In order to further study the application of phase change materials in inhibitors to prevent spontaneous combustion of coal, AlNH4(SO4)2·12H2O and MgSO4·7H2O were used as raw materials to obtain binary eutectic by melt impregnation. The phase transition temperature of the new material is around 70 °C, which is in the critical temperature range of the coal oxidation process. The material melts and absorbs the heat of coal during the phase change, so that the temperature of the coal is lower than the critical temperature. At the same time, it penetrates into the pores of the coal to isolate oxygen and achieves the effect of blocking the self-heating process of coal oxidation. The experimental results point out that as the proportion of AlNH4(SO4)2·12H2O in the binary eutectic increases, the better the material fusion becomes. The phase transition temperature decreases sharply at first and then slowly increases and stabilizes. The latent heat of change fluctuates back and forth between 260 and 290 J/g and then obviously decreases. Weight loss is basically between 20 and 40%. The optimization experiment pointed out that the best result is when the content of AlNH4(SO4)2·12H2O is 57.6%. Under this amount, the latent heat of phase transition is 298.67 J/g, the phase transition temperature is 65.88 °C, the weight loss rate is 27.2%, and the undercooling degree is 7.1 °C.

Aiming at the identification of coal and gas outburst risk, using the advantages of the clone selection algorithm (CSA), such as self-adaptation and robustness, and the characteristics of fast convergence of particle swarm optimization (PSO) algorithm, the complex decoding problem, and mutation process brought by CSA binary coding are used. It is difficult to control the problem. Using PSO optimization, the problem of abnormal detection and identification in coal and gas outburst monitoring is developed and studied, and a CSA coal and gas outburst risk anomaly detection and identification model based on PSO optimization variation is established. The model uses the coal and gas outburst index data as a collection of antigen-stimulated antibodies to achieve abnormal detection and identification of measured data. With the help of the measured data, the verification results show that the model can effectively detect and identify the risk of coal and gas outburst, and the identification results are consistent with the risk of coal and gas outburst in the field. It can be used as an effective risk identification model to guide coal mining work.