Volume 1: Pipeline and Facilities Integrity最新文献

{"title":"Managing the Threat of Selective Seam Weld Corrosion Using a State of the Art ILI System","authors":"Christopher Davies, S. Slater, Christoper De Leon","doi":"10.1115/IPC2020-9465","DOIUrl":"https://doi.org/10.1115/IPC2020-9465","url":null,"abstract":"For many years, pipeline safety regulations in the US have defined prescriptive minimum requirements for integrity management combined with a clear expectation that operators should do more than the minimum where appropriate. The regulations have also provided operators with the flexibility to take a performance based integrity management approach leveraging as much information available to manage threats effectively. One the threats that must be managed is Selective Seam Weld Corrosion (SSWC). SSWC is an environmentally assisted mechanism in which there is increased degree of metal loss in the longitudinal weld in comparison to the surrounding pipe body. An appropriate definition is linear corrosion that is deeper in the longitudinal weld zone than the surrounding pipe body. In some cases, the surrounding pipe body may have limited or no corrosion present, and in other cases the pipe body corrosion may have occurred but at a slower rate than the local corrosion in the longitudinal weld zone. Conventional responses to potential or identified threats focus on in-situ investigations, often resulting in expensive and un-planned repairs for features reported by In-line Inspection (ILI) that when assessed properly demonstrate a remnant life well into the next inspection interval. When ILI identifies metal loss indications co-located with the longitudinal seam weld, the current prescribed response is often a blanket call for remediation. Such a response may not be appropriate if an ILI system is deployed to discriminate feature types and integrity assessment is exercised leveraging a sound understanding of the pipe’s material properties. This paper describes an approach that can be taken to manage the threat of SSWC. The foundation of the approach is deployment of an appropriate ILI system incorporating an effective ILI technology, an optimized evaluation process considering the specific threat morphology, material testing and a structured dig program. The evaluation process uses the ILI data and data from the field in combination material properties data and a susceptibility analysis to classify anomalies as “Likely”, “Possible” and “Unlikely” SSWC. This is aligned with the guidance in API RP 1176 “Assessment and Management of Cracking in Pipelines” for defining an appropriate response to ILI calls. Approaching the management of SSWC in this way allows operators to define a structured response for excavation activities to verify the process and remediate features as required. By using likelihood classification the risk to pipeline integrity can be reduced by acting on the most likely SSWC features as a priority, whilst collecting the data needed to make informed decisions on where to focus resources and efforts on what is a very complicated and difficult to manage threat. The output form this work, including a future plan for managing the remaining metal loss features, can be documented in a procedure and incorporated into an existing Integrity Manage","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130193536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integration of Multiple ILI Technologies for Robust Understanding of Unique Anomalies on a Pipeline","authors":"T. Shie, A. Lutz, P. Taverna","doi":"10.1115/IPC2020-9548","DOIUrl":"https://doi.org/10.1115/IPC2020-9548","url":null,"abstract":"\u0000 Pipeline operators have many choices when selecting inline inspection (ILI) vendors and technologies. No single technology has a one hundred percent probability of detection, identification, and sizing for all anomaly types. Operators must match the threats on their system to the existing capabilities of the ILI technologies to achieve the goals defined by the company’s integrity management program. It is sometimes necessary to run multiple technologies to effectively assess all threats in a pipeline. Multiple technologies may be run during the same timeframe or they may be run at different times during the life of the pipeline to meet program goals.\u0000 Shell Pipeline Company, LP (SPLC) has a pipeline that is comprised of low frequency electric resistance welded (LFERW) pipe from Youngstown Sheet and Tube, seamless pipe from National Tube, double submerged arc welded (DSAW) pipe from Kaiser, and high frequency electric resistance welded (HF-ERW) pipe. The LF-ERW pipe was installed in 1948 while the HF-ERW was installed during relatively recent replacement projects. The DSAW pipe was installed in 1952 with the seamless pipe being installed in both 1948 and 1952.\u0000 From 2015 through 2018, SPLC executed an extensive integrity management program. This included: an axial magnetic flux leakage (AMFL) inspection, two circumferential magnetic flux leakage (CMFL) inspections, two deformation inspections, an electro-magnetic acoustic transducer (EMAT) inspection, an ultrasonic crack detection (UTCD) inspection, an ultrasonic wall measurement (UTWM) inspection, and a hydrotest. A dig campaign of nearly 100 excavations was completed as a result of these surveys. One of the focuses of the paper will be the comparison of EMAT to UTCD for Likely Cracks, Possible Cracks and Unlikely Cracks that have been field verified.