Casting Microstructure Inspection Using Computer Vision: Dendrite Spacing in Aluminum Alloys

被引:15
|
作者
Nikolic, Filip [1 ,2 ,3 ]
Stajduhar, Ivan [4 ]
Canadija, Marko [1 ]
机构
[1] Univ Rijeka, Fac Engn, Dept Engn Mech, Rijeka 51000, Croatia
[2] CIMOS Dd Automot Ind, Res & Dev Dept, Koper 6000, Slovenia
[3] Elaphe Prop Technol Ltd, CAE Dept, Ljubljana 1000, Slovenia
[4] Univ Rijeka, Fac Engn, Dept Comp Engn, Rijeka 51000, Croatia
关键词
secondary dendrite arm spacing; convolutional neural network; casting microstructure inspection; deep learning; aluminum alloys; MECHANICAL-PROPERTIES; LEARNING APPROACH; STEEL; CLASSIFICATION;
D O I
10.3390/met11050756
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This paper investigates the determination of secondary dendrite arm spacing (SDAS) using convolutional neural networks (CNNs). The aim was to build a Deep Learning (DL) model for SDAS prediction that has industrially acceptable prediction accuracy. The model was trained on images of polished samples of high-pressure die-cast alloy EN AC 46000 AlSi9Cu3(Fe), the gravity die cast alloy EN AC 51400 AlMg5(Si) and the alloy cast as ingots EN AC 42000 AlSi7Mg. Color images were converted to grayscale to reduce the number of training parameters. It is shown that a relatively simple CNN structure can predict various SDAS values with very high accuracy, with a R2 value of 91.5%. Additionally, the performance of the model is tested with materials not used during training; gravity die-cast EN AC 42200 AlSi7Mg0.6 alloy and EN AC 43400 AlSi10Mg(Fe) and EN AC 47100 Si12Cu1(Fe) high-pressure die-cast alloys. In this task, CNN performed slightly worse, but still within industrially acceptable standards. Consequently, CNN models can be used to determine SDAS values with industrially acceptable predictive accuracy.
引用
收藏
页数:13
相关论文
共 50 条
  • [31] Inspection of polarizer tiny bump defects using computer vision
    Yen, Hsu-Nan
    Syu, Min-Jyun
    2015 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS (ICCE), 2015, : 525 - 527
  • [32] Automated Sewer Pipeline Inspection Using Computer Vision Techniques
    Moradi, Saeed
    Zayed, Tarek
    Golkhoo, Farzaneh
    PIPELINES 2018: CONDITION ASSESSMENT, CONSTRUCTION, AND REHABILITATION, 2018, : 582 - 587
  • [33] Automated Inspection of Monopole Tower using Drones and Computer Vision
    Shajahan, Nadeem M.
    Sasikumar, Arjun
    Kuruvila, Thomas
    Davis, Dhivin
    2019 2ND INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (ICOIAS 2019), 2019, : 187 - 192
  • [34] USING CIRCULAR SYMMETRY AND INTENSITY PROFILES FOR COMPUTER VISION INSPECTION
    PERKINS, WA
    COMPUTER GRAPHICS AND IMAGE PROCESSING, 1981, 17 (02): : 161 - 172
  • [35] Using computer vision for the automatic inspection and alignment of television displays
    Yerem, GC
    Koch, DB
    IEEE SOUTHEASTCON 2002: PROCEEDINGS, 2002, : 67 - 72
  • [36] Computer modeling of the evolution of dendrite microstructure in binary alloys during non-isothermal solidification
    Grujicic, M
    Cao, G
    Miller, RS
    JOURNAL OF MATERIALS SYNTHESIS AND PROCESSING, 2002, 10 (04) : 191 - 203
  • [37] Effect of cooling rate on the mechanical strength and dendrite arm spacing of AC4B cylindrical aluminum alloy casting
    Mizuno, Kaneo
    Fan, Erqing
    Furutani, Sigeo
    Yokota, Shigeaki
    Fukusako, Tatsuichi
    Keikinzoku/Journal of Japan Institute of Light Metals, 1993, 43 (11): : 618 - 624
  • [38] The Influence of Sr Addition on the Microstructure and Mechanical Properties of Aluminum Die-casting Alloys
    Sun, Xiaodong
    Wu, Wenyun
    Wang, Donghong
    Deng, Peiran
    INTERNATIONAL SYMPOSIUM ON MATERIALS APPLICATION AND ENGINEERING (SMAE 2016), 2016, 67
  • [39] Surface Casting Defects Inspection Using Vision System and Neural Network Techniques
    Swillo, S. J.
    Perzyk, M.
    ARCHIVES OF FOUNDRY ENGINEERING, 2013, 13 (04) : 103 - 106
  • [40] Modeling of Microstructure and Mechanical Properties of Aluminum Alloys During the Casting and Heat Treatment Process
    Schneider, M.
    Heisser, C.
    TRANSACTIONS OF THE AMERICAN FOUNDRY SOCIETY, VOL 120, 2012, 120 : 97 - 105