Abstract: There exist many nonlinear optimization problems in the actual chemical process,for which the conventional swarm intelligence optimization algorithm easily falls into local optimum.This paper presents a parasitic behavior (FAPB) based double population firefly algorithm.By dividing into the evolutionary population into two ones linked together via the parasitic behavior of organisms,these population can share the information and improve the global searching ability.In order to prevent the algorithm from falling into local optimum,this paper further introduces Gauss mutation mechanism based on the adaptive coefficient to improve the local search ability.By simulations on four classical test functions,it is shown that,compared with the standard FA algorithm,FALS algorithm and LDPSO algorithm,the proposed FAPB algorithm can effectively improve the convergence accuracy and global search capability.Finally,the feasibility of the proposed algorithm is also demonstrated via diesel blending.