Pipe Leakage Research Articles

Fault diagnosis of power-shift system in continuously variable transmission tractors based on improved echo state network

For better reliability of tractors with continuously variable transmission, reported here is fault diagnosis of their power-shift systems. First, four hydraulic system faults are analyzed, i.e., pipe leakage, pipe blockage, a stuck solenoid valve spool, and a stuck clutch piston, and it is shown that these lead to clutch energy loss during power shifting and possibly even clutch burn-out. Second, fault simulations give more than 30000 groups of test data, and an improved dynamic time warping algorithm is used to segment the data samples automatically. Third, an improved echo state network is proposed to classify the above fault samples, and its performance is compared with those of traditional algorithms. Finally, the robustness of the proposed algorithm is tested using samples with noise superimposed. The results show that the accuracy, precision, recall, and F1-score of the improved echo state network are 96.87%, 96.31%, 97.11%, and 96.71%, respectively, making it equivalent in performance to a convolutional neural network with long short-term memory. However, the training speed of the former is significantly better than that of the latter, and even under the influence of strong noise, the proposed algorithm can still achieve an accuracy of 91.32%, which is better than the latter’s 86.62%. This is significantly better than traditional algorithms, thus demonstrating the better generalization characteristics and robustness of the proposed approach.

Penerapan Polluter Pays Principle dalam Perkara Tumpahan Minyak di Teluk Kota Balikpapan

The environmental pollution that occurred in Balikpapan Bay was the result of a pipe leak caused by PT Pertamina (Persero) Refinery Unit V, where this is the largest environmental pollution occurring with the impact of an oil spill that threatens the sustainability of the ecosystem in the sea and the coastal communities of the bay of Balikpapan City. This study aims to analyse how the polluter pays principle is regulated in Law Number 32 of 2009 on Environmental Protection and Management as well as identifying and applying this principle to environmental pollution that occurs in Balikpapan Bay. The method used in this research is normative juridical thus the data used is secondary data collected through literature study. The results of this research are, firstly, the polluter pays principle regulated in Article 87 of Law Number 32 of 2009, which states that business actors who pollute the environment are obliged to allocate funds for activities to improve the environment they have polluted. Second, PT. Pertamina (Persero) Refinery Unit V, apart from being subject to compensation, must also be responsible for taking legal action such as installing or repairing waste processing units in accordance with specified environmental quality standards, restoring environmental functions, eliminating or destroying the causes of pollution and/or damage to the environment, and provide compensation or compensation to communities affected by oil spills.

Synergistic effect of rainfall and pipe leakage erosion on the formation and development of loess caves in Weinan city, Loess Plateau, Northwest China

Synergistic effect of rainfall and pipe leakage erosion on the formation and development of loess caves in Weinan city, Loess Plateau, Northwest China

Train Brake System Pipe Leakage Detection and Early Warning Method Based on Bayesian Networks

This paper proposes a method for detecting and warning about leaks in train braking system pipelines based on Bayesian networks. Firstly, a detection model for pipeline leaks is established through the learning and inference of Bayesian networks. In the anomaly detection phase, the Bayesian network model is trained using historical data to monitor brake pressure abnormalities in real-time. Secondly, in the parameter regression calibration phase, the location and severity of the pipeline leaks are estimated based on the current brake pressure and relevant parameters. Finally, in the fault inference phase, the Bayesian network model is used to infer the possible causes of the leaks. The effectiveness and reliability of this method are verified through simulation design and actual data analysis. Compared to existing methods, this method can provide accurate leak detection and warning, thereby contributing to the safety of train operation. This research provides an effective method for detecting and warning about leaks in brake system pipelines and has practical application value.

