Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 59, Issue 19, 1916005(2022)

Temperature Prediction Based on Neural Network for Selective Laser Sintering

Ruidong Xie1、*, Jinwei Zhu1, Qi Zhong2, and Feng Gao1
Author Affiliations
  • 1Key Laboratory of Manufacturing Equipment of Shaanxi Province, Xi'an University of Technology, Xi'an 710048, Shaanxi, China
  • 2State Key Laboratory for Manufacturing Systems Engineering, Xi'an Jiaotong University, Xi'an 710049, Shaanxi, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (15)
    Equations (5)
    References (20)
    Cited By (1)
    Tools
    Paper Information
    Topics
    Figures & Tables(15)
    Schematic diagram of the SLS process of the multitrack-multilayer part

    Fig. 1. Schematic diagram of the SLS process of the multitrack-multilayer part

    Download full size
    4-beams SLS forming system and the infrared thermal imager. (a) FLIR A615 infrared thermal imager; (b) SLS forming system; (c) ceiling of the forming cabin

    Fig. 2. 4-beams SLS forming system and the infrared thermal imager. (a) FLIR A615 infrared thermal imager; (b) SLS forming system; (c) ceiling of the forming cabin

    Download full size
    SLS temperature field simulation image with the process parameters of the group 10

    Fig. 3. SLS temperature field simulation image with the process parameters of the group 10

    Download full size
    Detected images of sintering points temperatures with the process parameters of the group 10

    Fig. 4. Detected images of sintering points temperatures with the process parameters of the group 10

    Download full size
    SLS temperature field simulation image with the process parameters of the group 18

    Fig. 5. SLS temperature field simulation image with the process parameters of the group 18

    Download full size
    Detected images of sintering points temperatures with the process parameters of the group 18

    Fig. 6. Detected images of sintering points temperatures with the process parameters of the group 18

    Download full size
    Schematic diagram of sintering points temperatures prediction model based on neural network

    Fig. 7. Schematic diagram of sintering points temperatures prediction model based on neural network

    Download full size
    Algorithm flow of BP neural network optimized by GA

    Fig. 8. Algorithm flow of BP neural network optimized by GA

    Download full size
    Testing sample errors of the GA-BP neural network

    Fig. 9. Testing sample errors of the GA-BP neural network

    Download full size
    Interface of sintering points temperatures prediction software

    Fig. 10. Interface of sintering points temperatures prediction software

    Download full size
    Design model of the thin cuboid

    Fig. 11. Design model of the thin cuboid

    Download full size
    Comparison of predicted and detected sintering points temperatures of part 1. (a) Predicted temperatures; (b) detected temperatures

    Fig. 12. Comparison of predicted and detected sintering points temperatures of part 1. (a) Predicted temperatures; (b) detected temperatures

    Download full size
    Comparison of predicted and detected sintering points temperatures of part 2. (a) Predicted temperatures; (b) detected temperatures

    Fig. 13. Comparison of predicted and detected sintering points temperatures of part 2. (a) Predicted temperatures; (b) detected temperatures

    Download full size

    • Table 1. Process parameters of the simulation experiments

      View table

      Table 1. Process parameters of the simulation experiments

      No.Laser power /WScan speed /（m·s-1）Powder layer thickness /mmNo.Laser power /WScan speed /（m·s-1）Powder layer thickness /mm
      1450.10.1519410.30.15
      2500.10.1520470.30.15
      3580.10.1521500.30.25
      4400.10.2022570.30.25
      5450.10.2023600.30.25
      6500.10.2024500.30.30
      7450.10.3025550.30.30
      8500.10.3026650.30.30
      9550.10.3027360.40.15
      10500.20.2028420.40.15
      11550.20.2029450.40.15
      12600.20.2030450.40.25
      13480.20.2531500.40.25
      14550.20.2532580.40.25
      15650.20.2533440.40.30
      16400.20.3034480.40.30
      17450.20.3035550.40.30
      18350.30.15

    • Table 2. Technical parameters of the FLIR A615 infrared thermal imager

      View table

      Table 2. Technical parameters of the FLIR A615 infrared thermal imager

      ParameterValue
      Temperature range of the objects /℃-40-650
      Image frequency /Hz50
      Infrared resolution /（pixel×pixel）640×480
      Operating temperature range /℃-15-50
      Accuracy /℃±2（or ±2% of the readings）
      Field angle /［（°）×（°）］80×64.4
    Tools

    Get Citation

    Copy Citation Text

    Ruidong Xie, Jinwei Zhu, Qi Zhong, Feng Gao. Temperature Prediction Based on Neural Network for Selective Laser Sintering[J]. Laser & Optoelectronics Progress, 2022, 59(19): 1916005

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Materials

    Received: Sep. 22, 2021

    Accepted: Oct. 19, 2021

    Published Online: Sep. 23, 2022

    The Author Email: Xie Ruidong (rdxie2007@163.com)

    DOI:10.3788/LOP202259.1916005

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology