-The elongation prediction of strips in furnace is extremely important in annealing process, which determines the quality and yield of product [1, 2]. Furthermore, the safety of airknife also depends on the prediction accuracy [3, 4]. Thus, the optimal soft-sensing method is proposed based on kernel principal component analysis (KPCA) and optimized weighted least squares support vector machine (WLSSVM) by immune clone particle swarm optimization (ICPSO). Avoiding the particles are easy to sink into premature convergence and run into local optimization in the iterative process by using ICPSO , which generated by particle swarm optimization (PSO) algorithm, and the ICPSO is also used to optimize the parameters of WLSSVM. Then, the method uses KPCA to denoise the input data set and capture the high-dimensional nonlinear principal components in input data space, and the principal components are input into the ICPSO-WLSSVM model to establish the softsensing prediction model. The proposed method is successfully applied in the strip elongation prediction in annealing furnace. The simulations show that the KPCA and ICPSO-WLSSVM model has higher prediction accuracy compared with other algorithms that verified with production data.