Supervised Machine Learning Approaches for Leak Localization in Water Distribution Systems: Impact of Complexities of Leak Characteristics

Localizing pipe leaks is a significant challenge for water utilities worldwide. Pipe leaks in water distribution systems (WDSs) can cause the loss of a large amount of treated water, leading to pressure loss, increased energy costs, and contamination risks. What makes localizing pipe leaks challenging is the underground location of the water pipes and the similarity in impact on hydraulic properties (e.g., pressure, flow) due to leaks as compared to the effects of WDS operational changes. Physical methods to locate leaks are expensive, intrusive, and heavily localized. Computational approaches such as data-driven machine learning models provide an economical alternative to physical methods. Machine learning models are readily available and easily customizable to most problems; therefore, there is an increasing trend in their application for leak localization in WDSs. While several studies have applied machine learning models to localize leaks in single pipes and small test networks, these studies have yet to thoroughly test these models against the different complexities of leak localization problems, and hence their applicability to real-world WDSs is still unclear. The simplicity of the WDSs, the oversimplification of leak characteristics, and the lack of consideration of modeling and measuring device uncertainties adopted in most of these studies make the scalability of their proposed approaches questionable to real-world WDSs. Our study addresses this issue by devising four study cases of different complexity that account for realistic leak characteristics and model- and measuring device-related uncertainties. Two established machine learning models—multilayer perceptron (MLP) and convolutional neural network (CNN)—are trained and tested for their ability to localize the leaks and predict their sizes for each of the four study cases using different simulated hydraulic inputs. In addition, the potential benefit of combining different types of hydraulic data as inputs to the machine learning models in localizing leaks is also explored. Pressure and flow, two common hydraulic measurements, are used as inputs to the machine learning models. Further, the impact of single and multiple time point input in leak localization is also investigated. The results for the L-Town network indicate good accuracies for both the models for all study cases, with CNN consistently outperforming MLP.

Applying Plaxis 3D To Model Leaking Water Supply Pipe Causing Sandy Soil Erosion and Sinkhole Formation

Water supply pipes in urban areas are always buried underground. There are many causes of pipe breakage and leakage of high-pressure water from the pipe to the outside, the flow of water has a pressure higher than the soil erosion limit, causing the soil structure to be broken, eroding the surrounding clayey sandy soil. The development of the eroded clayey sandy soil area, which expands over time, is the cause of the formation of a sinkhole under the road, which is dangerous for vehicles and people. In this study, the authors apply finite element software (Plaxis 3D) to model water supply pipelines in sandy soil in case the pipeline leaks water with different pressures. Analytical models indicate that sinkhole formation is dependent on the extent of the erosive clayey sandy soil, which is related to the extent and direction of the pressurized water jet, and the depth of the pipe.

Study on the impact of ovality defect on structural stability of CIPP liner of drainage pipeline

Cured-in-Place Pipe (CIPP) is a trenchless pipeline rehabilitation technology commonly used for repairing underground municipal pipes. It effectively, safely, and environmentally friendly resolves drainage pipe leakage and dripping issues by curing a new resin-impregnated liner inside the original pipe. However, in practical applications, ovality defects may occur in CIPP liners due to insufficient inflation, deformation of the original pipe, joint misalignment, and other problems. These defects have the potential to reduce the structural bearing capacity of the liners. To investigate the buckling mechanism of oval liner structures under external water pressure, two sets of OD 600 mm CIPP liner buckling tests were conducted. The critical buckling stress state and buckling mode characteristics exhibited similarities across liners with different initial ovalities. With an increase in the ovality defect of the liners from 0% to 5%, the critical buckling pressure decreased by 10.62%, while the maximum radial deformation displacement decreased by 62%. Existing models have shown an inability to accurately predict the buckling pressure of oval liners with an initial annular gap. Consequently, this study proposes an improved analytical solution for calculating the critical buckling pressure of liners with ovality imperfections under the influence of an annular gap, which aligns well with the experimental data. The conclusions drawn from this study provide substantial data support for ensuring the accuracy and safety of CIPP liner rehabilitation design.

Effect of soil on leakage rates in water distribution pipes

Abstract This paper describes an experimental and analytical study that examined the effects of soil on leakage rate from defective water pipes. An experimental model was designed and constructed to simulate idealized cracks in defective water pipes discharging into a bed of granular materials. Tests were run on three different materials: LBS-B, LBS-A, and glass ballotini with different characteristics. The results reveal that the presence of bedding material surrounding a leaking pipe causes a significant change in the leakage rate versus free flow conditions. The bedding has a greater impact on larger defect openings. There was a significant drop in the values of the coefficient of discharge (Cd) when the pipe discharged into a soil bed versus free flow conditions; this value was 38% lower for coarse particles and 70% for finer particles. The results also showed that high leakage rates could flow from the defective pipe without fluidization of the bedding materials. An analytical model based on the method of fragments was presented to predict the leakage rate after which the predicted results were compared with values measured experimentally.

