Search

This paper presents an investigation of the capacity of machine learning methods (ML) to localize leakage in water distribution systems (WDS). This issue is critical because water leakage causes economic losses, damages to the surrounding infrastructures, and soil contamination. Progress in real-time monitoring of WDS and ML has created new opportunities to develop data-based methods for water leak localization. However, the managers of WDS need recommendations for the selection of the appropriate ML methods as well their practical use for leakage localization. This paper contributes to this issue through an investigation of the capacity of ML methods to localize leakage in WDS. The campus of Lille University was used as support for this research. The paper is presented as follows: First, flow and pressure data were determined using EPANET software, then, the generated data were used to investigate the capacity of six ML methods to localize water leakage. Finally, the results of the investigations were used for leakage localization from offline water flow data. The results showed excellent performance for leakage localization by the artificial neural network, logistic regression, and random forest, but there were low performances for the unsupervised methods because of overlapping clusters.

Increasing requirements for environmental protection, safety or reliability force automotive industries to use more efficient tests to measure tightness of the components. Currently adapted methods brings limitations which makes automotive industry open for new techniques for leakage tests. Infrared cameras are widely used in various fields. Using them to test leakage of closed-volume systems allows to significantly reduce test time, especially for objects which requires long stabilization times in competitive methods. In the article thermovision usage for leakage detection of gas springs were described.

Leakage in water distribution systems is a significant long-standing problem due to the huge economic and ecological losses. Different leak detection studies have been examined in literature using different types of technologies and data. Currently, although machine learning techniques have achieved tremendous progress in outlier detection approaches, they are still limited in terms of water leak detection applications. This research aims to improve the leak detection performances by refining the choices of learning data and techniques. From this perspective, commonly used techniques for leak detection are assessed in this paper, and the characteristics of hydraulic data are investigated. Four intelligent algorithms are compared, namely k-nearest neighbors, support vector machines, logistic regression, and multi-layer perceptron. This study focuses on six experiments based on identifying outliers in various packages of pressure and flow data, yearly data, seasonal data, night data, and flow data difference to detect leakage in water distribution networks. Different scenarios of realistic water demand in two networks from the benchmark dataset LeakDB are used. Results demonstrate that the leak detection accuracy varies between 30% and 100% depending on the experiment and the choices of algorithms and data.

Water supply networks are liable to leakages, resulting in loss of large quantities of water. Hence, it is required to implement a leak detection and localization system through water network simul...

As hydrogen gas increasingly becomes critical as a carbon-free energy carrier, the demand for robust hydrogen sensors for leak detection and concentration monitor will continue to rise. However, to...

Water distribution networks that are unoptimally operated can cause various problems so that water flows are not evenly distributed to consumers. One of the causes is the high water loss level due to leaks in the distribution pipeline system, as one of the water operators in Jakarta, Indonesia, PT. XYZ has tremendous efforts to improve the water supply system. One of them is to reduce physical water losses. The estimated percentage of physical water losses of water distribution networks in Green Garden District, West Jakarta, in April 2018 has amounted to 30%. It is still above the tolerance standard for the national water loss rate in Indonesia's Water Utilities, around 20%. It is necessary to reduce water loss to overcome this problem. After performing a step test program in the Green Garden District, it was found that there was a water loss of 84 lps in July 2018, which increased to 103.16 l/sin in May 2019 or showed an increase of 23%. Then, a pressure calibration was undertaken by placing six pressure monitoring points on the district in May 2019 using hydraulic simulation from WaterGEMS V.10. This calibration obtained the highest pressure Gap at pressure monitoring point #5 of 2.5 mH2O and the lowest pressure monitoring point #1 of 1.03 mH2O. Subsequently, leak detection measures were conducted to reduce physical water loss from January to May 2019, PT. XYZ water distribution network uses two leak detection methods, visible and invisible leak detections, which had successfully reduced its net night flows (NNFs). The leak repairs obtained 77 leak points, which consisted of 32 visible leaks and 45 invisible leaks. Total estimated leakage flows of 5.33 lps were obtained from the decrease in the net night flow, which indicates a decrease in physical water loss by 16% from January to March 2019.

