In situ real time defect detection of 3D printed parts

2017 ◽  
Vol 17 ◽  
pp. 135-142 ◽  
Author(s):  
Oliver Holzmond ◽  
Xiaodong Li
Keyword(s):  
Real Time ◽  
Defect Detection ◽  
3D Printed

scholarly journals Analytical modelling of in situ layer-wise defect detection in 3D-printed parts: additive manufacturing

2020 ◽  
Vol 111 (7-8) ◽  
pp. 2311-2321
Author(s):  
Oluwole K. Bowoto ◽  
Bankole I. Oladapo ◽  
S. A. Zahedi ◽  
Francis T. Omigbodun ◽  
Omonigho P. Emenuvwe
Keyword(s):  
Additive Manufacturing ◽  
Defect Detection ◽  
Analytical Modelling ◽  
3D Printed

scholarly journals Towards real-time in-situ monitoring of hot-spot defects in L-PBF: a new classification-based method for fast video-imaging data analysis

2021 ◽  
Author(s):  
Matteo Bugatti ◽  
Bianca Maria Colosimo
Keyword(s):  
Additive Manufacturing ◽  
Real Time ◽  
Process Monitoring ◽  
Defect Detection ◽  
High Speed ◽  
Data Extraction ◽  
In Situ Monitoring ◽  
Imaging Data ◽  
Computational Speed

AbstractThe increasing interest towards additive manufacturing (AM) is pushing the industry to provide new solutions to improve process stability. Monitoring is a key tool for this purpose but the typical AM fast process dynamics and the high data flow required to accurately describe the process are pushing the limits of standard statistical process monitoring (SPM) techniques. The adoption of novel smart data extraction and analysis methods are fundamental to monitor the process with the required accuracy while keeping the computational effort to a reasonable level for real-time application. In this work, a new framework for the detection of defects in metal additive manufacturing processes via in-situ high-speed cameras is presented: a new data extraction method is developed to efficiently extract only the relevant information from the regions of interest identified in the high-speed imaging data stream and to reduce the dimensionality of the anomaly detection task performed by three competitor machine learning classification methods. The defect detection performance and computational speed of this approach is carefully evaluated through computer simulations and experimental studies, and directly compared with the performance and computational speed of other existing methods applied on the same reference dataset. The results show that the proposed method is capable of quickly detecting the occurrence of defects while keeping the high computational speed that would be required to implement this new process monitoring approach for real-time defect detection.

scholarly journals The Application of Convolutional Neural Networks (CNNs) to Recognize Defects in 3D-Printed Parts

Materials ◽  
2021 ◽  
Vol 14 (10) ◽  
pp. 2575
Author(s):  
Hao Wen ◽  
Chang Huang ◽  
Shengmin Guo
Keyword(s):  
Image Analysis ◽  
Defect Detection ◽  
Original Video ◽  
Sem Images ◽  
Single Defect ◽  
Defect Image ◽  
3D Printed ◽  
Metallic Additive ◽  
Almost All

Cracks and pores are two common defects in metallic additive manufacturing (AM) parts. In this paper, deep learning-based image analysis is performed for defect (cracks and pores) classification/detection based on SEM images of metallic AM parts. Three different levels of complexities, namely, defect classification, defect detection and defect image segmentation, are successfully achieved using a simple CNN model, the YOLOv4 model and the Detectron2 object detection library, respectively. The tuned CNN model can classify any single defect as either a crack or pore at almost 100% accuracy. The other two models can identify more than 90% of the cracks and pores in the testing images. In addition to the application of static image analysis, defect detection is also successfully applied on a video which mimics the AM process control images. The trained Detectron2 model can identify almost all the pores and cracks that exist in the original video. This study lays a foundation for future in situ process monitoring of the 3D printing process.

A 3D-printed Microfluidic System for Automated and Near Real-time Quantitation of Biofilm-induced indole

2019 ◽  
Author(s):  
Giraso Kabandana ◽  
Curtis G. Jones ◽  
Sahra Khan Sharifi ◽  
Chengpeng Chen
Keyword(s):  
Real Time ◽  
Release Kinetics ◽  
Microfluidic System ◽  
3D Printed

We developed a novel microfluidic system that enables automated and near real-time quantitation of indole release kinetics from biofilms.

