A Composite Transformer-Based Multi-Stage Defect Detection Architecture for Sewer Pipes

Urban sewer pipes are a vital infrastructure in modern cities,and their defects must be detected in time to prevent potential malfunctioning.In recent years,to relieve the manual efforts by human experts,models based on deep learning have been introduced to automatically identify potential defects.However,these models are insufficient in terms of dataset complexity,model versatility and performance.Our work addresses these issues with amulti-stage defect detection architecture using a composite backbone Swin Transformer.Themodel based on this architecture is trained using a more comprehensive dataset containingmore classes of defects.By ablation studies on the modules of combined backbone Swin Transformer,multi-stage detector,test-time data augmentation and model fusion,it is revealed that they all contribute to the improvement of detection accuracy from different aspects.The model incorporating all these modules achieves the mean Average Precision(mAP)of 78.6% at an Intersection over Union(IoU)threshold of 0.5.This represents an improvement of 14.1% over the ResNet50 Faster Region-based Convolutional Neural Network(R-CNN)model and a 6.7% improvement over You Only Look Once version 6(YOLOv6)-large,the highest in the YOLO methods.In addition,for other defect detection models for sewer pipes,although direct comparison with themis infeasible due to the unavailability of their private datasets,our results are obtained from a more comprehensive dataset and have superior generalization capabilities.

Deep Learning Based Underground Sewer Defect Classification Using a Modified RegNet

The sewer system plays an important role in protecting rainfall and treating urban wastewater.Due to the harsh internal environment and complex structure of the sewer,it is difficult to monitor the sewer system.Researchers are developing different methods,such as the Internet of Things and Artificial Intelligence,to monitor and detect the faults in the sewer system.Deep learning is a promising artificial intelligence technology that can effectively identify and classify different sewer system defects.However,the existing deep learning based solution does not provide high accuracy prediction and the defect class considered for classification is very small,which can affect the robustness of the model in the constraint environment.As a result,this paper proposes a sewer condition monitoring framework based on deep learning,which can effectively detect and evaluate defects in sewer pipelines with high accuracy.We also introduce a large dataset of sewer defects with 20 different defect classes found in the sewer pipeline.This study modified the original RegNet model by modifying the squeeze excitation(SE)block and adding the dropout layer and Leaky Rectified Linear Units(LeakyReLU)activation function in the Block structure of RegNet model.This study explored different deep learning methods such as RegNet,ResNet50,very deep convolutional networks(VGG),and GoogleNet to train on the sewer defect dataset.The experimental results indicate that the proposed system framework based on the modified-RegNet(RegNet+)model achieves the highest accuracy of 99.5 compared with the commonly used deep learning models.The proposed model provides a robust deep learning model that can effectively classify 20 different sewer defects and be utilized in real-world sewer condition monitoring applications.

Solid Transfer in Low Flow Sewers, the Distance Travelled So Far Is Not Enough

Sewer blockages are on the increase whilst water closet (WC) flush volumes are on the decrease. Furthermore, Water UK reported figures show that the actual number of properties affected by sewer flooding is on the rise. Sewer blockages can lead to sewer flooding of homes and collapse of sewers which impact negatively on social, economic and environmental factors, and therefore, they are not sustainable. Water conservation is required due to water stress but reduced water use results in less water to waste, which in turn reduces solids’ transfer in sewers. When considering reducing water usage through water conservation, these savings could be cancelled out by an increased population and the situation exacerbated by the impacts of climate change. There are issues in relation to varying design methods, a reliance on engineering judgement in sewer design, uncertainty relating to future water stress, and a lack of cross disciplinary design decision-making. Public health engineering solutions are needed to reduce the number of sewer blockages and the environmental impact of sewer flooding. This paper examines the fundamental research that have been carried out in the area of “solid transfer in sewers” resulting from “less water to waste” since the mid-20th Century. Contrary to existing literature, this paper identifies that, now more than ever, this type of research is needed to deal with the increased need for water conservation. To judge that solid transfer research is complete can be compared to supporting a statement that “water conservation is complete”.

