Real-Time Analysis of Industrial Data Using the Unsupervised Hierarchical Density-Based Spatial Clustering of Applications with Noise Method in Monitoring the Welding Process in a Robotic Cell

被引:0
作者
Blachowicz, Tomasz [1 ,2 ]
Wylezek, Jacek [1 ]
Sokol, Zbigniew [1 ]
Bondel, Marcin [1 ]
机构
[1] PROPOINT SA, R&D Dept, Bojkowska 37 R Str, PL-44100 GLIWICE, Poland
[2] Silesian Univ Tech, Inst Phys, CSE, S Konarskiego 22B Str, PL-44100 Gliwice, Poland
关键词
machine learning; monitoring of industrial processes; predictive maintenance; industry; 4.0; HDBSCAN algorithm; welding in a robotic cell;
D O I
10.3390/info16020079
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The application of modern machine learning methods in industrial settings is a relatively new challenge and remains in the early stages of development. Current computational power enables the processing of vast numbers of production parameters in real time. This article presents a practical analysis of the welding process in a robotic cell using the unsupervised HDBSCAN machine learning algorithm, highlighting its advantages over the classical k-means algorithm. This paper also addresses the problem of predicting and monitoring undesirable situations and proposes the use of the real-time graphical representation of noisy data as a particularly effective solution for managing such issues.
引用
收藏
页数:16
相关论文
共 77 条
  • [1] Clustering for Metric and Nonmetric Distance Measures
    Ackermann, Marcel R.
    Bloemer, Johannes
    Sohler, Christian
    [J]. ACM TRANSACTIONS ON ALGORITHMS, 2010, 6 (04)
  • [2] Aggarwal CC, 2014, CH CRC DATA MIN KNOW, P1
  • [3] Clustering via nonparametric density estimation
    Azzalini, Adelchi
    Torelli, Nicola
    [J]. STATISTICS AND COMPUTING, 2007, 17 (01) : 71 - 80
  • [4] Leveraging Virtual Reality in Engineering Education to Optimize Manufacturing Sustainability in Industry 4.0
    Bano, Farheen
    Alomar, Madani Abdu
    Alotaibi, Faisal Mohammed
    Serbaya, Suhail H.
    Rizwan, Ali
    Hasan, Faraz
    [J]. SUSTAINABILITY, 2024, 16 (18)
  • [5] Fault detection and diagnosis for industrial processes based on clustering and autoencoders: a case of gas turbines
    Barrera, Jose M.
    Reina, Alejandro
    Mate, Alejandro
    Trujillo, Juan C.
    [J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2022, 13 (10) : 3113 - 3129
  • [6] Programming of Industrial Robots Using Virtual Reality and Digital Twins
    Burghardt, Andrzej
    Szybicki, Dariusz
    Gierlak, Piotr
    Kurc, Krzysztof
    Pietrus, Paulina
    Cygan, Rafal
    [J]. APPLIED SCIENCES-BASEL, 2020, 10 (02):
  • [7] Digital Twin to Control and Monitor an Industrial Cyber-Physical Environment Supported by Augmented Reality
    Caiza, Gustavo
    Sanz, Ricardo
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (13):
  • [8] Campello Ricardo J. G. B., 2013, Advances in Knowledge Discovery and Data Mining. 17th Pacific-Asia Conference (PAKDD 2013). Proceedings, P160, DOI 10.1007/978-3-642-37456-2_14
  • [9] Campello R.J.G.B., 2015, Data Min. Knowl. Discov, V29, P802
  • [10] Detecting Multi-Density Urban Hotspots in a Smart City: Approaches, Challenges and Applications
    Cesario, Eugenio
    Lindia, Paolo
    Vinci, Andrea
    [J]. BIG DATA AND COGNITIVE COMPUTING, 2023, 7 (01)