BAS Intelligent Recommendation Model for Optimum Proportion of Pellets

Combined with the advantages of GRNN in non-linear fitting and flexible network structure, the prediction model of pellet compressive strength is established, the ratio of raw materials (Ca, Si, Mg) is determined, and the important parameters (aged particles) that characterize the particle quality i...

Full description

Saved in:
Bibliographic Details
Published inJournal of physics. Conference series Vol. 1650; no. 3; pp. 32013 - 32021
Main Authors Zhu, Yinghao, Wang, Fengchuan, Duan, Ziqing, Shi, Kuanlong, Peng, Yangyang
Format Journal Article
LanguageEnglish
Published Bristol IOP Publishing 01.10.2020
Subjects
Charging
Compressive strength
Optimization
Particle production
Pellets
Physics
Prediction models
Raw materials
Search algorithms
Online AccessGet full text

Cover

More Information
Summary:Combined with the advantages of GRNN in non-linear fitting and flexible network structure, the prediction model of pellet compressive strength is established, the ratio of raw materials (Ca, Si, Mg) is determined, and the important parameters (aged particles) that characterize the particle quality in the particle production process are also determined. Based on the prediction model of compressive strength and the search algorithm of beetle antenna, the intelligent recommendation model of pellet loading proportion optimization is established. The results show that in the range of pellet loading variation not more than 20%, the best charging scheme recommended by intelligent can increase the compressive strength of cooked ball by more than 16% on average, the system runs stably, and the simulation results are effective. Bas intelligent recommendation model significantly improved the average daily compressive strength of cooked balls in the same period of last year.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1650/3/032013