Sewage flow optimization algorithm for large-scale urban sewer networks based on network community division

By considering the flow control of urban sewer networks to minimize the electricity consumption of pumping stations, a decomposition-coordination strategy for energy savings based on network community division is developed in this paper. A mathematical model characterizing the steady-state flow of urban sewer networks is first constructed, consisting of a set of algebraic equations with the structure transportation capacities captured as constraints. Since the sewer networks have no apparent natural hierarchical structure in general, it is very difficult to identify the clustered groups. A fast network division approach through calculating the betweenness of each edge is successfully applied to identify the groups and a sewer network with arbitrary configuration could be then decomposed into subnetworks. By integrating the coupling constraints of the subnetworks, the original problem is separated into N optimization subproblems in accordance with the network decomposition. Each subproblem is solved locally and the solutions to the subproblems are coordinated to form an appropriate global solution. Finally, an application to a specified large-scale sewer network is also investigated to demonstrate the validity of the proposed algorithm.

Prediction of Sewer Pipe Main Condition Using the Linear Regression Approach

This research presents the condition prediction of sewer pipes using a linear regression approach. The analysis is based on data obtained via Closed Circuit Television (CCTV) inspection over a sewer system. Information such as pipe material and pipe age is collected. The regression approach is developed to evaluate factors which are important and predict the condition using available information. The analysis reveals that the method can be successfully used to predict pipe condition. The specific model obtained can be used to assess the pipes for the given sewer system. For other sewer systems, the method can be directly applied to predict the condition. The results from this research are able to assist municipalities to forecast the condition of sewer pipe mains in an effort to schedule inspection, allocate budget and make decisions.

Global optimal control for regional sewer systems

In order to control combined system overflow (CSO) pollution of regional sewer systems in Shanghai,a global optimal control (GOC) is presented in this study.The GOC is based on the analysis of current situation and can maximize the utilization of the free storage of each sub systems and decrease the frequencies and durations of CSOs and flooding.A representative regional sewer system,which is located in the northwest of Shanghai and composed of sub systems of Zhenguang,Zhenru and Tongchuan,was taken as an example to demonstrate the efficiency of GOC with hydraulic model simulation test in the two representative scenarios (Scenario Ⅰ and Ⅱ).The results indicated that a great improvement in CSO emission is obtained by using the GOC in the two scenarios,and the CSO volume of three sub systems,Zhenru,Tongchuan and Zhenguang decreases to about 37.0%,38.3% and 35.7% in Scenario Ⅰ and 47.5%,51.8% and 63.5% in Scenario Ⅱ respectively.

Multi-Level Approach of the Ecotoxicological Impact of a Combined Sewer Overflow on a Peri-Urban Stream

In periurban zones, urban wet weather discharges have been recognized as the most significant vector of pollution in aquatic environments. The discharge of this water without treatment into the aquatic environment could present an ecotoxicological risk for biocenosis. The aim of the INVASION project is to assess the potential ecotoxicological impact of a combined sewer overflow (CSO) on a peri-urban stream. A comparative study between upstream and downstream areas of the CSO allowed observing significant effects of this overflow on the river. We studied three layers of stream: surface water, benthic layer and hyporheic layer. To characterize the potential ecotoxicological risk of water and sediments, we used a battery of 4 bioassays: Daphnia magna, Vibrio fischeri, Brachionus calyciflorus and Heterocypris incongruens. In parallel, we measured the physico-chemical parameters: ammonium (NH4+), chromium (Cr), copper (Cu) and lead (Pb). An ecological risk is greatest for the hyporheic zone in downstream river, particularly for the solid phase. These results corroborated with the physico-chemical data obtained.

Evaluating Subdivisions for Identifying Extraneous Flow in Separate Sanitary Sewer Systems

Separate sanitary sewer systems are designed to convey sewage waste from municipal areas to a central treatment facility;they are not designed to handle water associated with precipitation events. However, intercept of groundwater (infiltration) and of flows through manholes or unauthorized connections (inflows) introduces rainwater into the sanitary sewer system. Infiltration/Inflow (I/I) increases the costs associated with treatment and can create additional environmental problems. Identifying and quantifying the volume I/I can be complicated and costly. A simple quantitative method was developed to quantify the extent of I/I occurring in sewer sheds. The method uses measured sewer flows, water usage, precipitation values, and land cover data to calculate the volume of extraneous flows. To assess its utility, the method was used to compare two urban sewer sheds, Holiday Knolls and Eagle View. Both sewer sheds showed evidence of I/I in excess of 200 gallons per day per inch-mile of sewer pipe (gpd/in-mile). Holiday Knolls, the older subdivision had an average I/I of 1912 gpd/in-mile, while Eagle View had an average of 1143 gpd/in-mile. The devel- oped method provided simple means to calculate I/I and to identify sewer sheds in need of repair.

