针对传统粒子群算法存在求解精度低和易陷入局部最优等问题,提出一种基于巴特沃斯幅频特性的自适应粒子群算法(Butterworth amplitude-frequency characteristics based adaptive particle swarm opti-mization algorithm,BAC-PSO).一方面,借助巴特沃斯幅频特性设计一种惯性权重非线性递减策略,均衡算法中粒子的局部与全局搜索能力;另一方面,通过S型函数的粒子群优化策略和Sigmoid函数改进位置更新方法,进一步提升算法的求解精度.以5个经典的测试函数为基准,将BAC-PSO算法与5种经典粒子群算法的性能进行对比,并将其应用到求解压力容器模型的设计问题中.实验结果表明,相较于其他经典粒子群算法,BAC-PSO算法的求解精度更高,收敛速度更快,稳定性更好.
Adaptive particle swarm optimization algorithm based on Butterworth amplitude-frequency characteristics
The traditional particle swarm optimization algorithm has problems such as low accuracy and easy to fall into local optimality.An Butterworth amplitude-frequency characteristics based adaptive particle swarm optimization algorithm(BAC-PSO)is proposed.On the one hand,based on Butterworth amplitude-frequency characteristic,a nonlinear decline strategy of inertia weight is de-signed to balance the local and global search ability of particles in the algorithm.On the other hand,the position update method is improved by the particle swarm optimization strategy of S-shaped function and the Sigmoid function to further improve the solution accuracy of the algorithm.Based on five classical test functions,the performance of BAC-PSO algorithm is compared with that of five classical particle swarm optimization algorithms,and it is applied to solve the design problem of pressure vessel model.The experimental results show that compared with other classical particle swarm optimization algorithms,BAC-PSO algorithm has higher solution accuracy,faster conver-gence speed and better stability.
particle swarm optimization algorithmButterworth amplitude-frequency characteristicsadaptiveinertia weightpressure vessel model
NETL
NSTL
万方数据
