Welding in the World最新文献

Virtual reality based programming of human-like torch operation for robotic welding 基于虚拟现实技术的机器人焊枪仿人操作编程

IF 2.4 4区材料科学

Welding in the World Pub Date : 2025-03-15 DOI: 10.1007/s40194-025-01946-2

Yijie Hu, Jun Xiao, Shujun Chen, Shengnan Gai

{"title":"Virtual reality based programming of human-like torch operation for robotic welding","authors":"Yijie Hu, Jun Xiao, Shujun Chen, Shengnan Gai","doi":"10.1007/s40194-025-01946-2","DOIUrl":"10.1007/s40194-025-01946-2","url":null,"abstract":"<div><p>In complex welding tasks, skilled manual welders often outperform welding robots, primarily due to their expertise in torch manipulation. To address this, a robotic welding teaching system was developed to assist welders in controlling the torch. This system utilizes human–robot interaction to track the welder's movements, significantly enhancing the welding robot's ability to handle intricate weld seams. A virtual welding robot module, created in Unity3D with virtual reality (VR) technology, closely replicates the real robot. This module is integrated with a human–robot interaction interface and a welder operation module. Motion mapping strategies were devised to transfer the welder's movements from the handle to the welding torch, including \"static\", \"dynamic\", \"velocity\" and \"acceleration\" strategies. These strategies were tested across four trajectories: linear, arc, sinusoidal, and spatial intersection curves. The results revealed the superiority of the \"dynamic\" strategy. Further evaluations of the teaching system's performance—specifically its \"trajectory accuracy\", \"trajectory delay\" and \"time delay\"—were conducted for straight lines, arcs, and flip motions. The test results showed that, within the operating speed range of 1 to 40 mm/s and 10 to 40°/s, the system's time delay is less than 0.12 s, with actual trajectory errors remaining below 0.06 mm and 0.1°. These performance metrics demonstrate that the system effectively meets the requirements for precise tracking of both the weld seam and torch manipulation.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 5","pages":"1447 - 1458"},"PeriodicalIF":2.4,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835702","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

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, Zhifen Zhang, Jing Huang, Yu Su, Guangrui Wen, Weifeng He, 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

Identifying anomalous welding in the bud: A forecasting approach

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

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, Benjamin Merz, Konstantin Poka, Gunther Mohr, 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

Crack detection in laser-welded aluminum alloy based on the integration of generative adversarial networks

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, Sanghoon Kang, Jaewon Yang, Sukjoon Hong, 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

The role of convolutional kernels in automated welding defect detection using t-SNE and DBSCAN clustering

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, Xuefeng Zhao, Haoyu Wen, Juntao Wu, Xiaopeng Wang, Na Dong, 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

Editorial: Advances in intelligent welding manufacturing

IF 2.4 4区材料科学

Welding in the World Pub Date : 2025-02-21 DOI: 10.1007/s40194-025-01992-w

YuMing Zhang, Stephan Egerland, Zengxi Stephen Pan

引用次数: 0

Effect of surface roughness on rotating fatigue strength of as-built AlSi10Mg produced by laser powder bed fusion 表面粗糙度对激光粉末床熔融法生产的坯料 AlSi10Mg 旋转疲劳强度的影响

IF 2.4 4区材料科学

Welding in the World Pub Date : 2025-02-18 DOI: 10.1007/s40194-025-01963-1

Andrea El Hassanin, Umberto Prisco

{"title":"Effect of surface roughness on rotating fatigue strength of as-built AlSi10Mg produced by laser powder bed fusion","authors":"Andrea El Hassanin, Umberto Prisco","doi":"10.1007/s40194-025-01963-1","DOIUrl":"10.1007/s40194-025-01963-1","url":null,"abstract":"<div><p>AlSi10Mg samples with as-built surfaces characterized by three levels of increasing roughness were fabricated varying the building orientation by laser powder bed fusion. In particular, the sample axis was oriented at 0<span>(^{circ })</span>, 90<span>(^{circ })</span>, and 45<span>(^{circ })</span> with respect to the building direction. It is demonstrated that roughness directly influences the fatigue performance of as-built samples, since cracks initiate at surface notches related to features produced by surface roughness. Rougher surfaces generate higher concentration stress and show lower cyclic properties. Then, the rotating fatigue strength of the samples is non-destructively estimated using Murakami’s square root area parameter model. The equivalent size of the defect was calculated from the roughness parameters <b><i>S</i></b><span>(_{text {z}})</span> and <b><i>R</i></b><span>(_{text {Sm}})</span>. The model gives a good correlation with the experimental data, and then it can be applied to evaluate the fatigue strength of as-built AlSi10Mg. These results are important for the reliable design in terms of fatigue strength of selective laser-melted AlSi10Mg components.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 4","pages":"1123 - 1133"},"PeriodicalIF":2.4,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143581316","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

