Abstract: Considering the false alarm and miss detection during testing and diagnosis of complex system, a new method was proposed to solve test selection problems under unreliable test based on Simulated Annealing Particle Swarm Optimization (SA-PSO) algorithm. Firstly, a heuristic function was established to evaluate the capability of test point detection, coverage and reliance. Then, combining the heuristic function with the least test cost principle and considering the requirement of testability targets, a fitness function to ensure optimal selection was designed. Lastly, the process and key steps of SA-PSO were introduced and the superiority of this algorithm was verified by simulation results of launch system of Apollo. The results show that the proposed method can find the global optimal test points. It can minimize test cost on requirement of testability targets and has higher fault detection and isolation rate compared with greedy algorithm and genetic algorithm.