Abstract: A multi-sensor information fusion method based on support vector machine was studied to analyze the high-power disk laser welding status. During high-power disk laser welding, the metallic plume, spatters and molten pool are important phenomena which are related to the welding quality. An ultraviolet and visible sensitive video camera was used to capture the metallic plume and spatter dynamic images, and another infrared sensitive video camera was used to capture the molten pool images. The image processing and pattern recognition technologies were applied to extract the welding characteristics information and analyze the principal components. Weld bead width was used as a characteristic parameter that reflects the welding stability. After data normalization and characteristic analysis, the multi-sensor information was fused by the support vector machine, and the grid search method and particle swarm optimization were used to optimize the experimental parameters of support vector machine. Finally a fusion model based on support vector machine was established to estimate the weld bead width. Experimental results showed that the multi-sensor information fusion based on support vector machine could effectively predict the weld bead width, thus providing an experimental evidence for monitoring the high-power disk laser welding status.