Multi-objective optimization modelling of iron ore sinter process based on ore particles field

Konferenz: CAIBDA 2022 - 2nd International Conference on Artificial Intelligence, Big Data and Algorithms
17.06.2022 - 19.06.2022 in Nanjing, China

Tagungsband: CAIBDA 2022

Seiten: 5Sprache: EnglischTyp: PDF

Autoren:
Chen, Xiaoyan; Liu, Daifei (School of Energy and Power Engineering, Changsha University of Science and Technology, Changsha, Hunan, China)

Inhalt:
High efficiency ore blending and sintering of iron ore is an important guarantee to obtain the stability of blast furnace raw materials and establish reasonable technical and economic indicators in iron making production. In the existing sintering proportioning modes, the adjustment of iron ore proportion is mainly based on the goal of the lowest cost, while ignoring the impact of iron ore granulation performance and particle size composition on production or quality indicators. In this study, an optimization model with three objectives is proposed, which comprehensively considers the minimum cost of mixed ore, the lowest content of harmful substances and the highest content of ore particle size 3-5mm. The constraints of the model are composed of raw material ratio, raw material particle size composition and chemical index. In the solution process of the multi-objective function, four algorithms are considered, namely, NSGA-II, NSGA-III, CCMO and C-MOEA/ D. Through the comparison of calculation results, it is concluded that NSGA-II algorithm is the most reasonable solution method. And the obtained optimized value of the ore blending cost, sulfur content and 3-5mm mineral content are 461.89, 0.0495% and 2.15 respectively.