\u0000 This paper also shares some of the unique anomalies found through the dig campaign identifying the effectiveness of each technology and their combination for integrity purposes. The paper shows the benefits of combining ILI technologies to properly characterize, assess and mitigate reported anomalies and ensure there are no blind spots in the integrity management program. Case studies including dent with gouge (e.g. AMFL + Deformation), manufacturing, and cracking anomalies as well as the analytics of ILI versus field findings are presented and discussed in the paper. The paper concludes with the knowledge creation resulting from multiple ILI technology integration assisted with subject matter expert experience and analytics to provide a robust understanding of unique anomalies in pipelines.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125798911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pipe Knocked From Supports by Hydraulic Transient Event","authors":"L. Matta, Jacob Manuel, S. Ramamoorthy","doi":"10.1115/IPC2020-9464","DOIUrl":"https://doi.org/10.1115/IPC2020-9464","url":null,"abstract":"\u0000 Following what was considered a routine realignment of liquid product lines and tankage at a storage and transfer facility, an incident occurred that resulted in significant movement of a 20-inch pipeline, causing a large section of it to fall from its supports. The event also resulted in the failure of a gasket at a valve flange and loss of containment.\u0000 The alignment activities and pump startup were investigated for the potential to generate a hydraulic transient capable of generating sufficient force to cause the movement. A transient hydraulic model of the fluid in the piping as it was aligned at the time of the event was generated to assist in determining the cause and to help prevent a similar occurrence in the future. Several scenarios were modeled and are discussed in this paper: 1) pump shutdown from steady flow, 2) pump start up with the discharge valve open, 3) pump startup with the discharge valve closed, and 4) pump start up with a vapor cavity present near a closed valve at the high point in the line.\u0000 Pipe stress and finite element analysis were used to assess the displaced pipe and to determine if it could be placed back into service. The piping stress analysis indicated that the highest stress in the piping was below the yield stress of the material. Results from a detailed finite element analysis with material nonlinearity confirmed that there was no global plastic strain in the piping due to the event. This left a potential for local plastic strain due to the impact of the pipe against any hard surfaces, and this was addressed with visual examination. In the end, the pipe was lifted back onto the supports, lateral restraints were added at pipe support locations, and procedural changes were implemented to reduce the likelihood of future events.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121533015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing the Management of Excavation and Repair Data From Inline Inspection Programs","authors":"M. Safari, D. Shaw","doi":"10.1115/IPC2020-9683","DOIUrl":"https://doi.org/10.1115/IPC2020-9683","url":null,"abstract":"\u0000 As integrity programs mature over the life of a pipeline, an increasing number of data points are collected from second, third, or further condition monitoring cycles. Types of data include Inline Inspection (ILI) or External Corrosion Direct Assessment (ECDA) inspection data, validation or remediation dig information, and records of various repairs that have been completed on the pipeline system. The diversity and massive quantity of this gathered data proposes a challenge to pipeline operators in managing and maintaining these data sets and records.\u0000 The management of integrity data is a key element to a pipeline system Integrity Management Program (IMP) as per the CSA Z662[1]. One of the most critical integrity datasets is the repair information. Incorrect repair assignments on a pipeline can lead to duplicate unnecessary excavations in the best scenario and a pipeline failure in the worst scenario. Operators rely on various approaches to manage and assign repair data to ILIs such as historical records reviews, ILI-based repair assignments, or chainage-based repair assignments. However, these methods have significant gaps in efficiency and/or accuracy. Failure to adequately manage excavation and repair data can lead to increased costs due to repeated excavation of an anomaly, an increase in resources required to match historical information with new data, uncertainty in the effectiveness of previous repairs, and the possibility of incorrect assignment of repairs to unrepaired features.