期刊
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
卷 24, 期 2, 页码 140-150出版社
ASCE-AMER SOC CIVIL ENGINEERS
DOI: 10.1061/(ASCE)CP.1943-5487.0000020
关键词
Storm-water management; Probability; Neural networks; Hydraulic deterioration
A decrease in discharge capacity of storm-water drainage pipes is the result of the so-called hydraulic deterioration which reduces the cross sectional area of pipes and increases the pipe roughness. Hydraulic deterioration is caused by tree root intrusion, sediment accumulation, and encrustation, and is affected by many influential factors such as pipe size and pipe location. Predicting hydraulic deterioration is important for effective management of drainage pipes. An ordered probit deterioration model (OPDM) and a probabilistic neural network deterioration model (PNNDM) were developed in this study using the influential factors as model inputs and the hydraulic condition as model output. Their predictive performances were compared against each other using a case study from Melbourne, Australia with a sample of 417 storm-water drainage pipes subjected to closed circuit television inspection. The results show that the PNNDM is more suitable for predicting the hydraulic deterioration and outperforms the OPDM. Several input factors such as pipe size and pipe age are found significant to the hydraulic deterioration.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据