Probing the Dynamic Self-Assembly Behaviour of Photoswitchable Wormlike Micelles in Real Time

2018 ◽  
Author(s):  
Elaine A. Kelly ◽  
Judith E. Houston ◽  
Rachel Evans
Keyword(s):  
Real Time ◽  
Absorption Spectroscopy ◽  
Self Assembly ◽  
Uv Light ◽  
Wormlike Micelles ◽  
Tetraethylene Glycol ◽  
Light Illumination ◽  
First Time ◽  
Dependent Processes

Understanding the dynamic self-assembly behaviour of azobenzene photosurfactants (AzoPS) is crucial to advance their use in controlled release applications such as<i></i>drug delivery and micellar catalysis. Currently, their behaviour in the equilibrium <i>cis-</i>and <i>trans</i>-photostationary states is more widely understood than during the photoisomerisation process itself. Here, we investigate the time-dependent self-assembly of the different photoisomers of a model neutral AzoPS, <a>tetraethylene glycol mono(4′,4-octyloxy,octyl-azobenzene) </a>(C<sub>8</sub>AzoOC<sub>8</sub>E<sub>4</sub>) using small-angle neutron scattering (SANS). We show that the incorporation of <i>in-situ</i>UV-Vis absorption spectroscopy with SANS allows the scattering profile, and hence micelle shape, to be correlated with the extent of photoisomerisation in real-time. It was observed that C<sub>8</sub>AzoOC<sub>8</sub>E<sub>4</sub>could switch between wormlike micelles (<i>trans</i>native state) and fractal aggregates (under UV light), with changes in the self-assembled structure arising concurrently with changes in the absorption spectrum. Wormlike micelles could be recovered within 60 seconds of blue light illumination. To the best of our knowledge, this is the first time the degree of AzoPS photoisomerisation has been tracked <i>in</i><i>-situ</i>through combined UV-Vis absorption spectroscopy-SANS measurements. This technique could be widely used to gain mechanistic and kinetic insights into light-dependent processes that are reliant on self-assembly.

Flat Flexible Thin Milli-electrode Array for Real-time in situ Water Quality Monitoring in Distribution Systems

2017 ◽  
Vol 2017 (4) ◽  
pp. 5598-5617
Author(s):  
Zhiheng Xu ◽  
Wangchi Zhou ◽  
Qiuchen Dong ◽  
Yan Li ◽  
Dingyi Cai ◽  
...  
Keyword(s):  
Water Quality ◽  
Real Time ◽  
Distribution Systems ◽  
Electrode Array ◽  
Water Quality Monitoring ◽  
Quality Monitoring

scholarly journals Underground Microseismic Event Monitoring and Localization within Sensor Networks

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2830
Author(s):  
Sili Wang ◽  
Mark P. Panning ◽  
Steven D. Vance ◽  
Wenzhan Song
Keyword(s):  
Sensor Networks ◽  
Real Time ◽  
Information Needs ◽  
Localization Algorithm ◽  
Distributed Sensors ◽  
Distributed Sensor ◽  
Microseismic Events ◽  
The Stability ◽  
Stability And Accuracy

Locating underground microseismic events is important for monitoring subsurface activity and understanding the planetary subsurface evolution. Due to bandwidth limitations, especially in applications involving planetarily-distributed sensor networks, networks should be designed to perform the localization algorithm in-situ, so that only the source location information needs to be sent out, not the raw data. In this paper, we propose a decentralized Gaussian beam time-reverse imaging (GB-TRI) algorithm that can be incorporated to the distributed sensors to detect and locate underground microseismic events with reduced usage of computational resources and communication bandwidth of the network. After the in-situ distributed computation, the final real-time location result is generated and delivered. We used a real-time simulation platform to test the performance of the system. We also evaluated the stability and accuracy of our proposed GB-TRI localization algorithm using extensive experiments and tests.

Sign in / Sign up

Export Citation Format

Share Document