Machine-Learning-Based Health Monitoring and Leakage Management of Water Distribution Systems

The reduction of pipe leakage is one of the top priorities for water companies, with many investing in greater sensor coverage to improve the forecasting of flow and detection of leaks. The majority of research on this topic is focused on leakage detection through the analysis of sensor data from district metered areas (DMAs), with the aim of identifying bursts after occurrence. This study is a step towards development of ‘self-healing’ water infrastructure systems. In particular, the concepts of machine-learning (ML) and deep-learning (DL) are applied to the forecasting of water flow in DMAs at various temporal scales, thereby aiding in the health monitoring of water distribution systems. This study uses a dataset for ~2500 DMAs in Yorkshire, containing flow time-series recorded at every 15-minute interval over the period of a year. Firstly, the method of isolation forests is used to identify anomalies in the dataset which are verified as corresponding to entries in water mains repair log, indicating the occurrence of bursts. Going beyond leakage detection, this research proposes a hybrid framework of DL models - such as recurrent neural networks (RNNs) and transformer neural networks) - and state-space ML algorithms - such as Kalman filter and autoregressive integrated moving average (ARIMA). The ML algorithms are trained to forecast the stationary component of the expected flow patterns in real-time, which is then combined (through Bayesian updating) with the non-stationary component obtained from DL models. As well as providing expected day-to-day flow demands, this framework aims to issue sufficient early warning for any upcoming anomalous flow or possible leakages. For a given forecast period, the framework can be used to compute the probability of flow exceeding a pre-defined threshold, thus allowing decisions to be made regarding any necessary interventions. This can inform targeted repair strategies which best utilise resources to minimise leakage and disruptions by addressing both detected and predicted burst events.

Sewer subsidies from overflows and pipe leaks dominate urban stream solute loads in all storm events

Stream channel burial drastically alters watershed flowpaths by routing surface waters underground and increasing the potential for interactions between stream water and urban infrastructure such as storm and sanitary sewers. While numerous studies have investigated storm event solute loads from urban watersheds, the influences of stream channel burial and sewer overflows are often overlooked. This study uses grab samples and natural abundance stable isotope tracers to quantify the event dynamics of solute concentration-discharge relationships as well as cumulative loads in a buried urban stream. Our results demonstrate that different solutes, as well as different sources of the same solute (atmospheric NO3− and sewer-derived NO3− differentiated by the Δ17O tracer), are delivered via separate watershed flowpaths and thus have different timings within the event and contrasting relationships to flow. This inter-event variability reveals dynamics that result from temporal and spatial heterogeneity in infiltration, exfiltration, and pipe overflows. These results can help guide system-wide infrastructure maintenance as cities seek to meet challenges in sustaining and improving water quality as infrastructural systems age.

Research on pinhole accidental gas release in pipelines: Statistical modeling, real gas CFD simulation, and validation

The successful risk mitigation of Natural Gas (NG) leakage to reduce its environmental and economic impact depends chiefly on timely detection leaks and predicting the amount of gas release. In the present study, we investigated pinhole leaks and predicted the gas release rate for various leak to pipe diameter ratios and operating pressures ranging from 2 bar to 110 bar. We first set up a laboratory-scale experiment. The generalized likelihood ratio (GLR) is used as an advanced statistical hypothesis testing technique to detect any shifts in the mean and variance of the process measurements in real-time. These results improved the understanding of several leak detection systems and contributed to a reduction in false alarms in these systems. The presence of a leak was flagged almost immediately after it occurred, indicating the speed and efficiency of statistical techniques in detecting microleaks. The present computational fluid dynamics (CFD) study provides details on the entire leak flow field that are not possible to obtain with experimental methods. CFD is a critical tool in process safety management, helping to identify, analyze, and mitigate potential risks in natural gas pipeline. The CFD study proposes new correlations to predict the nominal leak volume flow rate by investigating the influence of leak size, pipe diameter, and pipe pressure for wide ranges of pressures. The correlations were derived from three-dimensional transient detachable eddy simulation model in a commercial CFD code (ANSYS Fluent R3). The correlations enhance the conventional models by incorporating the gas compressibility effect for high-pressure conditions. The percentage of error between the results of the CFD and delivered correlation fluctuated between 4% and − 5%, demonstrating the high accuracy of the new correlation.

