Monitoring of welding status by molten pool morphology during high-power disk laser welding

Gao, Xiangdong; Zhang, Yanxi

doi:10.1016/j.ijleo.2015.04.060

Cited by 44 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, emissions in the VIS can be used to determine keyhole length in deep penetration welding which allows the adjustment of the laser power in-situ in order to realize a defined penetration depth [2]. By adaption of the illumination, the morphology of parts of the process zone can be measured and correlated to process stability [59].…”

Section: Process Understanding 231 Process Observationmentioning

confidence: 99%

Advances in macro-scale laser processing

Schmidt

Zäh

et al. 2018

CIRP Annals

View full text Add to dashboard Cite

Section: Process Understanding 231 Process Observationmentioning

confidence: 99%

Advances in macro-scale laser processing

Schmidt

Zäh

et al. 2018

CIRP Annals

View full text Add to dashboard Cite

“…The low relative density can be attributed to the insufficient melting for 40 W power and more than 1000 mm/s scanning speed. We can find the width of tracks will narrow down when speed increase, which also leads to a shallow molten pool [ 33 ]. As a result, the shallow molten pool remelts of fewer previously printed layers to leave plenty of powders and cracks in the cubes.…”

Section: Resultsmentioning

confidence: 99%

Achieving Triply Periodic Minimal Surface Thin-Walled Structures by Micro Laser Powder Bed Fusion Process

Ding

Song

2021

Micromachines

View full text Add to dashboard Cite

Recently, triply periodic minimal surface (TPMS) lattice structures have been increasingly employed in many applications, such as lightweighting and heat transfer, and they are enabled by the maturation of additive manufacturing technology, i.e., laser powder bed fusion (LPBF). When the shell-based TPMS structure’s thickness decreases, higher porosity and a larger surface-to-volume ratio can be achieved, which results in an improvement in the properties of the lattice structures. Micro LPBF, which combines finer laser beam, smaller powder, and thinner powder layer, is employed in this work to fabricate the thin-walled structures (TWS) of TPMS lattice by stainless steel 316 L (SS316L). Utilizing this system, the optimal parameters for printing TPMS-TWS are explored in terms of densification, smoothness, limitation of thickness, and dimensional accuracy. Cube samples with 99.7% relative density and a roughness value of 2.1 μm are printed by using the energy density of 100 J/mm3. Moreover, a thin (100 μm thickness) wall structure can be fabricated through optimizing parameters. Finally, the TWS samples with various TPMS structures are manufactured to compare their heat dissipation capability. As a result, TWS sample of TPMS lattice exhibits a larger temperature gradient in the vertical direction compared to the benchmark sample. The steady-state temperature of the sample base presents a 7 K decrease via introducing TWS.

show abstract

“…At present, surface defects detection methods mainly include traditional image processing methods and deep learning methods [1][2][3]. Traditional image processing methods detect targets through edge detection, threshold segmentation, feature histogram, classical machine learning methods [2,[4][5][6][7][8][9][10] (support vector machine, k-Nearest Neighbor method and Naive Bayes, neural network, decision tree, etc.). Literature [11] constructed neural network to detect welding defects under alternating/rotating magnetic field, and the test detection accuracy is 94.1%.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Detection Algorithm for Surface Defects of Automobile Door Seals

2022

Teh. vjesn.

View full text Add to dashboard Cite

The surface defects of automobile door seals are mainly detected manually at present, which is costly and has low efficiency. Therefore, a deep learning automatic detection algorithm of automobile door seals is studied in this paper. At first, the defects are classified and the data set is made according to the geometric characteristics of the defects. While enhancing the data set, the K-means clustering algorithm is used to cluster the target annotation frame in the data set, and the anchor that matches with the surface defect size of the seal is obtained. Finally, in view of the characteristics of large variation range of defect size, the target detection algorithm YOLOV3 is selected as the basic framework. Meanwhile, considering the high proportion of small and medium-sized targets in defects, the output scale is introduced at 4 times of the sampling position of YOLOV3 backbone network. In order to further enhance the correlation between the extracted features and the channel, spatial position and coordinate position, the feature fusion and attention mechanism module is constructed. The test results show that the mean of the average precision is improved by 4.81% compared with YOLOV3.

show abstract

Monitoring of welding status by molten pool morphology during high-power disk laser welding

Cited by 44 publications

References 18 publications

Advances in macro-scale laser processing

Advances in macro-scale laser processing

Achieving Triply Periodic Minimal Surface Thin-Walled Structures by Micro Laser Powder Bed Fusion Process

Deep Learning Detection Algorithm for Surface Defects of Automobile Door Seals

Contact Info

Product

Resources

About