The main components of iron concentrate produced by Hualian Zinc Indium Concentrator are magnetite and pyrrhotite. There are some problems such as excessive sulfur content, poor quality, low sales price and high loss rate of tin metal in this iron concentrate. The efficient separation of pyrrhotite and magnetite was realized by the process of iron rough concentrate + low-intensity magnetic separation + pre-demagnetization + grading regrinding + pre-demagnetization + flotation desulfurization + magnetic separation. Finally, a high-quality iron concentrate with iron grade of 66.62% and sulfur content of 0.65% was obtained, and a high-iron sulfur concentrate with sulfur content of 25.61%, sulfur recovery rate of 96.06% and iron content of 59.52% was produced. At the same time, the loss rate of tin in iron concentrate was reduced, and a sulfur ore with a tin enrichment ratio of 3.69 times was produced, thereby reducing the loss of tin metal.

Due to the unique coal forming environment, the contents of alkali metals and alkaline earth metals in Zhundong coal are high, and some mining areas are accompanied by problems such as high iron and high calcium. These elements can cause boiler slagging and pollution during coal combustion, greatly limiting the development and utilization of Zhundong coal. In order to achieve efficient and clean utilization of Zhundong coal and fundamentally reduce the content of alkali metals and iron in Zhundong coal, it has been demonstrated that Fe₂O₃ in coal ash mainly comes from associated minerals of coal. Therefore, by sorting and reducing the content of coal ash, iron elements in coal can be removed to a certain extent. Several mature sorting technologies were compared and analyzed, it was found that due to the brittle nature of coal in the West Black Mountain mining area of Zhundong coalfield and its susceptibility to water, and it is difficult to improve its quality and utilization through wet sorting technology. The cost of magnetic separation technology equipment is high and the feeding particle size is small, which not only increases the crushing cost, but also doesn't conform to the actual production and sales situation of coal mines. The profit level and production of the composite dry sorting machine are relatively high, which meets the actual production needs of coal mines. It is recommended to use the the composite dry separation technology to improve the quality and reduce iron content of raw coal in the mining area. The composite dry separation technology can reduce about 30% of Fe₂O₃ of the raw coal ash in the research area, and the sorted clean coal can be subjected to powdering treatment to reduce the iron content in the clean coal to below 20%, thereby meeting the market demand.

In order to improve the level of on-line detection of ash in coal slime flotation process, the prediction of ash content of tailings in coal slime flotation process was studied, and the prediction model of ash content of flotation tailings based on LightGBM optimized by genetic algorithm was established. Through the collected production data, including slurry flow, concentration, foaming dose, collection dose and dry slime amount, the model training data set was constructed and the model was tested and verified. The experimental results show that the average absolute error of the prediction results of the model is 0.72, which is 11.1% higher than that of the unoptimized LightGBM model. Compared with other models, the average absolute error of the prediction results of the GA-LightGBM model is reduced by 15.8%, which further proves the validity of the model in the prediction accuracy of ash in coal tailings and provides a new technical support for the realization of intelligent flotation.