Postoperative leaks after gastrointestinal surgery are important to identify to decrease patient morbidity and mortality. Fluoroscopic studies are commonly employed to detect postoperative leak. While the literature addresses the sensitivity and specificity of these examinations, there is generally a lack of description of the fluoroscopic technique itself and there may be variability between radiologists in how these studies are performed. It is important to balance a standardized fluoroscopy protocol while tailoring the exam for each surgical and patient situation. Here we will briefly review common postoperative anatomy in the upper gastrointestinal tract, propose fluoroscopic techniques to improve postoperative leak detection, and illustrate teaching points with clinical cases.

In this work, a novel convolutional neural architecture (SE-CNN), which combines spectrum enhancement (SE) and convolutional neural network (CNN), is proposed to detect the leak of gas pipeline. The SE has the effect of enhancing the leak signals and reducing background noise. CNN can automatically extract leak features and realize leak diagnosis. The experimental results show that the SE-CNN can achieve an average accuracy of 94.3 % for 6 categories and only requires 1.04 s of detection time. In this experiment, the diameters of the main pipeline and the branch pipeline are 125 mm and 25 mm. Due to its excellent accuracy and efficiency, the proposed enhanced spectrum convolutional neural architecture paves the way for real-time leak detection in industrial environments, which can ensure the process safety of gas pipeline transportation. Under strong background noise, the average accuracy of the SE-CNN can reach 94.3 % , which is 33 % , 3.7 % higher than that of SVM and CNN. In particular, the SE can be regarded as a data compression method, which can significantly reduce the original data size. The training time of the SE-CNN is 539 s, reducing 90.6 % compared with CNN.

There is an increasing need for timely pipeline leak detection and localization methods, pipeline leak could lead to not only the loss of the goods but also considerable environmental and economic problems. With the rapid development of hardware and software, the pipeline leak detection and localization algorithms have been widely researched and applied in many Fields. However, traditional methods are usually limited by extracting features manually, which is inefficient and time-consuming. Convolutional neuron network is an effective method to extract features automatically. In this paper, a novel ensemble transfer learning one-dimension convolutional neural network (TL1DCNN) for the pipeline leak detection and localization is proposed. The TL1DCNN plays the role of base learner. The results of a set of obtained base learners are integrated to achieve the task of pipeline leak detection and localization. Firstly, one-dimension convolutional neural network (1DCNN) models with different parameters are pretrained with source domain data. A small learning rate is set to retrain the above 1DCNN models for target task with target domain data in order to obtain TL1DCNN base learners. Then, the four ensemble strategies with different number base learners whose ensemble weights are optimized by particle swarm optimization algorithm are obtained by minimizing the sum of similarity. The dataset simulated by pipeline network model is used to evaluate the effectiveness of the proposed approach. The indicators such as classification accuracy, precision, recall, F_score and confusion matrix are used to compare the proposed approach with traditional methods and other deep learning methods. The experimental results show that the performance of the proposed approach is superior to other compared methods.

In this study, a novel high-reliability liquid leakage sensor with a V-shaped defect coupling structure (VDCS) is proposed and experimentally demonstrated using polymer optical fibers (POFs) based on a light-emitting diode (LED) side-coupled light source. Liquid leakage detection is achieved with changes in the refractive index as the coupling medium transforms from air to liquid. The LED lamp both provides a light source and assists positioning. The coupling efficiency of the POF liquid leakage sensor varies with the depth and angle of the VDCS. Experimental results show that the coupling efficiency of the POF leakage sensor is high when the VDCS depth is 0.5 mm and the inclination angle is 60°. Compared to an existing leakage sensor with a hole-shape defect coupling structure (HDCS), the VDCS has a faster response time and higher reversibility. The average reliability of the liquid leakage sensor is increased to 5.92 μW/mL. This research provides a powerful structural reference for POF side-coupling leak measurement and can also be applied to the fields of gas and humidity sensing.

Managing pipe breaks in water supply networks has been a challenge for water utilities around the world. In order to transform from reactive to proactive management of pipe breaks, South Australia ...

