Intelligent Recommendation Framework for Iron Ore Matching Based on SA2PSO and Machine Learning to Reduce CO₂ Emissions

Optimization of sinter ore allocation is a key step in the steel production process, which has become the most important measure for steel enterprises to effectively reduce cost, improve quality, save energy and reduce emissions. In this paper, the first intelligent recommendation model for the sintering dosing scheme considering cost, quality and carbon emission in the sintering process is developed using the SA2PSO optimization algorithm combined with machine learning. To improve the optimization accuracy and speed of the PSO algorithm, the SA2PSO algorithm is based on the adaptive and simulated annealing operations to achieve different stages of particle optimization, and the convergence speed is reduced by about 5 s compared with PSO while ensuring the optimization accuracy. Based on the optimal solution, the random forest algorithm was used to achieve a high-accuracy prediction of quality. For carbon emission, this paper for the first time to our knowledge converts carbon tax into iron ore sintering cost, establishes a dosing scheme considering cost carbon emission and quality and finally establishes an intelligent recommendation model for sintering dosing based on VIKOR. The model can be used for optimal ore allocation in sintering to achieve low cost, high quality and low CO2 emission in iron ore sintering.