On the Importance of Sanitary Sewer Overflow on the Total Discharge of Microplastics from Sewage Water

The paper provides an investigation and understanding of the significance of various wastewater flows on microplastics retainment and emission to the environment. WWTPs and sewer overflows as an important pathway of microplastics to the environment are assessed by considering the removal of microplastics in WWTPs with different treatment processes and several sewer overflow types and their contribution to microplastic loads to recipients. On the example of the Baltic Sea basin, presented results indicate a considerable discharge of microplastic from WWTPs despite the relatively good overall removal efficiency. Results show that the discharge of microplastics from sewer overflows can be in the same magnitude as from treated wastewater although the total flow is much lower than that of treated wastewater. Sewer overflow events frequently occur and are expected to increase due to climate change and urbanization, unless infrastructure is adapted. At the same time, sewer overflows are often neglected in conventional wastewater handling.

Smart Sewers 1: Sewer Configuration at Rural Houses

The layout of houses and other buildings impacts the way in which foul sewer pipework is positioned internally and externally. Less water to waste through conservation measures reduces the distance that gross solids transfer in sewers and increases the number of sewer blockages. Dwelling houses are often laid out where the solids from faecal flushes are at the head of the sewer line with other flows entering downstream. Discharges from appliances such as washing machines, dishwashers, baths, showers and kitchen/utility sinks are often not utilised in the transfer of the gross solids when they enter downstream of the faecal flushes. At present, no recommendations or specific design guidance exist regarding the design of internal building layouts relating to sewer configuration requirements. Furthermore, to date, no specific research exists which examines pipeline configuration scenarios outside buildings in terms of the link between multiple grey water discharge points and solid transfer in a sewer system. The aim of this study was to investigate sewer layout at houses in terms of maximising greywater flow in relation to solid transfer. This study showed that smart sewers are needed which utilise all the foul water leaving a building as it was found that up to 100% of greywater in some instances is completely missed out in terms of solid transfer. Consequently, optimal sewer design is far from being realised and internal building layouts should be designed with consideration of the faecal flushes and greywater flows.

Experiment study on solidification effect of sewer sludge

Materials such as cement and composite active admixture were mixed in definite ratio to consolidate sewer sludge, which had been dried and smashed. Two kinds of solidified bodies were designed. A represented the solidified body which had not used any composite active admixture, and B represented the one which used composite active admixture as one of its compositions. The results show that the compressive strength （28 d） of these solidified bodies can reach 30 MPa under the standard maintain condition which could be used as subgrade material. The concentration of heavy metals in solidified body was far less than identification standard for hazardous wastes of China. Heavy metals were stabilized and solidified effectively. The organic matter in these solidified bodies of 56 d was 80 percent less than that in raw sludge. A large quantity of bacteria could also be killed because of the basic condition in solidified body. Scanning electron microscope （SEM） test explained the reason that solidified body B showed better properties in all tests.

Analysis of Inflow Solutions among Eleven Sewer Systems

This paper was undertaken to compare eleven utilities where part or all of the utility was tested for infiltration and inflow with the intention of determining the value of data gathered from midnight investigations, comparing potential costs (in 2020 dollars), and understanding whether statistical methods can be used to predict potential problems on the system. Inflow and infiltration amounts can be identified on a utility system without significant effort. Inflow correction is robust and easy to implement (though often overlooked). After inflow is addressed, the results indicated that a midnight investigation could quickly identify portions of the sewer system in need of attention. Maps of leaky pipe sections can be identified, and commonalities in the system may become apparent. Statistical methods were used to identify high groundwater levels and lateral issues as critical issues on these systems. The methods can be utilized at other utilities to help guide them to addressing the critical issues first as opposed to focusing only on the traditional pipe lining solutions that often ignore the lateral and inflow issues that plague utility managers.

