Browsing by Author "Shirzad, Akbar"

Now showing 1 - 2 of 2

Citation - WoS: 38
Citation - Scopus: 44
Pipe failure rate prediction in water distribution networks using multivariate adaptive regression splines and random forest techniques
(Taylor and Francis Ltd. michael.wagreich@univie.ac.at, 2019) Akbar Shirzad; Mir Jafar Sadegh Safari; Shirzad, Akbar; Safari, Mir Jafar Sadegh
This paper presents the results of a comparison between multivariate adaptive regression splines (MARS) and random forest (RF) techniques in pipe failure prediction in two water distribution networks. In this regard pipe diameter pipe length pipe installation depth pipe age and average hydraulic pressure are considered as input variables. Results show that the RF outperforms the MARS which is found as an accurate pipe failure rate predictor. The proposed models are further evaluated through dividing the data into three parts of lower medium and higher pipe failure rate values. According to the equations produced by MARS technique three variables of pipe diameter pipe age and average hydraulic pressure are distinguished as the most effective variables in predicting pipe failure rate in the first case study. Four variables of pipe diameter pipe length pipe age and average hydraulic pressure are determined as the most effective variables in the second case study. © 2020 Elsevier B.V. All rights reserved.
Citation - WoS: 23
Citation - Scopus: 26
Self-cleansing design of sewers: Definition of the optimum deposited bed thickness
(John Wiley and Sons Inc. P.O.Box 18667 Newark NJ 07191-8667, 2019) Mir Jafar Sadegh Safari; Akbar Shirzad; Safari, Mir Jafar Sadegh; Shirzad, Akbar
Sediment deposits may influence the performance of the sewer systems. Sediments are the main store of pollutants which causes sewer systems overflows. In order to prevent the deposition of sediment in sewer systems self-cleansing design criteria are used. Among various criteria “self-cleansing with deposited bed” criterion is found appropriate for designing of large sewers. Allowing small thickness of deposited bed in large sewers decreases the required channel bed slope and construction costs. This study presents a bed load self-cleansing model established on wide ranges of experimental data. Comparison of developed model with the existing models in the literature shows its higher performance on variety of data sources. Examples for the application of the model are presented and design graphs and charts for different pipe sizes are proposed. As a result the optimum deposited bed thickness is found 1%–5% of the pipe diameter, however 1% is recommended for sewer pipes design. Practitioner points: Nondeposition sediment transport condition with a bed deposit criterion is found appropriate for large sewer pipe design. The precision of a model is linked to the ranges of experimental data and parameters used for the models development. The optimum range of deposited bed thickness can be adopted in the range of 1% to 5% of the pipe diameter. © 2020 Elsevier B.V. All rights reserved.