An Evolutionary Multiobjective Approach to Fluorspar Blending in Aluminum Fluoride Production

Aluminum fluoride ($\mathrm{AlF_{3}}$) is a vital industrial material and its production is highly dependent on the precise blending of fluorspar. Conventional blending approaches rely heavily on manual expertise and often prove inefficient in handling complex ore compositions and multiple constraints. In this work, the fluorspar blending task is formulated as a constrained multiobjective optimization problem that simultaneously balances economic efficiency and production stability. Distinct from traditional cost-centric models, our approach explicitly incorporates the effects of fluorspar impurities on downstream reagent consumption, thereby achieving global cost minimization from raw material to final product. A novel constrained multiobjective state transition algorithm with self-adaptive shift-based penalty function under a dual-population framework is proposed to effectively handle complex constraints arising from inventory limits, compositional requirements, and impurity content. A fully functional intelligent fluorspar blending optimization system is developed and deployed using real-world data from multiple suppliers. Experimental results demonstrate superior performance in blending quality, cost-effectiveness, and industrial adaptability, offering a scalable solution for intelligent fluorspar blending optimization in$\mathrm{AlF_{3}}$production.