Volatile organic compounds (VOCs) contribute to the formation of ground-level ozone. This causes the phenomena of haze and photochemical smog pollution. Recently, the leak detection and repair (LDAR) program was required to implement in China’s petroleum industry on the background of the huge emissions from equipment leaks. This paper analyzed and compared the application of LDAR program in four petroleum refineries and six typical processing units in these refineries. The results showed that non-flanged connectors, flanges, valves, and open-ended lines were the most common components, which accounted for over 99% in these refineries. And over half were non-flanged connectors. About 0.2% to 0.4% of all components were found to leak and emitted up to 91.8% of VOCs, especially the leaking valves and open-ended lines. And over 88.5% of VOC emissions were from high leaking components. The VOC emissions reduced 42% to 57% by repairing 42% to 81% of leaking components. And 90% of the reduction was achieved by repairing high leaking components. Besides, under the same processing capacity, the gas fractionation unit and continuous catalytic reforming unit have a higher average number of components, leaking components and VOC emissions than the other four units. Finally, this paper proposed some problems and suggestions during the implementation of LDAR program. These findings can enhance and improve the effectiveness of LDAR program, and establish a comprehensive VOCs control system, which provides a scientific basis and technical support for the government and refineries. Implications: Recently, China required industries to implement leak detection and repair (LDAR) program to control volatile organic compound (VOC) emissions, especially the petroleum industry. In this paper, we analyzed and compared the LDAR program implementation in four refineries and six typical processing units in these refineries. The results indicate that the implementation of LDAR program was highly effective in petroleum industry. The comparison helps us to enhance the effectiveness of LDAR program by locating the high VOC emission components and units, which provides technical support for the government and refineries in developing specific regulations and plans.

The increase in pipeline safety would prevent incidents that can result in fatalities, environmental disasters, and economic losses. The present work proposes a technique that combines acoustic sensors and machine learning algorithms to identify and locate leakages in low-pressure gas pipelines. The patterns on the sound signal captured by microphones were used to accomplish those two tasks. The technique aims to solve two persistent problems, the detection of small leakages on pipelines operating under low pressures and the reduction of false alarms in the presence of external disturbances. The experimental results showed that the method identified 99.6% of the leakages and achieved a rate of false alarms of 0.3%, while the position of the leakages was estimated with a maximum location error of 4.31%. These results show that the technique proposed is an efficient and reliable alternative to monitor low-pressure pipelines.

The Demands in quality of the automobile production grows at a rapid pace with the pressure to reduce costs of the automobiles further. So it becomes necessary to subject the critical components for the leakage detection to enhance the overall quality and the customer satisfaction. Apart from the conventional methods and the recently evolved methods in leakage detection for the automobiles, the paper tries to put forth a novel method for the detection of the leakage in the automobiles using the image processing techniques. The proposed method concentrates on the image detection, classification and recognition for the leak detection of the air conditioning in the automobiles. The proposed method of image detection is evaluated using the MATLAB to evince accuracy in the leakage detection, classification and recognition

Leak detection of gas pipelines has attracted extensive attention in recent years because such a leak could result in significant damage to society. This paper proposes an integrated leak detection method using acoustic signals based on wavelet transform and Support Vector Machine (SVM). Specifically, the optimal wavelet basis is selected by the entropy-based algorithm adaptively, with which acoustic signals gathered by acoustic sensors are first pre-processed by wavelet transform. Then useful features containing leak severity information are extracted from multi-domain components of the acoustic signals. Moreover, for leak detection and severity classification, the Relief-F algorithm is applied to select the most discriminative features. Furthermore, selected features are used as the input of SVM classifiers to identify the leak severity of gas pipelines. The effectiveness of the proposed method is validated using laboratory experiments. The results demonstrate that the proposed method achieves high accuracy of 99.4% to determine the leak state and non-leak state by using the first three most discriminative features and 95.6% to classify the normal and several leak severity conditions by using the first five most discriminative features. Therefore, it is effective for leak detection and promising for the development of a real-time monitoring system.

Numerous novel improved support vector machine (SVM) methods are used in leak detection of water pipelines at present. The least square twin K-class support vector machine (LST-KSVC) is a novel simple and fast multi-classification method. However, LST-KSVC has a non-negligible drawback that it assigns the same classification weights to leak samples, including outliers that affect classification, these outliers are often situated away from the main leak samples. To overcome this shortcoming, the maximum entropy (MaxEnt) version of the LST-KSVC is proposed in this paper, called the MLT-KSVC algorithm. In this classification approach, classification weights of leak samples are calculated based on the MaxEnt model. Different sample points are assigned different weights: large weights are assigned to primary leak samples and outliers are assigned small weights, hence the outliers can be ignored in the classification process. Leak recognition experiments prove that the proposed MLT-KSVC algorithm can reduce the impact of outliers on the classification process and avoid the misclassification color block drawback in linear LST-KSVC. MLT-KSVC is more accurate compared with LST-KSVC, TwinSVC, TwinKSVC, and classic Multi-SVM.

