Weld image deep learning-based on-line defects detection using convolutional neural networks for Al alloy in robotic arc welding
تشخیص نقص تصویر جوش تشخیص عمیق مبتنی بر یادگیری عمیق برخط با استفاده از شبکه های عصبی همگرا برای آلیاژ آل در جوش قوس رباتیک-2019
Accurate on-line weld defects detection is still challenging for robotic welding manufacturing due to the complexity of weld defects. This paper studied deep learning–based on-line defects detection for aluminum alloy in robotic arc welding using Convolutional Neural Networks (CNN) and weld images. Firstly, an image acquisition system was developed to simultaneously collect weld images, which can provide more information of the real-time weld images from different angles including top front, top back and back seam. Then, a new CNN classification model with 11 layers based on weld image was designed to identify weld penetration defects. In order to improve the robustness and generalization ability of the CNN model, weld images from different welding current and feeding speed were captured for the CNN model. Based on the actual industry challenges such as the instability of welding arc, the complexity of the welding environment and the random changing of plate gap condition, two kinds of data augmentation including noise adding and image rotation were used to boost the CNN dataset while parameters optimization was carried out. Finally, non-zero pixel method was proposed to quantitatively evaluate and visualize the deep learning features. Furthermore, their physical meaning were clearly explained. Instead of decreasing the interference from arc light as in traditional way, the CNN model has taken full use of those arc lights by combining them in a various way to form the complementary features. Test results shows that the CNN model has better performance than our previous work with the mean classification accuracy of 99.38%. This paper can provide some guidance for on-line detection of manufacturing quality in metal additive manufacturing (AM) and laser welding.
Keywords: Deep learning | Defects detection | Al alloy | Robotic arc welding | Convolutional neural networks | Weld images | Feature visualization
Parallel multiphase field simulations with OpenPhase
شبیه سازی زمینه چند فازی موازی با OpenPhase-2017
The open-source software project OpenPhase allows the three-dimensional simulation of microstructural evolution using the multiphase field method. The core modules of OpenPhase and their implementation as well as their parallelization for a distributed-memory setting are presented. Especially communication and load-balancing strategies are discussed. Synchronization points are avoided by an increased halo-size, i.e. additional layers of ghost cells, which allow multiple stencil operations without data exchange. Load balancing is considered via graph-partitioning and sub-domain decomposition. Results are presented for performance benchmarks as well as for a variety of applications, e.g. grain growth in polycrystalline materials, including a large number of phase fields as well as Mg–Al alloy solidification.
Keywords: Material science | Phase field | Parallel computing | Load-balancing
Analysis of Surface Roughness in Hard Turning Using Wiper Insert Geometry
تجزیه و تحلیل ناهمواریهای سطحی در تبدیل سخت با استفاده از جادادن هندسی برف پاک کن-2016
© 2015 The Authors. Published by Elsevier B.V.Peer-review under responsibility of the Scientific Committee of 48th CIRP Conference on MANUFACTURING SYSTEMS - CIRP CMS 2015.Hard turning process is currently replacing the conventional grinding operations in many industries. If properly designed, hard turning can give equivalent results to grinding process in terms of accuracy and machined surface quality. Wiper inserts are being used in machining operations because of their competence to generate superior machined surface. Surface roughness is major requirement for many industrial components and is one of the important parameter considered to describe machinability of metals and metal alloys. This paper investigates performance of wiper inserts in hard turning of oil hardening non-shrinking steel. The oil hardening non-shrinking steel is commonly used material for making measuring instruments and gauges wherein surface roughness is very important aspect. The major emphasis here is given to study and compare performance of wiper insert in terms of surface finish with conventional inserts. Influence of process parameters such as speed, feed, depth of cut and nose radius (for wiper and conventional inserts) on surface roughness is analyzed using analysis of variance (ANOVA) and analysis of means (AOM) plots. From the analysis, it can be clearly seen that wiper inserts produce a very good machined surface compared to conventional inserts.© 2015 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).Peer-review under responsibility of the scientific committee of 48th CIRP Conference on MANUFACTURING SYSTEMS - CIRP CMS 2015
Keywords: Hard turning | surface roughness | wiper inserts | machining