Welding in the World最新文献

筛选
英文 中文
Enhanced mechanical properties and microstructure of Incoloy 825 components fabricated using pulsed cold metal transfer in wire arc additive manufacturing 电弧增材制造中脉冲冷金属转移制备的incoly 825部件的力学性能和显微组织
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-03-11 DOI: 10.1007/s40194-025-02004-7
Prasanna Nagasai Bellamkonda, Maheshwar Dwivedy
{"title":"Enhanced mechanical properties and microstructure of Incoloy 825 components fabricated using pulsed cold metal transfer in wire arc additive manufacturing","authors":"Prasanna Nagasai Bellamkonda,&nbsp;Maheshwar Dwivedy","doi":"10.1007/s40194-025-02004-7","DOIUrl":"10.1007/s40194-025-02004-7","url":null,"abstract":"<div><p>To address the challenges of heat input in wire arc additive manufacturing (WAAM), this study employed the pulsed cold metal transfer (PCMT) technique to fabricate Incoloy 825 (IN825) components. PCMT, characterized by controlled droplet transfer and reduced heat input, enhanced mechanical performance and microstructural quality. Comprehensive analyses, including microstructural examination, X-ray diffraction, energy-dispersive X-ray spectroscopy (EDS), and element mapping, were performed. Titanium and molybdenum-rich secondary particles were identified through EDS. The mechanical properties of PCMT-fabricated components were compared with both wrought IN825 and those produced by gas metal arc additive manufacturing (GMAAM). Results demonstrated that PCMT components, particularly those fabricated at a 45° orientation, achieved approximately 113% of the ultimate tensile strength (UTS) and 131% of the elongation compared to wrought IN825. This marked a significant improvement over GMAAM-fabricated components. The reduced heat input and enhanced cooling rates in the PCMT process contributed to finer microstructures and superior mechanical properties. Fractography studies revealed that PCMT components exhibited ductile fractures with significant plastic deformation and some brittle regions. These findings underscored the advantages of PCMT in producing high-performance IN825 components compared to traditional GMAAM.</p><h3>Graphical Abstract</h3><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 6","pages":"1481 - 1499"},"PeriodicalIF":2.4,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Impact of build direction on microstructure and high-temperature mechanical properties of SLM-fabricated 316L stainless steel 铸型方向对slm法制备316L不锈钢组织和高温力学性能的影响
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-03-11 DOI: 10.1007/s40194-025-02007-4
Mohammadamin Bakhtiarian, Matin Vafaei, Amirhossein Mashhuriazar, Hamid Omidvar
{"title":"Impact of build direction on microstructure and high-temperature mechanical properties of SLM-fabricated 316L stainless steel","authors":"Mohammadamin Bakhtiarian,&nbsp;Matin Vafaei,&nbsp;Amirhossein Mashhuriazar,&nbsp;Hamid Omidvar","doi":"10.1007/s40194-025-02007-4","DOIUrl":"10.1007/s40194-025-02007-4","url":null,"abstract":"<div><p>Additive manufacturing (AM) has gained significant attention over the last decade. Among the various factors influencing final product quality, the build direction notably affects mechanical properties. This study utilized selective laser melting (SLM) to fabricate 316L stainless steel in three directions: 45°, 90°, and 180°. These building directions were analyzed at room temperature and elevated temperatures to examine the building directions’ effects on the microstructure and tensile properties. Additionally, the impact toughness and microhardness of 316L stainless steel in different building directions were evaluated. SLM 316L stainless steel manufactures equiaxial and columnar cell structures that result in higher mechanical properties over conventionally produced 316L. The horizontal specimens exhibited a superior synergy of strength among the three building directions at room temperature, with yield stresses of 582 MPa and ultimate tensile stresses of 742 MPa. In contrast, the vertical specimen had the lowest yield stress of 474 MPa and ultimate tensile stress of 640 MPa and showed remarkably low ductility. At an elevated 400 °C temperature, strength values in all build directions decreased. Horizontal specimens have the highest mechanical properties at elevated temperatures, with a yield stress of 372 MPa and an ultimate tensile stress of 457 MPa. Overall, the horizontal and 45°-built specimens showed a better combination of mechanical properties than the vertical specimens in both temperatures. The vertical specimen had an elongation of 10.5%, which was less than half the elongation of the other building directions.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 6","pages":"1501 - 1514"},"PeriodicalIF":2.4,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Current status of research on the application of high-entropy alloys in the field of brazing 高熵合金在钎焊领域的应用研究现状
