Abstract
This research is focused on using digital image processing and machine learning techniques to classify Electrofused Magnesia for industry automation. We generate the data from different images by using a modern digital image process. This research proposes a new method to construct the digital image database. The propose new method is based on simple histogram mode and intensity deviation. A group of six popular machine learning algorithms has been tested to build up an automatic system for industry. We have concluded that the best suited algorithm for magnesia industry automation from this group is the PART algorithm.
Highlights
Magnesia Industry uses high quality magnesite to produce Electrofused Magnesia (EM)
During the sorting and screening processes, Electrofused Magnesium Oxide (EMO) will be manually divided by operators into three categories as follows: Electorfused Higgens 1 (EFH1), shown as Fig. 1, and Electorfused Higgens 2 (EFH2), shown as Fig. 2, and High Lime Core (HLC), shown as Fig. 3
Our research has identified that there are various with these operators, they determine what is EFH1 and what is HLC, and the remainder would be classified as EFH2
Summary
Electrofused Magnesium Oxide (EMO) is produced by transporting the calcined magnesia to the electrofusion plant where it is melted at 3000◦C in electric arc furnaces. The material adopts the structure of periclase - a white relatively non-reactive solid which presents exceptional dimensional stability and strength at high temperatures. Ingots formed in this process are cooled, stripped and broken up with a mobile rockbreaker. The product passes through a series of crushing, sorting, and screening processes before being bagged and containerised. It is transported through Rockhampton for shipment around the world. This research study is focused on the EM products classification and identification
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.