Optimal Control of Combined Sewer Overflows

Combined sewer networks carry wastewater and stormwater together.Capacity limitation of these sewer networks results in combined sewer overflows(CSOs)during high-intensity storms.Untreated CSOs when directly discharged to the nearby natural water bodies cause many environmental problems.Controlling existing urban sewer networks is one possible way of addressing the issues in urban wastewater systems.However,it is still a challenge,when considering the receiving water quality effects.This paper presents an evolutionary constrained multi-objective optimization approach to control the existing combined sewer networks.The control of online storage tanks was taken into account when controlling the combined sewer network.The developed multi-objective approach considers two important objectives,i.e.the pollution load to the receiving water from CSOs and the cost of the wastewater treatment.The proposed optimization algorithm is applied here to a realistic interceptor sewer system to demonstrate its effectiveness.

Arrival Analysis of Dry Weather Sanitary Sewer Overflows

This study investigates arrivals of sanitary sewer overflows collected from a municipality. The data set consists of recorded overflows from 2011 to 2014 during dry weather. Reliability analysis is conducted upon each data set. The Weibull distribution is adopted to evaluate the data sets. The results show that the arrival of dry weather SSOs cannot be simply modeled with a Poisson process that is featured with a constant arrival rate. For annual data set, 2-parameter Weibull generally has an acceptable fitting (except 2014 data). The shape parameters are close to 1 or a little greater than 1, indicating relatively constant arrival rate or slightly increased rate. For the entire data set, the 3-parameter Weibull distribution is able to fit the data well. The shape parameter is also greater than 1. Therefore, an increased SSO arrival rate is noticed for this data set. There are needs to make more efforts in maintaining the sewer system.

Emission of greenhouse gases from sewer networks:field assessment and isotopic characterization

Sewer networks play a vital role in sewage collection and transportation,and they are being rapidly expanded.However,the microbial processes occurring within these networks have emerged as significant contributors to greenhouse gas(GHG)emissions.Compared to that from other sectors,our understanding of the magnitude of GHG emissions from sewer networks is currently limited.In this study,we conducted a GHG emission assessment in an independent sewer network located in Beijing,China.The findings revealed annual emissions of 62.3 kg CH_(4) and 0.753 kg N20.CH_(4) emerged as the primary GHG emitted from sewers,accounting for 87.4%of the total GHG emissions.Interestingly,compared with main pipes,branch pipes were responsible for a larger share of GHG emissions,contributing to 76.7%of the total.A GHG emission factor of 0.26 kg CO_(2)-eq/(m:yr)was established to quantify sewer GHG emissions.By examining the isotopic signatures of CO_(2)/CH_(4) pairs,it was determined that CH_(4) production in sewers primarily occurred through acetate fermentation.Additionally,the structure of sewer pipes had a significant impact on GHG levels.This study offers valuable insights into the overall GHG emissions associated with sewer networks and sheds ight on themechanismsdriving theseemissions.

Experimental and modeling investigations on the unexpected hydrogen sulfide rebound in a sewer receiving nitrate addition: Mechanism and solution

Biogenic hydrogen sulfide is an odorous, toxic and corrosive gas released from sewage in sewers. To control sulfide generation and emission, nitrate is extensively applied in sewer systems for decades. However, the unexpected sulfide rebound after nitrate addition is being questioned in recent studies. Possible reasons for the sulfide rebounds have been studied,but the mechanism is still unclear, so the countermeasure is not yet proposed. In this study, a lab-scale sewer system was developed for investigating the unexpected sulfide rebounds via the traditional strategy of nitrate addition during 195-days of operation. It was observed that the sulfide pollution was even severe in a sewer receiving nitrate addition. The mechanism for the sulfide rebound can be differentiated into short-term and long-term effects based on the dominant contribution. The accumulation of intermediate elemental sulfur in biofilm resulted in a rapid sulfide rebound via the high-rate sulfur reduction after the depletion of nitrate in a short period. The presence of nitrate in sewer promoted the microorganism proliferation in biofilm, increased the biofilm thickness, re-shaped the microbial community and enhanced biological denitrification and sulfur production, which further weakened the effect of nitrate on sulfide control during the long-term operation. An optimized biofilminitiated sewer process model demonstrated that neither the intermittent nitrate addition nor the continuous nitrate addition was a sustainable strategy for the sulfide control. To minimize the negative impact from sulfide rebounds, a(bi)monthly routine maintenance(e.g., hydraulic flushing with nitrate spike) to remove the proliferative microorganism in biofilm is necessary.