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-03-08 DOI: 10.1007/s40194-025-01991-x
Shannan Zhang, Tao Wang, Guanxing Zhang, Jian Qin, Mingzhu You, Tianran Ding, Quanbin Lu, Xingxing Wang, Yuanxun Shen, Wenbin Li
{"title":"Current status of research on the application of high-entropy alloys in the field of brazing","authors":"Shannan Zhang,&nbsp;Tao Wang,&nbsp;Guanxing Zhang,&nbsp;Jian Qin,&nbsp;Mingzhu You,&nbsp;Tianran Ding,&nbsp;Quanbin Lu,&nbsp;Xingxing Wang,&nbsp;Yuanxun Shen,&nbsp;Wenbin Li","doi":"10.1007/s40194-025-01991-x","DOIUrl":"10.1007/s40194-025-01991-x","url":null,"abstract":"<div><p>High-entropy alloys (HEAs), a novel class of solid solution alloys, represent a significant advancement in materials science and engineering, substantially enriching the field of alloy research. These materials exhibit four core effects, i.e., the high-entropy effect, lattice distortion effect, sluggish diffusion effect, and cocktail effect, which contribute to their exceptional properties, including high strength, hardness, oxidation resistance, and radiation tolerance. These characteristics provide significant advantages in brazing technology. This paper provides an overview of the fundamental concepts and weldability associated with the four core effects of HEAs, reviews recent advancements in brazing using HEAs as base materials, and summarizes research on the use of HEAs in both homologous and heterologous joints. Furthermore, it outlines key research areas, including the design of HEA brazing systems based on first-principles calculations and high-throughput methods, simulation of HEA brazing behavior, and the study of intermetallic compound formation in HEA brazing joints. These efforts aim to advance the practical application of HEAs in engineering materials.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 6","pages":"1705 - 1720"},"PeriodicalIF":2.4,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deformable convolutional autoencoder-based feature selection and recognition for acoustic emission monitoring in laser shock peening 基于变形卷积自编码器的激光冲击强化声发射监测特征选择与识别
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-03-05 DOI: 10.1007/s40194-025-01978-8
Rui Qin, Zhifen Zhang, Jing Huang, Yu Su, Guangrui Wen, Weifeng He, Xuefeng Chen
{"title":"Deformable convolutional autoencoder-based feature selection and recognition for acoustic emission monitoring in laser shock peening","authors":"Rui Qin,&nbsp;Zhifen Zhang,&nbsp;Jing Huang,&nbsp;Yu Su,&nbsp;Guangrui Wen,&nbsp;Weifeng He,&nbsp;Xuefeng Chen","doi":"10.1007/s40194-025-01978-8","DOIUrl":"10.1007/s40194-025-01978-8","url":null,"abstract":"<div><p>Laser shock peening (LSP) monitoring based on acoustic emission (AE) technology not only needs to achieve the desired monitoring accuracy, but also faces the challenges posed by the transmission and storage of high-dimensional time-series data. Existing methods mainly consider the former singularly while ignoring the latter. To address this issue, this study proposes an autoencoder-based data feature selection and a decision tree–based data feature identification method for the task of real-time LSP-AE monitoring. Specifically, the autoencoder takes deformable convolution as the core unit, which can fully consider the global and local features in the time-varying AE signals, and guide the model to obtain more valuable feature vectors through offset calculation. The decision tree model can process the encoded features efficiently and accurately, which in turn enables real-time monitoring of the laser processing quality. The encoding of high-dimensional AE signals facilitates efficient data storage, and the encoded features are more portable and operable. The feasibility and reliability of the proposed method are verified based on LSP experiments. Compared with other methods, the proposed method can simultaneously meet the requirements of monitoring accuracy and data storage by encoding the original signal. Specifically, the original time series signal with dimension 4050 is reduced to 128 dimensions and has an optimal recognition accuracy of 98.76%.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 5","pages":"1241 - 1254"},"PeriodicalIF":2.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Depositing Al–Zn–Mg–Cu alloy with different positive electrode/negative electrode ratios of CMT advance process CMT超前工艺沉积不同正负极比的Al-Zn-Mg-Cu合金
