One-Shot Fault Diagnosis of Three-Dimensional Printers Through Improved Feature Space Learning

Li, Chuan; Cabrera, Diego; Sancho, Fernando; Sánchez, René–Vinicio; Cerrada, Mariela; Oliveira, José Valente de

doi:10.1109/tie.2020.3013546

Cited by 19 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attitude signal and acoustic emission (AE) are the most common data signal types used in mechanical fault diagnosis. All the respective papers used the same attitude sensor brand, and monitoring target except for [ 39 ]. Studies using the SLD-BL600-6 3D delta printer include [ 22 , 23 , 39 , 41 , 44 , 46 ].…”

Section: Equipmentmentioning

confidence: 99%

“…All the respective papers used the same attitude sensor brand, and monitoring target except for [ 39 ]. Studies using the SLD-BL600-6 3D delta printer include [ 22 , 23 , 39 , 41 , 44 , 46 ]. Studies using the Hyrel FDM printer include [ 38 , 60 , 68 ], all of which studied AE-based mechanical fault monitoring and used similar experimental setups to analyze extruder states.…”

Section: Equipmentmentioning

confidence: 99%

“…Unlike other mechanical fault monitoring studies, Ref. [ 39 ] used an electronic compass to acquire magnetic field data and stated that this sensor could be another option for a low-cost sensor due to its competitive performance.…”

Section: Equipmentmentioning

confidence: 99%

“… Acceleration signals produce information about the extrusion head’s change of motion, acceleration, and vibration. Reference [ 39 ] uses acceleration sensors for data-driven monitoring. …”

Section: Additive Manufacturing and Data-driven Preparationmentioning

confidence: 99%

See 3 more Smart Citations

Exploring Machine Learning-Based Fault Monitoring for Polymer-Based Additive Manufacturing: Challenges and Opportunities

Sampedro

Rachmawati

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

Three-dimensional printing, often known as additive manufacturing (AM), is a groundbreaking technique that enables rapid prototyping. Monitoring AM delivers benefits, as monitoring print quality can prevent waste and excess material costs. Machine learning is often applied to automating fault detection processes, especially in AM. This paper explores recent research on machine learning-based mechanical fault monitoring systems in fused deposition modeling (FDM). Specifically, various machine learning-based algorithms are applied to measurements extracted from different parts of a 3D printer to diagnose and identify faults. The studies often use mechanical-based fault analysis from data gathered from sensors that measure attitude, acoustic emission, acceleration, and vibration signals. This survey examines what has been achieved and opens up new opportunities for further research in underexplored areas such as SLM-based mechanical fault monitoring.

show abstract

Section: Equipmentmentioning

confidence: 99%

Section: Equipmentmentioning

confidence: 99%

Section: Equipmentmentioning

confidence: 99%

Section: Additive Manufacturing and Data-driven Preparationmentioning

confidence: 99%

See 2 more Smart Citations

Exploring Machine Learning-Based Fault Monitoring for Polymer-Based Additive Manufacturing: Challenges and Opportunities

Sampedro

Rachmawati

Kim

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Molded parts whose size exceeds the allowable working space of the 3DP must be split into sub-blocks, and then the split parts are spliced together to assemble the required molded parts. (18)…”

Section: General Principles For Model Splittingmentioning

confidence: 99%

Three-dimensional Printing of Product Design ModelsUsing Continuous-fiber-reinforced Composites

Cheng¹

2021

Sensors and Materials

View full text Add to dashboard Cite

Three-dimensional (3D) printing has the main advantages of a high material utilization rate, diversified design, rapid prototyping, the ability to form complex products, high printing speed, and high quality of printed products. Fused deposition modeling (FDM) technology can rapidly generate models with different structural characteristics and then transform the models into actual products. In this study, considering the basic principles of FDM, we first analyzed the process flow and the factors affecting 3D printing. The principle of separating the model and adding support was discussed. Next, the types of support of the model were classified. Finally, the process integrity of different models was studied using examples, and an optimal design scheme for different types of support was proposed. The rapid development of 3D printing technology is expected to realize the effective manufacturing of composite structures with complex geometric shapes, thus further expanding the application range of composite materials. Therefore, in this study, from the perspective of mechanical properties, we analyzed the research status of 3D printing using continuous-fiber-reinforced composites (CFRCs) and performed tests in terms of bending properties. The results show that, on the one hand, adding different types of support can improve the forming process and quality of the products. On the other hand, the effects of bending properties on the mechanical properties and damage evolution law of 3D-printed CFRC products were obtained under typical loads, and a strength/stiffness analysis and a prediction method were used to determine the main factors that affected the mechanical properties.

show abstract

Deep learning-based image segmentation for defect detection in additive manufacturing: an overview

Deshpande,

Venugopal,

Kumar

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Additive manufacturing (AM) applications are rapidly expanding across multiple domains and are not limited to prototyping purposes. However, achieving flawless parts in medical, aerospace, and automotive applications is critical for the widespread adoption of AM in these industries. Since AM is a complex process consisting of multiple interdependent factors, deep learning (DL) approaches are adopted widely to correlate the AM process physics to the part quality. Typically, in AM processes, computer vision-based DL is performed by extracting the machine’s sensor data and layer-wise images through camera-based systems. This paper presents an overview of computer vision-assisted patch-wise defect localization and pixel-wise segmentation methods reported for AM processes to achieve error-free parts. In particular, these deep learning methods localize and segment defects in each layer, such as porosity, melt-pool regions, and spattering, during in situ processes. Further, knowledge of these defects can provide an in-depth understanding of fine-tuning optimal process parameters and part quality through real-time feedback. In addition to DL architectures to identify defects, we report on applications of DL extended to adjust the AM process variables in closed-loop feedback systems. Although several studies have investigated deploying closed-loop systems in AM for defect mitigation, specific challenges exist due to the relationship between inter-dependent process parameters and hardware constraints. We discuss potential opportunities to mitigate these challenges, including advanced segmentation algorithms, vision transformers, data diversity for improved performance, and predictive feedback approaches.

show abstract

One-Shot Fault Diagnosis of Three-Dimensional Printers Through Improved Feature Space Learning

Cited by 19 publications

References 34 publications

Exploring Machine Learning-Based Fault Monitoring for Polymer-Based Additive Manufacturing: Challenges and Opportunities

Exploring Machine Learning-Based Fault Monitoring for Polymer-Based Additive Manufacturing: Challenges and Opportunities

Three-dimensional Printing of Product Design ModelsUsing Continuous-fiber-reinforced Composites

Deep learning-based image segmentation for defect detection in additive manufacturing: an overview

Contact Info

Product

Resources

About