Flow measurements in sewers based on image analysis: automatic flow velocity algorithm

Advancing sanitary surveillance: Innovating a live-feed sewer monitoring framework for effective water level and chamber cover detections

Efficient sanitation system management relies on vigilant sewage surveillance to uphold environmental hygiene. The absence of robust monitoring infrastructure jeopardizes unimpeded conduit flow, leading to floods and contamination. The accumulation of harmful gases in sewer chambers, coupled with tampered lids, compounds sewer network challenges, resulting in structural damage, disruptions, and safety risks from accidents and gas inhalation. Notably, even vehicular transit is vulnerable, facing collisions due to inadequately secured manholes. The core objective of this research was to deconstruct and synthesize a prototype blueprint for a live-feed sewer monitoring framework (LSMF). This involves creating a data gathering nexus (DGN) and empirically assessing diverse wireless sensing implements (WSI) for precision. Simultaneously, a geographic information matrix (GIM) was developed with algorithms to detect sewer surges, blockages, and missing manhole covers. Three scrutinized sensors-the LiDar TF-Luna, laser TOF400 VL53L1X, and ultrasonic JSN-SR04T-were evaluated for their ability to measure water levels in sewer vaults. The results showed that the TF-Luna LiDar sensor performed favorably within the 1.0-5.0 m range, with a standard deviation of 0.44-1.15. The TOF400 laser sensor ranked second, with a more variable standard deviation of up to 104 as obstacle distance increased. In contrast, the JSN-SR04T ultrasonic sensor exhibited lower standard deviation but lacked consistency, maintaining readings of 0.22-0.23 m within the 2.0-5.0 m span. The insights from this study provide valuable guidance for sustainable solutions to sewer surveillance challenges. Moreover, employing a logarithmic function, TF-Luna Benewake exhibited reliability at approximately 84.5%, while TOF400 VL53L1X adopted an exponential equation, boasting reliability approaching approximately 89.6%. With this navigational tool, TF-Luna Benewake maintained accuracy within ±10 cm for distances ranging from 8 to 10 m, showcasing its exceptional performance.

Flow Measurements Derived from Camera Footage Using an Open-Source Ecosystem

Sensors used for wastewater flow measurements need to be robust and are, consequently, expensive pieces of hardware that must be maintained regularly to function correctly in the hazardous environment of sewers. Remote sensing can remedy these issues, as the lack of direct contact between sensor and sewage reduces the hardware demands and need for maintenance. This paper utilizes off-the-shelf cameras and machine learning algorithms to estimate the discharge in open sewer channels. We use convolutional neural networks to extract the water level and surface velocity from camera images directly, without the need for artificial markers in the sewage stream. Under optimal conditions, our method estimates the water level with an accuracy of ±2.48% and the surface velocity with an accuracy of ±2.08% in a laboratory setting—a performance comparable to other state-of-the-art solutions (e.g., in situ measurements).

Deep-learning based monitoring of FOG layer dynamics in wastewater pumping stations

Accumulation of fat, oil and grease (FOG) in the sumps of wastewater pumping stations is a common failure cause for these facilities. Floating solids are often not transported by the pump suction inlets and the individual solids can accumulate to stiff and thick FOG layers. The lack of data about the dynamics in FOG layer formation still hampers the design of effective measures towards its mitigation. In this article, we present a low-cost camera-based automated system for the observation of FOG layer dynamics in wastewater pumping stations at high-frequency (minutes) over extended time windows (months). Optical imagery is processed through a deep-learning computer vision routine that allows describing FOG layer dynamics (e.g. accumulation rate and changes in shape) and various hydraulic processes in the pump sump (e.g. the water level, surface flow velocity fields, vorticity, or circulation). Furthermore, the system can perform in-camera image processing, thus allowing the transfer of compressed-processed datasets when deployed in remote locations (Edge AI computing), which could be of great utility for the hydro-ecological monitoring community. In this study, the technology applied is illustrated with a dataset (six months, two-minute frequency) collected at a wastewater pumping station at the municipality of Rotterdam, The Netherlands. This monitoring system represents a source of information for the management of (waste)water pumping stations (e.g. detection of free-surface vortices and scheduling of sump cleaning operations) and facilitates the collection of standardized high-frequency FOG layer dynamics data for a detailed description of FOG build-up and transport processes.

Water Level Estimation in Sewer Pipes Using Deep Convolutional Neural Networks

Sewer pipe inspections are currently conducted by professionals who remotely control a robot from above ground. This expensive and slow approach is prone to human mistakes. Therefore, there is both an economic and scientific interest in automating the inspection process by creating systems able to recognize sewer defects. However, the extent of research put into automatic water level estimation in sewers has been limited despite being a prerequisite for further analysis of the pipe as only sections above the water level can be visually inspected. In this work, we utilize a dataset of still images obtained from over 5000 inspections carried out for three different Danish water utilities companies. This dataset is used for training and testing decision tree methods and convolutional neural networks (CNNs) for automatic water level estimation. We pose the estimation problem as a classification and regression problem, and compare the results of both approaches. Furthermore, we compare the effect of using different inspection standards for labeling the ground truth water level. By treating the problem as a classification task and using the 2015 Danish sewer inspection standard, where water levels are clustered based on visual appearance, we achieve an averaged F1 score of 79.29% using a fine-tuned ResNet-50 CNN. This shows the potential of using CNNs for water level estimation. We believe including temporal and contextual information will improve the results further.