This study is aimed to determine the source of a sound occurred on solid objects. Such that; It is aimed to detect the position of the sound caused by sudden impact on objects such as water or fuel pipes reaching long distances by using sensors placed at certain intervals on these objects. At the same time, separately synchronized LoRa radios are used for communication between the sensors and the processing center where the data is processed. While a significant part of the work is the positioning of the sound source in solid objects, another noteworthy part has been the work done for the synchronization of LoRa radios and the evaluation of the received signals together.

Underground natural gas (NG) leaks pose an urgent safety threat, motivating ongoing efforts to improve leak detection methods. The objectives of this study were to investigate how realistic environ...

In this paper the potential of the principal component analysis(PCA) technique for the application of detecting leaks in water pipe networks was evaluated. For this purpose the PCA was conducted to evaluate the relevance of the calculated outliers of a PCA model utilizing the recorded pipe flows and the recorded pipe leak incidents of a case study water distribution system. The PCA technique was enhanced by applying the computational algorithms developed in this study which were designed to extract a partial set of flow data from the original 24 hour flow data so that the effective outlier detection rate was maximized. The relevance of the calculated outliers of a PCA model and the recorded pipe leak incidents was analyzed. The developed algorithm may be applied in determining further leak detection field work for water distribution blocks that have more than 70% of the effective outlier detection rate. However, the analysis suggested that further development on the algorithm is needed to enhance the applicability of the PCA in detecting leaks by considering series of leak reports happening in a relatively short period.

One of the largest movers of the world economy is the oil and gas industry. The industry generates billions of barrels of oil to match more than half the world’s energy demands. Production of energy products at such a massive scale is supported by the equally massive oil and gas infrastructure sprawling around the globe. Especially characteristic of the industry are vast networks of pipelines that traverse tens of thousands of miles of land and sea to carry oil and gas from the deepest parts of the earth to faraway destinations. With such lengths come increased chances for damage, which can have disastrous consequences owing to the hazardous substances typically carried by pipelines. Subsea pipelines in particular face increased risk due to the typically harsher environments, the difficulty of accessing deepwater pipelines, and the possibility of sea currents spreading leaked oil across a wide area. The opportunity for research and engineering to overcome the challenge of subsea inspection and monitoring is tremendous and the progress in this area is continuously generating exciting new developments that may have far reaching benefits far outside of subsea pipeline inspection and monitoring. Thus, this review covers the most often used subsea inspection and monitoring technologies as well as their most recent developments and future trends.

Multiproduct pipelines play an important role in linking the upstream and downstream ends of the petroleum industry. Promoting energy conservation and carbon abatement in a multiproduct pipeline is imperative to the entire petroleum industry in China to move toward sustainable and cleaner production. This paper studies the promotion of technical progress on the operation of a multiproduct pipeline under policy control in terms of economic, energy-saving and carbon abatement potential (EECP) from a long-term perspective, which fills a gap in the reference literature. A complete bottom-up framework for detailed calculations of energy consumption and carbon dioxide emissions for four categories of energy-saving technical measures is proposed, including pipeline scheduling, transmix treatment, pressure loss control and a leak detection system. Three scenarios are applied to forecast the regional demand of the pipeline in response to different low-carbon policy contexts, and a stepwise multiple linear regression is used to realize the forecast of prices of oil products under the regulation of government. To demonstrate the proposed method, a real multiproduct pipeline in the Zhejiang Province, China is used as an example. The results show that two-thirds of selected technical measures are economically feasible. The forecasted EECP of the studied multiproduct pipeline is rather significant, with the NPV, energy-saving potential and carbon-abatement potential being 198.32 million CNY, 60.25% and 49.57% from 2016 to 2050, respectively. The proposed method is not case-specific and can be used for any multiproduct pipeline in China.