\u0000 This paper describes the approach adopted by Enbridge Gas to track and maintain repairs, as a part of the Pipeline Risk and Integrity Management (PRIM) platform. This approach was designed to create a robust excavation and repair management framework, providing a robust system of data gathering and automation, while ensuring sufficient oversight by Integrity Engineers. Using this system, repairs are assigned to each feature in an excavation, not only to a certain chainage along the pipeline. Subsequently, when a new ILI results report is received, a process of “Repair Matching” is completed to assign preexisting repairs and assessments to the newly reported features at a feature level. This process is partially automated, whereby pre-determined box-to-box features matched between ILIs can auto-populate repairs for many of the repaired features.\u0000 The proposed excavation management system would provide operators a superior approach to managing their repair history and projecting historical repairs and assessments onto new ILI reports, prior to assessing the ILI and issuing further digs on the pipeline. This optimized method has many advantages over the conventional repair management methods used in the industry. This method is best suited for operators that are embarking on their second or third condition monitoring cycle, with a moderate number of historical repairs.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131107360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Getting to Know Your Bends to Support SCC Management","authors":"C. Wood, Fernando Merotto, Brian Kerrigan, Ramon Loback, P. Géa","doi":"10.1115/IPC2020-9578","DOIUrl":"https://doi.org/10.1115/IPC2020-9578","url":null,"abstract":"\u0000 Nova Transportadora do Sudeste (NTS) own and operate a gas transmission system in Brazil constructed in 1996. One of the confirmed primary integrity threats to this system is axial stress corrosion cracking. The pipelines vary in diameter, weld type, manufacturer and age. One of the pipelines failed in 2015 due to an axial stress corrosion crack. Since the failure, NTS have executed an intense inspection campaign to detect and size axial cracking within their network.\u0000 The 2015 failure occurred on a field bend. The inspection campaign and following dig campaign has confirmed that cracking (both axial and circumferential) within field bends is the primary integrity threat. Brazil has a challenging terrain and approximately 40% of joints within the network were subject to cold field bending. The influences of the pipeline geometry within these areas have resulted in localised elevated stresses where the axial stress corrosion cracking colonies are initiating and growing. To date, no cracking (axial or circumferential) has been verified within their straight pipe joints.\u0000 NTS initially took a conservative baseline assessment approach using API 579 Part 9, due to the limited information regarding the pipe material and complex stress state. In addition to the hoop stress from internal pressure, the baseline assessment also considered weld residual stress and bending stress due to ovalization to determine immediate and future integrity.\u0000 An intensive dig campaign is underway following a crack detection in-line inspection campaign using electromagnetic acoustic transducer technology. A large number of deep cracks were reported by the in-line inspection system, these were verified to be deep and repaired with a type B sleeve. However, at one site an entire joint was removed for further analysis, to investigate the crack morphology, confirm material properties and refine the predictive failure pressure modelling.\u0000 This paper outlines how NTS have combined a burst test, mechanical testing, FEA modelling, fractography and metallographic examination to further understand the feature morphology and stresses within these areas and how they have been able to reduce conservatism from their baseline assessment with confidence and adopt a plastic collapse approach to accurately predict failure.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134471796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing Soil Corrosivity for Buried Structural Steel","authors":"Y. Beauregard, Andrea Mah","doi":"10.1115/IPC2020-9285","DOIUrl":"https://doi.org/10.1115/IPC2020-9285","url":null,"abstract":"\u0000 Corrosion of steel structures in soils has been a topic of industrial research for many decades. The research has shown that the corrosivity of a soil is highly variable and a function of numerous interconnected parameters including soil resistivity, moisture content and pH. Despite the complexity of the soil environment, methods to evaluate soil corrosivity, guidelines for corrosion control during the design phase and lifetime of a structure have been developed. By applying this understanding, an opportunity exists to optimize the corrosion protection and capital expenses for new projects associated with corrosion protection of buried structural steel components. For instance, for new projects, e.g., identifying regions of low corrosivity where coatings are not required could lead to cost savings without compromising the integrity of the structure. However, within the industry, there is no universally accepted method to guide such decisions.