Measuring Surface Velocity of Water Flow by Dense Optical Flow Method

Recent advances in video processing technology have provided a new approach to measuring the surface velocity of water flow (SVWF). However, most of the previous researches using video processing technology depended on tracers for target tracing, requiring spraying tracers in the measurement process. These methods are not convenient for velocity measurement. In this study, a dense optical flow method (Farneback optical flow method) was used to process the water flow video to get the estimated SVWFs. The estimated SVWFs were verified by the actual SVWFs measured by a portable propeller velocimeter. The regression analyses between the estimated SVWFs and the measured SVWFs were conducted. The coefficient of determinations (R2) of the estimated and the measured SVWFs in different test regions are between 0.81 and 0.85. The average relative errors of the estimated and the measured SVWFs in all test regions are no more than 6.5%. The results indicate that the method had a good accuracy in estimating the SVWF and is a feasible and promising approach to analyzing the surface velocity distribution of water flow.

The development and application of improved solids modelling to enable resilient urban sewer networks

Decreasing per capita water consumption in several OECD countries has led to a notable flow reduction into sewer systems. However, sewers still transport similar quantities of solids and pollutants, leading to increased wastewater concentration and, potentially, excess solids deposition. The shift towards decentralised water schemes in cities and widely reported changes in rainfall patterns cast additional uncertainty on future wastewater quality and flows into sewers. Excess solids deposition in sewers can cause increased environmental pollution risks at Combined Sewer Overflows from solids resuspension and reduced sewer hydraulic capacities. This review analyses the magnitude of excess solids deposition due to changing wastewater composition and evaluates current approaches to modelling sewer solids. Gaps in commonly used modelling approaches for deposited bed processes, specifically in bed consolidation and bed particle cohesion processes, and gross solids transport were identified and addressed to enable better solids risk prediction and management.

A robust and accurate surrogate method for monitoring the frequency and duration of combined sewer overflows

Discharges of untreated wastewater from combined sewer overflows (CSOs) can affect hydraulic stress and have significant environmental impacts on receiving water bodies. Common flow rate and water level sensors for monitoring of CSO events are expensive in terms of investment costs, installation, operation and maintenance. This paper presents a novel surrogate method to detect CSO events by using two low-cost temperature sensors. The novelty is the experimental setup for installation of temperature sensors in CSO structures and an algorithm developed to automatically calculate the duration of CSO events considering the response time of the system. The occurrence and duration of CSO events is computed based on the convergence of the two temperature signals. The method was tested under field conditions in a CSO structure, and the results were compared to the information gathered from a parallel installed flow sensor. The application of two temperature sensors installed inside a CSO structure was proven to be robust and accurate for the automatic detection of the occurrence and duration of CSO events. Within the 7-month test phase, 100% of the 20 CSO events could be detected without false detections. The accuracy of detecting the start and end of the CSO events was 2 min in comparison to the flow sensor.

Non-contact assessment of COD and turbidity concentrations in water using diffuse reflectance UV-Vis spectroscopy

Water contamination is an important environmental concern underlining the need for reliable real-time information on contaminant concentrations in natural waters. Here, a new non-contact UV-Vis spectroscopic approach for monitoring contaminants in water, and especially wastewater, is proposed. Diffuse reflectance UV-Vis spectroscopy was applied to measure simultaneously the chemical oxygen demand (COD) and turbidity (TUR) concentrations in water. The measurements were carried out in the wavelength range from 200-1100 nm. The measured spectra were analysed using partial-least-squares (PLS) regression. The correlation coefficient between the measured and the reference concentrations of COD and TUR in the water samples were R(2) = 0.85 and 0.96, respectively. These results highlight the potential of non-contact UV-Vis spectroscopy for the assessment of water contamination. A system built on the concept would be able to monitor wastewater pollution continuously, without the need for laborious sample collection and subsequent laboratory analysis. Furthermore, since no parts of the system are in contact with the wastewater stream the need for maintenance is minimised.

Field validation of a new low-cost method for determining occurrence and duration of combined sewer overflows

Combined sewer overflow (CSO) events produced in combined sewer systems (CSS) during wet weather conditions are a threat for the receiving water bodies. The large number of CSO structures normally present in a CSS makes that the monitoring of the complete CSO network in a simultaneous way would drastically increase the investment costs. In this paper, a new methodology is presented aiming to characterize the occurrence and duration of CSO events by means of low-cost temperature sensors. Hence, a large number of CSO structures can be simultaneously monitored and the system can be characterized as a whole. The method assumes temperature differences between the overflowing mix of wastewater and stormwater and the sewer gas phase, so the temperature shift produced during a rainfall episode is related to a CSO event occurrence. The method has been tested and validated in La Garriga CSS (Spain) where the temperature at 13 CSO weirs was monitored for a period of 1 year (57 rainfall episodes). For the whole set of CSO events, occurrence and duration were successfully determined in 80% of cases. Advantages, limitations and potential applications of the method are discussed at the end of the paper.