WATER LOSS PREDICTION MODEL FOR PIPE LEAKS IN WATER DISTRIBUTION NETWORKS LAID ON SLOPING TERRAINS

One of the major elements affecting the working of a water distribution network (WDN) is the natural topography of the area on which it is laid, and when such a scenario is coupled with a pipe leak, the results are not known as yet. The effects of a sloping terrain on pressure distribution and transient state due to leakage in pipes are studied in detail in this research by considering three common types of pipe leaks. Significant results are obtained after the hydraulic simulation, and critical points are identified in the WDN. Statistical analysis is performed based on the data obtained through simulation results to develop a model for predicting the amount of flow through a leak in a WDN laid on sloping terrain. The model is found to be dependent on water demand, the pressure of water during the transient state, and the slope of a particular node from the main source of water. The model is validated by comparing the simulated values with the calculated ones and shows a good match. The research proves to be beneficial for better management of water distribution through pipe networks and overcoming water loss through pipe leaks.

Optimal Pressure Sensor Deployment for Leak Identification in Water Distribution Networks

Pipe leakage is an inevitable phenomenon in water distribution networks (WDNs), leading to energy waste and economic damage. Leakage events can be reflected quickly by pressure values, and the deployment of pressure sensors is significant for minimizing the leakage ratio of WDNs. Concerning the restriction of realistic factors, including project budgets, available sensor installation locations, and sensor fault uncertainties, a practical methodology is proposed in this paper to optimize pressure sensor deployment for leak identification in terms of these realistic issues. Two indexes are utilized to evaluate the leak identification ability, that is, detection coverage rate (DCR) and total detection sensitivity (TDS), and the principle is to determine priority to ensure an optimal DCR and retain the largest TDS with an identical DCR. Leakage events are generated by a model simulation and the essential sensors for maintaining the DCR are obtained by subtraction. In the event of a surplus budget, and if we suppose the partial sensors have failed, then we can determine the supplementary sensors that can best complement the lost leak identification ability. Moreover, a typical WDN Net3 is employed to show the specific process, and the result shows that the methodology is largely appropriate for real projects.

Computational Simulation of the Flow Induced by Water Leaks in Pipes

Despite recent advances in leak detection in water supply systems, previous studies focused mainly on material aspects or orifice opening characteristics. This study evaluated geometric, hydraulic, and hydrodynamic factors influencing on water leaks using three-dimensional (3D) computational fluid dynamics (CFD) simulations. The simulated discharge coefficient (Cd) had a maximum absolute deviation of 8% compared with experimental data. The results indicated that the variation of Cd as a function of the diameter and orifice size can be attributed to the effect of tube curvature on flow convergence through the orifice. The statistical analysis concluded that the orifice-to-pipe diameter ratio d/D is the best dimensionless parameter that explains this phenomenon, which agreed with the analyses of the streamlines and turbulent eddy dissipation rate in the simulations. Other important dimensionless parameter are the ratio of the pressure head differential at the orifice to the pipe diameter ΔH/D, Reynolds number (R), and the ratio of the pressure head differential at the orifice to the wall thickness ΔH/e, in order of relevance. A set of empirical correlations was elaborated through a nonlinear multiple regression analysis with Reynolds numbers ranging between 12,000 and 52,000, and pressure head differential ranging from 1 to 45 m. This study advances the knowledge of cross-flows through orifices, and the proposed correlations potentially can improve the prediction of water leaks in pipes.

