Machine learning-based optimization of process parameters in selective laser melting for biomedical applications

Park, Hong Seok; Nguyen, Dinh Son; Le-Hong, Thai; Tran, Xuan Van

doi:10.1007/s10845-021-01773-4

Cited by 53 publications

(19 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The remarkable impact of ML in the additive manufacturing research stream can be easily evaluated by two recent review papers (Wand et al, 2020;Meng et al, 2020), but some contributions consistent with the present papers are worthy to be mentioned in the following. Park et al (2021) adopted a supervised learning deep neural network based on the backpropagation algorithm to select the optimal input parameters (laser power, scanning speed, layer thickness and hatch distance) for a set of quality measures outputs (density ratio and surface roughness) related to biomedical applications. The same machine learning technique along with the same processing parameter have been used in another research work in which a user-friendly module for preprocessing SLM printing is presented (Nguyen et al, 2020).…”

Section: Prediction-optimization Strategies In Slmmentioning

confidence: 99%

“…Notably, the neural network architecture 6-5-5-1 has been selected (See Fig. 10a), where the number of neurons in the input layer entails the six process parameters and the single output node refers to the density (Park et al, 2021). To prevent any risk of overfitting the Kfold cross-validation by 10 folds has been performed (Jung & Hu, 2015), similarly being done in other studies regarding the additive manufacturing topic (Xia et al, 2021).…”

Section: Response Prediction By Annmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid prediction-optimization approaches for maximizing parts density in SLM of Ti6Al4V titanium alloy

et al. 2022

View full text Add to dashboard Cite

It is well known that the processing parameters of selective laser melting (SLM) highly influence mechanical and physical properties of the manufactured parts. Also, the energy density is insufficient to detect the process window for producing full dense components. In fact, parts produced with the same energy density but different combinations of parameters may present different properties even under the microstructural viewpoint. In this context, the need to assess the influence of the process parameters and to select the best parameters set able to optimize the final properties of SLM parts has been capturing the attention of both academics and practitioners. In this paper different hybrid prediction-optimization approaches for maximizing the relative density of Ti6Al4V SLM manufactured parts are proposed. An extended design of experiments involving six process parameters has been configured for constructing two surrogate models based on response surface methodology (RSM) and artificial neural network (ANN), respectively. The optimization phase has been performed by means of evolutionary computations. To this end, three nature-inspired metaheuristic algorithms have been integrated with the prediction modelling structures. A series of experimental tests has been carried out to validate the results from the proposed hybrid optimization procedures. Also, a sensitivity analysis based on the results from the analysis of variance was executed to evaluate the influence of the processing parameter and their reciprocal interactions on the part porosity.

show abstract

Section: Prediction-optimization Strategies In Slmmentioning

confidence: 99%

Section: Response Prediction By Annmentioning

confidence: 99%

Hybrid prediction-optimization approaches for maximizing parts density in SLM of Ti6Al4V titanium alloy

et al. 2022

View full text Add to dashboard Cite

show abstract

“…ML methods allow complex pattern recognition and regression analysis to be performed without constructing and solving physical models. A wide range of industries, such as manufacturing, aerospace, and biomedicine, rely on this method to model, predict, and analyze parameter interactions [49][50][51]. Due to their high processing power and sophisticated architectures, arti cial neural networks (ANNs) are the most widely used ML algorithms.…”

Section: Introductionmentioning

confidence: 99%

Experimental, Computational, and Data-Driven Study of the Effects of Selective Laser Melting (SLM) Process Parameters on Single-Layer Raster Scanning Surface Characteristics

