Pipeline Leak Localization Using Pattern Recognition and a Bayes Detector

Author(s):  
Marti´n Di Blasi ◽  
Renan Martins Baptista ◽  
Carlos Muravchik

A novel leak localization method for multi section pipelines is presented. Based on normal operation flowing thermodynamic pressure drop patterns along the pipeline, the system continuously compares with the measured pressure drops, and makes a decision based on the best fit finding the section where the leak occurs. A statistical approach is used accounting for noisy measured signals. The method uses steady state fluid equations, a recursive parameter estimation algorithm, and statistical decision and pattern recognition techniques. A modification is introduced to consider the cost of making a wrong leaky section choice in terms of the excess volume spilled due to gravitational flow after pipeline shut down. This leads to a Bayesian decision scheme minimizing a risk functional. The costs are the spill volumes, obtained from dynamical simulation of the pipeline, under the various possible decision scenarios. Finally, details are given of the successful implementation of the system on a 500km long oil pipeline, and real data from a simulated leak experiment are shown.

Author(s):  
Marti´n Di Blasi ◽  
Carlos Muravchik

The use of statistical tools to improve the decision aspect of leak detection is becoming a common practice in the area of computer pipeline monitoring. Among these tools, the sequential probability ratio test is one of the most named techniques used by commercial leak detection systems [1]. This decision mechanism is based on the comparison of the estimated probabilities of leak or no leak observed from the pipeline data. This paper proposes a leak detection system that uses a simplified statistical model for the pipeline operation, allowing a simple implementation in the pipeline control system [2]. Applying linear regression to volume balance and average pipeline pressure signals, a statistically corrected volume balance signal with reduced variance is introduced. Its expected value is zero during normal operation whereas it equals the leak flow under a leak condition. Based on the corrected volume balance, differently configured sequential probability ratio tests (SPRT) to extend the dynamic range of detectable leak flow are presented. Simplified mathematical expressions are obtained for several system performance indices, such as spilled volume until detection, time to leak detection, minimum leak flow detected, etc. Theoretical results are compared with leak simulations on a real oil pipeline. A description of the system tested over a 500 km oil pipeline is included, showing some real data results.


2009 ◽  
Vol 131 (2) ◽  
Author(s):  
Martín Di Blasi ◽  
Carlos Muravchik

The use of statistical tools to improve the decision process within leak detection is becoming a common practice in the area of computer pipeline monitoring. Among these tools, the sequential probability ratio test is one of the most named techniques used by commercial leak detection systems (Zhang and Di Mauro, 1998, “Implementing a Reliable Leak Detection System on a Crude Oil Pipeline,” Advances in Pipeline Technology, Dubai, UAE). This decision mechanism is based on the comparison of the estimated probabilities of leak or no leak observed from the pipeline data. This paper proposes a leak detection system that uses a simplified statistical model for the pipeline operation, allowing a simple implementation in the pipeline control system (Di Blasi, M., 2004, “Detección y localización de fugas en sistemas de transporte de fluidos incompresibles,” MS thesis, Universidad Nacional de La Plata, Buenos Aires, Argentina). Applying real-time recursive linear regression to volume balance and average pipeline pressure signals, a statistically corrected volume balance signal with reduced variance is derived. Its average value is zero during normal operation whereas it equals the leak flow under a leak condition. Based on the corrected volume balance, differently configured sequential probability ratio tests are presented to extend the dynamic range of detectable leak flow. Simplified mathematical expressions are obtained for several system performance indices, such as spilled volume until detection, time to leak detection, minimum leak flow detected, etc. Theoretical results are compared with leak simulations on a real oil pipeline. A description of the system tested over a 500 km oil pipeline is included, showing some real data results.


Agriculture ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 208
Author(s):  
Daniel Queirós da Silva ◽  
André Silva Aguiar ◽  
Filipe Neves dos Santos ◽  
Armando Jorge Sousa ◽  
Danilo Rabino ◽  
...  

Smart and precision agriculture concepts require that the farmer measures all relevant variables in a continuous way and processes this information in order to build better prescription maps and to predict crop yield. These maps feed machinery with variable rate technology to apply the correct amount of products in the right time and place, to improve farm profitability. One of the most relevant information to estimate the farm yield is the Leaf Area Index. Traditionally, this index can be obtained from manual measurements or from aerial imagery: the former is time consuming and the latter requires the use of drones or aerial services. This work presents an optical sensing-based hardware module that can be attached to existing autonomous or guided terrestrial vehicles. During the normal operation, the module collects periodic geo-referenced monocular images and laser data. With that data a suggested processing pipeline, based on open-source software and composed by Structure from Motion, Multi-View Stereo and point cloud registration stages, can extract Leaf Area Index and other crop-related features. Additionally, in this work, a benchmark of software tools is made. The hardware module and pipeline were validated considering real data acquired in two vineyards—Portugal and Italy. A dataset with sensory data collected by the module was made publicly available. Results demonstrated that: the system provides reliable and precise data on the surrounding environment and the pipeline is capable of computing volume and occupancy area from the acquired data.