\u0000 This paper is intended to address this issue by presenting a literature review and a case study on the topic. The literature review identifies the factors that influence the corrosion of buried steel structures, the range of corrosion rates observed on buried steel structures and quantitative and qualitative methods for assessing soil corrosivity. In the desktop case study, industry standards identified during the literature review (AASHTO R27-01, DIN50929-3:2018, ANSI/AWWA C105/A21.5 and Eurocode 3-5) are applied to applied to evaluate the soil corrosivity at three meter station sites in Alberta. The results are compared and recommendations for implementation are discussed. DIN 50929-3 stands out among the standards as it provides conservative estimates based on the most comprehensive data set and unlike the other standards, it assesses soil corrosivity both qualitatively and quantitatively.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133789054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved Surface Loading Stress Analysis Method Considering Protection Measures","authors":"Shenwei Zhang, Ke Zhang, Maria Pino, Jonathan Law, Tammie Matchim","doi":"10.1115/IPC2020-9478","DOIUrl":"https://doi.org/10.1115/IPC2020-9478","url":null,"abstract":"\u0000 This paper presents a methodology to evaluate pipe stress induced by surface vehicle loading at uncased road crossings that are protected by mat or bridging. When vehicles cross an existing pipeline, additional circumferential and longitudinal pipe stresses induced by surface vehicle loadings should be comprehensively considered to ensure pipe integrity and safe operation. Surface protection measures are sometimes installed to distribute the surface loading away from pipe centerline and reduce “footprint pressure”. A modified CEPA equation was proposed to calculate the radius of relative stiffness (or effective length) of mat and was validated by comparing with results from continuum FEA. The effective length calculated by the modified equation demonstrates good consistency with the FEA-predicted effective length. An approach was proposed to evaluate the pipe stress with user-defined free span of bridging, which provide flexibility for optimizing bridging protection in the field. A tool was developed to facilitate the assessment of surface loading stress of pipeline with mat or bridging protection.\u0000 Case studies were presented to demonstrate the application of the proposed methods and the effect of mat thickness or bridging free span on the reduction of live load stress. The proposed methods will benefit pipeline operators with derived cost-effective protection measures for vehicle crossing while assuring safety of pipeline operation.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122343426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Crack Driving Force Calculation in Arbitrarily Shaped Defects Based on 3D Non-Destructive Evaluation and Finite Element Analysis","authors":"S. Hertelé, Vitor Adriano, Somsubhro Chaudhuri, L. D. Wilde, O. Huising","doi":"10.1115/IPC2020-9357","DOIUrl":"https://doi.org/10.1115/IPC2020-9357","url":null,"abstract":"\u0000 The actual shape of a real defect differs from the simplified shapes that are assumed within an engineering critical assessment. Additionally, the re-characterization of interacting defects into one simplified defect is known to introduce conservatism, which may be undesirably large. Ongoing and expected technological advances of 3D NDE techniques (such as full-matrix capture ultrasonics and X-ray CT) allow to assume that defect simplification will no longer be required in the future, thus bypassing the uncontrolled conservatism resulting from defect simplification. A recently finished EPRG project has shown the feasibility of integrating the information provided by 3D NDE systems into finite element models. Promising results are obtained which, with additional effort, will provide a solid basis for in-the-field application.\u0000 This paper first reports on the overall procedure of defect assessment by the adopted finite element analysis (both linearelastic and elastic-plastic). Next, the ability to couple FE model construction with non-destructive evaluation results is demonstrated for three scans obtained from different sources (one X-ray CT and two ultrasonic full matrix capture scans). Finally, concrete opportunities to improve the robustness, speed and accuracy of the methodology are addressed, which will be tackled in a follow-up project funded within PRCI.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126578375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Puddling Puddle Welds","authors":"Dane Burden, Nic Roniger, Matthew Romney","doi":"10.1115/IPC2020-9476","DOIUrl":"https://doi.org/10.1115/IPC2020-9476","url":null,"abstract":"\u0000 Unique characteristics of individual pipelines come from over a century of evolving design, construction, maintenance, regulation and operation. These characteristics are especially true for legacy, pre-regulated pipelines. Due to the unique nature of the threats present on these assets, there is a need for unique inspection technologies and techniques that can increase pipeline integrity. Reconditioned and repaired pipe utilizing puddle weld repairs is one such threat.