scholarly journals Comparative Study of AI-Based Methods—Application of Analyzing Inflow and Infiltration in Sanitary Sewer Subcatchments

2020 ◽  
Vol 12 (15) ◽  
pp. 6254
Author(s):  
Zhe Zhang ◽  
Tuija Laakso ◽  
Zeyu Wang ◽  
Seppo Pulkkinen ◽  
Suvi Ahopelto ◽  
...  

Inflow and infiltration (I/I) is a common problem in sanitary sewer systems. The I/I rate is also considered to be an important indicator of the operational and structural condition of the sewer system. Situation awareness in sanitary sewer systems requires accurate wastewater-flow information at a fine spatiotemporal scale. This study aims to develop artificial intelligence (AI)-based models (adaptive neurofuzzy inference system (ANFIS) and multilayer perceptron neural network (MLPNN)) and to compare their performance for identifying the potential inflow and infiltration of the sanitary sewer subcatchment of two pumping stations. We tested the performance of these AI models by using data gathered from two pumping stations through a supervisory control and data acquisition (SCADA) system. As a result, these two AI models produced similar inflow and infiltration patterns—both subcatchments experienced inflow and infiltration. On the other hand, the ANFIS had overall higher performance than that of the MLPNN model for modelling the I/I situation for the catchments. The results of the research can be used to support spatial decision making in sewer system maintenance.

2018 ◽  
Vol 4 (3) ◽  
pp. 385-393 ◽  
Author(s):  
Mingkai Zhang ◽  
Yanchen Liu ◽  
Qian Dong ◽  
Yi Hong ◽  
Xia Huang ◽  
...  

Rainfall-derived inflow and infiltration (RDII) of urban sanitary sewer systems poses serious challenges for public health and management issues.


2019 ◽  
Vol 11 (10) ◽  
pp. 2746 ◽  
Author(s):  
Seong-Nam Nam ◽  
Thao Thi Nguyen ◽  
Jeill Oh

In this study, performance indicators (PIs) for assessing services of the sanitary sewer system in South Korea were evaluated based on general opinions collected from experts in the field. The analytic hierarchy process (AHP) was then carried out. The evaluated set of PIs consisted of five major criteria: management, operation and maintenance, service, environment, and finance. Using the experts’ survey incorporated into the AHP tool, the prioritization of the five criteria was performed, consisting of a total of 14 indicators and 34 checklists on three levels. Of the criteria groups, operation and maintenance was found to be the most important indicator, comprising 43% of all the scores. The AHP results showed that, of the 34 checklists, 13 indicators were explained as candidates of key PIs: on-the-job training and work role and responsibility from management, sewer condition inspection, pump, sewer maintenance, flow rate/water quality/odor monitoring from operation and maintenance, complaint resolution from service, inflow volume from environment, and operational cost in annual expenditures from finance. The PIs developed in this study are expected to be used by stakeholders involved in the provision of sewer services, such as undertaking companies, policy-making bodies, and financing agencies.


2008 ◽  
Vol 57 (8) ◽  
pp. 1271-1276 ◽  
Author(s):  
H. Korving ◽  
E. C. Ottenhoff

It is generally accepted that sewage pumping stations are directly responsible for affecting sewer system performance in terms of combined sewer overflows and flooding. However, the specific causes of pump failure are unknown. This paper presents the analysis of pump failure data provided by four sewer management authorities in The Netherlands. Pump failures have been studied accounting for the nature of failures, operation and maintenance procedures of the management authority, ageing of the pumps and changes in the environment of pumps. Pumps have been clustered on the basis of specific characteristics of their ‘environment’, including pump age, operating time, pump capacity and degree of pollution of the sewage. The analysis shows that the well known ‘bathtub’ type failure rate curve can describe failures of sewage pumps. The impact of the degree of pollution of the sewage, however, is less clear. Operating time and total pumping capacity show no correlation with failure rate. Consequently, further research using data mining techniques is needed to separate the impact of the different aspects of the environment of a pump.


2021 ◽  
Vol 21 (5) ◽  
pp. 271-280
Author(s):  
Young Jun Lee ◽  
Chae Young Lee

Even after the sewer system rehabilitation project, sewer system-related problems caused by inflow still persist. However, analysis of the characteristics of the inflow has been limited to specific rainfall events and monitoring points. This study analyzed inflow characteristics according to rainfall events using an XP-SWMM model and the Sanitary Sewer Overflow Analysis and Planning (SSOAP) Toolbox. In this study, the XP-SWMM model was built for sewers and collecting pipes in urban areas where classification projects were completed. The R, T, and K parameters were calculated using the SSOAP tool based on the sewer volume data of the study area. The calculated parameters were inputted into the XP-SWMM model and used to analyze R, T, and K of unmeasured sampling intervals. The amount of rainfall-derived inflow and infiltration (RDII) increased according to the amount of rainfall, and the correlation coefficient between the amount of rainfall and the amount of RDII was 0.9352, indicating a high correlation. The results of this study can support efficient facility planning that reflects the rainfall characteristics of specific areas, including areas where actual survey of sewage data is not possible.


