Reverse engineering of additive manufactured composite part by toolpath reconstruction using imaging and machine learning

Yanamandra, Kaushik; Chen, Guan Lin; Xu, Xianbo; Mac, Gary; Gupta, Nïkhil

doi:10.1016/j.compscitech.2020.108318

Cited by 51 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 23 and Table 5 shows the parameters used in this work and the CAD models used to train the model. Yanamandra et al [ 89 ] revealed an important application of reverse engineering of 3D printed composite part using imaging and machine learning assisted approach. The study analyzed the microstructure using the machine learning approach and even the tool was reconstructed.…”

Section: Data-driven Based Machine Learning (Ml) Approachesmentioning

confidence: 99%

See 1 more Smart Citation

3D Printing of Fiber-Reinforced Plastic Composites Using Fused Deposition Modeling: A Status Review

et al. 2021

View full text Add to dashboard Cite

Composite materials are a combination of two or more types of materials used to enhance the mechanical and structural properties of engineering products. When fibers are mixed in the polymeric matrix, the composite material is known as fiber-reinforced polymer (FRP). FRP materials are widely used in structural applications related to defense, automotive, aerospace, and sports-based industries. These materials are used in producing lightweight components with high tensile strength and rigidity. The fiber component in fiber-reinforced polymers provides the desired strength-to-weight ratio; however, the polymer portion costs less, and the process of making the matrix is quite straightforward. There is a high demand in industrial sectors, such as defense and military, aerospace, automotive, biomedical and sports, to manufacture these fiber-reinforced polymers using 3D printing and additive manufacturing technologies. FRP composites are used in diversified applications such as military vehicles, shelters, war fighting safety equipment, fighter aircrafts, naval ships, and submarine structures. Techniques to fabricate composite materials, degrade the weight-to-strength ratio and the tensile strength of the components, and they can play a critical role towards the service life of the components. Fused deposition modeling (FDM) is a technique for 3D printing that allows layered fabrication of parts using thermoplastic composites. Complex shape and geometry with enhanced mechanical properties can be obtained using this technique. This paper highlights the limitations in the development of FRPs and challenges associated with their mechanical properties. The future prospects of carbon fiber (CF) and polymeric matrixes are also mentioned in this study. The study also highlights different areas requiring further investigation in FDM-assisted 3D printing. The available literature on FRP composites is focused only on describing the properties of the product and the potential applications for it. It has been observed that scientific knowledge has gaps when it comes to predicting the performance of FRP composite parts fabricated under 3D printing (FDM) techniques. The mechanical properties of 3D-printed FRPs were studied so that a correlation between the 3D printing method could be established. This review paper will be helpful for researchers, scientists, manufacturers, etc., working in the area of FDM-assisted 3D printing of FRPs.

show abstract

Section: Data-driven Based Machine Learning (Ml) Approachesmentioning

confidence: 99%

“… ( a ) CAD model with dimensions. ( b ) Micro-level CT scan of the 3D printed part [ 89 ] (reprinted with kind permission from Elsevier). …”

Section: Figurementioning

confidence: 99%

3D Printing of Fiber-Reinforced Plastic Composites Using Fused Deposition Modeling: A Status Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This feature is key to further develop a reverse-engineering approach to design complex in-plane orientations in composites according to geometrical, structural, or functional demands, using methods such as finite element analysis or machine learning. 51,52 Along with the modulation in-plane of the orientation of the flakes, a similar approach could be used to vary the local concentration in magnetic flakes. Indeed, gradients in magnetic field strengths can generate attractive forces on ferromagnetic flakes and concentrate them at the areas of strongest magnetic fields.…”

Section: Discussionmentioning

confidence: 99%

Magnetically driven in-plane modulation of the 3D orientation of vertical ferromagnetic flakes

Ferrand

Arrieta

2022

Soft Matter

View full text Add to dashboard Cite

show abstract

“…Data-driven methods are rarely used to explore the factors that affect the waiting times of inpatients. Data mining technology and machine learning methods have been successfully applied in many fields, such as intelligent diagnosis and treatment [ 31 – 33 ], engineering [ 34 ], and security [ 35 ]. The wide range of these applications suggests that data mining technology may be used to analyze the factors that affect waiting time.…”

Section: Introductionmentioning

confidence: 99%

Big Data-Enabled Analysis of Factors Affecting Patient Waiting Time in the Nephrology Department of a Large Tertiary Hospital

Zhu

Luo

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The length of waiting time has become an important indicator of the efficiency of medical services and the quality of medical care. Lengthy waiting times for patients will inevitably affect their mood and reduce satisfaction. For patients who are in urgent need of hospitalization, delayed admission often leads to exacerbation of the patient’s condition and may threaten the patient’s life. We gathered patients’ information about outpatient visits and hospital admissions in the Nephrology Department of a large tertiary hospital in western China from January 1st, 2014, to December 31st, 2016, and we used big data-enabled analysis methods, including univariate analysis and multivariate linear regression models, to explore the factors affecting waiting time. We found that gender ( P = 0.048 ), the day of issuing the admission card (Saturday, P = 0.028 ), the applied period for admission ( P < 0.001 ), and the registration interval ( P < 0.001 ) were positive influencing factors of patients’ waiting time. Disease type (after kidney transplantation, P < 0.001 ), number of diagnoses ( P = 0.037 ), and the day of issuing the admission card (Sunday, P = 0.001 ) were negative factors. A linear regression model built using these data performed well in the identification of factors affecting the waiting time of patients in the Nephrology Department. These results can be extended to other departments and could be valuable for improving patient satisfaction and hospital service quality by identifying the factors affecting waiting time.

show abstract

Reverse engineering of additive manufactured composite part by toolpath reconstruction using imaging and machine learning

Cited by 51 publications

References 27 publications

3D Printing of Fiber-Reinforced Plastic Composites Using Fused Deposition Modeling: A Status Review

3D Printing of Fiber-Reinforced Plastic Composites Using Fused Deposition Modeling: A Status Review

Magnetically driven in-plane modulation of the 3D orientation of vertical ferromagnetic flakes

Big Data-Enabled Analysis of Factors Affecting Patient Waiting Time in the Nephrology Department of a Large Tertiary Hospital

Contact Info

Product

Resources

About