For the shortcoming that quantum-behaved particle swarm
optimization(QPSO) is often premature convergence, two improved QPSO algorithms are presented by integrating selection mechanism. One is the QPSO with tournament
selection(QPSO-TS) and the other is the QPSO with roulette-wheel
selection(QPSO-RS). The
selection operator is exerted on the global best position to improve the
search ability of the QPSO algorithm. Furthermore, global convergence of the algorithm is proved. The
experiment results on benchmark functions show that both QPSO-RS and QPSO-TS
have stronger global search ability than QPSO and standard PSO.