Deep Learning Applied to Defect Detection in Powder Spreading Process of Magnetic Material Additive Manufacturing

Chen, Hsin-Yu; Lin, Ching‐Chih; Horng, Ming-Huwi; Chang, Lien-Kai; Hsu, Jian-Han; Chang, Tsan‐Kuo; Hung, Jhih-Chen; Lee, Rong-Mao; Tsai, Mi-Ching

doi:10.3390/ma15165662

Cited by 14 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al. [25] proposed a two‐stage Convolutional Neural Network (CNN) based approach for defect detection in metal laser melting manufacturing (MAM). In this detection method, images are recorded by powder bed fusion equipment.…”

Section: Related Workmentioning

confidence: 99%

Ensemble learning based defect detection of laser sintering

Xin,

Faheem,

Umer

et al. 2023

IET Optoelectronics

View full text Add to dashboard Cite

In rapid development, Selective Laser Sintering (SLS) creates prototypes by processing industrial materials, for example, polymers. Such materials are usually in powder form and fused by a laser beam. The manufacturing quality depends on the interaction between a high‐energy laser beam and the powdered material. However, in‐homogeneous temperature distribution, unstable laser powder, and inconsistent powder densities can cause defects in the final product, for example, Powder Bed Defects. Such factors can lead to irregularities, for example, warping, distortion, and inadequate powder bed fusion. These irregularities may affect the profitable SLS production. Consequently, detecting powder bed defects requires automation. An ensemble learning‐based approach is proposed for detecting defects in SLS powder bed images from this perceptive. The proposed approach first pre‐processes the images to reduce the computational complexity. Then, the Convolutional Neural Network (CNN) based ensembled models (off‐the‐shelf CNN, bagged CNN, and boosted CNN) are implemented and compared. The ensemble learning CNN (bagged and boosted CNN) is good for powder bed detection. The evaluation results indicate that the performance of bagged CNN is significant. It also indicates that preprocessing of the images, mainly cropping to the region of interest, improves the performance of the proposed approach. The training and testing accuracy of the bagged CNN is 96.1% and 95.1%, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Ensemble learning based defect detection of laser sintering

Xin,

Faheem,

Umer

et al. 2023

IET Optoelectronics

View full text Add to dashboard Cite

show abstract

“…While additive manufacturing technologies have seen significant development and yielded promising outcomes, ensuring the mechanical integrity of the manufactured components remains a challenge. It is necessary to maintain caution in monitoring the AM process and inspecting the parts' quality during production [8]. Detecting defects in the early stages of printing could trigger an alert to either pause or halt the printing process.…”

Section: Introductionmentioning

confidence: 99%

Condition Monitoring in Additive Manufacturing: A Critical Review of Different Approaches

Khanafer,

Cao,

Kokash

2024

JMMP

View full text Add to dashboard Cite

This critical review provides a comprehensive analysis of various condition monitoring techniques pivotal in additive manufacturing (AM) processes. The reliability and quality of AM components are contingent upon the precise control of numerous parameters and the timely detection of potential defects, such as lamination, cracks, and porosity. This paper emphasizes the significance of in situ monitoring systems—optical, thermal, and acoustic—which continuously evaluate the integrity of the manufacturing process. Optical techniques employing high-speed cameras and laser scanners provide real-time, non-contact assessments of the AM process, facilitating the early detection of layer misalignment and surface anomalies. Simultaneously, thermal imaging techniques, such as infrared sensing, play a crucial role in monitoring complex thermal gradients, contributing to defect detection and process control. Acoustic monitoring methods augmented by advancements in audio analysis and machine learning offer cost-effective solutions for discerning the acoustic signatures of AM machinery amidst variable operational conditions. Finally, machine learning is considered an efficient technique for data processing and has shown great promise in feature extraction.

show abstract

“…[5]. Problems intensify in the case of powders with low flowability caused by the existence of irregular or elongated particles [6] or having magnetic properties [7]. Such materials include iron-based metallic glasses that are often characterized by soft magnetic properties [8] and are extensively applied in the SLM process [9].…”

Section: Introductionmentioning

confidence: 99%

Application of machine vision for the detection of powder bed defects in additive manufacturing processes

Korzeniowski,

Małachowska,

Wiatrzyk

2023

Materials Science-Poland

View full text Add to dashboard Cite

The quality of the powder layers in the 3D printing process is extremely important and directly corresponds to the quality of the structures made with this technology. Therefore, it is essential to control it. It can be made in-line with a vision system combined with image processing algorithms, which can significantly improve control of the process and help with the adjustment of powder spreading systems, especially in case of difficult-to-feed powders like magnetic ones – e.g., Fe-based metallic glass powder – Fe56.04Co13.45Nb5.5B25. In this work, two algorithms – machine learning – Support Vector Machines (SVM), deep learning – Convolutional Neural Networks (CNN) – were evaluated for their ability to detect and classify the enumerated anomalies based on powder layer images. The SVM algorithm makes it possible to efficiently and quickly analyze the powder-spreading process. CNN, however, appears to be a more promising choice for the developed application, as they alleviate the need for complex image operations.

show abstract

Deep Learning Applied to Defect Detection in Powder Spreading Process of Magnetic Material Additive Manufacturing

Cited by 14 publications

References 27 publications

Ensemble learning based defect detection of laser sintering

Ensemble learning based defect detection of laser sintering

Condition Monitoring in Additive Manufacturing: A Critical Review of Different Approaches

Application of machine vision for the detection of powder bed defects in additive manufacturing processes

Contact Info

Product

Resources

About