基于生物算法优化人工神经网络的城市需水预测模型构建  

Construction of Urban Water Demand Prediction Model Based on Biological Algorithm Optimization Artificial Neural Network

作　　者：康静雯 Kang Jingwen(Chongqing Water Conservancy and Power Construction Survey,Design and Research Institute Co.,Ltd.,Chongqing,China)

机构地区：[1]重庆市水利电力建筑勘测设计研究院有限公司,重庆

出　　处：《科学技术创新》2023年第21期60-63,共4页Scientific and Technological Innovation

摘　　要：为得出城市需水量最优预测模型,缓解城市用水问题,本文以人工神经网络模型(ANN)为基础,基于哈里斯鹰算法(HHO)、蝙蝠算法(BA)和鸽群算法(PIO)共3种生物算法,构建了3种优化ANN模型,并将模型结果与实测值进行了对比,结果表明:HHO-ANN模型模拟值与实测值变化趋势最为接近,同时该模型模拟值的误差最低,一致性最高,可推荐用于估算城市需水量。To obtain the optimal prediction model of urban water demand and alleviate the urban water problem,in this paper we constructed three optimal ANN models based on artificial neural network model(ANN)and three biological algorithms,namely Harris Eagle algorithm(HHO),Bat algorithm(BA)and pigeon flock algorithm(PIO).The model results were compared with the measured values.The results showed that:the variation trend of the simulated value of HHO-ANN model was the closest to the measured value,and the simulated value of HHO-ANN model had the lowest error and the highest consistency,so it can be recommended for estimating urban water demand.

关 键 词：城市需水量 人工神经网络 哈里斯鹰算法 生物算法 

分 类 号：TV212[水利工程—水文学及水资源]