2002 ◽  
Vol 45 (3) ◽  
pp. 273-279 ◽  
Author(s):  
F.M. Ferreira ◽  
J.S. Matos ◽  
A.C. Rodigues ◽  
H.M. do Monte

The aim of this document is to present and discuss the results of the experimental work undertaken in Laje stream, in a section near the village of Oeiras in Portugal. The work was developed with the main objective of characterising stormwater quality in Portuguese drainage systems, and to predict the effects of the performance of partially separate sewer systems on receiving waters. For this purpose, volume and characteristics of stormwater carried by a partially separated sewer system were estimated, both in terms of flow and Chemical Oxygen Demand (COD) loads. The study also analyses the eventual implementation of non-conventional solutions, as a way of reducing problems of bacteriological contamination of seawaters. This aspect is particularly important in Portugal, where the population is mainly concentrated in urban areas located down-stream of important drainage basins, close to the coastline. Therefore, sanitary sewer overflows discharging directly into receiving waters are frequent, with possible consequences in terms of bacteriological contamination of bathing areas. Based on experimental research and available data it was possible to collect informations regarding stormwater average COD and overflow coliform loads, and the occurrence of first flush effects.


2009 ◽  
Vol 60 (4) ◽  
pp. 901-908 ◽  
Author(s):  
T. Goormans ◽  
D. Engelen ◽  
R. Bouteligier ◽  
P. Willems ◽  
J. Berlamont

Many European countries tend to shift from constructing combined sewer systems to separate ones, in order to optimise wastewater treatment efficiency and reduce CSO impact on surface waters. An economic design minimises maintenance requirements by aiming at self-cleansing pipes. However, providing the necessary slopes for self-cleansing sanitary sewer pipes often is unfeasible in flat regions, resulting in an increased risk of loss of hydraulic capacity or blocking. To reduce these risks, flushing tanks can be installed in the sewer system. Where most other researchers contribute to a better understanding of the hydraulics of flushing, this paper rather tries to formulate a methodology to design and test flushing devices in sanitary sewer systems using standards and hydrodynamic simulations. Therefore, several aspects that require consideration when incorporating flushing devices into a sanitary sewer system are discussed. For instance, when flushing sanitary sewers the increase in discharge has to be explicitly considered. A Belgian case study is used to investigate the suitability of the developed methodology. Although the pipe slopes in the methodology are derived assuming uniform flow, the simulation results comply with it. Furthermore, pressurisation of the conduits due to multiple flushing waves remains within acceptable limits.


2020 ◽  
Vol 82 (11) ◽  
pp. 2472-2481
Author(s):  
Shuai Guo ◽  
Xiang Shi ◽  
Xujia Luo ◽  
Haoming Yang

Abstract Previous studies on the extraneous water problem (or infiltration/inflow) in sanitary sewer systems assumed that the wastewater flow is mainly composed of foul sewage (FS), groundwater infiltration (GWI) and rainfall-derived inflow and infiltration (RDII). Most existing assessment methods are based on this assumption. In 2018, China initiated the ‘Protection of the Yangtze River Program’, and the two-year research data showed that it was neither the GWI nor the RDII but the direct surface water intrusion (DSWI), which has rarely been reported in literatures, that serves as the main source of the extraneous water in many local sewer systems. The discovery has enriched the understanding of the extraneous water in sewer systems. Meanwhile, it brings new challenges for the assessment of extraneous water. In this study, starting from the analysis of the low influent concentration of chemical oxygen demand (COD) of the wastewater treatment plant in a southeastern city in China, a river water intrusion point was successfully localized and the volume of river water intrusion was quantified by a series of field experiments. The methodology used in this study can also be applied in other areas with DSWI.


2019 ◽  
Vol 79 (9) ◽  
pp. 1727-1738 ◽  
Author(s):  
Eliana Soriano Pulido ◽  
Carlos Valencia Arboleda ◽  
Juan Pablo Rodríguez Sánchez

Abstract The planning and scheduling of maintenance operations of large conventional sewer systems generate a complex decision-making environment due to the difficulty in the collection and analysis of the spatiotemporal information about the operational and structural condition of their components (e.g. pipes, gully pots and manholes). As such, water utilities generally carry out these operations following a corrective approach. This paper studies the impact of the spatiotemporal correlation between these failure events using Log-Gaussian Cox Process (LGCP) models. In addition, the association of failure events to physical and environmental covariates was assessed. The proposed methods were applied to analyze sediment-related blockages in the sewer system of an operative zone in Bogotá (Colombia). The results of this research allowed the identification of significant covariates that were further used to model spatiotemporal clusters with high sediment-related failure risk in sewer systems. The LGCP model proved to be more accurate in comparison to those models that build upon a fundamental assumption that a failure is equally likely to occur at any time regardless of the state of the system and the system's history of failures (i.e. a homogeneous Poisson process model).


Sign in / Sign up

Export Citation Format

Share Document