检索结果-南通市图书馆

A hybrid Wavelet-CNN-LSTM deep learning model for short-term urban water demand forecasting

Frontiers of Environmental Science & Engineering 2023年第2期17卷 97-110页

作者： Zhengheng Pu Jieru Yan Lei Chen Zhirong Li Wenchong Tian Tao Tao Kunlun Xin College of Environmental Science and Engineering Tongji UniversityShanghai 200092China Smart Water Joint Innovation RD Center Tongji UniversityShanghai 200092China

short-term water demand forecasting provides guidance on real-time water allocation in the water supply network, which help water utilities reduce energy cost and avoid potential accidents. Although a variety of methods have been proposed to improve forecast accuracy, it is still difficult for statistical models to learn the periodic patterns due to the chaotic nature of the water demand data with high temporal resolution. To overcome this issue from the perspective of improving data predictability, we proposed a hybrid Wavelet-CNN-LSTM model, that combines time-frequency decomposition characteristics of Wavelet Multi-Resolution Analysis (MRA) and implement it into an advanced deep learning model, CNN-LSTM. Four models - ANN, Conv1D, LSTM, GRUN - are used to compare with Wavelet-CNN-LSTM, and the results show that Wavelet-CNN-LSTM outperforms the other models both in single-step and multi-steps prediction. Besides, further mechanistic analysis revealed that MRA produce significant effect on improving model accuracy.

关键词： short-term water demand forecasting long-short term memory neural network Convolutional neural network Wavelet multi-resolution analysis Data-driven models

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Double LSTM Structure for network Traffic Flow Prediction

引用

国际计算机前沿大会会议论文集 2020年第1期 380-388页

作者： Lin Huang Diangang Wang Xiao Liu Yongning Zhuo Yong Zeng State Grid Sichuan Information and Communication Company Chengdu 610041China University of Electronic Science and Technology of China Chengdu 611731China The 10th Research Institute of China Electronics Technology Group Corporation Chengdu 610036China

The network traffic prediction is important for service quality control in computer network.The performance of the traditional prediction method significantly degrades for the burst short-term flow.In view of the problem,this paper proposes a double LSTMs structure,one of which acts as the main flow predictor,another as the detector of the time the burst flow starts at.The two LSTM units can exchange information about their internal states,and the predictor uses the detector’s information to improve the accuracy of the prediction.A training algorithm is developed specially to train the structure offline.To obtain the prediction online,a pulse series is used as a simulant of the burst event.A simulation experiment is designed to test performance of the predictor.The results of the experiment show that the prediction accuracy of the double LSTM structure is significantly improved,compared with the traditional single LSTM structure.

关键词： Time sequence long-short term memory neural network Traffic prediction Service quality control

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fault detection method of tightly coupled GNSS/INS integration assisted by LSTM

Fault detection method of tightly coupled GNSS/INS integrati...

引用

第十三届中国卫星导航年会

作者： ZIHAN SHEN XIUBIN ZHAO CHUNLEI PANG LIANG ZHANG LIJIAN REN HAOWEI CHANG Information and Navigation College Air Force Engineering University

Aiming at the problem that the traditional fault detection method of tightly coupled GNSS/INS integration is not efficient for small-amplitude faults and gradual faults, a dual-threshold fault detection method based on long-short term memory neural network is proposed. This method establishes GNSS pseudo-range and pseudo-range rate prediction models through a long-short term memory neural network, sets the lower detection threshold based on the accuracy of the prediction model and the residual distribution characteristics, and assists the residual chi-square detection method for fault detection and isolation. The actual measurement data is used for simulation verification from the perspectives of fault detection performance and positioning accuracy. The results show that the proposed method retains the excellent detection performance of the residual detection method for large-amplitude faults, and has better detection sensitivity for small-amplitude faults and gradual faults, which can improve the positioning accuracy and fault detection performance of the system effectively.

关键词： Tightly Coupled GNSS/INS Integration long-short term memory neural network Small-amplitude Faults Gradual Faults Dual-threshold

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：