Gaussian-process based modeling and optimal control of melt-pool geometry in laser powder bed fusion

Ren, Yong; Wang, Qian

doi:10.1007/s10845-021-01781-4

Cited by 17 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GPR is a supervised non-parametric learning method that does not assume any functional shape. As the structure of the model relies on a dataset, it has been used in fields in which the physical phenomena or mechanisms have not yet been explained, such as the prediction of additive manufacturing (AM) product quality [ 37 , 38 ], AM optimization [ 39 ], and AM modelling [ 40 ].…”

Section: Her Prediction Modelmentioning

confidence: 99%

Prediction of Hole Expansion Ratio for Advanced High-Strength Steel with Image Feature Analysis of Sheared Edge

Jeong

Lee

et al. 2023

Materials

View full text Add to dashboard Cite

The punching process of AHSS induces edge cracks in successive process, limiting the application of AHSS for vehicle bodies. Controlling and predicting edge quality is substantially difficult due to the large variation in edge quality, die wear induced by high strength, and the complex effect of phase distribution. To overcome this challenge, a quality prediction model that considers the variation of the entire edge should be developed. In this study, the image of the entire edge was analyzed to provide a comprehensive evaluation of its quality. Statistical features were extracted from the edge images to represent the edge quality of DP780, DP980, and MART1500 steels. Combined with punching monitoring signals, a prediction model for hole expansion ratio was developed under punch conditions of varying clearance, punch angle, and punch edge radius. It was found that the features of grayscale variation are affected by the punching conditions and are related to the double burnish and uneven burr, which degrades the edge quality. Prediction of HER was possible based on only edge image and monitoring signals, with the same performance as the prediction based solely on punching parameters and material properties. The prediction performance improved when using all the features.

show abstract

Section: Her Prediction Modelmentioning

confidence: 99%

Prediction of Hole Expansion Ratio for Advanced High-Strength Steel with Image Feature Analysis of Sheared Edge

Jeong

Lee

et al. 2023

Materials

View full text Add to dashboard Cite

show abstract

“…A purely data-driven model to predict and control melt pool size was also suggested [13]. Another example of data-driven control-oriented melt pool modeling was presented in [14]. There, Gaussian process regression (GPR) was used to model the melt pool dynamics, and feedforward control was applied to control the melt pool in a simulated environment.…”

Section: Introductionmentioning

confidence: 99%

An empirical model for feedforward control of laser powder bed fusion

Shkoruta¹,

Park²,

Mishra³

2022

Preprint

View full text Add to dashboard Cite

Highlights• Laser scanning of narrow features in LPBF parts results in predictable changes in melt pool geometry as observed in coaxial melt pool images.• An empirical model of this geometry-related behavior, validated on different geometries, is presented.• A model-based feedforward controller is designed to correct for this behavior. The proposed controller reduces geometry-related deviations by a factor of two, as demonstrated experimentally.

show abstract