Author(s):  
Xiaozhou Wang ◽  
Xi Chen ◽  
Qihang Lin ◽  
Weidong Liu

The performance of clustering depends on an appropriately defined similarity between two items. When the similarity is measured based on human perception, human workers are often employed to estimate a similarity score between items in order to support clustering, leading to a procedure called crowdsourced clustering. Assuming a monetary reward is paid to a worker for each similarity score and assuming the similarities between pairs and workers' reliability have a large diversity, when the budget is limited, it is critical to wisely assign pairs of items to different workers to optimize the clustering result. We model this budget allocation problem as a Markov decision process where item pairs are dynamically assigned to workers based on the historical similarity scores they provided. We propose an optimistic knowledge gradient policy where the assignment of items in each stage is based on the minimum-weight K-cut defined on a similarity graph. We provide simulation studies and real data analysis to demonstrate the performance of the proposed method.


2020 ◽  
Vol 12 (18) ◽  
pp. 2923
Author(s):  
Tengfei Zhou ◽  
Xiaojun Cheng ◽  
Peng Lin ◽  
Zhenlun Wu ◽  
Ensheng Liu

Due to the existence of environmental or human factors, and because of the instrument itself, there are many uncertainties in point clouds, which directly affect the data quality and the accuracy of subsequent processing, such as point cloud segmentation, 3D modeling, etc. In this paper, to address this problem, stochastic information of point cloud coordinates is taken into account, and on the basis of the scanner observation principle within the Gauss–Helmert model, a novel general point-based self-calibration method is developed for terrestrial laser scanners, incorporating both five additional parameters and six exterior orientation parameters. For cases where the instrument accuracy is different from the nominal ones, the variance component estimation algorithm is implemented for reweighting the outliers after the residual errors of observations obtained. Considering that the proposed method essentially is a nonlinear model, the Gauss–Newton iteration method is applied to derive the solutions of additional parameters and exterior orientation parameters. We conducted experiments using simulated and real data and compared them with those two existing methods. The experimental results showed that the proposed method could improve the point accuracy from 10−4 to 10−8 (a priori known) and 10−7 (a priori unknown), and reduced the correlation among the parameters (approximately 60% of volume). However, it is undeniable that some correlations increased instead, which is the limitation of the general method.


Electronics ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 199 ◽  
Author(s):  
Kanwar Bharat Singh

Information about the vehicle sideslip angle is crucial for the successful implementation of advanced stability control systems. In production vehicles, sideslip angle is difficult to measure within the desired accuracy level because of high costs and other associated impracticalities. This paper presents a novel framework for estimation of the vehicle sideslip angle. The proposed algorithm utilizes an adaptive tire model in conjunction with a model-based observer. The proposed adaptive tire model is capable of coping with changes to the tire operating conditions. More specifically, extensions have been made to Pacejka's Magic Formula expressions for the tire cornering stiffness and peak grip level. These model extensions account for variations in the tire inflation pressure, load, tread depth and temperature. The vehicle sideslip estimation algorithm is evaluated through experimental tests done on a rear wheel drive (RWD) vehicle. Detailed experimental results show that the developed system can reliably estimate the vehicle sideslip angle during both steady state and transient maneuvers.


1992 ◽  
Vol 36 (15) ◽  
pp. 1143-1147
Author(s):  
John D. Lee ◽  
Neville Moray

Although technological innovations have changed the role of operators from active participants to supervisors of semiautomatic processes, an understanding of the cognitive demands of supervisory control has not kept pace. In particular, little is known about when, and how well, operators might intervene and switch control from automatic to manual. This research addresses this issue by monitoring the information use and control actions of operators of a simulated semiautomatic pasteurization plant. The results of this experiment shows that individual differences in operators” monitoring patterns during the normal operation of the plant correspond to differences in their ability to mitigate the effects of faults. Specifically, an operator who controls the plant well during both normal and fault conditions tends to observe the plant frequently, integrating control actions with other control actions, and does not fixate on narrow sub-systems of the plant. On the other hand, an operator who performs poorly when exposed to faults tends to observe the plant less often, fails to integrate control actions, and fixates attention on a narrow subset of plant variables. Although all operators interacted with the plant using the same interface and automation, large individual differences in the operators” monitoring patterns, and the associated differences in performance suggest that individuals” attitudes, motivation, and training may play a critical role in the successful implementation of automation.


Author(s):  
Aline Figueiredo ◽  
Carina N. Sondermann ◽  
Rodrigo A. C. Patricio ◽  
Raphael Viggiano ◽  
Gustavo C. R. Bodstein ◽  
...  

