A Data Driven Validation of a Defect Assessment Model and its Safe Implementation

2020 ◽  
Author(s):  
Shahani Kariyawasam ◽  
Shenwei Zhang ◽  
Jason Yan
Keyword(s):  
Data Analytics ◽  
Model Performance ◽  
Management Program ◽  
Assessment Model ◽  
Metal Loss ◽  
Good Representation ◽  
Validation Data ◽  
Corrosion Morphology ◽  
Integrity Assessment ◽  
Defect Assessment

Abstract This paper presents data analytics that demonstrates the safe implementation of defect assessment models which use uncertain measurements of defect and material properties as inputs. Even though this validation is done for a corrosion assessment model implementation, it can be generalized for any defect assessment validation where the inputs have uncertainty (as they do in implementation). The questions arising from the validation of the Plausible Profiles (Psqr) model and related review led to a large amount of data analytics to demonstrate various aspects of safety in implementation. The data analytics demonstrates how the safety of model implementation can be verified using a well-designed set of data. The validation of Psqr model was conducted on a unique set of data consisting of metal-loss corrosion clusters with Inline Inspection (ILI) reported size, laser scan-measured dimension, and well monitored burst testing pressure. Therefore, this validation provided an unprecedented set of validation data that could represent many perspectives, such as model performance (with all uncertainties associated with other parameters removed), in-the-ditch decision scenario, and ILI-based decision scenario. Moreover, the morphologies of the 30 corrosion clusters tested is a good representation of large corrosion clusters that have failed historically in the pipeline industry. One of learnings from post-ILI failures due to corrosion in the industry is that corrosion morphology played a significant role. Previous model validations were mostly performed on simple single anomalies or simple clusters with few individual corrosion anomalies. It is important that a corrosion model is validated using real corrosion morphologies that are representative of in-service conditions. The analysis of this unprecedented and comprehensive set of data led to great learning and revealed how safety can be achieved optimally with good understanding of how uncertainties associated with ILI sizing error, material property, model error, and safety factors interact and play into integrity. It also revealed the role of common misunderstandings that are barriers to effective pipeline integrity assessment. Overcoming these misunderstandings have helped in developing a more effective ILI based corrosion management program that will avoid more failures and reduce unnecessary integrity actions.

A More Accurate and Precise Method for Large Metal Loss Corrosion Assessment

2018 ◽  
Author(s):  
Shenwei Zhang ◽  
Jason Yan ◽  
Shahani Kariyawasam ◽  
Terry Huang ◽  
Mohammad Al-Amin
Keyword(s):  
Case Studies ◽  
Pressure Ratio ◽  
Field Measurements ◽  
Assessment Model ◽  
Metal Loss ◽  
Worst Case ◽  
Corrosion Morphology ◽  
Surgical Tool ◽  
Cutting Out

Pipeline integrity decisions are highly sensitive to the assessment model. A less accurate and less precise model can conservatively trigger many unnecessary actions such as excavations without providing additional safety. Therefore, a more accurate and precise model will reduce excavations and provide higher assurance of safety. This is akin to using a more precise surgical tool such as a laser for cutting out a brain tumor where you can cut closer to the edge and be assured of cutting out more of the tumor (safer) and yet cut less of the surrounding brain tissue (less conservative). This paper presents a novel model for assessing large metal-loss corrosion based on in-line inspection (ILI) or field measurement. The model described in this paper utilized an unconventional approach, namely multiple plausible profiles (P2), to idealize the shape of the corrosion, and therefore is referred to as P2 model. In contrast, all existing models use one single profile for characterizing corrosion profile, e.g. RSTRENG utilizes a single worst-case river bottom profile to characterize the shape of corrosion. The P2 model has been initially validated using fourteen (14) full scale specimen-based hydrostatic tests on pipes containing real large corrosion features. Validation results showed that the P2 model is safe, but less conservative and more precise than RSTRENG. The magnitude of reduction in conservatism depends on the corrosion morphology. On average, the P2 model achieves 15% reduction in model bias and 44% reduction in standard deviation of model error. Further validation was provided using the testing data published by PRCI and PETROBRAS. Another set of burst tests are being conducted by TransCanada as part of the continuous validation of P2 model. The effectiveness of the P2 model was demonstrated through two case studies (denoted by Case study 1 and 2). Case Study 1 included 170 external metal-loss corrosion features that were excavated from different pipeline sections, and have field-measurements using laser scan tool. Case Study 2 included 154 ILI-reported external metal-loss corrosion features with RSTRENG calculated rupture-pressure-ratio (RPR) of less than or equal to 1.25 (i.e. RPR ≤ 1.25); hence, these features were classified as immediate features. The Case Studies showed that the use of the P2 model resulted in 80% less number of ILI-reported features requiring immediate action (i.e., RPR ≤ 1.25) and 89% less number of excavated features requiring repair (e.g., sleeve or cut-out) compared to the respective number of features identified by RSTRENG-based assessment. The reduction in the number of features requiring excavation or repair is highly morphology-dependent with the highest reduction achievable for pipeline containing long and wide corrosion clusters (e.g., tape-coated pipeline). However, the P2 model is applicable to all clusters regardless of the number of individual corrosion anomalies associated with the cluster.