To reduce the secondary damage caused by leakage accidents in plant piping systems, a constant surveillance system is necessary. To ensure leaks are promptly addressed, the surveillance system should be able to detect not only the leak itself, but also the location of the leak. Recently, research to develop new methods has been conducted using cameras to detect leakage and to estimate the location of leakage. However, existing methods solely estimate whether a leak exists or not, or only provide two-dimensional coordinates of the leakage location. In this paper, a method using multiple cameras to detect leakage and estimate the three-dimensional coordinates of the leakage location is presented. Leakage is detected by each camera using MADI(Moving Average Differential Image) and histogram analysis. The two-dimensional leakage location is estimated using the detected leakage area. The three-dimensional leakage location is subsequently estimated based on the two-dimensional leakage location. To achieve this, the coordinates (x, z) for the leakage are calculated for a horizontal section (XZ plane) in the monitoring area. Then, the y-coordinate of leakage is calculated using a vertical section from each camera. The method proposed in this paper could accurately estimate the three-dimensional location of a leak using multiple cameras. Keywords: Image processing, Camera, Steam leakage, Leakage detection, 3D leakage location

The increasing application of fibre-reinforced composite components in aviation results in new problems in production when compared to the conventional production of components from aluminium alloys. For instance, the existence of leakages in the vacuum bag can substantially impact the component quality. A significant increase of both time and cost, and even the rejection of the entire component are caused. Commercially available methods are suitable for identifying leakages in vacuum bags; however, their application is predominantly associated with high outlay in labour and time, and, thus, high costs. Market analysis and comparison of different available leakage detection technologies conducted in the course of the advanced detection of leakages project with our collaborative partner Airbus Operations GmbH Stade has shown that the combination of run-time based leakage detection and infrared thermography is the most promising concept for quick, reliable, and automated identification of leakages in vacuum bags for large components. In combination, both technologies are able to compensate for their respective detection limits, and significantly reduce the time required. In addition to the analysis and assessment of different technologies for leakage detection, the investigations presented also include the development of run-time based leakage detection using sensors integrated into the vacuum bag. Furthermore, the linking, further development, and automation of leakage detection using infrared thermography are described.

The trajectory motion of a robot can be a valuable information to estimate the localization of an autonomous robotic system, especially in a very dynamic but structurally-known environments like water pipes where the sensor readings are not reliable. The main focus of this research is to estimate the location of meso-scale robots using a deep-learning-based motion trajectory segment detection system from recorded sensory measurements while the robot travels through a pipe system. The idea is based on the classification of the motion measurements, acquired by inertial measurement unit (IMU), by exploiting the deep learning approach. Proposed idea and utilized methodology are explained in the related sections and it is observed that convolutional neural network approach is quite powerful to overcome the unreliability of IMU data.

It has become an accepted approach to construct room-temperature phosphorescence (RTP) materials by suppressing the non-radiative decay process. However, there is limited success in developing fluid phosphorescence materials due to the ultrafast non-radiation relaxation of vibration and collision of molecules in fluid matrixes. In this study, a universal strategy was proposed for pure organic phosphorescent fluid materials that are able to generate effective phosphorescent emissions at both room temperature (ΦRTP, 293 K ~ 30%) and even higher temperature (ΦRTP, 358 K ~ 4.53%). Based on these findings, a qualitative analytical method was developed for leak detection and a quantitative analytical technique was further validated to help visually identify the heat distribution of irregular surfaces. This advancement greatly empowers the current organic phosphorescent system offering an alternative approach to determine moisture and heat from non-invasive photoluminescence emission colors.

The water supply network (WSN) is subjected to leaks that compromise its service to the communities, which, however, is challenging to identify with conventional approaches before the consequences surface. This study developed Machine Learning (ML) models to detect leaks in the WDN. Water pressure data under leaking versus non-leaking conditions were generated with holistic WSN simulation code EPANET considering factors such as the fluctuating user demands, data noise, and the extent of leaks, etc. The results indicate that Artificial Neural Network (ANN), a supervised ML model, can accurately classify leaking versus non-leaking conditions; it, however, requires balanced dataset under both leaking and non-leaking conditions, which is difficult for a real WSN that mostly operate under normal service condition. Autoencoder neural network (AE), an unsupervised ML model, is further developed to detect leak with unbalanced data. The results show AE ML model achieved high accuracy when leaks occur in pipes inside the sensor monitoring area, while the accuracy is compromised otherwise. This observation will provide guidelines to deploy monitoring sensors to cover the desired monitoring area. A novel strategy is proposed based on multiple independent detection attempts to further increase the reliability of leak detection by the AE and is found to significantly reduce the probability of false alarm. The trained AE model and leak detection strategy is further tested on a testbed WSN and achieved promising results. The ML model and leak detection strategy can be readily deployed for in-service WSNs using data obtained with internet-of-things (IoTs) technologies such as smart meters.

