Generalisable 3D printing error detection and correction via multi-head neural networks

Brion, Douglas A. J.; Pattinson, Sebastian W.

doi:10.1038/s41467-022-31985-y

Cited by 60 publications

(15 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The apparent limitations of parts created using AM, including structural flaws diminished strength between layers, shape deformation, machine failures, and the additional material required to create supports for overhanging regions, pose substantial barriers to its adoption as a mainstream technology. Because of this, a growing field of research has centered on overcoming these limitations through the use of AI systems.…”

Section: Applicationsmentioning

confidence: 99%

“…271 Notably, computational tools that improve these areas may also be applied to other applications such as recyclability of materials for large-scale applications such as printing with recycled concrete. 279 The apparent limitations of parts created using AM, including structural flaws 280 diminished strength between layers, 281 shape deformation, 282 machine failures, 283 and the additional material required to create supports for overhanging regions, 284 pose substantial barriers to its adoption as a mainstream technology. Because of this, a growing field of research has centered on overcoming these limitations through the use of AI systems.…”

Section: Additive Manufacturingmentioning

confidence: 99%

See 1 more Smart Citation

Computational Design and Manufacturing of Sustainable Materials through First-Principles and Materiomics

et al. 2023

View full text Add to dashboard Cite

Engineered materials are ubiquitous throughout society and are critical to the development of modern technology, yet many current material systems are inexorably tied to widespread deterioration of ecological processes. Next-generation material systems can address goals of environmental sustainability by providing alternatives to fossil fuel-based materials and by reducing destructive extraction processes, energy costs, and accumulation of solid waste. However, development of sustainable materials faces several key challenges including investigation, processing, and architecting of new feedstocks that are often relatively mechanically weak, complex, and difficult to characterize or standardize. In this review paper, we outline a framework for examining sustainability in material systems and discuss how recent developments in modeling, machine learning, and other computational tools can aid the discovery of novel sustainable materials. We consider these through the lens of materiomics, an approach that considers material systems holistically by incorporating perspectives of all relevant scales, beginning with first-principles approaches and extending through the macroscale to consider sustainable material design from the bottom-up. We follow with an examination of how computational methods are currently applied to select examples of sustainable material development, with particular emphasis on bioinspired and biobased materials, and conclude with perspectives on opportunities and open challenges.

show abstract

Section: Applicationsmentioning

confidence: 99%

Section: Additive Manufacturingmentioning

confidence: 99%

Computational Design and Manufacturing of Sustainable Materials through First-Principles and Materiomics

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In the past, Luyang Xu et al proposed an improved model based on the YOLO v4 network structure to detect ow defects [6]. Douglas A. J. Brion et al proposed a method for detecting and correcting 3D printing errors using a multi-head neural network [7]. Guo Dong Goh et al proposed four trained models, YOLOv3 and YOLOv4, including their "tiny" variants [8].…”

Section: Introductionmentioning

confidence: 99%

An Improved 3D Printing Extrusion Defect Detection Method Based On YOLO-v8

Cao,

Fu,

et al. 2024

Preprint

View full text Add to dashboard Cite

Additive manufacturing (AM) technology finds widespread use in consumer and industrial manufacturing. However, large-scale 3D printers in the manufacturing industry encounter challenges like extended printing times, high nozzle flow, and maintaining flow stability. Addressing these issues necessitates thorough research and optimization of 3D printers to enhance printing efficiency and stability. This study proposes a real-time monitoring system for identifying flow defects in large 3D printers using machine vision. The system comprises a camera capturing extrusion images, a computer processing real-time screens, and a lower computer within the monitoring system designed for real-time monitoring and correction of flow quality in large 3D printers. Defects are detected and image data captured by adjusting the extrusion speed, while an attention mechanism module optimizes the YOLOv8 model. The model is trained for deep learning using mAP50 as the performance evaluation index, achieving a mean average precision (mAP) of 92.1%. Subsequently, the optimized model is deployed on a host computer. Upon detecting flow defects, it sends commands to a Raspberry Pi, generating G-code commands to adjust extrusion speed and relay them to the 3D printer. This enables real-time monitoring and automatic calibration of the printing process. The study presents an effective solution for real-time monitoring and calibration in closed-loop processes within additive manufacturing.

show abstract

“…These reviews show that thermal and optical methods, the ones most commonly used, have already been successfully demonstrated for defect detection and closed-loop control purposes. State-of-the-art examples of this are geometry monitoring through optical measurements with a digital twin 11 , real-time defect detection through measuring of melt pool temperature deviations 12 , real-time defect detection through comparison of combined thermal and optical imaging to a baseline 13 , real-time error detection and correction with cameras in combination with large-scale machine learning 5 and a method to link real-time defect detection with an optical camera to structural part quality 14 .…”

Section: Introductionmentioning

confidence: 99%

“…It offers simplicity, low cost and a wide variety of available materials and is therefore used in applications as diverse as aerospace, automotive, electronics, prosthetics, fashion, construction and education 2,3 . Despite its advantages, FFF is vulnerable to errors and failures due to uncertainties in equipment and process, limiting its consistency and time-and resource-efficiency 4,5 . These failures typically result in geometric deviations, voids, warping, compromised mechanical properties, delamination, lack of material and bad surface quality 6,7 .…”

Section: Introductionmentioning

confidence: 99%

FFF print defect characterization through in-situ electrical resistance monitoring

Jonkers,

Dijkshoorn,

Stramigioli

et al. 2024

Preprint

View full text Add to dashboard Cite

Fused Filament Fabrication is a popular fabrication technique. Currently there is a need for in-situ monitoring modalities to gather real-time information on prints, both for quality control and closed-loop control. Despite current advancements, effective and affordable in-situ monitoring techniques for non-destructive defect detection of voids and bonding quality are still limited. This work demonstrates in-situ monitoring of Fused Filament Fabrication through electrical resistance measurements as an alternative to thermal and optical methods. A new, easy-to-implement setup is demonstrated which measures the electrical resistance of a conductively doped filament between the nozzle and single or multi-electrodes on the bed. Defects can be located in an unprecedented way with the use of encoded axes in combination with the observed resistance variations throughout the part. A model of the anisotropic electrical conduction is used to interpret the measurements, which matches well with the data. Warping, inter-layer adhesion, under-extrusion and overhang sagging print defects can be observed in the measurements of parts with a complex geometry, which would be difficult to measure otherwise. Altogether in-situ electrical resistance monitoring offers a tool for optimising prints by online studying the influence of the print parameters for quality assessment and it opens up possibilities for closed-loop control.

show abstract

Generalisable 3D printing error detection and correction via multi-head neural networks

Cited by 60 publications

References 67 publications

Computational Design and Manufacturing of Sustainable Materials through First-Principles and Materiomics

Computational Design and Manufacturing of Sustainable Materials through First-Principles and Materiomics

An Improved 3D Printing Extrusion Defect Detection Method Based On YOLO-v8

FFF print defect characterization through in-situ electrical resistance monitoring

Contact Info

Product

Resources

About