Abstract: An immune particle swarm optimization algorithm(immune-PSO) based on clonal selection was proposed.In the method,the strategy of antibody clone,mutation and limit was introduced into PSO algorithm to avoid trapping in local minimum.To resolve the problem that the choice of parameters influences the forecast precision of support vector machine(SVM) forecasting model,the immune-PSO algorithm was used to design the aero-engine lubrication debris forecasting model based on SVM with self-adaptive optimized parameters.The simulation results show that the forecasting model optimized by immune-PSO algorithm can achieve automatic optimization of parameters,and increase forecasting accuracy than the conventional cross-validation algorithm.