基于T-S模糊神经网络的模型在台风灾情预测中的应用——以海南为例  

Typhoon Disaster Prediction Model Based on T-S Fuzzy Neural Network and Its Application——A Case Study of Hainan Island

作　　者：张广平[1,2] 张晨晓[2] 谢忠[1] 

机构地区：[1]中国地质大学(武汉),湖北武汉430074 [2]钦州学院,广西钦州535000

出　　处：《灾害学》2013年第2期86-89,共4页Journal of Catastrophology

基　　金：广西自然科学基金重大专项研究课题(2010GXNSFE013001);广西壮族自治区教育厅科研立项项目(201010LX453);钦州市科学研究与技术开发计划项目(2011813901)

摘　　要：使用1992-2011年间海南省台风灾害数据,综合T-S模糊神经网络的模糊逻辑和神经网络学习优化的性能,设计了一种灾害损失预测模型并定量地表达了台风灾害损失致灾因子与灾情指标因子之间的规律。调节模型的参数cji、σji和pji(k),控制学习性能指标误差值Ep和总误差E来优化模型的性能。将模型应用于201108号台风"洛坦"灾害损失预测中,实验结果表明该模型具有较好的预测功能。The typhoon disaster loss data from 1992 to 2011 in Hainan Province are used for statistical analysis.The principal component analysis is used by statistical analysis.The five main factors of disasters and four disaster indicators factor are identified in typhoon disaster.With the advantages of fuzzy logic and neural network in T-S fuzzy neural network,a T-S fuzzy neural network model is designed and applied to the losses forecast for the typhoon disaster,and the law of the typhoon disaster hazard factor with disaster indicators factors is studied using Quantitative method.Adjust the parameters in this model,control the learning performance error value and the total error,the performance of the model can be optimized.The prediction model which had established is applied to ＂Nock-ten＂ Typhoon disaster loss forecast and the experimental results show that the model has a better ability to predict the typhoon disaster losses.The prediction model will be better value for disaster mitigation and prevention.

关 键 词：台风灾害 预测模型 T-S模糊神经网络 海南 

分 类 号：X43[环境科学与工程—灾害防治] P444[天文地球—大气科学及气象学]