Error assessment of laser cutting predictions by semi-supervised learning
来源期刊:中南大学学报(英文版)2014年第10期
论文作者:Mustafa Zaidi Imran Amin Ahmad Hussain Nukman Yusoff
文章页码:3736 - 3745
Key words:semi-supervised learning; training algorithm; kerf width; edge quality; laser cutting process; artificial neural network (ANN)
Abstract: Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.
Mustafa Zaidi1, Imran Amin1, Ahmad Hussain2, Nukman Yusoff 3
(1. Department of Computing, Shaheed Zulfikar Ali Bhutto Institute of Science & Technology (SZABIST),
Karachi, Pakistan;
2. Department of Nuclear Engineering, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia;
3. Manufacturing Systems Integration, Department of Mechanical Engineering, University of Malaya, Malaysia)
Abstract:Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.
Key words:semi-supervised learning; training algorithm; kerf width; edge quality; laser cutting process; artificial neural network (ANN)