Abstract: Parallel genetic algorithm is used to optimize the space diversity orthogonal wavelet blind equalization algorithm, each branch equalizer weight vector of the space diversity is used as the subpopulation of the parallel genetic algorithm to select, cross and mutate. The best adaptable individual is transmitted regularly from one subpopulation to another, and the worst adaptable individual is eliminated. Then each branch output signal of the diversity is inputted to the orthogonal wavelet blind equalizer using the equal gain merging. Computer simulation shows that the proposed algorithm can find the global optimal solution and has many advantages including the fast convergence rate and the small steady-state error.