A Study on Cable Restrained Seismic Behavior of Suspended Piping Systems with Rod Support

台灣在公共工程、醫院等建築物中，經常以螺紋牙桿為懸吊構件，支撐裝載水系的單桿管線或共同吊架，例如：懸吊式消防撒水系統、懸吊式共同管線吊架系統等。然而，多數的懸吊設備不會額外顧及受震振動問題，僅考慮自重支撐是否足夠，因此該類型以螺紋牙桿為懸吊構件的設備，經常在地震中震動過大損壞、漏水，造成使用空間既有機能停擺、增加維修成本。本研究針對國內常見螺紋牙桿之消防撒水系統與共同管線吊架系統，及其常用之施工與補強方式，參考NFPA13與ISAT之補強建議下，利用經UL認證市售鋼索補強，進行振動台實驗，分析比較補強前後系統識別、動靜態特性差異。實驗顯示利用鋼索補強可以大量降低地震造成的管線振動量，確認該補強構件為實務亦可使用之耐震補強策略。In Taiwan, rod supports are usually used for suspension systems in hospitals and public spaces, such as fire-sprinkler piping systems and trapeze systems. Because pipe breakage and leakage after an earthquake can reduce the building function and cost lots of money and time to recover, the dynamic behavior of the above systems is important to understand before a good retrofit program is proposed. This study focuses on the rod support for suspended fire-protection sprinkler piping systems and suspended trapeze system. Retrofitted with cables that satisfied the seismic component requirements from NFPA13 and ISAT, and the cable restraint components which were certified by UL, we studied their dynamic behavior. By shaking table tests, the system identification and system characteristic were analyzed for before and after retrofit. Test results indicated that cables are effective to reduce the horizontal displacement of rod supported piping and trapeze systems in earthquake motion.

A novel non-contact, magnetic-based stress inspection technology and its application to stress concentration zone diagnosis in pipelines

During their construction and long-term operation, stress concentration zones (SCZs) will inevitably occur in buried pipelines. This may cause pipe leakage or fracture failures. Therefore, it is essential to inspect and identify the precise position and stress damage degree of SCZs. Non-contact pipeline magnetic-based stress inspection (PMSI) is an important topic in the field of oil and gas pipeline stress inspection. In order to determine the response of a non-contact magnetic gradient signal to the stress damage of SCZs, we establish a PMSI model to analyze the three-dimensional magnetic signals of SCZs. The effects of changes to the axial stress value, the stress concentration length, the detection height and the gradiometer jitter are also studied. In addition, the PMSI is carried out on a 10.3 km liquefied natural gas buried pipeline, which is validated by the excavation inspection results. The results indicate that the x component of the magnetic gradient signal, Gx , shows sinusoidal fluctuation near a SCZ, and the y and z components, Gy and Gz, each reach a peak value. The G max value, the maximal magnetic gradient modulus, increases with the severity and length of the SCZs. As a result, two level-II SCZs and two level-III SCZs are identified.

Buried gas pipe leak localization using dual-wave spectrum estimation

To accurately locate leaks in buried gas pipes, a three-dimensional (3D) localization method using dual-wave velocity pairing and multi-array fusion localization was developed in this study to locate leak-induced vibroacoustic sources. Two velocities at which the P1 and S waves propagated along soil were estimated when the peaks of the dual-wave spectrum coincided with each other. Root-MUSIC algorithm was introduced to quickly determine the superimposed peak, thereby reducing the computational complexity. To address the issue of 3D localization using the P1 wave that propagated in soil according to a far-field model, least-squares (LS) estimation for the 3D coordinates was performed using the fusion localization method. A numerical model of geometrical dilution of precision (GDOP) was constructed to analyze the performances of multi-array layouts. A uniform circular array of eight accelerometers was utilized to visualize the leak-induced vibroacoustic source, and the imaging showed that the vibroacoustic source coincided with the leak. Accurate direction of arrival (DOA) estimation under multiple soil conditions was achieved, which proved that the velocity near the array was accurately estimated. An equilateral-triangle multi-array layout was selected using GDOP analyzing, and the results of localization experiments revealed that the equilateral-triangle layouts with 1.5-m and 2-m spacings achieved relatively good accuracy. Compared to the 3D localization method using a single array, the fusion localization method showed better accuracy for the remote leak, and the maximum reduction in error is 84.75 %. GDOP of fusion localization was found less than 0.1 m when the internal pipe pressure ≥ 0.4 MPa and the signal-to-noise ratio (SNR) ≥ 0 dB under the conditions of experiments in this study.