\u0000 An advanced analysis was completed on a 10-inch, 68-mile light products pipeline. The pipeline was constructed with reconditioned pipe that was estimated to contain tens of thousands of puddle welds. Historical in-line inspection (ILI) data generally underperformed in classifying and discriminating puddle welds versus metal loss features.\u0000 The primary objective of this project was to assess the probability of identification (POI) of a multiple dataset ILI tool utilizing multiple magnetic flux leakage (MFL) magnetization directions and residual (RES) magnetization measurements. A secondary objective was to scrutinize data for signs of coincident features. Hydrostatic testing failures showed that puddle welds with porosity and cracking were susceptible to failure and that the identification of these features would be beneficial.\u0000 Analysis of historical puddle weld investigations and newly completed multiple dataset ILI data revealed strong identification capabilities in the RES dataset. The high-field magnetizations offered secondary confirmation but often saturated out thermal effects or material differences. The final report included over 40,000 identified puddle welds and five classifications for further investigation. Field investigations for 212 features were completed and the results compared to the ILI data to assess performance. A confusion matrix was created for true positive (TP), true negative (TN), false positive (FP) and false negative (FN) conditions. The smallest TP puddle weld dimension was 0.7″ × 0.7″, and the population had a statistical sensitivity value of 98% (132 TP and 3 FP).\u0000 Three additional anomalies denoted as atypical were also investigated. The ILI signatures at these locations were consistent with previous repairs in which puddle welds with cracking were found and repaired. Two of the three features investigated were found to have cracking. Crack propagation was found to be both axial and non-axial in orientation. The results show that puddle welds can be detected and identified with extremely high accuracy. In addition, the preliminary classification results for atypical puddle welds show a high potential for identifying secondary coincident features. This paper details the stages, deliverables and results from an ILI advanced analysis focused on puddle welds.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"15 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132931350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Feature-Specific Probabilistic Assessment of Pipeline Defect Size From ILI MFL Signal Using Convolutional Neural Network","authors":"Jenny Chen, S. Westwood, David Heaney","doi":"10.1115/IPC2020-9331","DOIUrl":"https://doi.org/10.1115/IPC2020-9331","url":null,"abstract":"\u0000 When estimating pipeline burst pressure, one of the prevalent sources of uncertainty that needs to be factored into the calculation is the model error in the estimation of feature depth and length from the in-line inspection tool. Due to modeling technique limitation, as of today many ILI vendors have feature specific error bounds depending on the morphologies of the corrosion, this error can only be reported to operators as an overall error known as the ILI tool tolerance which is usually obtained from samples of excavation data or pull test data. At the most, the error is reported by classes based on corrosion morphologies specified by Pipeline Operators Forum. For example, a commonly reported corrosion depth sizing specification is ±10% of pipe wall thickness at 80% confidence for the General type of corrosion. This can be interpreted as that the error of each reported depth estimations is assumed to fall in a normal distribution with a mean equal to 0 and standard deviation equal to 7.8% of wall thickness. The shape of the distribution, the mean and standard deviation will then be used as constants to factor in the burst pressure calculation.\u0000 However, these factors are never constant for a sample of defects in reality. In fact, they ought to be variables on an individual feature basis. An example of such an approach would be a feature specific error tolerance, this could be that the estimated depth of a feature is 36%wt in an interval of [30%, 48%] of wall thickness with 80% confidence. This is believed to greatly reduce the level of uncertainty when it comes to failure pressure estimation or other type of pipeline risk assessment. The advancement in Machine Learning today, deep learning with deep neural networks, allows feature-specific error tolerance to be obtained after analyzing visual imagery of MFL signal. In this paper we will describe a novel approach to predict the size of metal loss defects and more importantly the distribution associated with each prediction. We will then discuss the benefits of this approach has with respect to risk assessment such as failure pressure estimation.","PeriodicalId":273758,"journal":{"name":"Volume 1: Pipeline and Facilities Integrity","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125685938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}