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 ...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.展开更多
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 ris...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”.展开更多
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 t...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.展开更多
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.Resear...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.展开更多
基金supported by the Science and Technology Development Fund of Macao(Grant No.0079/2019/AMJ)the National Key R&D Program of China(No.2019YFE0111400).
文摘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.
文摘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”.
文摘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.
基金supported by Basic ScienceResearch Program through the National Research Foundation ofKorea(NRF)funded by the Ministry of Education(2020R1A6A1A03038540)by Korea Institute of Planning and Evaluation for Technology in Food,Agriculture,Forestry and Fisheries(IPET)through Digital Breeding Transformation Technology Development Program,funded by Ministry of Agriculture,Food and Rural Affairs(MAFRA)(322063-03-1-SB010)by the Technology development Program(RS-2022-00156456)funded by the Ministry of SMEs and Startups(MSS,Korea).
文摘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.
