Least squares support vector machine (LSSVM) developed based on support vector machines (SVM) with better nonlinear generalizationability, has higher fitting and prediction precision. Now it is widely used in equipment condition trend prediction. In order to further improve its prediction accuracy, a new trend prediction method combined with full vector spectrum technology based on information fusion homologous with a same source was proposed—full vector LSSVM. This method was used of full vector spectrum technology to fuse dualchannel information to ensure integrity of LSSVM prediction data feature extraction compared to the traditional singlechannel signal extraction methods, which improved prediction accuracy. The method is applied to predict the vibration data of No.1 steam turbinein in a power plant, and the experimental results show that full vector LSSVM has higher prediction accuracy.