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-03-05 DOI: 10.1007/s40194-025-01998-4
Xiangyang Wu, Shanqing Xu, Ji Chen, Chuansong Wu
{"title":"Depositing Al–Zn–Mg–Cu alloy with different positive electrode/negative electrode ratios of CMT advance process","authors":"Xiangyang Wu,&nbsp;Shanqing Xu,&nbsp;Ji Chen,&nbsp;Chuansong Wu","doi":"10.1007/s40194-025-01998-4","DOIUrl":"10.1007/s40194-025-01998-4","url":null,"abstract":"<div><p>To explore the influence of electrode positive/electrode negative (EP/EN) ratio on the CMT advance-based wire arc additive manufacturing (WAAM) process for Al–Zn–Mg–Cu alloy, the behaviors of the deposition process, the microstructure and mechanical properties of Al–Zn–Mg–Cu alloy WAAM are studied. The results showed that electrical waveforms and arc/metal transfer were unstable with a low EP/EN ratio, which deteriorated the stability of WAAM. The forming accuracy of deposited samples firstly increased with the EP/EN ratio ranging from 4:16 to 13:7 and then decreased if the EP/EN ratio continued increasing. In the inter-layer region, the samples showed a combination of columnar grains and pony-size equiaxed grains with an EP/EN ratio ranging from 4:16 to 10:10, while the size and quantity of equiaxed grains increased and the columnar grains almost disappeared with a higher EP/EN ratio (≥ 13:7). The enriched alloy elements in the grain boundary were easy to form large-scale precipitated phases, which were harmful to the mechanical properties. The microhardness distribution of all samples had the apparent fluctuation along the building direction due to the existence of the microstructure evolution and pores defect. This study proved that the CMT advance process was a practicable and effective way for improving the performances of Al–Zn–Mg–Cu WAAM components with optimal EP/EN ratio.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 6","pages":"1469 - 1480"},"PeriodicalIF":2.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
High-strength heterostructure joint of 6063Al alloys manufactured by ultrasonic-assisted TLP bonding using an Zn/Mg/Zn composite interlayer 用Zn/Mg/Zn复合中间层制备6063Al合金高强度异质结构接头
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-03-01 DOI: 10.1007/s40194-025-01997-5
Yuanming Zhao, Keheng Pu, Guanhong Liu, Pu Zhao, Zhengwei Li, Zhiwu Xu, Jiuchun Yan
{"title":"High-strength heterostructure joint of 6063Al alloys manufactured by ultrasonic-assisted TLP bonding using an Zn/Mg/Zn composite interlayer","authors":"Yuanming Zhao,&nbsp;Keheng Pu,&nbsp;Guanhong Liu,&nbsp;Pu Zhao,&nbsp;Zhengwei Li,&nbsp;Zhiwu Xu,&nbsp;Jiuchun Yan","doi":"10.1007/s40194-025-01997-5","DOIUrl":"10.1007/s40194-025-01997-5","url":null,"abstract":"<div><p>As the most advanced development of low-temperature and high-strength diffusion bonding of Al alloys, the lowest joining temperature of ultrasonic-assisted transient liquid phase (U-TLP) bonding of Al alloys can only be limited to 390 °C using Zn interlayer. Further reduction of bonding temperature is an urgent need to avoid strength loss of base metal. In this work, U-TLP bonding of 6063Al alloy only required 350 °C, which was achieved in the air by a newly designed composite interlayer of Zn/Mg/Zn. The surface oxide films on metals were broken by the cavitation effect of ultrasonic in Mg-Zn eutectic liquid phase. The joint composition undergone a transition from MgZn<sub>2</sub> + η-Zn to MgZn<sub>2</sub> + η-Zn + Zn-Al eutectoid to MgZn<sub>2</sub> + Zn-Al eutectoid. Final joint of MgZn<sub>2</sub> + Zn-Al eutectoid with a strength coefficient of 100% was obtained only required an ultrasonic vibration of 180 s. The initial joint was a brittle structure composed by the MgZn<sub>2</sub> and the η-Zn phases, and it finally transformed to a reinforced structure with a network shape of the Zn-Al eutectoid-coated dispersed MgZn<sub>2</sub> particles. The joint was strengthened due to the Zn-Al eutectoid phase and MgZn<sub>2</sub> hard particles with differences in hardness based on the heterogeneous deformation strengthening theory.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 6","pages":"1721 - 1732"},"PeriodicalIF":2.4,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Identifying anomalous welding in the bud: A forecasting approach 在萌芽阶段识别异常焊接:一种预测方法