Fotovvati

Rauniyar²,

Arnold³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this study, the influence of selective laser melting (SLM) parameters on the surface characteristics of “single-layer” raster scanning deposits, with Ti6Al4V powder, is thoroughly investigated through experimental, computational, and data-driven approaches. In layer-wise manufacturing processes, such as SLM, the evaluation and understanding of the surface characteristics of individual layers of materials are important; however, there is limited work in the literature on the “single-layer” surface characteristics in SLM. Single-layer samples are designed on a smooth surface on top of semi-cylinders and fabricated using different levels of SLM processing parameters, i.e., laser power, scan speed, and hatch spacing, in different numbers of scan lines, i.e., 5, 10, 20, and 40. The fabricated sample surface data are acquired using non-contact optical interferometry. The computational approach utilizes the discrete element method (DEM) for the powder bed distribution, as well as computational fluid dynamics (CFD) for simulating the laser-powder interaction. One of the main contributions of this study is to investigate and provide predictive models for the correlations between the surface roughness of raster scans and SLM process parameters through experiments and computational work. In addition, a method for comparing the surface characteristics of the thermo-fluid simulation and experimental results is presented. A technique is employed to extract the surface roughness from the simulated results. The discussion on the experiment-simulation comparison challenges provides a deep insight into the criteria selection for experiment-simulation comparison in the SLM process. Moreover, an artificial neural network was trained using the back-propagation method and K-fold cross-validation, as well as regularization techniques to avoid overfitting. The laser power proved to be the most significant parameter, having a contribution of 48.3%, in determining the surface roughness with a unique trend affected by the spattering of powder particles. The simulation results showed noticeable deviations from the experiments in cases with extreme parameters, e.g., too high or too low values of power, speed, or hatch spacing. The machine learning algorithm achieves reasonable predictability of the single-layer surface roughness, showing a root mean square error and a coefficient of determination of 0.9589 µm and 98.78%, respectively, for a separate testing dataset.

show abstract

“…For practical use the LPBF manufactured parts need specific properties which can be set by the process parameters adequately [ 12 ]. One approach for process parameter prediction is presented by Park et al [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

“…Predicting the relative density for known parameters is constrained by the complexity of the interactions of the parameters. Machine learning models can be trained to solve this problem allowing more precise predictions of the resulting relative density [ 13 , 16 ]. However, they also need a great amount of experimental data.…”

Section: Introductionmentioning

confidence: 99%

Programmable Density of Laser Additive Manufactured Parts by Considering an Inverse Problem

et al. 2022

View full text Add to dashboard Cite

In this Article, the targeted adjustment of the relative density of laser additive manufactured components made of AlSi10Mg is considered. The interest in demand-oriented process parameters is steadily increasing. Thus, shorter process times and lower unit costs can be achieved with decreasing component densities. Especially when hot isostatic pressing is considered as a post-processing step. In order to be able to generate process parameters automatically, a model hypothesis is learned via artificial neural networks (ANN) for a density range from 70% to almost 100%, based on a synthetic dataset with equally distributed process parameters and a statistical test series with 256 full factorial combined instances. This allows the achievable relative density to be predicted from given process parameters. Based on the best model, a database approach and supervised training of concatenated ANNs are developed to solve the inverse parameter prediction problem for a target density. In this way, it is possible to generate a parameter prediction model for the high-dimensional result space through constraints that are shown with synthetic test data sets. The presented concatenated ANN model is able to reproduce the origin distribution. The relative density of synthetic data can be predicted with an R2-value of 0.98. The mean build rate can be increased by 12% with the formulation of a hint during the backward model training. The application of the experimental data shows increased fuzziness related to the big data gaps and a small number of instances. For practical use, this algorithm could be trained on increased data sets and can be expanded by properties such as surface quality, residual stress, or mechanical strength. With knowledge of the necessary (mechanical) properties of the components, the model can be used to generate appropriate process parameters. This way, the processing time and the amount of scrap parts can be reduced.

show abstract

Machine learning-based optimization of process parameters in selective laser melting for biomedical applications

Cited by 53 publications

References 59 publications

Hybrid prediction-optimization approaches for maximizing parts density in SLM of Ti6Al4V titanium alloy

Hybrid prediction-optimization approaches for maximizing parts density in SLM of Ti6Al4V titanium alloy

Experimental, Computational, and Data-Driven Study of the Effects of Selective Laser Melting (SLM) Process Parameters on Single-Layer Raster Scanning Surface Characteristics

Programmable Density of Laser Additive Manufactured Parts by Considering an Inverse Problem

Contact Info

Product

Resources

About