Authors: Alpana; Satish Chand; Subrajeet Mohapatra; Vivek Mishra
Addresses: School of Computer and Systems Sciences, Jawaharlal Nehru University, New Mehrauli Road, JNU Ring Road, New Delhi-110067, Delhi, India ' School of Computer and Systems Sciences, Jawaharlal Nehru University, New Mehrauli Road, JNU Ring Road, New Delhi-110067, Delhi, India ' Department of Computer Science and Engineering, Birla Institute of Technology, Mesra, Ranchi-835215, Jharkhand, India ' Hebei Collaborative Innovation Center of Coal Exploitation, Hebei University of Engineering, Handan-056038, Hebei, China
Abstract: Coal is one of the most available sources of energy worldwide, and is used vigorously. Char particles are formed by devolatising of coal during combustion and signify the foremost step in the ignition method. Char particles are categorised into two reactive phases based on their morphologies by experts, namely reactive and non-reactive. These are taken into consideration to estimate the impact of coal on the burner's performance. Presently, the semi-automatic method is followed by industries to determine the classification of char groups. This conventional method is time-consuming and subjective. Char characterisation may be executed automatically with advantages like fast processing and consistency. In this article, we attempt to suggest an automated scheme for classification of char into its reactive and non-reactive groups using image analysis and artificial intelligence methods. Subsequently, the proposed system is recognised to be an efficient technique for characterisation of char with more accurate results in reduced computational time. [Received: December 20, 2019; Accepted: April 26, 2020]
Keywords: coal; char; image analysis; artificial intelligence; deep learning.
International Journal of Oil, Gas and Coal Technology, 2021 Vol.28 No.2, pp.235 - 248
Received: 20 Dec 2019
Accepted: 26 Apr 2020
Published online: 22 Jul 2021 *