中文摘要：

多客观的参数调整在改进认知收音机(CR ) 的性能起一个重要作用系统。基因算法(GA ) 到的当前的研究焦点在 CR 完成参数优化，当时一般 GA 总是掉进早熟的集中。此后，这篇论文建议了线性规模转变到单个染色体的健康，它能减少在早进化重复退出的非凡的个人的影响，并且在后者进化重复保证在个人之间的竞争。这篇论文也介绍一个适应转线路和变化概率算法进参数调整，它能保证人口的差异和集中。二应用在 CR 的参数调整被使用，一应用比较喜欢小点错误率，另外一个比较喜欢带宽。模拟结果证明没有掉进早熟的集中，改进参数调整算法能快收敛到全球最佳的解决方案。

英文摘要：

Multi-objective parameter adjustment plays an important role in improving the performance of the cognitive radio （CR） system. Current research focus on the genetic algorithm （GA） to achieve parameter optimization in CR, while general GA always fall into premature convergence. Thereafter, this paper proposed a linear scale transformation to the fitness of individual chromosome, which can reduce the impact of extraordinary individuals exiting in the early evolution iterations, and ensure competition between individuals in the latter evolution iterations. This paper also introduces an adaptive crossover and mutation probability algorithm into parameter adjustment, which can ensure the diversity and convergence of the population. Two applications are applied in the parameter adjustment of CR, one application prefers the bit error rate and another prefers the bandwidth. Simulation results show that the improved parameter adjustment algorithm can converge to the global optimal solution fast without falling into premature convergence.