采用基于 T-S模型的模糊神经网络 ,用改进的遗传算法来训练网络权值 ,隶属函数参数调整算法则采用动量法和学习率自适应调整相结合的策略 ,以上证指数和厦新电子 (个股 )为研究对象予以建模和预测 .结果表明 ,此种模型具有较好的泛化、学习、映射能力 ,对股票市场或类似的非线性经济系统的走势研判或其相应预测决策具有较好的应用价值 The fuzzy neural network based on TS model is used to train the network weights with the improved genetic algorithm. The membership function parameter adjustment algorithm uses the combination of the momentum method and the learning rate adaptive adjustment. Taking the Shanghai Composite Index and Xia Xin Electronics (stocks) as The results show that this model has a good generalization, learning and mapping capabilities, and has good application value to the stock market or similar trend analysis of nonlinear economic system or its corresponding forecasting and decision-making