Características hidroquímicas y ambiente acuático de las aguas superficiales y subterráneas poco profundas en el norte del delta del río Amarillo, China

The present study envisaged the dynamic monitoring and study of the hydrochemistry of the surface water and shallow groundwater in the northern part of the Yellow River Delta, China. Analysis of the surface water and shallow groundwater revealed that the shallow groundwater exhibited in two forms: precipitation evaporation type and hydrological type, and the latter was obviously affected by the dynamic water level of the Yellow River. The surface water and shallow groundwater exhibited a higher degree of mineralization. Cations of Mg2+, Na+ and K+ and anions of Cl- and SO42- were the main ion components of the total dissolved solids. The hydro-chemical type of shallow groundwater was Cl-Na·K that was a typical seawater or brine form. The water chemical type of surface water changed to Cl·SO4-Na·K·Ca due to the industrial, agricultural and urban pollution. The overall quality of surface water was poor, and the main pollution indexes were found to be present, except for cyanide. The levels of COD and fluorine exceeded the standard values in the surface water. The groundwater quality was poor, since most of the pollutants were detected, except for cyanide and volatile phenol. Eight indexes exceeded the groundwater quality standard levels including Cl-, Na+, total hardness, COD, NH4+, Hg, As, NO3-, Cl- and Na+. The pollution of the surface water and shallow groundwater was mainly caused by the discharge of the wastewater from the petroleum; chemical industry and brine enterprises; agricultural non-point source pollution; leakage of septic tanks and sewage pipes in urban and rural areas, and rainwater leaching from the garbage piles. In order to improve the water quality, the sewage control and management needs be optimised, and the industrial layout should be reconsidered.

Improved Leakage Detection Generalization Ability for Multiscenes Deployment in Industry

In the unattended industrial environment, the piping leakage detection algorithm based on the combination of image detection and machine learning has the advantages of high sensitivity and reliability. However, there are some problems in the practical application, such as a large number of industrial leakage scenes to be detected, a big spatial feature gap between the deployed scenes and the undeployed scenes and the unpredictable actual leakage situation. These cause a significant decrease in the accuracy and reliability of vision-based piping leakage detection models during large-scale multi-scenes industrial deployment. To solve the above problems, we propose a piping leakage detection method with domain generalization (DG) capability. First, we use the adaptive color recovery multi-scale Retinex (AMSRCR) to enhance the spatial features and improve the image quality of leakage liquid which is colorless and transparent. Based on the idea of DG we design the structure of DCM-DenseNet121, which can improve the generalization ability of the model by learning the domain invariant features of the leakage liquid and solve the problem of decreasing accuracy in large-scale multi-scenes deployment. The experiment results show that the leakage detection balanced accuracy achieve 99.7% when inferring on three target scenes. Furthermore, our model achieves efficient detection, maintains a relatively lightweight when performing in extra-domain target scenes and satisfies the industrial field bandwidth limitations.

DISTRIBUTION SERVICE PERFORMANCE OPTIMIZATION OF PDAM TIRTA TAMAN BONTANG CITY EAST KALIMANTAN PROVINCE

To achieve the level of service performance from PDAM Tirta Taman Kota Bontang , obtained based on user perceptions of PDAM Taman Tirta obtained from the results of a questionnaire with a Likert scale using the Importance Performance Analysis (IPA) method. From the results of the IPA analysis, interviews were then conducted using the Strength Weakness Opportunities Threats (SWOT) method . The results of the IPA analysis were used in quadrant I, namely service to the registration process (x11), survey of prospective customer locations (x12), time of survey implementation (x13) , Payment orders before installation (x15), Notice the length of the installation process (X15). Registration up to installation (X16), the supplied water meets health standards, attributes (X21 ), the quality of the supplied water (color, smell, taste) (X22) , report to PDAM Tirta Taman if there is a disturbance or it doesn't work smoothly (x 33 ), the duration of handling the damage house connection (x 43 ), customer or prospective customer database of PDAM Tirta Taman (x 71 ). Then the SWOT quadrant matrix with the SO ( Strengths-Opportunities ) strategy, namely development with IT and with social media Periodic pipe rejuvenation to avoid pipe leaks that can affect quality, Providing Customer Service via WhatsApp for service notifications, disruptions and payment orders, Issuing SOPs new and regular schedule for maintenance., Continue to perform security updates on the database storage system , Use of official forms for prospective customers with the interest of installing a new connection