Due to the difficulty of acquiring real aerial infrared cloud images, we propose an efficient way to set up cloud simulation data set by particle system and texture synthesis, in order to alleviate the problem of data shortage. The deep network for cloud segmentation is trained on our simulation image data set, substantially decreasing the demand for real aerial cloud images. When testing on the real image data set, a satisfactory segmentation result with 79.64% has been reached which can meet the usage requirements. Our method can make the deep cloud segmentation network training feasible despite of the real image shortage, reducing the cost of data acquisition.