients (W-TL network), and a dual-enhanced model incorporating both weight coefficients and residual connections (W-Res-TL model). Meanwhile, four auto-HPO algorithms—Random, TPE, Naive Evolution, and Anneal—were implemented over an extensive hyperparameter search space. During the auto-HPO process, the performance of TL was evaluated through 5-fold cross-validation, utilizing Smooth L1 Loss as the metric. Results demonstrated that the W-Res-TL network, when integrated with Naive Evolution, exhibits superior performance. Thus, an ensemble comprising 100 instances of this network was developed. The resulting Bagging model was systematically discussed with respect to accuracy, extrapolation performance, and SHAP-based interpretability. Accuracy assessment showed that the W-Res-TL Bagging model consistently attains high predictive precision on both the training and test sets. Extrapolation analysis suggested that the W-Res-TL Bagging model demonstrates strong generalization capabilities across a broad spectrum of temperatures and stresses, without yielding any non-physical results. SHAP analysis substantiated the model's interpretability by elucidating the contribution of input features to its predictions. Moreover, the performance of proposed creep life modeling framework was demonstrated to surpass that of the traditional Larson-Miller method as well as six widely employed machine learning (ML) algorithms. This can be attributed to the effective capability of the W-Res-TL approach in capturing and transferring the inherent creep knowledge of CrMo steels to 2.25Cr1Mo0.25V steel. This study can facilitate the accurate and rapid prediction of creep life for materials characterized by scarce creep data.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"220 ","pages":"Article 105734"},"PeriodicalIF":3.5,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neural network-aided constitutive modeling of cyclic softening in 2.25Cr–1Mo steel across temperatures and strain amplitudes","authors":"Fuhai Gao ,&nbsp;Cheng Li ,&nbsp;Rou Du ,&nbsp;Jianguo Gong ,&nbsp;Xiaoming Liu ,&nbsp;Fuzhen Xuan","doi":"10.1016/j.ijpvp.2025.105738","DOIUrl":"10.1016/j.ijpvp.2025.105738","url":null,"abstract":"<div><div>2.25Cr–1Mo steel is widely used in high-temperature components of nuclear and fossil power plants. Accurate modelling of its cyclic behavior over a wide temperature range is essential for structure integrity assessment. In this study, a Chaboche-type constitutive model is employed to describe the cyclic response of 2.25Cr–1Mo steel under various strain amplitudes and temperatures. The isotropic hardening parameter <span><math><mrow><mi>Q</mi></mrow></math></span>, defined as the difference between the initial and the stabilized peak stresses, plays a key role in characterizing cyclic softening. To capture the coupled dependence of <span><math><mrow><mi>Q</mi></mrow></math></span> on strain amplitude and temperature, a physics-constrained neural network was developed. The approach incorporates experimental scatter into the calibration process. The predicted parameters are expressed as logarithmic functions of temperature, enabling smooth interpolation and direct implementation in finite element simulations. The proposed model reproduces the experimental cyclic softening behavior with good accuracy. This framework provides a practical and reliable tool for fatigue and inelastic analysis of high-temperature structural components.</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"221 ","pages":"Article 105738"},"PeriodicalIF":3.5,"publicationDate":"2025-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TFA_Net: A time-frequency attention network for enhancing defect recognition and noise robustness in ultrasonic guided wave pipeline inspection","authors":"Yunliang Zhao ,&nbsp;Donglin Tang ,&nbsp;Chao Ding ,&nbsp;Heng Cheng","doi":"10.1016/j.ijpvp.2025.105735","DOIUrl":"10.1016/j.ijpvp.2025.105735","url":null,"abstract":"<div><div>Ultrasonic guided wave-based pipeline defect detection is crucial for achieving efficient and cost-effective structural health monitoring of pipelines. However, signal attenuation and noise interference during wave propagation severely hinder the accurate identification of defect signals. To address this challenge, a Time-Frequency Attention Network (TFA_Net) is proposed, integrating time-frequency domain signal processing with deep learning techniques to improve defect recognition accuracy and enhance noise robustness in ultrasonic guided wave signals. First, the Ultrasonic Guided Wave Defect Dataset (UGW-Dataset) was established, including experimental and simulated data, covering cracks and corrosion defects of various sizes and shapes. Next, a time-frequency attention block (TFA_Block) was designed in TFA_Net to perform multi-scale feature extraction in both time and frequency domains, enabling effective capture of global and local characteristics of defect signals. Experimental results demonstrate that TFA_Net achieves a defect recognition accuracy of 99.4 % on the UGW-Dataset, confirming its exceptional feature extraction and defect recognition capabilities. Furthermore, TFA_Block significantly enhances the robustness of TFA_Net within the signal-to-noise ratio (SNR) range from 40 dB to 10 dB, effectively mitigating the negative impact of noise on recognition accuracy. This study provides an efficient and noise-resilient approach for defect recognition in pipeline structural health monitoring (SHM).</div></div>","PeriodicalId":54946,"journal":{"name":"International Journal of Pressure Vessels and Piping","volume":"220 ","pages":"Article 105735"},"PeriodicalIF":3.5,"publicationDate":"2025-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145883893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}