Water may be a precious resource that ought to be managed fastidiously. But because of leak in water distributed networks an outsized quantity of water is lost annually. The innovative plan is automatism of the water leak detection in water distributed network system. The amount of water distributed is detected using water flow device. The situation of autonomous water leak detection in an exceedingly immense space are often tracked and monitored. The paradigm has been designed for water leak detection. The system is controlled by ATMEGA328 microcontroller. The direction of water is monitored by resistance detector. Correct location and leak are the areas of concern that have been concentrated in the system.

The most common type of vacuum pumps and measuring gauges based on available literature are studied with emphasis on how new research and development will enable the new generation of vacuum technology specially in designing, its operational procedure and applications. The technologies were developed to meet the operational goal which include vacuum chamber structures, compatible materials, specialized vacuum pump and gauges. There are many areas where different vacuum condition is required for conducting experiments therefore modeling of pumping system is on demand. The basic understanding of how and when the particular pumping and measurement system can be applied most effectively and economically is essential. The poor choice of pumping and measurement system will interfere the scientific objectives and may leads to substantial maintenance demands and an unpleasant working environment. The development and fundamental investigation of innovative vacuum techniques for creation and measurement of vacuum used for various applications necessary for the research work to be done in future are presented.

The significance of vacuum measurement technology is increasingly prominent in China’s thriving space industry. Lanzhou Institute of Physics (LIP) has been dedicated to the development of payloads and space-related vacuum technology for decades, and widely participated in China’s space programs. In this paper, we present several payloads carried on satellites, spaceships, and space stations; the methodologies of which covered the fields of total and partial pressure measurement, vacuum and pressure leak detection, and standard gas inlet technology. Then, we introduce the corresponding calibration standards developed in LIP, which guaranteed the detection precision of these payloads. This review also provides some suggestions and expectations for the future development and application of vacuum measurement technology in space exploration.

Pipeline leak detection sensors are created by using fiber Bragg gratings (FBGs) that are inscribed through polyimide coatings of optical fiber with an infrared femtosecond laser and then specially packaged in materials susceptible to hydrocarbons. Depending on the sensor geometry, strain is either applied or released upon exposure to toluene or crude oil., Optical Fiber Sensors 2020, June 8–12, 2020 , Washington, DC, USA

This paper presents an experimental smart water distribution network that addresses the hydraulic parameters of water i.e. flow rate and pressure for leak detection. An experimental test rig was developed in CSIR-CEERI lab and data collected from all the sensors is sent to the SCADA software using PLC. Data of infield sensors (i.e. pressure, flow, temperature, and pump frequency) is collected. Detection of leakage is performed by two techniques (i) by monitoring change in pressure, flow rate, temperature trends using SCADA (ii) by using machine learning techniques - Logistic Regression and Support Vector Machine (SVM).

Pipeline leak detection technology is one of the core issues in the field of pipeline safety research. Based on the classification of hardware-based and software-based methods, this paper summarizes the current mainstream pipeline leak detection technology at home and abroad, and expounds the mechanism, advantages and disadvantages and applicable conditions of each detection technology. This paper mainly introduces the pipeline leak detection technology based on DAS system, summarizes the current detection technology of this system at home and abroad, and proposes to apply VMD composite algorithm and deep learning neural network to pipeline leak detection. This paper also puts forward the design of pipeline leakage monitoring platform based on DAS system and the prospect of applying this system to pipeline monitoring in petrochemical wharf.

A key production measurement is the periodic well testing for both fiscal and reservoir management requirements and a key element is the use of a multiport selector valve (MSV) upstream of a multiphase flow metering (MPFM) system. Typically, an MSV can connect to 7-wells (total of 8 ports, one spare) where the valve isolates the flow from one of the wells and connect it to the MPFM system. The production flow of the other wells is mixed inside the valve body cavity and is directed to a common header. This process is repeated for each well to measure all wells periodically and the key requirement for the valve is absolutely no leak from all wells flow into the well port connected to the MPFM. However, leakages through the valve ports seals occur, even to new equipment, and as a result, the well measurements are inaccurate. An Innovative automatic port leak detection had been developed to eliminate the disadvantages of conventional multiport selector valves. Thus, preventing seal leakage, avoid valve operation when there is a leakage, inform personnel in case of a leak and replace seals in time and avoid any damage to valve internals. The automatic leak detection is based on exploiting the use of a multi-function seat process and pressure switches measurements. In the case some particles (physical impurities or debris) are trapped between the port seals, the automatic leak detection system will automatically perform a cleansing procedure by retracting and pushing the valve piston back to the seat port, allowing well fluid inside the valve to flush away any kind of solids. If the problem remains a leakage alarm signal can be sent to the operator desk from the valve control panel thus ensuring total integrity of the connection between the well and the metering line connected to the MPFM for accurate well test measurements. An accurate well test measurement using MPFM systems for multi-wells can be achieved only if there are no leakages from wells into the wells port seal being measured and this will guarantee confident measurements as wells operational benefits such as detecting valve malfunction, a substantial reduction of maintenance and major repair costs and ultimately extending the multiport port valve operational life.

