改进的蝗虫优化算法及其应用

Improved grasshopper optimization algorithm and its application

针对蝗虫优化算法(GOA)收敛精度不高、易陷入局部最优等问题,提出一种非线性自适应模拟退火的蝗虫优化算法(SA-NGOA)。利用非线性自适应更新GOA的关键参数,更好地协调算法的全局探索和局部开发;利用模拟退火算法,以一定概率接收GOA的劣势解,提高算法的收敛精度。实验结果表明,SA-NGOA算法具有良好的优化性能。同时,将SA-NGOA算法用于扩展同步参数观测器(ESPO)参数优化,其结果表明,该算法优化后的ESPO具有更快的辨识速度和更稳定的精度。

The nonlinear adaptive and simulation annealing grasshopper optimization algorithm(SA-NGOA)was proposed to avoid the disadvantages that the locust optimization algorithm is easy to fall into local optimum and has low convergence accuracy.The key parameters of GOA were updated by nonlinear adaptation to better coordinate the global exploration and local development of the algorithm.The simulated annealing algorithm was used to receive the inferior solution of GOA with a certain probability to improve the convergence accuracy of the algorithm.The results show that the SA-NGOA algorithm has good optimization performance.At the same time,the SA-NGOA algorithm was used to optimize the parameters of the extended synchronous parameter observer(ESPO).The results show that the ESPO optimized using the algorithm has higher identification speed and more stable accuracy.