基于改进蚁群算法的模糊逻辑系统的设计

Design of Fuzzy Logic System Based on Improved Ant Colony Algorithm

提出了一种进行全局信息素迹更新的改进蚁群算法(IACO),并用此智能算法来进行模糊逻辑系统规则的筛选,以此来提高模糊逻辑系统(FLS)的精确性。将选择出来性能最优的规则作为规则基,融入神经网络中并设计相应的模糊逻辑系统。为了检验系统的性能,将设计的模糊逻辑系统用于国际石油价格的预测,仿真结果表明,提出的方法是有效的。与无规则筛选的和基于蚁群算法(ACO)的模糊逻辑系统相比,都能够取得良好的效果。

This paper proposes an improved ant colony algorithm（IACO） for global pheromone trail updating, and uses this algorithm to select rules of the fuzzy logical system to improve the accuracy of fuzzy logical system（FLS）. Those selected rules are regarded as rule bases, and integrated into the neural network to design the corresponding fuzzy logic system. In order to test the performance of the system, the system is designed for the prediction of international petroleum price, and the simulation results show that the proposed method is effective. Compared with the fuzzy logic system without rules selected and the ant colony algorithm（ACO）, the algorithm can obtain a better result.