基于改进PSO和FCM的模糊辨识

为了提高T-S模糊模型的辨识精度和效率，本文提出了一种改进的粒子群算法和模糊C均值聚类算法相结合的模糊辨识新方法。在该方法中，针对粒子群算法在处理高维复杂函数时容易陷入局部极值的问题，提出了一种粒子群局部搜索和全局搜索动态调整的全新优化算法。模糊C均值聚类算法是模糊辨识最常用的方法之一，该算法简单，计算效率高，但是对初始化特别敏感，容易陷入局部最优。为了解决这一问题，利用改进粒子群算法的全局搜索能力优化聚类中心，显著地提高了算法的辨识精度和效率。最后，针对非线性系统进行建模仿真，仿真结果表明了本文方法的有效性和优越性。

Fuzzy identification based on improved PSO and FCM

To improve the accuracy and efficiency of T-S model, a new fuzzy identification approach based on improved particle swarm optimization (PSO) algorithm and fuzzy C-means (FCM) algorithm is proposed. Considering that it is easy for PSO to fall into the local extremum in the treatment of high-dimensional complex functions, a PSO algorithm with dynamic adjustment between local search and global search is proposed in this paper. Moreover, the FCM algorithm is one of the most commonly used methods of fuzzy identification. The algorithm is simple and efficient, but it is particularly sensitive to initialization and easily falls into local optimum. To solve this problem, the global search capability of improved PSO is used to optimize the clustering center, and this significantly improves the accuracy and efficiency of the algorithm. Finally, a nonlinear system is modeled and simulated. The simulation results show the effectiveness and superiority of this method.