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-02-28 DOI: 10.1007/s40194-025-01994-8
Rundong Lu, Ming Lou, Yujun Xia, Yongbing Li
{"title":"Identifying anomalous welding in the bud: A forecasting approach","authors":"Rundong Lu,&nbsp;Ming Lou,&nbsp;Yujun Xia,&nbsp;Yongbing Li","doi":"10.1007/s40194-025-01994-8","DOIUrl":"10.1007/s40194-025-01994-8","url":null,"abstract":"<div><p>To forecast anomalous welding processes, we propose a novel two-stage framework that integrates generative models and adversarial learning techniques for predicting anomalies in molten pool behavior. In the first stage, the goal is to generate molten pool videos (MPVs) for future welding operations by sequentially predicting molten pool frames under consistent welding parameters. The second stage uses one-class classification on the generated molten pool images to detect anomalies. This is done by maximizing the discrepancy between outliers (anomalies) and inliers (normal behavior) while minimizing the variation within the inliers. By leveraging the generative error introduced by spatiotemporal prediction, the framework enhances the separability between normal inliers and anomalous outliers. The proposed framework was evaluated by identifying anomalies in a variety of weld seams. Our results demonstrate that the framework successfully forecasts welding anomalies on real-world MPV datasets, highlighting its potential for practical applications in defect detection and process control.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 5","pages":"1335 - 1347"},"PeriodicalIF":2.4,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Crack detection in laser-welded aluminum alloy based on the integration of generative adversarial networks 基于生成对抗网络集成的激光焊接铝合金裂纹检测
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-02-25 DOI: 10.1007/s40194-025-01952-4
Jeonghun Shin, Sanghoon Kang, Jaewon Yang, Sukjoon Hong, Minjung Kang
{"title":"Crack detection in laser-welded aluminum alloy based on the integration of generative adversarial networks","authors":"Jeonghun Shin,&nbsp;Sanghoon Kang,&nbsp;Jaewon Yang,&nbsp;Sukjoon Hong,&nbsp;Minjung Kang","doi":"10.1007/s40194-025-01952-4","DOIUrl":"10.1007/s40194-025-01952-4","url":null,"abstract":"<div><p>Monitoring weld quality in high-speed laser welding is crucial due to the complex dynamics of defect formation. Temperature-based sensors, such as infrared (IR) cameras and pyrometers, provide valuable insights into crack formation by capturing temperature distributions. However, these sensors face limitations in resolution and frequency, particularly under high-speed conditions. This study addresses these challenges by integrating a deep-learning model based on generative adversarial networks (GANs) for video frame interpolation (VFI), enhancing both resolution and frequency. This enables precise temporal synchronization between high-speed and IR camera data, facilitating robust, high-resolution crack detection. The developed CNN model effectively predicts defect occurrences in self-restraint crack test specimens of 6014-T4 aluminum during laser oscillation welding, demonstrating the feasibility of using GANs to augment input data and generate high-quality synthetic images. Both IR and high-speed camera images captured essential crack characteristics, while VFI interpolation enhanced the frame rate to 2000 fps, achieving an average peak signal-to-noise ratio (PSNR) of 39.01 dB. Confusion matrix analysis revealed high prediction accuracy, exceeding 99% across all models. The study concludes that GANs can identify significant data regions to support real-time crack detection in high-speed laser welding, with optimal pixel-to-image ratios proposed based on experimental findings.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 5","pages":"1323 - 1333"},"PeriodicalIF":2.4,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Surface structure analysis using visual high-resolution in situ process monitoring in laser powder bed fusion 利用可视化高分辨率激光粉末床熔融原位过程监控进行表面结构分析
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-02-25 DOI: 10.1007/s40194-025-01955-1
Jonathan Schmidt, Benjamin Merz, Konstantin Poka, Gunther Mohr, Kai Hilgenberg
