| It is significant to reduce the release of sodium during combustion for large-scale use of Zhundong coal. The common salic minerals of kaolin, alumina and diatomaceous were selected as the Zhundong Coal additives. Retention rates of NaCl, Na2SO4, NaOH and the sodium in Zhundong coal were investigated at different blending ratios and temperatures. The results show that kaolin has the best sodium retention effect for all sodium minerals and the sodium in Zhundong coal, because it contains both silicon and aluminum elements. The sodium retention rates increase with blending ratio, and decrease slightly with increasing temperature due to the reduced concentration of reactants and sintering.The best additive of kaolin was selected as the further research object and the coal ash fusion temperatures were investigated at different blending ratios. XRD and ternary phase diagram were used to identify mineral transformations at high temperatures. The results show that the change of ash fusion temperature is due to the mineral content changes of rankinite, gehlenite and anorthite. The lowest ash fusion temperatures at the blending ratios of 3% and 4% are mainly caused by the low temperature eutectic phenomenon. The blending ratio of 2% is conductive to solid-state slag-tap boiler, and the blending ratio of 3~4% is suitable for liquid-state slag-tap boiler.Coal blending is another important way to reduce the release of sodium and Zhungeer was selected as the blended coal into Zhundong coal. Sodium retention rates, coal ash fusion temperatures and the mineral transformations in ash were investigated at different blending ratios and temperatures. The results show that Zhungeer coal has a strong sodium retention ability. The sodium retention rates increase with blending ratio, and decrease slightly with increasing temperature. The fusion temperatures of the blended ashes initially decrease and then increase with the blending ratio due to the occurrence of eutectic melting. The main eutectic reactants are gehlenite, magnetite, merwinite, and diopside. The blending ratio of 3% is conductive to liquid-state slag-tap boiler, and the blending ratio more than 5% is suitable for solid-state slag-tap boiler.A CSBP model based on BP (Back Propagation) Neural Network optimized by Cuckoo Search (CS) was proposed for predicting the ash deformation temperature of single coal, coal blended with additive and coal blending. The deformation ash temperatures of Zhundong coal blended with kaolin and Zhungeer were used to verify the validity of CSBP model. The results show that CSBP model has a better performance compared with BP model. And comparing the prediction results of three kinds of samples, both the CSBP model and BP model have higher prediction errors for coal blended with additive and coal blending more than that for single coal. The CSBP model also indicates a good predicting effect on the deformation ash temperatures of Zhundong coal blended with kaolin and Zhungeer. |