scholarly journals Water Quality Modelling Qual 2KW for River Tungabhadra (India).

2020 ◽  
Vol 9 (1) ◽  
pp. 461-464
Keyword(s):  
Water Quality ◽  
Monsoon Season ◽  
Industrial Effluent ◽  
Model Performance ◽  
Oxygen Demand ◽  
Simulated Data ◽  
Good Representation ◽  
Quality Model ◽  
Validation Data ◽  
Calibration And Validation

The River Tungabhadra takes its course through the Davangere district of Karnataka state of India. Along this course lies Harihar, the administrative headquarters of Harihar Taluk and other villages which are linear settlements on the bank of the River. These human settlements discharge untreated domestic waste and industrial effluent into the water as it flows. Therefore, it is imperative to study the degree of pollution of this water and ascertain its suitability for various uses. In this study, we shall make use of QUAL2Kw water quality model to predict the quality of water in the sections of the River that have been polluted. While making use of this Model, it was calibrated and validated for Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), and Total Nitrogen (TN) during the pre-monsoon season. The data derived from the field and laboratory measurements were applied for the calibration and validation. The statistical method applied for the evaluation of the model performance was Standard Errors (SE) and Mean Multiplicative Error (MME). It was found that the Model is a good representation of the field data, but there are some minor exceptions. Although there are differences between the simulated data and the one measured in some instances, the results of the calibration and validation data are still acceptable. This type of result is applicable, especially in developing nations, where there are insufficient funds for frequent monitoring campaigns or more accurate research methodologies

Plausible Profile (Psqr) Corrosion Assessment Model: Refinement, Validation and Operationalization

2020 ◽  
Author(s):  
Shenwei Zhang ◽  
Jason Yan ◽  
Shahani Kariyawasam ◽  
Terry Huang ◽  
Mohammad Al-Amin
Keyword(s):  
Oil And Gas ◽  
Effective Area ◽  
Companion Paper ◽  
Assessment Model ◽  
Metal Loss ◽  
Model Refinement ◽  
Corrosion Morphology ◽  
Internal Review ◽  
Project Outcome ◽  
Corrosion Assessment

Abstract This paper presents the refinement, validation, and operationalization of Plausible Profiles (Psqr) corrosion assessment model that TC Energy (TCE) published in IPC 2018. Metal-loss corrosion continues to be a major integrity threat to oil and gas pipelines. Inline inspection (ILI) based corrosion management, where ILI measured anomalies are assessed and mitigated, has proven to be the best way to manage corrosion. The assessment model used to estimate the burst pressure of pipelines has the most significant impact on integrity decisions. These decisions include (1) which anomalies to excavate based on In-line inspection (ILI); (2) pressure reduction (i.e. derate) required to maintain safety until repairs are completed, and (3) repair decisions during the excavation. Consequently, TCE focused on improving the shape factor of the Modified B31G effective area technique and published an overview of the improvement in IPC 2018 paper titled “A More Accurate and Precise Method for Large Metal Loss Corrosion Assessment”. From 2018 TCE refined the model using further testing, validation, internal review, and external review. In 2019, the model was reviewed by eight industry experts through Pipeline Research Council International (PRCI) project “EC-2-9 Peer Review of the Plausible Profile (Psqr) Corrosion Assessment Model”. The project outcome recommended Psqr as an improved corrosion assessment model. The comments and recommendations provided by the reviewers will be reported in IPC 2020 in a companion paper. Validation results show the Psqr model is safe, and more accurate and precise than RSTRENG. The resulting magnitude of reduction in unnecessary activities depends on the corrosion morphology.

