Open AccessThe estimation of the laser point temperature based on CNN (Convolutional Neural Network)
Author(s) -
Yingmin Yi,
Ruidong Xie,
Haichuan Yang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/740/1/012023
Subject(s) - convolutional neural network , laser , point (geometry) , computer science , artificial intelligence , heat equation , artificial neural network , image (mathematics) , thermal , pattern recognition (psychology) , materials science , optics , mathematics , physics , mathematical analysis , thermodynamics , geometry
For the requirements of the laser temperature in additive manufacturing, there is a high precision and high heat need in the industry. The method is proposed to estimate the temperature of laser point, which is based on CNN. In this method, a model of CNN is carried out. The collected laser thermal radiation images are used to train the model. Image recognition and isotherm estimation can be obtained by the trained model. The conclusion can be verified by the experiment. The isotherm and temperature of the laser can be measured efficiently in this method.