Abstract: In view of the problems of low accuracy and long time-consuming of traditional command and control network fault detection methods of Chinese army in complex battlefield environment, a method based on decision gray wolf optimization support vector machine is proposed to realize the fault detection of command and control network. Firstly, the collected network fault data sets are processed for normalization; and then the Principal Component Analysis（PCA）is used to reduce the dimension of the data sets to eliminate the dimension with less information in the data sets; After that, the Support Vector Machines（SVM）model is built, and the Decision Gray Wolf Optimization （DGWO）algorithm is used to perform global optimization, and the position of the wolf pack is used to replace the values of kernel function and penalty factors in the SVM, the position of the wolf pack is updated through continuous iterative optimization, and the optimal kernel function and penalty factors are obtained, so as to detect the fault of the command and control network. The experimental results show that the proposed method has a detection accuracy of 98.68% compared with other methods, the proposed method has higher practicability and effectiveness.