Retrofitting low-performance units to abate sewer overflow pollution based on mathematical model and Sobol algorithm

Optimal retrofit of low-performance units(LPUs)is promising to abate overflow pollutant mass loading of sewer systems during wet-weathers.This study presents a combination of mathematical model and Sobol algorithm to help identify LPUs of sewer systems and design retrofitting strategies.Therefore,the solution to minimize the overflow pollutant mass loading from sewers systems can be efficiently obtained.The developed method was demonstrated at a catchment served by one wastewater treatment plant in the Chaohu City,Anhui Province of China,with five pumping stations and a total sewer length of 58.3 km.Within the catchment,there are three rivers and a small lake to receive overflows from the sewer system.Among them,one river that was mostly polluted was selected as the object of overflow pollution abatement during wet weather period.After identifying the LPUs of the sewer system and developing retrofitting strategies using Sobol sequence,the mitigation of overflow pollution during wet weather period was analyzed.Results show that the mass loading of chemical oxygen demand(COD)discharged into the target river could be reduced by 40.6%,by implementing optimal retrofit strategy of LPUs,i.e.,increasing the conveyance capacities of two pumping stations by 2.5–3.2 times and augmenting the diameters of 12 sewers by 1.25–1.29 times.To further coordinate the abatement of overflow pollution and retrofit investment,Sobol sensitivity analysis was conducted to screen the dominant LPUs to update the optimal retrofit strategy.By applying the updated strategy,the overflow COD mass loading per overflow event was close to that of non-updated strategy,while the retrofitting length of sewers was reduced by 40%.Therefore,on the basis of the presented method,decision-makers can flexibly develop retrofitting strategies of sewer system to abate overflow pollution during wet weathers in a cost-effective way.

海绵城市背景下合流制改造及溢流污染控制路径研究

我国合流制排水管渠数量多、建设情况复杂、运行问题突出,已成为当前制约城市水环境质量提升的关键,在系统化全域推进海绵城市建设的背景下,合流制系统改造及溢流污染控制成为许多城市的重点任务。根据多年城市建设统计年鉴数据对我国城市合流制排水管渠数量、分布及逐年变化情况进行分析;梳理我国城市合流制管渠系统状况、存在问题及当前海绵城市建设、黑臭水体治理、内涝综合整治、污水提质增效工作对合流制系统的相关要求,在此基础上提出适用于我国城市合流制系统的界定与评价方法;结合当前各城市在推进相关工作过程中存在的问题,提出海绵城市建设背景下合流制系统改造及溢流污染控制路径,即因地制宜制定合流制改造及溢流污染控制系统化方案,并明确系统化方案编制流程及技术要点。

基于监测与模型的典型合流制排水系统溢流污染来源解析

以北京中心城区某典型合流制分区为研究区,开展自“地表-管网-排口”的全过程监测,基于MIKE URBAN软件构建数值模型,构建一套结合监测与模型的溢流污染解析方法,量化分析不同降雨量级下溢流污染来源。结果表明:管道沉积物、地表径流和生活污水对COD的贡献率分别为43.4%~53.9%、27.4%~27.5%和18.6%~29.2%。中雨流量峰值晚于浓度峰值,大雨反之;两场降雨溢流水质浓度峰值差异小于流量峰值。随着降雨量级及强度增加,地表径流和管道沉积物的污染负荷增加,后者增加量更大。管道沉积物是合流制溢流污染的主要来源,应优先对其进行控制。

模型技术在雨水管网规划设计中的应用研究

针对传统雨水管网规划设计方法的适用条件限制和潜在设计风险,基于雨水管网规划设计基础参数,提出具有实际可操作性的模型辅助规划设计的技术应用方案,通过基于模型的管网设计标准评估、瓶颈管段分析和管网抗涝能力评价3个部分,实现对雨水管网系统排水能力更全面和综合性的评价.通过实例研究表明:基于模型的管网设计标准评估可以验证管网系统是否满足预定的规划设计标准要求,并确定每一段管道排水能力所对应的重现期标准;瓶颈管段分析可以定位系统中的主要问题管段,从而针对问题管段优先制定调整方案;管网抗涝能力评价可以定位系统中的内涝防灾“短板”管段,从而可针对“短板”管段采取相应工程技术措施,提高管网系统的内涝抗灾能力.