The iron and steel industry has made an important contribution to China’s economic development, and sinter accounts for 70–80% of the blast furnace feed charge. However, the average grade of domestic iron ore is low, and imported iron ore is easily affected by transportation and price. The intelligent ore blending model with an intelligent algorithm as the core is studied. It has a decisive influence on the development of China’s steel industry. This paper first analyzes the current situation of iron ore resources, the theory of sintering ore blending, and the difficulties faced by sintering ore blending. Then, the research status of the neural network algorithms, genetic algorithms, and particle swarm optimization algorithms in the intelligent ore blending model is analyzed. On the basis of the neural network algorithm, genetic algorithm and particle swarm algorithm, linear programming method, stepwise regression analysis method, and partial differential equation are adopted. It can optimize the algorithm and make the model achieve better results, but it is difficult to adapt to the current complex situation of sintering ore blending. From the sintering mechanism, sintering foundation characteristics, liquid phase formation capacity of the sinter, and the influencing factors of sinter quality were studied, it can carry out intelligent ore blending more accurately and efficiently. Finally, the research of intelligent sintering ore blending model has been prospected. On the basis of sintering mechanism research, combined with an improved intelligent algorithm. An intelligent ore blending model with raw material parameters, equipment parameters, and operating parameters as input and physical and metallurgical properties of the sinter as output is proposed.

Accurate prediction of carbon monoxide (CO) concentration at the main exhaust outlet of the sintering process is important for combustion state assessment and CO emission control. Existing data-driven methods treat process variables as homogeneous inputs, neglecting their process affiliations and cross-system interactions. This study proposes a process-guided Kolmogorov–Arnold network (PG-KAN) for CO concentration soft measurement. According to process relationships, 230 process variables are organized into material, flue gas, and auxiliary systems, and independent radial basis function-based Kolmogorov–Arnold network (RBF-KAN) encoding branches extract system-specific nonlinear representations. Cross-system interaction modules capture interactions among these systems. A tail coverage-aware loss reduces large errors and underestimation bias in high-CO concentration intervals. Experiments on 18,749 industrial samples show that PG-KAN achieves a mean absolute error (MAE) of 107.700 mg/m³, a coefficient of determination (R²) of 0.9105, and a Pearson correlation coefficient of 0.9542, outperforming six baseline models. Ablation studies verify the effectiveness of process-guided variable organization, cross-system interactions, and the proposed loss. Edge-function and SHapley Additive exPlanations (SHAP) analyses provide insights into nonlinear mappings and feature contributions learned by the model. The proposed method provides an interpretable, process-guided framework for CO concentration soft measurement in industrial sintering processes.

Iron tailings are solid waste generated after the mining of iron mines, which have caused serious damage to the surrounding ecology and environment and have attracted widespread attention. By analyzing the formation causes, main components, and environmental effect mechanisms of iron tailings, the article systematically elaborates on the degree and mechanism of the harm of iron tailings to water bodies, atmosphere, soil, and ecosystems, and evaluates its impact on human health and sustainable development of society. On this basis, specific prevention and control measures have been proposed to reduce iron tailings emissions, realize resource recycling, and restore ecosystems. Research shows that iron tailings containing heavy metals can widely pollute the environment through dissolution and migration, and have significant biological toxicity effects. The research results can provide a theoretical reference for decision-making departments to formulate scientific and reasonable iron tailings disposal and ecological protection policies. It is recommended to strengthen specific research on the infiltration of toxic and harmful components in tailings in the future, and develop efficient and stable solidification technology, and vegetation-microbial joint restoration models to further reduce the ecological and environmental risks of iron tailings.