Monitoring and detection of meltpool and spatter regions in laser powder bed fusion of super alloy Inconel 625

Yang, Lihang; Lo, Lydia; Ding, Sijie; Özel, Tuğrul

doi:10.1007/s40964-020-00140-8

Cited by 37 publications

(13 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…11 shows that, as the energy density increases, the spatter intensity tends to increase as well. This is in agreement with the fact that a higher energy density generates a larger and hotter melt pool with more intense convective and recoil motions, which translates into a more intense spatter ejection (Yang et al, 2020;Repossini et al, 2017;Bidare et al, 2018). More interestingly, Fig.…”

Section: Resultssupporting

confidence: 87%

“…One possible way consists of estimating synthetic quantities (like the number of spatters, their size, etc.) and translating the original video frame into a multivariate vector of descriptors (Yang et al, 2020;Andani et al, 2017;Repossini et al, 2017). This approach entails an intrinsic information loss and an arbitrary and problem dependent choice of descriptors.…”

Section: Introductionmentioning

confidence: 99%

“…Referring to the example in Fig. 1, the FANOVA approach may be used to study the effect of different process conditions on the spatter behaviour, which is a problem that attracted great interest in the additive manufacturing community, because the spatter behaviour can be regarded as a proxy of process stability and quality (Yang et al, 2020;Andani et al, 2017;Repossini et al, 2017;Ly et al, 2017;Bidare et al, 2018). Ramsay (2005) proposed a functional ANOVA test, based on a pointwise F -test statistic, that relies on the normality assumption of the error function.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Robust Functional ANOVA with Application to Additive Manufacturing

Centofanti¹,

Colosimo²,

Grasso³

et al. 2021

Preprint

View full text Add to dashboard Cite

The development of data acquisition systems is facilitating the collection of data that are apt to be modelled as functional data. In some applications, the interest lies in the identification of significant differences in group functional means defined by varying experimental conditions, which is known as functional analysis of variance (FANOVA). With real data, it is common that the sample under study is contaminated by some outliers, which can strongly bias the analysis. In this paper, we propose a new robust nonparametric functional ANOVA method (RoFANOVA) that reduces the weights of outlying functional data on the results of the analysis. It is implemented through a permutation test based on a test statistic obtained via a functional extension of the classical robust M -estimator. By means of an extensive Monte Carlo simulation study, the proposed test is compared with some alternatives already presented in the literature, in both one-way and two-way designs. The performance of the RoFANOVA is demonstrated in the framework of a motivating real-case study in the field of additive manufacturing that deals with the analysis of spatter ejections. The RoFANOVA method is implemented in the R package rofanova, available online at https://github.com/unina-sfere/rofanova.

show abstract

Section: Resultssupporting

confidence: 87%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Functional ANOVA with Application to Additive Manufacturing

Centofanti¹,

Colosimo²,

Grasso³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Various approaches have been proposed to monitor the stability of the LPBF process, with differences in the choice of sensor to sense the printing process [ 8 , 9 , 10 ], the choice of analysis to be performed [ 11 , 12 , 13 ], and the signals communicated to the LPBF printer [ 14 , 15 , 16 ]. The use of optical sensors has been preferred in these monitoring systems with the trend being towards more detailed sensing: initially, photodiodes were the sensor of choice [ 12 , 17 , 18 ], but more recently, cameras in the visual [ 19 , 20 ] or infrared spectrum [ 21 , 22 ] have seen increasingly use.…”

Section: Introductionmentioning

confidence: 99%

“…The processing of the melt pool video typically consists of two stages: feature extraction and the translation of features into useful printer control signals. For feature extraction, classical hand-designed features such as melt pool geometry [ 9 ] or image texture features [ 23 ] have been used due to the ease of computation and interpretation. More recently, deep learning approaches have also been applied to learn features from individual video frames [ 16 , 24 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

Encoding Stability into Laser Powder Bed Fusion Monitoring Using Temporal Features and Pore Density Modelling

Booth

Heylen

Nourazar

et al. 2022

Sensors

View full text Add to dashboard Cite

In laser powder bed fusion (LPBF), melt pool instability can lead to the development of pores in printed parts, reducing the part’s structural strength. While camera-based monitoring systems have been introduced to improve melt pool stability, these systems only measure melt pool stability in limited, indirect ways. We propose that melt pool stability can be improved by explicitly encoding stability into LPBF monitoring systems through the use of temporal features and pore density modelling. We introduce the temporal features, in the form of temporal variances of common LPBF monitoring features (e.g., melt pool area, intensity), to explicitly quantify printing stability. Furthermore, we introduce a neural network model trained to link these video features directly to pore densities estimated from the CT scans of previously printed parts. This model aims to reduce the number of online printer interventions to only those that are required to avoid porosity. These contributions are then implemented in a full LPBF monitoring system and tested on prints using 316L stainless steel. Results showed that our explicit stability quantification improved the correlation between our predicted pore densities and true pore densities by up to 42%.

show abstract

Model Interpretability, Explainability and Trust for Manufacturing 4.0

Colosimo

Centofanti

2022

Interpretability for Industry 4.0 : Statistical and Machine Learning Approaches

View full text Add to dashboard Cite

Monitoring and detection of meltpool and spatter regions in laser powder bed fusion of super alloy Inconel 625

Cited by 37 publications

References 22 publications

Robust Functional ANOVA with Application to Additive Manufacturing

Robust Functional ANOVA with Application to Additive Manufacturing

Encoding Stability into Laser Powder Bed Fusion Monitoring Using Temporal Features and Pore Density Modelling

Model Interpretability, Explainability and Trust for Manufacturing 4.0

Contact Info

Product

Resources

About