基于QPSO算法优化的区间二型模糊逻辑系统预测

设计了一类区间二型模糊逻辑系统,研究基于历史数据的预测问题.在区间二型模糊逻辑系统设计中,前件、后件、输入测量区间二型模糊的主隶属函数均选择成具有不确定标准偏差的高斯型二型隶属函数.量子粒子群优化(QPSO)算法用来调整所设计的区间二型模糊逻辑系统参数.部分欧洲智能技术网络(EUNITE)的负荷竞赛数据和美国田纳西州(WTI)原油价格数据用来测试所提出的模糊逻辑系统预测方法.定义综合评价误差和作为模糊逻辑系统的预测性能指标.仿真研究表明,所提出的区间二型模糊逻辑系统预测方法在收敛性和稳定性上均优于相应的一型模糊逻辑系统.

Forecasting by Interval Type-2 Fuzzy Logic System Optimized with QPSO Algorithm

A kind of interval type-2 fuzzy logic system was designed to investigate forecasting problems based on the historical data. In the process of designing the interval type-2 fuzzy logic system， the antecedent， consequent and input measurement primary membership functions of interval type-2 fuzzy sets were all Gaussian type-2 membership functions with uncertain standard deviation. The quantum particle swarm optimization algorithm was used to tune the parameters of the designed interval type-2 fuzzy logic system. Part of the load competition data of European network on intelligent technologies and the price data of West Texas Intermediate crude oil were used to test the proposed fuzzy logic system forecasting method. Comprehensive evaluation error sum was defined as the forecasting performance index of fuzzy logic system. Simulation studies showed that the proposed interval type-2 fuzzy logic system forecasting methods outperform their corresponding type-1 fuzzy logic system on convergence and stability.