In the oil industry liquid pipelines are very important for the transport of liquids, particularly in long offshore pipelines. The operation of these oil pipelines is susceptible to the occurrence of leaks in the system. Localizing a leak in a very long oil pipeline is an important piece of information that needs to be obtained before mitigating actions can be taken. These pipelines are usually subject to the temperature gradients that exist in the bottom of the ocean, and the resulting heat transfer process may lead to wax formation and deposition. The single-phase flow that occurs in this type of offshore pipeline that presents one leak point and suffers the effects of an external temperature gradient is numerically simulated in this paper. We consider a one-dimensional mathematical model that includes conservation equations of mass, momentum and energy, and its associated numerical method to calculate the transient liquid flow inside the pipeline. We are particularly interested in testing a leak localization model based upon the intersection of the hydraulic grade lines emanating from the pipeline ends under the influence of a non-zero temperature distribution. This paper proposes to compare the results for a non-isothermal flow with the corresponding isothermal flow to study the influence of the temperature distribution upon the leak localization strategy. The flow that develops along the entire pipeline, upstream and downstream of the leak, strongly affects the pressure gradient and has a significant influence on the location of the leak. Our numerical simulations show results that allow the model sensitivity to be studied by changing the leak magnitude, for a given leak position. From this analysis, we may observe how these parameters affect the pressure gradients along the pipeline that develop upstream and downstream of the leak and the model’s ability to predict the leak location.


2013 ◽  
Vol 401-403 ◽  
pp. 891-894 ◽  
Author(s):  
Qing Lin Cheng ◽  
Xu Xu Wang ◽  
Xian Li Li ◽  
Wei Sun ◽  
Ling De Meng

In waxy crude oil transportation process, wax crystals start to precipitate as the oil temperature drops to wax appearance point, and then form a network structure gradually which attaches to the wall. The problem of wax deposition seriously affects the normal operation of pipeline. Based on the wax deposition tendency coefficient method, combined with experimental data, the parameters related to wax deposition tendency coefficient is fitted, and the wax deposition rate equation of crude oil is determined finally. The variation law of wax deposition rate along the pipeline is analyzed, and the influence of different seasons and different throughput the on wax deposition rate is discussed subsequently.


Author(s):  
William Chien ◽  
Josenor De Jesus ◽  
Ben Taylor ◽  
Victor Dods ◽  
Leo Alekseyev ◽  
...  

Purpose: As part of the FDA’s DSCSA Pilot Project Program, UCLA and its solution partner, LedgerDomain (collectively referred to as the team hereafter), focused on building a complete, working blockchain-based system, BRUINchain, which would meet all the key objectives of the Drug Supply Chain Security Act (DSCSA) for a dispenser operating solely on commercial off-the-shelf (COTS) technology. Methods: The BRUINchain system requirements include scanning the drug package for a correctly formatted 2D barcode, flagging expired product, verifying the product with the manufacturer, and quarantining suspect and illegitimate products at the last mile: pharmacist to patient, the most complex area of the drug supply chain. The authors demonstrate a successful implementation where product-tracing notifications are sent automatically to key stakeholders, resulting in enhanced timeliness and reduction in paperwork burden. At the core of this effort was a blockchain-based solution to track and trace changes in custody of drug. As an immutable, time-stamped, near-real-time (50-millisecond latency), auditable record of transactions, BRUINchain makes it possible for supply chain communities to arrive at a single version of the truth. BRUINchain was tested with real data on real caregivers administering life-saving medications to real patients at one of the busiest pharmacies in the United States. Results: In addition to communicating with the manufacturer directly for verification, BRUINchain also initiated suspect product notifications. During the study, a 100% success rate was observed across scanning, expiration detection, and counterfeit detection; and paperwork reduction from approximately 1 hour to less than a minute. The authors demonstrate a successful implementation where product-tracing notifications are sent automatically to key stakeholders, resulting in enhanced timeliness and reduction in paperwork burden. At the core of this effort was a blockchain-based solution to track and trace changes in custody of drug. As an immutable, time-stamped, near-real-time (50-millisecond latency), auditable record of transactions, BRUINchain makes it possible for supply chain communities to arrive at a single version of the truth. BRUINchain was tested with real data on real caregivers administering life-saving medications to real patients at one of the busiest pharmacies in the United States.   Conclusions: By automatically interrogating the manufacturer’s relational database with our blockchain-based system, our results indicate a projected DSCSA compliance cost of 17 cents per unit, and potentially much more depending on regulatory interpretation and speed of verification. We project that this cost could be reduced with manufacturers’ adoption of a highly performant, fully automated end-to-end system based on digital ledger technology (DLT). In an examination of the interoperability of such a system, we elaborate on its capacity to enable verification in real time without a human in the loop, the key feature driving lower compliance cost. With 4.2 billion prescriptions being dispensed each year in the United States, DLT would not only reduce the projected per-unit cost to 13 cents per unit (saving $183 million in annual labor costs), but also serve as a major bulwark against bad or fraudulent transactions, reduce the need for safety stock, and enhance the detection and removal of potentially dangerous drugs from the drug supply chain to protect U.S. consumers.


Sign in / Sign up

Export Citation Format

Share Document