AMPP Store - Products tagged with 'machine learning'

Available for download

51318-11233-Cyclic Oxidation Behavior of Ni-Cr Alloys in Wet Air

Product Number: 51318-11233-SG

Author: Jiheon Jun / Dongwon Shin / Sebastien Dryepondt, / J. Allen Haynes / Bruce A. Pint

Publication Date: 2018

$20.00

Both commercial and model Ni-based alloys were tested in 1-h cycles at 800-950°C in wet air, and the oxide scales formed on wrought Ni-(14-25)wt%Cr binary alloys were characterized.

Available for download

A Prediction of Corrosion-related Leakage on Distribution Pipelines via Machine Learning Method

Product Number: 51323-18972-SG

Author: Zhuoran Zhang, Guanlan Liu

Publication Date: 2023

$20.00

In the United States, there are fuel pipelines spanning more than 2.6 million miles. A major portion of the pipelines is gas distribution lines, where the product is delivered from the pressure regulating station to the customer’s home or facility. The Pipeline and Hazardous Materials and Safety Administration (PHMSA) finalized rules for Distribution Integrity Management Program (DIMP) plans in 2009, enforcing the distribution pipeline operators to assess, report, and manage the risk associated with the pipeline operation. Corrosion threat is one major threat to the pipeline operation and integrity based on CFR 192, CFR 195 and ASME B31.82. A comprehensive understanding and assessment of corrosion risk are indispensable for a safer pipeline operation. This demands a more precise understanding, prediction, and management of the pipeline corrosion

Available for download

Analysis and Monitoring of Welded Carbon Steel Corrosion in Aqueous Solutions Using Electrochemical Noise and Wavelet Analysis

Product Number: 51324-21243-SG

Author: Ahmed Abdulmutaali; Katerina Lepkova; Chris Aldrich

Publication Date: 2024

$40.00

The corrosion of welded carbon steel in the presence of aqueous chloride-containing solutions at 30 °C was analyzed by use of electrochemical noise (EN) and wavelet transform analysis (WTA) in three different solution systems. It is shown that features extracted from sections of the EN signals imaged by way of wavelet scalograms could be used to identify different types of corrosion, as well as for online monitoring of corrosion. Moreover, the corroded welded steel surfaces were examined using 3D profilometry to gather information about localized defects (pits). These results demonstrated that electrochemical noise associated with wavelet transform analysis, particularly wavelet scalograms, is an effective tool for monitoring localized corrosion of welded carbon steel.

Available for download

Application of Artificial Intelligence in Corrosion Management

Product Number: 51324-20711-SG

Author: Mohd Aswadi Ton Alias; Nurul Asni Mohamed; M Iskandar Bakeri; Izzatdin A Aziz; M Hilmi Hasan

Publication Date: 2024

$40.00

Corrosion management system encompassing the various stages of an asset life starting from design, construction, through to operation and decommissioning remains the key focus in ensuring integrity and safe operation of the asset. Corrosion study is conducted during the initial design phase, followed by multiple reviews during the operational stage as part of the overall corrosion management process. These studies aim to identify all damage mechanisms that can be present, including both non-age-related and age-related mechanisms. Currently in the oil and gas industry, corrosion rate predictions for age-related mechanisms are generated via mathematical equations or correlations as outcome from laboratory testing and analyses which may not be representative of the actual operating condition. These predictions impose limitations with regards to utilizing inputs produced from big data. Application of artificial intelligence to predict corrosion rate offers advantages where real high frequency data streams from IoT sensors are analyzed via machine learning algorithm thus providing prediction based on historical experience of specific asset. Data preprocessing is an important step in machine learning that involves transforming raw data from various parameters so that issues owing to the incompleteness, inconsistency, and/or lack of appropriate representation of trends are resolved to arrive at a data set that is in an understandable format. Feature engineering will then be performed which analyze the parameter correlation to obtain the most suitable combination and the best features and data characteristics. For corrosion rate prediction, the supervised learning algorithm is applicable such as logistic regression, naive bayes, support vector machines, artificial neural networks, and random forests. The final step of the machine learning modelling is the model validation. The predicted corrosion rates will be verified with actual thickness measurement at site. To date, we have covered 30 process units which includes different trains, 120 corrosion groups selected from a total of about 3800 corrosion groups for the whole facility. 700 customized machine learning models were developed. Success is defined by best highest accuracy (>80%) with an optimum model run time. Recent validation has shown the ability to predict an anomaly in future trend which coincides with actual increase in corrosion rate.

Available for download

Applying Machine Learning Techniques To Identify And Predict Behavior Of Rectifier And Groundbed State Change

Product Number: 51322-17833-SG

Author: Matt Barrett, Will Maize, Tony da Costa

Publication Date: 2022

$20.00

Impressed current rectifiers are the backbone of a pipeline operator’s cathodic protection (CP) systems. A rectifier’s ability to protect a large length of electrically continuous pipeline considerably improves efficiencies and reduces material costs as compared to galvanic systems. However, like galvanic anodes, impressed current anodes are a consumable asset, and require replacement at the end of their service life to ensure that the rectifier can continue to adequately protect the pipeline.

