Polymer extrusion die design using a data-driven autoencoders technique

被引:5
作者
Ghnatios, Chady [1 ]
Gravot, Eloi [2 ]
Champaney, Victor [2 ]
Verdon, Nicolas [3 ]
Hascoet, Nicolas [2 ]
Chinesta, Francisco [4 ,5 ]
机构
[1] HESAM Univ, Arts & Metiers Inst Technol, Lab PIMM, CNRS,Cnam,PIMM Lab,SKF Chaire ENSAM, 151 Blvd Hop, F-75013 Paris, France
[2] HESAM Univ, Arts & Metiers Inst Technol, PIMM Lab, CNRS,Cnam, 151 Blvd Hop, F-75013 Paris, France
[3] Goodyear, Paris Def 1,Tour First,1 Sq Saisons, F-92400 Courbevoie, France
[4] ENSAM Inst Technol, ESI Grp Chair, 151 Blvd Hop, F-75013 Paris, France
[5] ENSAM Inst Technol, PIMM Lab, 151 Blvd Hop, F-75013 Paris, France
关键词
Die design; Machine learning; Artificial intelligence; Autoencoder; Data-driven modeling; NON-NEWTONIAN FLUID; FLOW;
D O I
10.1007/s12289-023-01796-7
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Designing extrusion dies remains a tricky issue when considering polymers. In fact, polymers exhibit strong non-Newtonian rheology that manifest in noticeable viscoelastic behaviors as well as significant normal stress differences. As a consequence, when they are pushed through a die, an important die-swelling is observed, and consequently the final geometry of the extruded profile differs significantly from the one of the die. This behavior turns the die's design into a difficult task, and its geometry must be defined in such a way that the extruded profile results in the targeted one. Numerical simulation was identified as a natural way for building and solving the inverse problem of defining the die, leading to the targeted extruded geometry. However, state-of-the-art rheological models reveal inaccuracies for the desired level of precision. In this paper, we propose a data-driven approach that, based on the accumulated experience on the extruded profiles for different dies, learns the relation enabling efficient die design.
引用
收藏
页数:10
相关论文
共 50 条
[41]   Design of concrete-filled steel tubular columns using data-driven methods [J].
Degtyarev, Vitaliy V. ;
Thai, Huu-Tai .
JOURNAL OF CONSTRUCTIONAL STEEL RESEARCH, 2023, 200
[42]   Digital design and optimization of the integrated synthesis and crystallization process using data-driven approaches [J].
Ma, Yiming ;
Li, Wei ;
Liu, Jiaxu ;
Shang, Gao ;
Yang, Huaiyu ;
Gong, Junbo ;
Nagy, Zoltan K. ;
Benyahia, Brahim .
AICHE JOURNAL, 2025,
[43]   Data-driven system health monitoring technique using autoencoder for the safety management of commercial aircraft [J].
Hyunseong Lee ;
Hyung Jin Lim ;
Aditi Chattopadhyay .
Neural Computing and Applications, 2021, 33 :3235-3250
[44]   Data-driven system health monitoring technique using autoencoder for the safety management of commercial aircraft [J].
Lee, Hyunseong ;
Lim, Hyung Jin ;
Chattopadhyay, Aditi .
NEURAL COMPUTING & APPLICATIONS, 2021, 33 (08) :3235-3250
[45]   Data-driven approaches for runoff prediction using distributed data [J].
Heechan Han ;
Ryan R. Morrison .
Stochastic Environmental Research and Risk Assessment, 2022, 36 :2153-2171
[46]   Data-driven approaches for runoff prediction using distributed data [J].
Han, Heechan ;
Morrison, Ryan R. .
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2022, 36 (08) :2153-2171
[47]   Data-driven, using design of dynamic experiments, versus model-driven optimization of batch crystallization processes [J].
Fiordalis, Andrew ;
Georgakis, Christos .
JOURNAL OF PROCESS CONTROL, 2013, 23 (02) :179-188
[48]   Toward data-driven research: preliminary study to predict surface roughness in material extrusion using previously published data with machine learning [J].
Garcia-Martinez, Fatima ;
Carou, Diego ;
de Arriba-Perez, Francisco ;
Garcia-Mendez, Silvia .
RAPID PROTOTYPING JOURNAL, 2023, 29 (08) :1640-1652
[49]   Data-driven advisory system for industrial manufacturing. Application to the aluminum extrusion process [J].
Kochanski, Andrzej ;
Kozlowski, Jacek ;
Perzyk, Marcin ;
Sadlowska, Hanna .
KNOWLEDGE-BASED SYSTEMS, 2024, 294
[50]   Data-driven through-process modelling of aluminum extrusion: predicting mechanical properties [J].
Oien, Christian Dalheim ;
Ringen, Geir .
MANUFACTURING LETTERS, 2024, 41 :1274-1281