scholarly journals Optimizing the Environmental and Economic Sustainability of Remote Community Infrastructure

2020 ◽  
Vol 12 (6) ◽  
pp. 2208 ◽  
Author(s):  
Jamie E. Filer ◽  
Justin D. Delorit ◽  
Andrew J. Hoisington ◽  
Steven J. Schuldt
Keyword(s):  
Environmental Impacts ◽  
Sustainability Assessment ◽  
Model Performance ◽  
Assessment Model ◽  
Remote Communities ◽  
Remote Community ◽  
Rural Villages ◽  
Sustainable Technologies ◽  
Study Results

Remote communities such as rural villages, post-disaster housing camps, and military forward operating bases are often located in remote and hostile areas with limited or no access to established infrastructure grids. Operating these communities with conventional assets requires constant resupply, which yields a significant logistical burden, creates negative environmental impacts, and increases costs. For example, a 2000-member isolated village in northern Canada relying on diesel generators required 8.6 million USD of fuel per year and emitted 8500 tons of carbon dioxide. Remote community planners can mitigate these negative impacts by selecting sustainable technologies that minimize resource consumption and emissions. However, the alternatives often come at a higher procurement cost and mobilization requirement. To assist planners with this challenging task, this paper presents the development of a novel infrastructure sustainability assessment model capable of generating optimal tradeoffs between minimizing environmental impacts and minimizing life-cycle costs over the community’s anticipated lifespan. Model performance was evaluated using a case study of a hypothetical 500-person remote military base with 864 feasible infrastructure portfolios and 48 procedural portfolios. The case study results demonstrated the model’s novel capability to assist planners in identifying optimal combinations of infrastructure alternatives that minimize negative sustainability impacts, leading to remote communities that are more self-sufficient with reduced emissions and costs.

MITIGATION COST AND CLIMATE DAMAGE VERSUS INCENTIVE SHIFTS OF CLIMATE COALITION

2016 ◽  
Vol 07 (04) ◽  
pp. 1650011
Author(s):  
ZILI YANG
Keyword(s):  
Climate Change ◽  
Bargaining Game ◽  
Integrated Assessment Model ◽  
Assessment Model ◽  
Policy Implications ◽  
Good Representation ◽  
Ghg Mitigation ◽  
Mitigation Cost ◽  
The Core ◽  
Cooperative Bargaining

Climate damage and greenhouse gas (GHG) mitigation cost plays important roles in a region’s willingness and incentives to join the global climate coalition. Negotiation of climate treaty can be modeled as a cooperative bargaining game of externality provision. The core of this game is a good representation of incentives of the participants. In this paper, we examine the relationship between the shocks of mitigation cost/climate damage and the shifts of the core of cooperative bargaining game of climate negotiation within the framework of RICE [Nordhaus and Yang, 1996. A regional dynamic general equilibrium model of alternative climate change strategies. American Economic Review, 86, 741–765], a widely used integrated assessment model (IAM) of climate change. Constructing a method that maps the core allocations onto a convex hull on the simplex of social welfare weights, we describe the scope of the core in simple metrics and capture the shifts of the core representation on the simplex in response to the shocks of mitigation cost and climate damage. A series of simulations are conducted in RICE to demonstrate the usefulness of the approach explored here. In addition, policy implications of methodological results are indicated.

