基于混沌自适应变异粒子群优化的解相干算法

张陆游; 张永顺; 杨云

doi:10.3724/SP.J.1146.2008.01188

基于混沌自适应变异粒子群优化的解相干算法

doi: 10.3724/SP.J.1146.2008.01188

基金项目:

国家自然科学基金(60601016)资助课题

计量
- 文章访问数: 3654
- HTML全文浏览量: 76
- PDF下载量: 1032
- 被引次数: 0
出版历程
- 收稿日期: 2008-09-22
- 修回日期: 2009-03-16
- 刊出日期: 2009-08-19

A De-correlation Algorithm Based on Chaos Adaptive Mutation PSO Optimization

摘要

摘要: 针对相干信源波达方向估计的需要，结合粒子群优化算法，论文提出了一种基于混沌自适应变异粒子群优化的广义极大似然算法(CAMPSOGML)，算法对阵列的几何结构没有任何约束，分辨的信源数可大于阵元数，算法把混沌初始化和自适应变异策略引进粒子群算法中，有效地提高了收敛速度，克服了粒子群算法容易陷入局部最优值的缺点。计算机仿真表明：与基于实数遗传算法和粒子群算法的广义极大似然估计方法相比，CAMPSOGML算法在收敛速度和估计精度上都有优势，是一种新颖的有效的解相干算法。
- 波达方向估计;混沌自适应变异;广义最大似然;粒子群算法;相干
Abstract: Meeting to the need of coherent signal direction-of-arrival estimation, applying particle swarm optimization algorithm, a Generalized Maximum Likelihood algorithm Based on Chaos Adaptive Mutation PSO (CAMPSOGML) optimization is proposed, the arrays geometry is unrestricted, furthermore, the number of sources resolved can be larger than the number of sensors, chaos initiation and adaptive mutation strategy is applied to basic PSO algorithm, the algorithm convergence speed is improved. The PSO algorithms defect which is easy to running into local optimum is overcome. Computer simulation results show that compared with the GML algorithm based on real genetic algorithm (GA) or PSO algorithm, CAMPSOGML algorithm is better at the aspects of convergence speed and estimation accuracy, this algorithm is a new and effective de-correlation DOA algorithm.

HTML全文

参考文献(1)

王布宏, 王永良, 陈辉. 相干信源波达方向估计的广义最大似然算法[J].电子与信息学报.2004, 26(2):225-232浏览[2]Kenney J and Eberhart R C. Particle swarm optimization [C].Proc IEEE international conference on Neural Networks.Perth, USA, 1995: 123-125.[3]Eberharte C and Shi Y. Particle swarm optimizationdevelopments, applications and resources [C]. Proceedings ofthe IEEE congress on evolutionary computation. Piscataway,USA, 2003: 24-26.[4]唐贤伦. 混沌粒子群优化算法理论及应用. [博士论文], 重庆大学, 2007: 34-36.Tang X L. The theory and application of particle swarmoptimization algorithm based on chaos. [Ph.D. dissertation],Chongqing University: 2007, 34-36.[5]高尚, 杨静宇. 群智能算法及其应用[M]. 北京: 中国水利水电出版社, 2006: 79-81.[6]吕振肃, 侯志荣. 自适应变异的粒子群优化算法[J]. 电子学报, 2004, 32(3): 416-420.Lu Z S and Hou Z R. ParticIe swarm optimization withadaptive mutation[J]. Acta Electronica Sinica, 2004, 32(3):416-420.[7]张陆游, 张永顺, 潘克战. 变步长自适应算法在雷达旁瓣对消系统中的应用[J]. 空军工程大学学报, 2008, 9(4): 25-28.Zhang L Y, Zhang Y S, and Pan K Z. The application ofun-constant-step adaptive algorithm in radar SLC system [J].Journal of Air Force Engineering University, 2008, 9(4):25-28.[8]王永良, 陈辉, 彭应宁等. 空间谱估计理论与算法[M]. 清华大学出版社, 2004: 146-149.Wang Y L, Chen H, and Peng Y L, et al.. Spatial SpectrumEstimation Theory and Algorithm [M]. Beijing: TsinghuaUniversity Press, 2004: 146-149.[9]刘伟, 王科俊, 邵克勇. 混沌时间序列的混合粒子群优化预测[J]. 控制与决策. 2007, 22(5): 562-564.Liu W, Wang K J, and Shao K J. Predicting chaotic timeseries using hybrid particle swarm optimization on algorithm[J]. Control and Decision, 2007, 22(5): 562-564.

施引文献

资源附件(0)

访问统计