DIGITALIZATION OF A ROBOT-BASED DIRECTED ENERGY DEPOSITION PROCESS FOR IN-SITU MONITORING AND POST-PROCESS DATA ANALYTICS

被引:0
|
作者
Cousin, Frederic [1 ]
Prakash, Vishnuu Jothi [1 ]
Weber, Julian Ulrich [1 ]
Kelbassa, Ingomar [1 ]
机构
[1] Fraunhofer IAPT, Hamburg, Germany
来源
PROCEEDINGS OF ASME 2024 19TH INTERNATIONAL MANUFACTURING SCIENCE AND ENGINEERING CONFERENCE, MSEC2024, VOL 1 | 2024年
关键词
In-situ Monitoring; Data Analytics; Geomapping; Additive Manufacturing; Digitalization; QUALITY;
D O I
暂无
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
To enhance quality and productivity as well as reduce trial and error in directed energy deposition (DED) processes, data analytics are essential. Collecting different signals like melt pool images, melt pool temperatures, environment conditions, and robot data during production, enables insights into the process. In general, the collected data can be either used during the process for in-situ monitoring or for post-process analytics anytime after the print job. Hence, in order to generate a digital twin of the process, the software architecture has to cover both cases, real-time data processing as well as data storage and access for post-process analysis. For this purpose, a software architecture consisting of four different layers, namely the physical-, distribution-, storage- and application layer was developed. The physical layer takes care of the sensor integration in the process and the real-time connection between the sensors and the data collection device. This device hosts at the same time the developed in-situ monitoring software ("DED Process Monitor"). The distribution layer is the connection layer between the physical- and storage layers by organizing the data transfer between the sensors and the database used by potential applications. The storage layer is embodied by a time-series database. A web- based software tool ("DED Process Analyzer"), representing the application layer, makes the database accessible for multiple users on different devices e.g. computers, notebooks, tablets, and smartphones. Through this architecture, a robot-based directed energy deposition process was digitalized including in-situ monitoring as well as postprocess data analytics. The DED Process Monitor is useable for the operator through a human-machine interface at the robot cell to observe the current production. This supports him in reacting to process deviations by adjusting process parameters or early stopping the process. In contrast to the DED Process Monitor, the DED Process Analyzer is realized through a decentralized web-based software tool. Therefore, the tool is useable for every employee with a suitable device connected to the internal network. Thereby multiple data engineers can use the collected data simultaneously for their analysis. Hereby different data analytic options are available. The scope starts from simple 2D data visualizations and ends up in post-process robot path simulations as well as complex 3D-Geomapping of sensor data. Through the 3D-Geomapping process sensor values are considered together with robot position data. This increases the extractable information content enormously. This method allows a geometrical representation of the sensor data over the contour of the printed part. By mapping sensor data to specific positions given by the robot, the sensor values are mapped to geometrical areas in the printed part. Thereby critical areas in the part can be identified. Using this information, later quality tests can focus on these areas instead of the total part. This saves time and costs. Furthermore, the DED Process Analyzer can be used to easily perform data preprocessing tasks like filtering and cleaning to create data sets which can then be used to train machine learning models.
引用
收藏
页数:9
相关论文
共 50 条
  • [31] In-situ process monitoring for eco-friendly chemical vapor deposition chamber cleaning
    Su-Rin An
    Jeong Eun Choi
    Sang Jeen Hong
    Journal of the Korean Physical Society, 2021, 79 : 1027 - 1036
  • [32] In-situ Monitoring of Resin Curing Process Based on Interdigital Impedance Sensors
    Pihera, J.
    Freisleben, J.
    Polansky, R.
    Blecha, T.
    Vik, R.
    Prosr, P.
    Cermak, M.
    Hromadka, K.
    Hamacek, A.
    Pavlica, R.
    Komarek, J.
    2016 IEEE INTERNATIONAL CONFERENCE ON DIELECTRICS (ICD), VOLS 1-2, 2016, : 552 - 555
  • [33] In-situ directed energy deposition of Al based low density steel for automotive applications
    Rott, Matej
    Li, Ying
    Koukolikova, Martina
    Sipova, Martina
    Salvetr, Pavel
    Novy, Zbysek
    Wolf, Gerhard
    Dzugan, Jan
    SCIENTIFIC REPORTS, 2023, 13 (01)
  • [34] In-situ directed energy deposition of Al based low density steel for automotive applications
    Matěj Rott
    Ying Li
    Martina Koukolíková
    Martina Šípová
    Pavel Salvetr
    Zbyšek Nový
    Gerhard Wolf
    Jan Džugan
    Scientific Reports, 13
  • [35] In process monitoring of the thermal profile during solidification in laser directed energy deposition of aluminium
    Hagenlocher, Christian
    O'Toole, Patrick
    Xu, Wei
    Brandt, Milan
    Easton, Mark
    Molotnikov, Andrey
    ADDITIVE MANUFACTURING LETTERS, 2022, 3
  • [36] Development of multi-defect diagnosis algorithm for the directed energy deposition (DED) process with in situ melt-pool monitoring
    Hyewon Shin
    Jimin Lee
    Seung-Kyum Choi
    Sang Won Lee
    The International Journal of Advanced Manufacturing Technology, 2023, 125 : 357 - 368
  • [37] Development of multi-defect diagnosis algorithm for the directed energy deposition (DED) process with in situ melt-pool monitoring
    Shin, Hyewon
    Lee, Jimin
    Choi, Seung-Kyum
    Lee, Sang Won
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2023, 125 (1-2): : 357 - 368
  • [38] Dynamic in-situ temperature profile monitoring of a deep UV post exposure bake process
    Cohen, B
    Renken, W
    Miller, P
    METROLOGY, INSPECTION, AND PROCESS CONTROL FOR MICROLITHOGRAPHY XVI, PTS 1 & 2, 2002, 4689 : 1133 - 1142
  • [39] Development of Data-Driven In-Situ Monitoring and Diagnosis System of Fused Deposition Modeling (FDM) Process Based on Support Vector Machine Algorithm
    Kim, Jung Sub
    Lee, Chang Su
    Kim, Sung-Min
    Lee, Sang Won
    INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING-GREEN TECHNOLOGY, 2018, 5 (04) : 479 - 486
  • [40] Development of Data-Driven In-Situ Monitoring and Diagnosis System of Fused Deposition Modeling (FDM) Process Based on Support Vector Machine Algorithm
    Jung Sub Kim
    Chang Su Lee
    Sung-Min Kim
    Sang Won Lee
    International Journal of Precision Engineering and Manufacturing-Green Technology, 2018, 5 : 479 - 486