Explainable AI for layer-wise emission prediction in laser fusion

被引：7

作者：

Guo, Weihong Grace ^{[1
,2
]}

Gawade, Vidita ^{[1
,2
]}

Zhang, Bi ^{[3
]}

Guo, Yuebin ^{[2
,4
]}

机构：

[1] Rutgers Univ New Brunswick, Dept Ind & Syst Engn, Piscataway, NJ 08854 USA

[2] Rutgers Univ New Brunswick, New Jersey Adv Mfg Inst, Piscataway, NJ 08854 USA

[3] Southern Univ Sci & Technol, Dept Mech & Energy Engn, Shenzhen 518055, Peoples R China

[4] Rutgers Univ New Brunswick, Dept Mech & Aerosp Engn, Piscataway, NJ 08854 USA

来源：

CIRP ANNALS-MANUFACTURING TECHNOLOGY | 2023年 / 72卷 / 01期

关键词：

Additive manufacturing; Machine learning; Explainable AI; POWDER;

D O I：

10.1016/j.cirp.2023.03.009

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

The dynamic behavior of melt pools in powder bed-based laser fusion is very challenging to model using physics-based models and conventional black-box data-driven models. Explainable Artificial Intelligence is developed in this work to advance the understanding of convoluted links of non-sequential process physics, online time series sensing data, and process anomaly (e.g., overheating in the melt pool). A Shapley Additive Explanations (SHAP)-enabled Deep Neural Network-Long Short-Term Memory (DNN-LSTM) model has been developed as a mechanism to integrate process parameter knowledge with process history information through online sensing data while providing local and global model interpretation and transparency. & COPY; 2023 CIRP. Published by Elsevier Ltd. All rights reserved.

引用

页码：437 / 440

页数：4

共 12 条

[1] Effect of process parameters on the surface roughness of overhanging structures in laser powder bed fusion additive manufacturing [J].

Fox, Jason C. ;

Moylan, Shawn P. ;

Lane, Brandon M. .

3RD CIRP CONFERENCE ON SURFACE INTEGRITY, 2016, 45 :131-134

[2] Investigation of laser consolidation process for metal powder by two-color pyrometer and high-speed video camera [J].

Furumoto, Tatsuaki ;

Ueda, Takashi ;

Alkahari, Mohd Rizal ;

Hosokawa, Akira .

CIRP ANNALS-MANUFACTURING TECHNOLOGY, 2013, 62 (01) :223-226

[3]

Galkin G, 2022, MANUF LETT, V33, P862, DOI 10.1016/j.mfglet.2022.07.106

[4]

Gawade V, 2022, P IISE ANN C EXPO 20

[5] A physics-driven deep learning model for process-porosity causal relationship and porosity prediction with interpretability in laser metal deposition [J].

Guo, Weihong 'Grace' ;

Tian, Qi ;

Guo, Shenghan ;

Guo, Yuebin .

CIRP ANNALS-MANUFACTURING TECHNOLOGY, 2020, 69 (01) :205-208

[6]

Gutknecht K., 2020, Procedia CIRP, V95, P127, DOI [10.1016/J.PROCIR.2020.01.147, DOI 10.1016/J.PROCIR.2020.01.147]

[7] Additive manufacturing of metals [J].

Herzog, Dirk ;

Seyda, Vanessa ;

Wycisk, Eric ;

Emmelmann, Claus .

ACTA MATERIALIA, 2016, 117 :371-392

[8] Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms [J].

Lago, Jesus ;

De Ridder, Fjo ;

De Schutter, Bart .

APPLIED ENERGY, 2018, 221 :386-405

[9]

Lundberg SM, 2017, ADV NEUR IN, V30

[10] An Evaluation of Classification Methods for 3D Printing Time-Series Data [J].

Mahato, Vivek ;

Obeidi, Muhannad Ahmed ;

Brabazon, Dermot ;

Cunningham, Padraig .

IFAC PAPERSONLINE, 2020, 53 (02) :8211-8216

← 1 2 →