Open AccessA Detection and Identification Method Based on CNN for Laser Point Thermal Radiation
Author(s) -
Haichuan Yang,
Ruidong Xie,
Yingmin Yi
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1654/1/012107
Subject(s) - laser , identification (biology) , computer science , point (geometry) , artificial intelligence , radiation , thermal , image (mathematics) , computer vision , pattern recognition (psychology) , optics , mathematics , physics , botany , geometry , meteorology , biology
Aiming at the high demands of temperature and precision in the aspect of additive manufacturing, a method based on CNN was proposed for estimating measurement. The network was trained through the collected laser thermal radiation images for image recognition and isotherm estimation after modeling a CNN. The experimental conclusion verifies that the isotherm detection and temperature estimation of the laser point can be efficiently implemented in proposed method.