An Innovative Approach for Pipeline Repairs

2002 ◽  
Author(s):  
Don Robertson ◽  
Wayne Russell ◽  
Nigel Alvares ◽  
Debra Carrobourg ◽  
Graeme King
Keyword(s):  
Relational Databases ◽  
Cost Effective ◽  
Metal Loss ◽  
Final Report ◽  
Integrity Assessment ◽  
Maintenance Program ◽  
Oil Pipelines ◽  
New Methodologies ◽  
Reduced Costs

A strategic combination of integrity software, relational databases, GIS, and GPS technologies reduced costs and increased quality of a comprehensive pipeline integrity assessment and repair program that Greenpipe Industries Ltd. completed recently on three crude oil pipelines—two 6-inch and one 8-inch—for Enbridge Pipelines (Saskatchewan) Inc. Greenpipe analyzed metal loss data from recent in-line inspection logs, calculated real-world coordinates of defects and reference welds, prioritized anomalies for repair taking environmental risks into account, and prepared detailed dig sheets and site maps using PipeCraft™, Greenpipe’s advanced GIS-based pipeline integrity-maintenance software package. GPS technology was used to navigate to dig sites and the accuracy of the GPS approach was compared with traditional chainage methods. Pipelines were purged and all defects were cut out and replaced by new pipe during a two-day shutdown on each pipeline. A comprehensive set of data, including high-accuracy GPS location of anomalies, reference welds, and replacement pipe welds, was collected at each dig site and entered into the PipeCraft relational database. After all repairs were completed, the client was provided with a GIS-based electronic final report, allowing point-and-click access to all data collected in the field, including in-line inspection logs, dig information sheets and as-built drawings. The new methodologies employed on this project resulted in a high quality, comprehensive and cost-effective integrity maintenance program.

scholarly journals Artificial intelligence method to classify ophthalmic emergency severity based on symptoms: a validation study

BMJ Open ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. e037161
Author(s):  
Hyunmin Ahn
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Model Performance ◽  
Armed Forces ◽  
Validation Data ◽  
Data Set ◽  
Orange Yellow ◽  
Hospital Visits ◽  
Input Variables ◽  
Fully Connected

ObjectivesWe investigated the usefulness of machine learning artificial intelligence (AI) in classifying the severity of ophthalmic emergency for timely hospital visits.Study designThis retrospective study analysed the patients who first visited the Armed Forces Daegu Hospital between May and December 2019. General patient information, events and symptoms were input variables. Events, symptoms, diagnoses and treatments were output variables. The output variables were classified into four classes (red, orange, yellow and green, indicating immediate to no emergency cases). About 200 cases of the class-balanced validation data set were randomly selected before all training procedures. An ensemble AI model using combinations of fully connected neural networks with the synthetic minority oversampling technique algorithm was adopted.ParticipantsA total of 1681 patients were included.Major outcomesModel performance was evaluated using accuracy, precision, recall and F1 scores.ResultsThe accuracy of the model was 99.05%. The precision of each class (red, orange, yellow and green) was 100%, 98.10%, 92.73% and 100%. The recalls of each class were 100%, 100%, 98.08% and 95.33%. The F1 scores of each class were 100%, 99.04%, 95.33% and 96.00%.ConclusionsWe provided support for an AI method to classify ophthalmic emergency severity based on symptoms.

scholarly journals A combined strategy of feature selection and machine learning to identify predictors of prediabetes

2019 ◽  
Vol 27 (3) ◽  
pp. 396-406 ◽  
Author(s):  
Kushan De Silva ◽  
Daniel Jönsson ◽  
Ryan T Demmer
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
National Health ◽  
Screening Tool ◽  
Model Performance ◽  
Nutrition Examination Survey ◽  
Validation Data ◽  
Internal Validation ◽  
Health And Nutrition ◽  
Wide Range

Abstract Objective To identify predictors of prediabetes using feature selection and machine learning on a nationally representative sample of the US population. Materials and Methods We analyzed n = 6346 men and women enrolled in the National Health and Nutrition Examination Survey 2013–2014. Prediabetes was defined using American Diabetes Association guidelines. The sample was randomly partitioned to training (n = 3174) and internal validation (n = 3172) sets. Feature selection algorithms were run on training data containing 156 preselected exposure variables. Four machine learning algorithms were applied on 46 exposure variables in original and resampled training datasets built using 4 resampling methods. Predictive models were tested on internal validation data (n = 3172) and external validation data (n = 3000) prepared from National Health and Nutrition Examination Survey 2011–2012. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC). Predictors were assessed by odds ratios in logistic models and variable importance in others. The Centers for Disease Control (CDC) prediabetes screening tool was the benchmark to compare model performance. Results Prediabetes prevalence was 23.43%. The CDC prediabetes screening tool produced 64.40% AUROC. Seven optimal (≥ 70% AUROC) models identified 25 predictors including 4 potentially novel associations; 20 by both logistic and other nonlinear/ensemble models and 5 solely by the latter. All optimal models outperformed the CDC prediabetes screening tool (P < 0.05). Discussion Combined use of feature selection and machine learning increased predictive performance outperforming the recommended screening tool. A range of predictors of prediabetes was identified. Conclusion This work demonstrated the value of combining feature selection with machine learning to identify a wide range of predictors that could enhance prediabetes prediction and clinical decision-making.

