A Machine Learning Model to Detect Flow Disturbances during Manufacturing of Composites by Liquid Moulding

被引:20
|
作者
Gonzalez, Carlos [1 ,2 ]
Fernandez-Leon, Joaquin [1 ,2 ]
机构
[1] IMDEA Mat, C Eric Kandel 2, Madrid 28906, Spain
[2] Univ Politecn Madrid, Dept Ciencia Mat, ETS Ingn Caminos, Madrid 28040, Spain
来源
JOURNAL OF COMPOSITES SCIENCE | 2020年 / 4卷 / 02期
关键词
machine learning; mould filling simulations; composite materials; liquid moulding; NETWORKS;
D O I
10.3390/jcs4020071
中图分类号
TB33 [复合材料];
学科分类号
摘要
In this work, a supervised machine learning (ML) model was developed to detect flow disturbances caused by the presence of a dissimilar material region in liquid moulding manufacturing of composites. The machine learning model was designed to predict the position, size and relative permeability of an embedded rectangular dissimilar material region through use of only the signals corresponding to an array of pressure sensors evenly distributed on the mould surface. The burden of experimental tests required to train in an efficient manner such predictive models is so high that favours its substitution with synthetically-generated simulation datasets. A regression model based on the use of convolutional neural networks (CNN) was developed and trained with data generated from mould-filling simulations carried out through use of OpenFoam as numerical solver. The evolution of the pressure sensors through the filling time was stored and used as grey-level images containing information regarding the pressure, the sensor location within the mould and filling time. The trained CNN model was able to recognise the presence of a dissimilar material region from the data used as inputs, meeting accuracy expectation in terms of detection. The purpose of this work was to establish a general framework for fully-synthetic-trained machine learning models to address the occurrence of manufacturing disturbances without placing emphasis on its performance, robustness and optimization. Accuracy and model robustness were also addressed in the paper. The effect of noise signals, pressure sensor network size, presence of different shape dissimilar regions, among others, were analysed in detail. The ability of ML models to examine and overcome complex physical and engineering problems such as defects produced during manufacturing of materials and parts is particularly innovative and highly aligned with Industry 4.0 concepts.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] A Machine Learning Strategy for Race-Tracking Detection During Manufacturing of Composites by Liquid Moulding
    Joaquín Fernández-León
    Keayvan Keramati
    David Garoz
    Luis Baumela
    Carlos Miguel
    Carlos González
    Integrating Materials and Manufacturing Innovation, 2022, 11 : 296 - 311
  • [2] A Machine Learning Strategy for Race-Tracking Detection During Manufacturing of Composites by Liquid Moulding
    Fernandez-Leon, Joaquin
    Keramati, Keayvan
    Garoz, David
    Baumela, Luis
    Miguel, Carlos
    Gonzalez, Carlos
    INTEGRATING MATERIALS AND MANUFACTURING INNOVATION, 2022, 11 (02) : 296 - 311
  • [3] Stochastic modelling of microscale flow during liquid composites moulding process
    Weng, M
    Ding, X
    Proceedings of 2005 International Conference on Advanced Fibers and Polymer Materials (ICAFPM 2005), Vol 1 and 2: NEW CENTURY , NEW MATERIALS AND NEW LIFE, 2005, : 573 - 578
  • [4] A digital twin for smart manufacturing of structural composites by liquid moulding
    Joaquín Fernández-León
    Keayvan Keramati
    Luis Baumela
    Carlos González
    The International Journal of Advanced Manufacturing Technology, 2024, 130 : 4679 - 4697
  • [5] A digital twin for smart manufacturing of structural composites by liquid moulding
    Fernandez-Leon, Joaquin
    Keramati, Keayvan
    Baumela, Luis
    Gonzalez, Carlos
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2024, 130 (9-10): : 4679 - 4697
  • [6] Transverse liquid composite moulding processes for advanced composites material manufacturing
    Lee, Jeeeun
    Duhovic, Miro
    Allen, Tom
    Kelly, Piaras
    PLASTICS RUBBER AND COMPOSITES, 2022, 51 (08) : 373 - 382
  • [7] A Review of Permeability and Flow Simulation for Liquid Composite Moulding of Plant Fibre Composites
    Pantaloni, Delphin
    Bourmaud, Alain
    Baley, Christophe
    Clifford, Mike J.
    Ramage, Michael H.
    Shah, Darshil U.
    MATERIALS, 2020, 13 (21) : 1 - 23
  • [8] A Machine Learning Based Approach to Detect False Calls in SMT Manufacturing
    Thielen, Nils
    Werner, Dominik
    Schmidt, Konstantin
    Seidel, Reinhardt
    Reinhardt, Andreas
    Franke, Joerg
    2020 43RD INTERNATIONAL SPRING SEMINAR ON ELECTRONICS TECHNOLOGY (ISSE), 2020,
  • [9] Experimental process pressure analysis for model-based manufacturing of composites by resin transfer moulding
    Fauster, E.
    Thirunavukkarasu, J.
    Hergan, P.
    Schledjewski, R.
    13TH INTERNATIONAL CONFERENCE ON TEXTILE COMPOSITES (TEXCOMP-13), 2018, 406
  • [10] Design of a machine learning model for the precise manufacturing of green cementitious composites modified with waste granite powder
    Sławomir Czarnecki
    Marijana Hadzima-Nyarko
    Adrian Chajec
    Łukasz Sadowski
    Scientific Reports, 12