Abstract—The 4th 1 industrial revolution is promoting manufacturing industry to be vitalized again. The manufacturing industry requires many industrial materials. Among them, different gases are also used in many fields. While they are useful, industrial gases can be also hazardous at the same time. In order to control those bad features of gases, their dynamic characteristics are required to be understood. In this paper we tried to understand the characteristics by applying several machine learning methods such as MLP, DLP and LSTM. Two ensemble methods are applied to compensate the lack of raw data. Simulation outputs are compared each other to know which method is proper for this case.
Index Terms—Data mining, neural networks, computer simulation, pattern recognition.
The authors are with the Department of Smart Factory and Computer Science, Korea Polytechnic University, Korea (e-mail: yrho@kpu.ac.kr, k010511@naver.com).
[PDF]
Cite: K. M. Gwak and Young J. Rho, "Gas Diffusion Simulation Based on Ensemble Approach," International Journal of Modeling and Optimization vol. 10, no. 5, pp. 160-169, 2020.
