A review of machine learning techniques for process and performance optimization in laser beam powder bed fusion additive manufacturing

Liu, Jia; Ye, Jiafeng; Izquierdo, Daniel Silva; Vinel, Aleksandr; Shamsaei, Nima; Shao, Shuai

doi:10.1007/s10845-022-02012-0

Cited by 27 publications

(12 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging ML methods to investigate defect features of different defect types from XCT requires understanding different ML methods 37 . In general, high-resolution XCT images can improve the classification accuracy of ML methods.…”

Section: Discussionmentioning

confidence: 99%

Feature-based volumetric defect classification in metal additive manufacturing

Poudel

Yasin

et al. 2022

Nat Commun

View full text Add to dashboard Cite

Volumetric defect types commonly observed in the additively manufactured parts differ in their morphologies ascribed to their formation mechanisms. Using high-resolution X-ray computed tomography, this study analyzes the morphological features of volumetric defects, and their statistical distribution, in laser powder bed fused Ti-6Al-4V. The geometries of three common types of volumetric defects; i.e., lack of fusions, gas-entrapped pores, and keyholes, are quantified by nine parameters including maximum dimension, roundness, sparseness, aspect ratio, and more. It is shown that the three defect types share overlaps of different degrees in the ranges of their morphological parameters; thus, employing only one or two parameters cannot uniquely determine a defect’s type. To overcome this challenge, a defect classification methodology incorporating multiple morphological parameters has been proposed. In this work, by employing the most discriminating parameters, this methodology has been shown effective when implemented into decision tree (>98% accuracy) and artificial neural network (>99% accuracy).

show abstract

Section: Discussionmentioning

confidence: 99%

Feature-based volumetric defect classification in metal additive manufacturing

Poudel

Yasin

et al. 2022

Nat Commun

View full text Add to dashboard Cite

show abstract

“…explore: This mode selects amount the identified expanders to increase system understanding. In this way the interpretability of our presented approach can be valuable for industrial applications (Liu et al, 2022). It is not to be understood as an optimization mode.…”

Section: Interaction Modesmentioning

confidence: 98%

Safe contextual Bayesian optimization integrated in industrial control for self-learning machines

et al. 2023

View full text Add to dashboard Cite

Intelligent manufacturing applications and agent-based implementations are scientifically investigated due to the enormous potential of industrial process optimization. The most widespread data-driven approach is the use of experimental history under test conditions for training, followed by execution of the trained model. Since factors, such as tool wear, affect the process, the experimental history has to be compiled extensively. In addition, individual machine noise implies that the models are not easily transferable to other (theoretically identical) machines. In contrast, a continual learning system should have the capacity to adapt (slightly) to a changing environment, e.g., another machine under different working conditions. Since this adaptation can potentially have a negative impact on process quality, especially in industry, safe optimization methods are required. In this article, we present a significant step towards self-optimizing machines in industry, by introducing a novel method for efficient safe contextual optimization and continuously trading-off between exploration and exploitation. Furthermore, an appropriate data discard strategy and local approximation techniques enable continual optimization. The approach is implemented as generic software module for an industrial edge control device. We apply this module to a steel straightening machine as an example, enabling it to adapt safely to changing environments.

show abstract

“…Spatter ejections are either caused by a vapor-driven entrapment of powder particles or by unstable solid-liquid transitions leading to molten material ejections (Liu et al, 2015;Khairallah et al, 2016;Ly et al, 2017). The interested reader is referred to McCann et al, 2021;Kumar et al, 2022;Li et al, 2020;Tercan & Meisen, 2022;Liu et al, 2022;Zhang et al, 2022) for review studies devoted to these phenomena and to the development of process monitoring tools in L-PBF.…”

Section: Motivating Examplementioning

confidence: 99%

Modeling spatial point processes in video-imaging via Ripley’s K-function: an application to spatter analysis in additive manufacturing

2022

View full text Add to dashboard Cite

For an increasing number of applications, the quality and the stability of manufacturing processes can be determined via image and video-image data analysis and new techniques are required to extract and synthesize the relevant information content enclosed in big sensor data to draw conclusions about the process and the final part quality. This paper focuses on video image data where the phenomena under study is captured by a point process whose spatial signature is of interest. A novel approach is proposed which combines spatial data modeling via Ripley’s K-function with Functional Analysis of Variance (FANOVA), i.e., Analysis of Variance on Functional data. The K-function allows to synthesize the spatial pattern information in a function while preserving the capability to capture changes in the process behavior. The method is applicable to quantities and phenomena that can be represented as clusters, or clouds, of spatial points evolving over time. In our case, the motivating case study regards the analysis of spatter ejections caused by the laser-material interaction in Additive Manufacturing via Laser Powder Bed Fusion (L-PBF). The spatial spread of spatters, captured in the form of point particles through in-situ high speed machine vision, can be used as a proxy to select the best conditions to avoid defects (pores) in the manufactured part. The proposed approach is shown to be not only an efficient way to translate the high-dimensional video image data into a lower dimensional format (the K-function curves), but also more effective than benchmark methods in detecting departures from a stable and in-control state.

show abstract

A review of machine learning techniques for process and performance optimization in laser beam powder bed fusion additive manufacturing

Cited by 27 publications

References 88 publications

Feature-based volumetric defect classification in metal additive manufacturing

Feature-based volumetric defect classification in metal additive manufacturing

Safe contextual Bayesian optimization integrated in industrial control for self-learning machines

Modeling spatial point processes in video-imaging via Ripley’s K-function: an application to spatter analysis in additive manufacturing

Contact Info

Product

Resources

About