中文摘要：

为了解决不同通信模式下认知无线电发射机参数合理优化的问题，提出了一种基于二进制混沌粒子群算法（BCPSO）的认知决策引擎，该引擎利用粒子群优化算法收敛速度快和混沌运动全局遍历性的特点，使认知决策在多目标优化过程中有效地摆脱了局部极值点，提高了参数优化的精度和稳定性．基于认知正交频分复用（OFDM）系统的仿真结果表明，相对于现有认知引擎，该引擎具有平均适应度值高、对不同通信模式鲁棒性强的特点，实现了有效优化发射机参数的目的．

英文摘要：

To solve the problem of transmitter parameter optimization in different communication modes for cognitive radio （CR） systems, a cognitive decision engine based on binary chaotic particle swarm optimization （BCPSO） is proposed. The BCPSO algorithm has both the fast convergence of particle swarm optimization and global ergodic property of chaos. Therefore, the cognitive decision engine based on BCPSO can jump off the local extreme points effectively, which can improve the precision and stability of parameter optimization. The cognitive orthogonal frequency division multiplexing （OFDM） system is used for the performance analysis. And the simulation results show that the proposed cognitive decision engine, which has higher fitness value and stronger robustness for different communication modes, is better than the other existing engines. The proposed engine achieves the objective of parameter optimization effectively.