According to EPA (United States Environmental Protection Agency) the average household’s leaks can account for nearly 10,000 gallons of water wasted every year and ten percent of homes have leaks that waste 90 gallons or more per day. Common types of leaks found in the home are worn toilet flappers, dripping faucets, and other leaking valves. This study proposes the development of a smart home system for saving water in the toilet tank by using a controller that opens and closes the valve, detects water leaking and toilet overflow. When leak or overflow is detected, the device will perform the corresponding operation and indicate the type of error by lighting the specific LED (light-emitting diode). The process for measuring water level and leak detection as well as device implementation is given by this paper.

Leak detection, diagnostics, and prediction constitute a crucial phase of the flow assurance risk management process for onshore and offshore pipelines. There are a variety of techniques and algorithms that can be deployed to address each aspect. To date, most review papers have concentrated on steady-state and single-phase flow conditions. The goal of the current review is therefore to carry out a thorough analysis of the available leak detection and diagnosis methods by focusing on (i) multiphase flow and transient flow conditions, (ii) model-based and data-driven techniques, (iii) prediction tools, and (iv) performance measures. Detailed assessment of leak detection methods based on accuracy, complexity, data requirement, and cost of installation are discussed. Data-driven techniques are utterly dependent on qualitative and quantitative data available from pipeline systems. Contrastingly data-driven techniques, model-based techniques require less data to achieve leak detection, provided that a nearly accurate base model is available. Different methodologies and technologies can be combined in order to produce the best detection and diagnosis outputs. In many cases, statistical analysis was combined with the Real Time Transient Method (RTTM), which helped to minimize false alarms. The material in this review can be used as a robust guide for the design of diagnostic systems and further research.

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 201552, “Leak Detection in Carbon Sequestration Projects Using Machine Learning Methods: Cranfield Site, Mississippi, USA,” by Saurabh Sinha, SPE, University of Oklahoma and Los Alamos National Laboratory; Rafael Pires De Lima, Geological Survey of Brazil; and Youzuo Lin, Los Alamos National Laboratory, et al., prepared for the 2020 SPE Annual Technical Conference and Exhibition, originally scheduled to be held in Denver, 5–7 October. The paper has not been peer reviewed. Saline aquifers and depleted hydrocarbon reservoirs with good seals located in tectonically stable zones make an excellent storage formation option for geological carbon sequestration.Ensuring that carbon dioxide (CO2) does not leak from these reservoirs is the key to any successful carbon capture and storage (CCS) project. In the complete paper, the authors demonstrate automated leakage detection in CCS projects using pressure data obtained from the Cranfield reservoir in Mississippi in the US. Results indicate that even simple deep-learning architectures such as multilayer feed-forward neural networks (MFNNs) can identify a leak using pressure data. Introduction Several methods that use different types of data currently are available to detect leaks. Although some of the methods are a direct indicator of CO2 presence, they cannot provide an early warning for the leaks, thus delaying remedial measures. An ideal process for the identification of leakages requires constant and repetitive comparisons of different data. Machine-learning (ML) techniques are ideally suited for this task. In this work, the authors demonstrate the use of ML techniques such as linear model, random forest, and MFNN on time-series signals obtained from a pressure-pulse test. The methodology uses the time-series data instead of 2D images or 3D voxels, thus providing a computational advantage. The authors write that an ML algorithm can distinguish between a pressure signal corresponding to a leak vs. the pressure signal corresponding to a baseline nonleak case. The trained models can then be used as an early-warning system to flag anomalous data to then be analyzed by a human interpreter. Background A pressure-pulse test uses at least two wells: an injection well and a monitoring well. The reservoir is then shocked by a series of predetermined cycles of injection and shut-ins (i.e., a pulse). The response then is recorded at the monitoring well with a pressure gauge that measures the target formation pressure. The test may be repeated with different pulses to understand the reservoir properties better. A harmonic pulse is preferred over a square wave because it allows for spectral decomposition of the pulse to analyze the reservoir response at different frequencies. Three wells are used in the study: F1, F2, and F3. Well F1 is the injector well, where alternative cycles of injection of CO2 and shut-in are carried out. Well F2 is the monitor well, which remains shut in for the duration of the test and where the pressure is monitored with the use of a pressure gauge. An artificial leak is simulated in the test by opening a surface valve at Well F3.

