2012 | OriginalPaper | Buchkapitel
Leakage Prediction Model Based on RBF Neural Network
verfasst von : Wang Lijuan, Zhang Hongwei, Niu Zhiguang
Erschienen in: Software Engineering and Knowledge Engineering: Theory and Practice
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Pipe breaks and leaks in water distribution networks may bring about economic, environmental and safety issues. It is critical to evaluate the current and future condition of the system for maintenance decision-making. RBF neural network model was proposed for forecasting pipe leakage. Two models based on RBF neural network were established according to previous leakage data set. The goal of the pipe leakage time prediction model is to forecast the leakage time of each pipe and the goal of the leakage time series prediction model is to forecast the future leakage trend of pipelines. The date set used for analysis comes from a city of north China. The results show that the models provide good estimates for pipe leakage and can be useful for water utilities in pipe inspection and maintenance. Active leakage control in pipe networks can be achieved using the models and the blindness maintenance will be reduced.