To explore the effect of sulfate on the ash-fusion temperature (AFT) of coal ash, different contents of calcium sulfate were added to coal ash, and AFT and X-ray diffractometry (XRD) spectral analyses were carried out. The AFT of experimental coal ash was reduced at a low content, but when the calcium sulfate (CaSO4) content increased beyond 15%, the coal-ash AFT increased. The deformation temperature of real coal ash was predicted based on the content of different components and a combination of the coal-ash parameters. The support-vector machine model was optimized by using the grey-wolf algorithm. The model could predict the deformation temperatures of the different coal ash and a more accurate prediction model was obtained. In the grey-wolf-algorithm-support-vector-machine model, 58 coal samples were used, and SO3 was compared as an independent variable for training prediction. The results showed that the relative error of the deformation-temperature prediction was small and the prediction result with the SO3 input was more accurate, which agrees with the experimental results.