Based on chaos PSO algorithm optimization parameters of LS-SVM

monitoring of INS’s initial alignment is realized.Noises in INS’s error data are eliminated by wavelet decomposition

learning and testing samples for LS-SVM are also acquired.Aimed at LS-SVM solving large scale data regression led to long training time and slow convergence speed

chaos PSO algorithm optimization parameters of LS-SVM is proposed.The disadvantages of earliness and tending to get into local solution in traditional PSO algorithm are overcomed by this method.It also remarkably improves forecasting ability of LS-SVM.The results of general LS-SVM and GM（1

1） forecasting model is compared with the results of this article

it proves this method has a transparent superior in forecasting precision.