A gas leak detection system considers various factors for detecting leaks. Sensors are placed around the leak-prone areas, and the presence of a leak is determined based on the concentration values of the sensors. The models produce a variety of results depending on the type of algorithm used to determine the leak. An error in leak detection may cause harmful consequences if the gas is explosive or corrosive in nature. In this paper, we take the concentration values for consideration and applying 4 machine learning techniques namely decision tree, random forest, ACF, and Naive Bayes to a concentration data of a 20-sensor network, and then the results have been compared. The experimental results show that the random forest has the best performance when compared to the other algorithms.

Optical gas imaging (OGI) is a commonly utilized leak detection method in the upstream and midstream sectors of the U.S. natural gas industry. This study characterized the detection efficacy of OGI surveyors, using their own cameras and protocols, with controlled releases in an 8-acre outdoor facility that closely resembles upstream natural gas field operations. Professional surveyors from 16 oil and gas companies and 8 regulatory agencies participated, completing 488 tests over a 10 month period. Detection rates were significantly lower than prior studies focused on camera performance. The leak size required to achieve a 90% probability-of-detection in this study is an order-of-magnitude larger than prior studies. Study results indicate that OGI survey experience significantly impacts leak detection rate: Surveyors from operators/contractors who had surveyed more than 551 sites prior to testing detected 1.7 (1.5-1.8) times more leaks than surveyors who had completed fewer surveys. Highly experienced surveyors adjust their survey speed, examine components from multiple viewpoints, and make other adjustments that improve their leak detection rate, indicating that modifications of survey protocols and targeted training could improve leak detection rates overall.

This study aims to introduce the integrated approach, namely the integration of the Faster R-CNN technique and Optical gas imaging (OGI) for real-time natural gas leak detection of offshore platforms. OGI is used to record large number of leak videos which are essential to develop the desirable Faster R-CNN model. Due to the fact that the natural gas leak incidents are rare on the offshore platforms, it is difficult to record large number of the real-world leak videos by using the OGI. This study firstly proposes the strategy to simulate the OGI by the CFD tool. The proposed strategy could generate large number of virtual infrared images. Based on the infrared images, the Faster R-CNN approach is trained and its performance is tested. A case study of deep-water drilling platform is conducted. The results demonstrate the feasibility of the proposed strategy as well as the competing performance of the Faster R-CNN approach for the real-time automatic natural gas leak detection of offshore platforms.

The main results achieved by exploiting quartz enhanced photoacoustic spectroscopy (QEPAS) sensors for real world applications will be here reviewed. The obtained results clearly demonstrate the capability of QEPAS-based sensors for in-situ and real time operations. Outdoor monitoring of a CO sensor for several days will be discussed. Results achieved by implementing an SF 6 sensor in an industrial environment for leak detection in mechatronic systems will be also described. Finally, the monitoring of CH 4 around a landfill with a QEPAS mobile system will be reported. All these achievements lead to the first commercialization of QEPAS sensing modules.

In this work, an innovative system for structural health monitoring of metallic pipes is presented. The proposed system relies on exploiting the pipeline as a waveguide for the propagation of an electromagnetic (EM) signal. By analyzing the reflected signal, it is possible to assess the possible presence of anomalies or damage in the pipe.The innovative aspect of the proposed monitoring system is that the EM test signal is injected in the pipeline/waveguide through a coaxial/waveguide transition that is made on the surface of the pipe. In practical applications, this strategy would allow to connect more easily to operating, buried pipes.To characterize the propagation of the EM signal in such conditions and to verify the changes on the reflected signal provoked by variation of the conditions of the pipe, experimental tests were carried out and a dedicated processing strategy was developed. The obtained results, although preliminary, confirmed that the proposed method holds unexplored potential to be used as a structural health monitoring solution.