基于粗糙集和遗传神经网络的城市日用水量预测模型  

Urban Daily Water Consumption Forecast Model Based On Rough Set and Genetic Neural Network

作　　者：陈磊[1] 杨敏[1] 

机构地区：[1]浙江工业大学建筑工程学院,杭州310014

出　　处：《节水灌溉》2011年第7期32-35,共4页Water Saving Irrigation

基　　金：国家自然科学基金资助项目(50878108)

摘　　要：为克服日用水量主要影响因素一般采用主观判断确定的不足,利用改进粗糙集算法对影响因素进行属性约简,确定日用水量的主要影响因素。以日用水量的主要影响因素和相关日用水量为BP网络的输入,采用遗传算法优化BP网络的权阈值,建立了基于粗糙集算法和优化BP网络的日用水量预测模型。实例分析表明,与基于传统BP网络和基于遗传算法优化BP网络的模型相比,本文提出的日水量预测模型具有更高的预测精度。结果验证了所提出模型的合理性和有效性。To overcome the disadvantage that the main influence factors affecting daily water consumption are generally determined by subjective judgment,the improved rough set algorithm is used to analyze the factors to determine the principal factors.The principal factors and correlative daily water consumption are used as the inputs of back-propagation（BP） neural network,and the genetic algorithm（GA） is introduced to optimize the weights and thresholds of BP neural network.Then the daily water consumption forecast model based on rough set and optimal BP neural network is established.Case study shows that the proposed model has better predicting performance than the BP neural network model and the genetic BP neural network model.The results proved the rationality and validity of the proposed model.

关 键 词：日用水量 粗糙集 BP网络 回归估计 遗传算法 自相关 建模 优化 

分 类 号：TU991.33[建筑科学—市政工程]