Image Segmentation for Defect Analysis in Laser Powder Bed Fusion: Deep Data Mining of X-Ray Photography from Recent Literature

Zhang, Jiahui; Lyu, Tianyi; Hua, Yujie; Shen, Zeren; Sun, Qiang; Ye, Rong; Zou, Yu

doi:10.1007/s40192-022-00272-5

Cited by 7 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 2 below, IoU and BF-score are high and close to 1 for both datasets 1 and 2 for run 1, which means that this method successfully segments out the keyhole region in test datasets. Considering IoU, this method is on the same level as other segmentation tools proposed in previous works, and a high BF-score further validates the segmentation accuracy on the boundary [14]. The same tool is later tested using cross-validation, with three more runs trained and tested as Table 3 below.…”

Section: Testing and Performance Matricesmentioning

confidence: 83%

“…More specifically, sufficient data for machine learning-based pore prediction for many types of LPBF systems, conditions, and alloys, will require very large efforts to label keyhole morphologies unless accessible automatic tools that can segment the keyholes are developed. Several automatic tools have recently been explored in previous works: Pyeon et al developed a non-machine learning-based semi-automatic keyhole region extraction tool [13], and Zhang et al tested several semantic segmentation and object detection models and compared the performances of extracting keyholes and pores at the same time [14]. However, the filter developed by Pyeon et al was only tested with clean images without metal powder, and models tested by Zhang et al segment both keyholes and pores in the same classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep-Learning-Based Segmentation of Keyhole in In-Situ X-ray Imaging of Laser Powder Bed Fusion

Dong,

Lian,

Yan

et al. 2024

Materials

View full text Add to dashboard Cite

In laser powder bed fusion processes, keyholes are the gaseous cavities formed where laser interacts with metal, and their morphologies play an important role in defect formation and the final product quality. The in-situ X-ray imaging technique can monitor the keyhole dynamics from the side and capture keyhole shapes in the X-ray image stream. Keyhole shapes in X-ray images are then often labeled by humans for analysis, which increasingly involves attempting to correlate keyhole shapes with defects using machine learning. However, such labeling is tedious, time-consuming, error-prone, and cannot be scaled to large data sets. To use keyhole shapes more readily as the input to machine learning methods, an automatic tool to identify keyhole regions is desirable. In this paper, a deep-learning-based computer vision tool that can automatically segment keyhole shapes out of X-ray images is presented. The pipeline contains a filtering method and an implementation of the BASNet deep learning model to semantically segment the keyhole morphologies out of X-ray images. The presented tool shows promising average accuracy of 91.24% for keyhole area, and 92.81% for boundary shape, for a range of test dataset conditions in Al6061 (and one AliSi10Mg) alloys, with 300 training images/labels and 100 testing images for each trial. Prospective users may apply the presently trained tool or a retrained version following the approach used here to automatically label keyhole shapes in large image sets.

show abstract

Section: Testing and Performance Matricesmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Segmentation of Keyhole in In-Situ X-ray Imaging of Laser Powder Bed Fusion

Dong,

Lian,

Yan

et al. 2024

Materials

View full text Add to dashboard Cite

show abstract

“…As discussed in Section 4.2, the detachment-based SOTA involves using image segmentation to determine when the melt pool (MP) divides into separate volumes. Image segmentation has garnered significant attention in additive manufacturing (AM) research, leading to various successful models tailored to specific AM-related segmentation problems [31]. On the contrary, the Segment Anything Model (SAM) [30], developed by Meta, stands out due to its zero-shot learning capabilities, which allow it to operate across new datasets without further training or finetuning.…”

Section: Appendix Amentioning

confidence: 99%

Monitoring Variability in Melt Pool Spatiotemporal Dynamics (VIMPS): Towards Proactive Humping Detection in Additive Manufacturing

Hassan,

Lee

et al. 2024

JMMP

View full text Add to dashboard Cite

Humping is a common defect in direct energy deposition processes that reduces the geometric integrity of printed products. The available literature on humping detection is deemed reactive, as they focus on detecting late-stage melt pool spatial abnormalities. Therefore, this work introduces a novel, proactive indicator designed to detect early-stage spatiotemporal abnormalities. Specifically, the proposed indicator monitors the variability of instantaneous melt pool solidification-front speed (VIMPS). The solidification front dynamics quantify the intensity of cyclic melt pool elongation induced by early-stage humping. VIMPS tracks the solidification front dynamics based on the variance in the melt pool infrared radiations. Qualitative and quantitive analysis of the collected infrared data confirms VIMPS’s utility in reflecting the intricate humping-induced dynamics and defects. Experimental results proved VIMPS’ proactivity. By capturing early spatiotemporal abnormalities, VIMPS predicted humping by up to 10 s before any significant geometric defects. In contrast, current spatial abnormality-based methods failed to detect humping until 20 s after significant geometric defects had occurred. VIMPS’ proactive detection capabilities enable effective direct energy deposition control, boosting the process’s productivity and quality.

show abstract

“…As discussed in Section0, the detachment-based SOTA involves using image segmentation to determine when the melt pool (MP) divides into separate volumes. Image segmentation has garnered significant attention in additive manufacturing (AM) research, leading to various successful models tailored to specific AM-related segmentation problems [31]. On the contrary, the Segment Anything Model (SAM) [30], developed by Meta, stands out due to its zero-shot learning capabilities, which allow it to operate across new datasets without further training or finetuning.…”

Section: Fundingmentioning

confidence: 99%

VIMPS: Physics-Based Spatiotemporal Indicator for Proactive Humping Detection in Metal Additive Manufacturing

Hassan,

Lee

et al. 2024

Preprint

View full text Add to dashboard Cite

Direct Energy Deposition (DED) is a versatile and efficient method in metal additive manufacturing. However, humping, caused by abnormal dynamics in the melt pool (MP), poses a significant threat to the geometric integrity of manufactured products. Current state-of-the-art (SOTA) methods primarily detect humping by analyzing late-stage spatial abnormalities, such as MP detachment. This approach is fundamentally reactive, leading to a tendency to miss early humping spatiotemporal dynamics, like cyclic elongation of the MP. This study introduces a novel, proactive indicator named VIMPS (Variability of Instantaneous MP Solidification-Front Speed), a physics-based tool designed to quantify early abnormal fluctuations in MP solidification speed. The experiments demonstrate VIMPS correlation with humping-induced geometric inaccuracies. By capturing early spatiotemporal dynamics of the MP, VIMPS reduces detection latency by 30 seconds compared to existing SOTAs that focus solely on spatial abnormalities. This significant improvement transforms detection from reactive to proactive, providing the time needed for corrective actions to enhance the overall productivity and quality of the DED process.

show abstract

Image Segmentation for Defect Analysis in Laser Powder Bed Fusion: Deep Data Mining of X-Ray Photography from Recent Literature

Cited by 7 publications

References 33 publications

Deep-Learning-Based Segmentation of Keyhole in In-Situ X-ray Imaging of Laser Powder Bed Fusion

Deep-Learning-Based Segmentation of Keyhole in In-Situ X-ray Imaging of Laser Powder Bed Fusion

Monitoring Variability in Melt Pool Spatiotemporal Dynamics (VIMPS): Towards Proactive Humping Detection in Additive Manufacturing

VIMPS: Physics-Based Spatiotemporal Indicator for Proactive Humping Detection in Metal Additive Manufacturing

Contact Info

Product

Resources

About