Machine learning in additive manufacturing: State-of-the-art and perspectives

Wang, Chengcheng; Tan, Xipeng; Tor, Shu Beng; Lim, Chu Sing

doi:10.1016/j.addma.2020.101538

Cited by 338 publications

(204 citation statements)

References 156 publications

Supporting

Mentioning

204

Contrasting

Order By: Relevance

“…With recent advances in Deep Learning and ML in general, data-driven techniques are increasingly being used for various tasks in the area of 3D printing. In various sub-domains such as part design, quality control, process optimization, cloud platforms services, as well as cyber-attack and weapon detection, ML has already shown its potential in a variety of applications [49][50][51]. In the specific field of process optimization and in-situ quality control, artificial neural networks can be considered as the most widely used ML technique [50].…”

Section: Existing Work On Process Optimization and Limitationsmentioning

confidence: 99%

Improving Build Quality in Laser Powder Bed Fusion Using High Dynamic Range Imaging and Model-Based Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

In laser-based additive manufacturing (AM) of metal parts from powder bed, information about actual part quality obtained during build is essential for cost-efficient production and high product quality. Reliable and effective monitoring strategies for laser powder bed fusion (LPBF) therefore remain in high demand and are the subject of current research. To address this demand, a novel analysis approach using high dynamic range (HDR) optical imaging in combination with convolutional neural networks (CNN) is proposed for spatially resolved and layer-wise prediction of the surface roughness of LPBF parts. In a further step, the predicted surface roughness maps are used as a feedback signal for a reinforcement learning technique that employs a dynamics model to subsequently identify optimal process parameters under varying and uncertain conditions. The proposed approach ultimately combines the estimation of the local surface roughness based on image texture and model-based reinforcement learning to an in-situ optimization framework for LPBF processes. In addition, the relationship between the layer surface roughness of the part and the overall part density is discussed on the basis of experimental data, which also indicate the applicability of the proposed method in industrial environments. This preliminary study is a first step towards highly adaptive and intelligent machines in the field of automated laser powder bed fusion with the primary goals of reducing production costs and improving the environmental fingerprint as well as print quality.

show abstract

Section: Existing Work On Process Optimization and Limitationsmentioning

confidence: 99%

Improving Build Quality in Laser Powder Bed Fusion Using High Dynamic Range Imaging and Model-Based Reinforcement Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This was also highlighted in a review on the use of Neural-Network-based ML in AM where Fused Deposition Modelling, Selective Laser Sintering, Binder Jetting and Electron Beam Melting used build parameters in a ML model to predict the density, build time, tensile strength, dimensional accuracy and more (Qi et al 2019). Both reviews underline the potential of using ML to establish process-structure-property-performance relationships in AM, without the need for underlying physical models linkage (Wang et al 2020;Qi et al 2019). However, one of the key limitations of using ML with LPBF is the small data set available to train the models (Wang et al 2020).…”

Section: Introductionmentioning

confidence: 99%

“…An emerging modelling trend in AM is to use machine learning (ML) models (Qi et al 2019;Koeppe et al 2018;Wang et al 2020;Sanchez et al 2021c). Fundamentally, ML models operate on the principle of minimising predicted error iteratively using data.…”

Section: Introductionmentioning

confidence: 99%

“…ML is also gaining attention as a process monitoring and control tool for AM, as demonstrated by Li et al (2020) and Baturynska and Martinsen (2021). A review by Wang et al (2020) on the use of ML in AM shows that most of the studies used process parameters (such as laser power, scan speed and build orientation) as inputs and both material and mechanical properties like porosity, hardness and fatigue resistance, as outputs. This was also highlighted in a review on the use of Neural-Network-based ML in AM where Fused Deposition Modelling, Selective Laser Sintering, Binder Jetting and Electron Beam Melting used build parameters in a ML model to predict the density, build time, tensile strength, dimensional accuracy and more (Qi et al 2019).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning to determine the main factors affecting creep rates in laser powder bed fusion

et al. 2021

View full text Add to dashboard Cite

There is an increasing need for the use of additive manufacturing (AM) to produce improved critical application engineering components. However, the materials manufactured using AM perform well below their traditionally manufactured counterparts, particularly for creep and fatigue. Research has shown that this difference in performance is due to the complex relationships between AM process parameters which affect the material microstructure and consequently the mechanical performance as well. Therefore, it is necessary to understand the impact of different AM build parameters on the mechanical performance of parts. Machine learning (ML) models are able to find hidden relationships in data using iterative statistical analyses and have the potential to develop process–structure–property–performance relationships for manufacturing processes, including AM. The aim of this work is to apply ML techniques to materials testing data in order to understand the effect of AM process parameters on the creep rate of additively built nickel-based superalloy and to predict the creep rate of the material from these process parameters. In this work, the predictive capabilities of ML and its ability to develop process–structure–property relationships are applied to the creep properties of laser powder bed fused alloy 718. The input data for the ML model included the Laser Powder Bed Fusion (LPBF) build parameters used—build orientation, scan strategy and number of lasers—and geometrical material descriptors which were extracted from optical microscope porosity images using image analysis techniques. The ML model was used to predict the minimum creep rate of the Laser Powder Bed Fused alloy 718 samples, which had been creep tested at $$650\,^\circ $$ 650 ∘ C and 600 MPa. The ML model was also used to identify the most relevant material descriptors affecting the minimum creep rate of the material (determined by using an ensemble feature importance framework). The creep rate was accurately predicted with a percentage error of $$1.40\%$$ 1.40 % in the best case. The most important material descriptors were found to be part density, number of pores, build orientation and scan strategy. These findings show the applicability and potential of using ML to determine and predict the mechanical properties of materials fabricated via different manufacturing processes, and to find process–structure–property relationships in AM. This increases the readiness of AM for use in critical applications.

show abstract

“…When the task is the modelling of the original geometry, the form of the object must be kept, and the elastic behavior of the object must be ensured [ 7 , 8 ]. In some cases, the expectation is to realize a deformation that is given to the effect of external load [ 9 , 10 , 11 ]. In the case of pharmaceutical application, the model can be optimized for different purposes, i.e., the enlargement of the carrier surface, ensuring the necessary biocompatibility [ 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

The Investigation of Interlaminar Failures Caused by Production Parameters in Case of Additive Manufactured Polymers

2021

View full text Add to dashboard Cite

The use of three-dimensional (3D) printing technologies is an ever-growing solution. The product realized in many cases is applicable not only for visual aid, or model, but for tool, or operating element, or as an implant for medical use. For correct calculation, a proper model that is based on the theory of elasticity is necessary. The basis of this kind of model is the knowledge of the exact material properties. The PLA filament has been used to perform this study for matrix material. Our presumption is that the different layers do not fuse completely, and they do not fill up the space available. The failures between the layers and the deposited filaments and the layer arrangement could be the reason for the direction-dependent material properties of the 3D printed objects. Based on our investigation, we can conclude that the increase of the layer thickness and printing speed adversely affect the mechanical properties of the product.

show abstract

Machine learning in additive manufacturing: State-of-the-art and perspectives

Cited by 338 publications

References 156 publications

Improving Build Quality in Laser Powder Bed Fusion Using High Dynamic Range Imaging and Model-Based Reinforcement Learning

Improving Build Quality in Laser Powder Bed Fusion Using High Dynamic Range Imaging and Model-Based Reinforcement Learning

Machine learning to determine the main factors affecting creep rates in laser powder bed fusion

The Investigation of Interlaminar Failures Caused by Production Parameters in Case of Additive Manufactured Polymers

Contact Info

Product

Resources

About