In this paper, the problem of partner selection for virtual enterprise (VE) is addressed. A mathematical model considering the process time, cost, quality and reliability in partner selection of VE is constructed and an algorithm based on self-adaptive genetic algorithms is proposed for that problem. In this algorithm, self-adaptive crossover and mutation functions are designed considering the individual's fitness. Thus, each individual of the population owns the ability of self-adaptation according to the variation of the environment. The designed operators can avoid the emergency of premature and contribute to the convergence of the algorithm, which guarantee the global optimal solution being found as well.
展开▼