Multiscale FE modeling of SLMed ASS316 L reinforced with nanoparticles during FSP: exploring the impact of particle volume fraction, shape, and type on mechanical strength 用纳米颗粒强化 SLMed ASS316 L 的多尺度 FE 建模：探索颗粒体积分数、形状和类型对机械强度的影响

IF 2.4 4区材料科学

Welding in the World Pub Date : 2025-02-17 DOI: 10.1007/s40194-025-01985-9

Ali Ebrahimpour, Morteza Omidi, Amir Mostafapour

{"title":"Multiscale FE modeling of SLMed ASS316 L reinforced with nanoparticles during FSP: exploring the impact of particle volume fraction, shape, and type on mechanical strength","authors":"Ali Ebrahimpour, Morteza Omidi, Amir Mostafapour","doi":"10.1007/s40194-025-01985-9","DOIUrl":"10.1007/s40194-025-01985-9","url":null,"abstract":"<div><p>This study investigates the effect of nanoparticle volume fraction, shape, and type on the strength of nanocomposites made of selective laser melted (SLM) austenitic stainless steel (AISI 316L) reinforced with nanoparticles during friction stir processing (FSP). Using the mean field homogenization (MFH) method with the Mori–Tanaka model, multiscale finite element simulations were conducted to predict the mechanical behavior of the composites. These simulations were validated through experimental tests, yielding consistent results, with tensile strength reaching 740 MPa for reinforced sample, compared to 670 MPa for unreinforced FSP-treated material. A systematic design of experiments (DOE) was implemented using response surface methodology (RSM), generating 15 sample configurations. The strength of these configurations was calculated via finite element modeling. Analysis of variance (ANOVA) was then performed to evaluate the direct and interaction effects of the parameters, identifying the volume fraction as the most critical factor, with significant contributions from particle shape and type. A mathematical model derived from the ANOVA results demonstrated strong predictive accuracy (<i>R</i><sup>2</sup> = 98.33%) and was validated against simulation data. This integrated framework underscores the potential of combining experimental and computational techniques for optimizing metal matrix nanocomposites in advanced engineering applications.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 4","pages":"1135 - 1147"},"PeriodicalIF":2.4,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s40194-025-01985-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143581199","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

Improving accuracy and precisely controlling molten pool of stepped filling wire–assisted DP-GTA-AM

IF 2.4 4区材料科学

Welding in the World Pub Date : 2025-02-17 DOI: 10.1007/s40194-025-01980-0

Gang Zhang, Jianbo Wang, Zhen Wen Zhu, Lu Peng Li, Yu Shi

{"title":"Improving accuracy and precisely controlling molten pool of stepped filling wire–assisted DP-GTA-AM","authors":"Gang Zhang, Jianbo Wang, Zhen Wen Zhu, Lu Peng Li, Yu Shi","doi":"10.1007/s40194-025-01980-0","DOIUrl":"10.1007/s40194-025-01980-0","url":null,"abstract":"<div><p>Conventional wire arc additive manufacturing (WAAM) possesses inherent attributes, including the robust coupling interaction between the arc-droplet and the weld pool, non-linear time-varying, and heat accumulation. These characteristics often lead to suboptimal deposition processes and morphologies. This paper introduced a novel double-pulsed gas tungsten arc welding additive manufacturing (DP-GTAW-AM) process, which utilized a stepped filling wire to achieve independent control of heat input and mass transfer during the WAAM process. The fundamental principle of the proposed process was illustrated, and the construction of the experimental system was detailed. A series of experiments was conducted to verify the decoupling of heat-mass transfer. Moreover, the droplet transfer behavior, molten pool variation, and morphological changes as deposition layers increase were analyzed utilizing visual images and mathematical modeling. The results indicate that a stable heat-mass transfer process is achieved, resulting in deposited layers with the desired accuracy. This demonstrates the feasibility of improving deposition accuracy in WAAM by controlling pulse parameters. This approach offers a promising method for precise control of deposition accuracy in industrial WAAM applications.</p></div>","PeriodicalId":809,"journal":{"name":"Welding in the World","volume":"69 5","pages":"1255 - 1266"},"PeriodicalIF":2.4,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835643","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