论文部分内容阅读
无线传感器网络中基于声音能量的声源定位常采用最大似然估计法,该方法将定位问题转换为非线性函数的极值优化问题.本文提出一种文化-改进的量子粒子群优化算法(CMQPSO)解决这一非线性优化问题.首先,在量子粒子群(QPSO)的基础上,结合自适应变异思想和RSNTO算法,提出改进的量子粒子群算法(MQPSO).然后,为了进一步改善算法的全局搜索能力、提高计算精度,利用文化算法的双重演化机制,将改进的量子粒子群算法纳入文化算法框架形成本文提出的CMQPSO算法.大量仿真实验表明,CMQPSO算法在全局搜索能力和收敛性能上较PSO、混合PSO-SNTO算法都有很大的提高;在解决声源定位上,CMQPSO算法与其他优化算法相比,定位精度有了明显提高.
The maximum likelihood estimation method is often used to locate sound source based on sound energy in wireless sensor networks, which transforms the localization problem into the extreme value optimization problem of nonlinear function.This paper presents a culture-improved quantum particle swarm optimization algorithm (CMQPSO ) To solve this nonlinear optimization problem.Firstly, based on Quantum Particle Swarm Optimization (QPSO), an improved Quantum Particle Swarm Optimization (MQPSO) is proposed based on adaptive mutation theory and RSNTO algorithm.Then, in order to further improve the overall situation of the algorithm Search ability to improve the accuracy of the calculation, the use of cultural evolution of the dual mechanism of the algorithm, the improved quantum particle swarm algorithm into the cultural algorithm framework proposed in this paper CMQPSO algorithm.Many simulation experiments show that the CMQPSO algorithm in the global search capability and convergence performance than the PSO , Hybrid PSO-SNTO algorithm has greatly improved; to solve the sound source localization, CMQPSO algorithm compared with other optimization algorithms, positioning accuracy has been significantly improved.