Abstract: An intelligent algorithm for fault prediction of communication equipment is proposed, in which particle swarm optimization algorithm and least square support vector machine is combined and the particle swarm optimization algorithm is adopted to optimize the parameters of least square support vector machine.The method overcomes the human's blindness on parameters selection and has more superior performance on global optimization and convergence speed.The simulation results show that LS-SVM optimized by PSO has better prediction accuracy and better computing speed, compared with the method based on BP neural network and support vector machine and LS-SVM.The effectiveness and feasibility of the method is better.