{"title":"Surface structure analysis using visual high-resolution in situ process monitoring in laser powder bed fusion","authors":"Jonathan Schmidt,&nbsp;Benjamin Merz,&nbsp;Konstantin Poka,&nbsp;Gunther Mohr,&nbsp;Kai Hilgenberg","doi":"10.1007/s40194-025-01955-1","DOIUrl":"10.1007/s40194-025-01955-1","url":null,"abstract":"<div><p>Parameter studies are a common step in selecting process parameters for laser powder bed fusion of metals (PBF-LB/M). Density cubes are commonly used for this purpose. Density cubes manufactured with varied process parameters can exhibit distinguishable surface structures visible to the human eye. The layer-wise process enables such surface structures to be detected during manufacturing. However, industrial visual in situ monitoring systems for PBF-LB/M currently have limited resolution and are incapable of reliably capturing small differences in the surface structures. In this work, a 65 MPixel high-resolution monochrome camera was integrated into an industrial PBF-LB/M machine together with a high-intensity LED (light-emitting diode) bar. Post-exposure images were taken to analyse differences in light reflection of fused areas. It is revealed that the grey-level co-occurrence matrix can be used to quantify the visual surface structure of nickel-based superalloy Inconel®939 density cubes per layer. The properties of the grey-level co-occurrence matrix correlate to the energy input and the resulting porosity of density cubes. Low-energy samples containing lack of fusion flaws show an increased contrast in the grey-level co-occurrence matrix compared to specimens with optimal energy input. The potential of high-resolution images for quality assurance via in situ process monitoring in PBF-LB/M is further discussed.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 4","pages":"1087 - 1101"},"PeriodicalIF":2.4,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s40194-025-01955-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143581306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The role of convolutional kernels in automated welding defect detection using t-SNE and DBSCAN clustering 卷积核在基于t-SNE和DBSCAN聚类的焊接缺陷自动检测中的作用
IF 2.4 4区 材料科学
Welding in the World Pub Date : 2025-02-24 DOI: 10.1007/s40194-025-01984-w
Baoxin Zhang, Xuefeng Zhao, Haoyu Wen, Juntao Wu, Xiaopeng Wang, Na Dong, Xinghua Yu
{"title":"The role of convolutional kernels in automated welding defect detection using t-SNE and DBSCAN clustering","authors":"Baoxin Zhang,&nbsp;Xuefeng Zhao,&nbsp;Haoyu Wen,&nbsp;Juntao Wu,&nbsp;Xiaopeng Wang,&nbsp;Na Dong,&nbsp;Xinghua Yu","doi":"10.1007/s40194-025-01984-w","DOIUrl":"10.1007/s40194-025-01984-w","url":null,"abstract":"<div><p>Welding defect detection is a critical aspect of quality control in the manufacturing industry, ensuring structural integrity and preventing failures in essential infrastructure. As the demand for higher quality standards continues to rise, ensuring the reliability and safety of welded structures has become increasingly important. Traditional methods of defect detection rely heavily on manual interpretation of radiographic images, which is time-consuming and prone to inconsistencies. Automated approaches using machine learning, particularly convolutional neural networks, have emerged as a promising solution to overcome these challenges. In this study, we analyze the changes in the categories and distributions of convolutional kernels during the training process of a welding defect detection model using a convolutional neural network. In this study, we analyze the changes in the categories and distributions of convolutional kernels during the training process of a welding defect detection model using a convolutional neural network. We systematically analyze the roles of convolutional kernels in feature extraction through a combination of dimensionality reduction using t-Distributed Stochastic Neighbor Embedding and clustering using Density-Based Spatial Clustering of Applications with Noise. Our analysis reveals that convolutional kernels within the network can be categorized into four distinct types, each contributing uniquely to feature extraction. Additionally, we quantitatively track the distribution of kernel types throughout the training process, demonstrating how the model’s feature extraction strategy evolves to enhance accuracy in welding defect detection. The insights gained from this study provide guidance for optimizing convolutional neural networks to achieve improved performance in automated non-destructive testing applications.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 5","pages":"1267 - 1275"},"PeriodicalIF":2.4,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信