Evaluating evidence for alternative natural mortality and process error assumptions using a state-space, age-structured assessment model

2018 ◽  
Vol 75 (5) ◽  
pp. 691-703 ◽  
Author(s):  
Timothy J. Miller ◽  
Saang-Yoon Hyun
Keyword(s):  
State Space ◽  
Gulf Of Maine ◽  
Model Performance ◽  
Simulated Data ◽  
State Space Models ◽  
Assessment Model ◽  
Biomass Estimation ◽  
Natural Mortality ◽  
Space Age ◽  
Age Structured

State-space models explicitly separate uncertainty associated with unobserved, time-varying parameters from that which arises from sampling the population. The statistical aspects of formal state-space models are appealing and these models are becoming more widely used for assessments. However, treating natural mortality as known and constant across ages continues to be common practice. We developed a state-space, age-structured assessment model that allowed different assumptions for natural mortality and the degree of temporal stochasticity in abundance. We fit a suite of models where natural mortality was either age-invariant or an allometric function of mass and interannual transitions of abundance were deterministic or stochastic to observations on Gulf of Maine – Georges Bank Acadian redfish (Sebastes fasciatus). We found that allowing stochasticity in the interannual transition in abundance was important and estimating age-invariant natural mortality was sufficient. A simulation study showed low bias in annual biomass estimation when the estimation and simulation model matched and the Akaike imformation criterion accurately measured relative model performance, but it was important to allow simulated data sets to include the stochasticity in interannual transitions of abundance-at-age.

Probability of Exceedance (POE) Methodology for Developing Integrity Programs Based on Pipeline Operator-Specific Technical and Economic Factors

2002 ◽  
Author(s):  
Rafael G. Mora ◽  
Curtis Parker ◽  
Patrick H. Vieth ◽  
Burke Delanty
Keyword(s):  
Decision Making ◽  
Probabilistic Models ◽  
Cost Benefit Analysis ◽  
Management Program ◽  
Metal Loss ◽  
Decision Making Process ◽  
Pipeline System ◽  
Probability Of Exceedance ◽  
Integrity Verification ◽  
Inspection Data

With the availability of in-line inspection data, pipeline operators have additional information to develop the technical and economic justification for integrity verification programs (i.e. Fitness-for-Purpose) across an entire pipeline system. The Probability of Exceedance (POE) methodology described herein provides a defensible decision making process for addressing immediate corrosion threats identified through metal loss in-line inspection (ILI) and the use of sub-critical in-line inspection data to develop a long term integrity management program. In addition, this paper describes the process used to develop a Corrosion In-line Inspection POE-based Assessment for one of the systems operated by TransGas Limited (Saskatchewan, Canada). In 2001, TransGas Limited and CC Technologies undertook an integrity verification program of the Loomis to Herbert gas pipeline system to develop an appropriate scope and schedule maintenance activities along this pipeline system. This methodology customizes Probability of Exceedance (POE) results with a deterministic corrosion growth model to determine pipeline specific excavation/repair and re-inspection interval alternatives. Consequently, feature repairs can be scheduled based on severity, operational and financial conditions while maintaining safety as first priority. The merging of deterministic and probabilistic models identified the Loomis to Herbert pipeline system’s worst predicted metal loss depth and the lowest safety factor per each repair/reinspection interval alternative, which when combined with the cost/benefit analysis provided a simplified and safe decision-making process.

Sign in / Sign up

Export Citation Format

Share Document