YANGMeng-qi,XUZhi-wei,WANGYi-ming,et al.Deep LSTM Neural Network Model for Real-time Control of Urban Drainage System[J].China Water & Wastewater,2023,39(1):105-110.
面向实时控制的排水系统深度LSTM神经网络模型
- Title:
- Deep LSTM Neural Network Model for Real-time Control of Urban Drainage System
- 关键词:
- 城市排水系统; 实时控制; 长短时记忆（LSTM）神经网络; 深度学习; 泵站站前液位
- Keywords:
- urban drainage system; real-time control; long short term memory (LSTM) neural network; deep learning; water level in front of pumping station
- 摘要:
- 如何得到兼顾运算时间和预测效果的排水系统预测模型是排水系统实时控制领域亟需解决的问题。针对这一难点，以非线性映射能力较强且运算速度较快的长短时记忆（LSTM）神经网络为基础，构建了面向实时控制的城市排水系统深度LSTM神经网络模型，并以苏州市福星片区为案例区域，验证该模型的预测效果和计算效率。结果显示，该模型对18个泵站站前液位预测结果的纳什效率系数均在0.5以上，且在不同降雨情景下均能得到较好的拟合结果；与机理模型相比，该模型能节约99.7%的计算时间，可显著提高排水系统预测模型的实时性。
- Abstract:
- An urgent problem in the context of real?time control of drainage system is to establish a predicting model which balances operation time and prediction effect. To solve this problem, a deep long short term memory (LSTM) neural network model for real-time control of urban drainage system was constructed, which had strong nonlinear mapping ability and fast operation speed. The prediction performance and operation efficiency of the model were verified in Fuxing area of Suzhou City. The Nash-Sutcliffe efficiency coefficient of the prediction results of the water level in front of 18 pumping stations was above 0.5, and good fitting results were obtained under different rainfall scenarios. Compared with the mechanism model, the proposed model saved 99.7% of the operation time and significantly improved the real-time performance of the drainage system prediction model.
相似文献/References:
[1]段庄,陈诗浩,姚娟娟,等.珠海浅丘地区城中村合流制排水的水量和水质特征[J].中国给水排水,2020,36(13):101.
DUAN Zhuang,CHEN Shi-hao,YAO Juan-juan,et al. Wastewater Quantity and Quality Characteristics of Combined Sewer System in Urban Village in Shallow Hilly Region of Zhuhai City [J].China Water & Wastewater,2020,36(1):101.
[2]王浩正,刘智晓,刘龙志,等.流域治理视角下构建弹性城市排水系统实时控制策略[J].中国给水排水,2020,36(14):66.
WANG Hao-zheng,LIU Zhi-xiao,LIU Long-zhi,et al.Real Time Control Solutions for Urban Drainage System Under Watershed Treatment[J].China Water & Wastewater,2020,36(1):66.
[3]刘智晓.碳中和视角下城市可持续排水系统构建及评估指标体系[J].中国给水排水,2022,38(16):1.
LIUZhi-xiao.Establishment and Evaluation Index System of Urban Sustainable Drainage System from the Perspective of Carbon Neutrality[J].China Water & Wastewater,2022,38(1):1.
[4]许光明,戴俊龙,曲亚纯,等.面向排水系统实际运行场景的控制策略优化方法[J].中国给水排水,2023,39(2):100.
XUGuang-ming,DAIJun-long,QUYa-chun,et al.Control Optimization Methods for Drainage System Real-time Control in Actual Scenario[J].China Water & Wastewater,2023,39(1):100.
[5]刘智晓,刘龙志,吴凡松.“双碳”战略下构建面向未来气候适应型城镇排水系统[J].中国给水排水,2024,40(8):1.
LIUZhi-xiao,LIU Long-zhi,WU Fan-song.Construction of Future Climate Adaptable Urban Drainage System under the “Dual Carbon” Strategy[J].China Water & Wastewater,2024,40(1):1.
[6]韩冠宇,王殿常,王浩正,等.源-网-厂-河排水系统多目标实时优化控制方法与实践[J].中国给水排水,2023,39(24):21.
HANGuan-yu,WANG Dian-chang,WANGHao-zheng,et al.Method and Practice of Multi-objective and Real-time Optimal Control in Urban Drainage System[J].China Water & Wastewater,2023,39(1):21.