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
  • [21] The interpretive model of manufacturing: a theoretical framework and research agenda for machine learning in manufacturing
    Sharma, Ajit
    Zhang, Zhibo
    Rai, Rahul
    INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH, 2021, 59 (16) : 4960 - 4994
  • [22] Machine learning to detect signatures of disease in liquid biopsies - a user's guide
    Ko, Jina
    Baldassano, Steven N.
    Loh, Po-Ling
    Kording, Konrad
    Litt, Brian
    Issadore, David
    LAB ON A CHIP, 2018, 18 (03) : 395 - 405
  • [23] A Numerical Framework of Simulating Flow-Induced Deformation during Liquid Composite Moulding
    Alotaibi, Hatim
    Soutis, Constantinos
    Zhang, Dianyun
    Jabbari, Masoud
    JOURNAL OF COMPOSITES SCIENCE, 2024, 8 (10):
  • [24] Machine learning in composites manufacturing: A case study of Automated Fiber Placement inspection
    Sacco, Christopher
    Radwan, Anis Baz
    Anderson, Andrew
    Harik, Ramy
    Gregory, Elizabeth
    COMPOSITE STRUCTURES, 2020, 250 (250)
  • [25] Combining Simulation and Machine Learning as Digital Twin for the Manufacturing of Overmolded Thermoplastic Composites
    Huerkamp, Andre
    Gellrich, Sebastian
    Ossowski, Tim
    Beuscher, Jan
    Thiede, Sebastian
    Herrmann, Christoph
    Droeder, Klaus
    JOURNAL OF MANUFACTURING AND MATERIALS PROCESSING, 2020, 4 (03):
  • [26] Implementing a Model to Detect Parkinson Disease using Machine Learning Classifiers
    Kumar, Uday G. S.
    Baskaran, S.
    Sumathi, D.
    JOURNAL OF ALGEBRAIC STATISTICS, 2022, 13 (01) : 99 - 110
  • [27] Development of an optimal machine learning model to detect features of wheezing in children
    Kim, Kyunghoon
    Moon, Hye Jeong
    Kim, Baek Seung
    EUROPEAN RESPIRATORY JOURNAL, 2023, 62
  • [28] Feature Selection Techniques for a Machine Learning Model to Detect Autonomic Dysreflexia
    Suresh, Shruthi
    Newton, David T.
    Everett, Thomas H.
    Lin, Guang
    Duerstock, Bradley S.
    FRONTIERS IN NEUROINFORMATICS, 2022, 16
  • [29] Developing a machine learning model to detect diagnostic uncertainty in clinical documentation
    Marshall, Trisha L.
    Nickels, Lindsay C.
    Brady, Patrick W.
    Edgerton, Ezra J.
    Lee, James J.
    Hagedorn, Philip A.
    JOURNAL OF HOSPITAL MEDICINE, 2023, 18 (05) : 405 - 412
  • [30] Using machine learning to detect the turbulent region in flow past a circular cylinder
    Li, Binglin
    Yang, Zixuan
    Zhang, Xing
    He, Guowei
    Deng, Bing-Qing
    Shen, Lian
    JOURNAL OF FLUID MECHANICS, 2020, 905