Available for download

Combination Of High Ph SCC And Near Neutral Ph SCC Models Using Bayesian Networks

Product Number: 51322-17851-SG

Author: Francois Ayello, Guanlan Liu, Narasi Sridhar, Ramgopal Thodla

Publication Date: 2022

$20.00

Environmentally Assisted Cracking (EAC) of gas transmission lines constitute about 2.6% of the total number of significant incidents recorded in the U.S. Pipeline and Hazardous Materials Administration (PHMSA) database [1]. For the hydrocarbon liquid pipelines, the EAC-related incidents constitute about 1%. Although Stress Corrosion Cracking (SCC) incidents are a relatively small percentage of significant incidents, it is important to predict the location and rate of growth of SCC because of the potential for catastrophic consequences from the growth of undetected cracks.

Available for download

Corrosion and Risk Modelling Analytics

Product Number: 51324-20833-SG

Author: B. R. Shivadhanush; N. J. Laycock; M. Geeta; F. Samie; P. Panchami

Publication Date: 2024

$40.00

The CARMA (Corrosion and Risk Modelling Analytics) project aims to provide improved corrosion prediction capability by using Machine Learning techniques. For the selected system, the initial CARMA model is trained by using a combination of online process monitoring data as the input, combined with online corrosion monitoring data as the output. Once trained and validated, the resulting model can then be used to predict corrosion rates in similar systems or in other parts of the same system, without the need to install corrosion monitoring devices or carry out routine physical inspections at the same frequency as in the past. This paper provides an overview of the model development process for one example system, incorporating data from both online monitoring in the plant and from laboratory experiments.

Available for download

Corrosion Risk Prediction Based On Offshore Pipeline Service Database And Machine Learning

Product Number: 51322-17711-SG

Author: Zhihao Qu, Xiaoqi Yue, Yi Li, Xiaqiao Li, Lihua Hu, Yue Ren, Yao Lv, Lei Zhang

Publication Date: 2022

$20.00

Pipelines have been the main transportation pattern of oil and gas because of their safety and economy, which are considered as the lifeline of offshore oil and gas transportation. With the booming development of offshore oil industry, the frequency of pipeline leakage is also increasing. Corrosion is one of the important factors due to some characteristics such as operating environment, service life and transportation medium, etc., which damages the integrity of the pipeline and damage the normal operation of pipelines. Furthermore, leakage accidents caused by pipeline corrosion have occurred all over the world, accounting for 70~90% of total accidents, which has caused huge economy losses and catastrophic environmental damage.

Available for download

Data-Driven Machine Learning Techniques Case Study for Corrosion Depth Prediction in Facilities Station Piping

Product Number: 51323-18927-SG

Author: Kane Kaiqi Cheng, Michael Snow

Publication Date: 2023

$20.00

The pipeline industry has widely used integrity principles to manage time-dependent and time-independent threats. The detection of time-dependent threats such as corrosion has been accomplished by using inline inspection tool technologies such as ultrasonic and magnetic flux leak inspection tools. However, most facility piping assets can not easily be inspected using in-line inspection methods and must instead be assessed using data collected from operations, such as flow frequency, product type, Cathodic protection record, or Direct Assessment Methods using Non Destructive Testing such as ultrasonic measurements or monitoring of corrosion coupons.

Available for download

Datascience To Enhance Pipeline Maintenance

Product Number: 51322-17508-SG

Author: David Toschini, Markéta Lallementová, Anthony Dequick, Bernard Masson, Thomas Zamojski

Publication Date: 2022

$20.00

The paper will cover the construction method (based on Random forest algorithms), the first results. We will see the enhancements of the model by injecting more data and modifying mathematical rule, and how it will be able to integrate a new decision support tool.

Available for download

Development of Corrosion Severity Assessment Algorithms Using Environmental Monitoring Sensors in Naval Aviation Environments

Product Number: 51324-20663-SG

Author: Alexander Lilly; Steven Kopitzke; Ian Long

Publication Date: 2024

$40.00

Currently, Naval aircraft are inspected for corrosion based on Reliability Centered Maintenance analysis of component failure rates in a feedback loop scheme. Recently developed sensors allow for the measurement and recording of temperature, relative humidity, and solution conductivity in 30 minute intervals. These sensors were deployed collocated with corrosion witness coupons across two 1-year deployments spanning 26 naval aviation relevant locations. Features were engineered from the sensor data, and algorithms were trained to predict the mass loss observed on the collocated witness coupons. Using leave-one-out-cross-validation, the highest performing algorithms possessed an accuracy of 77% in the classification of site corrosion severity based on Aermet 100 mass loss, a landing gear high strength steel.

Available for download

Environmental Exposure Profiles for Atmospheric Corrosion

Product Number: 51323-19416-SG

Author: Christopher D Taylor, David Borth, Douglas C Hansen

Publication Date: 2023

$20.00

Atmospheric corrosion proceeds via several processes that proceed in sequence and/or parallel
across multiple classes of matter (the atmosphere, condensed aqueous solution, polymer coatings, oxide
scales, precipitated salts, and microstructurally heterogeneous metal alloys). Multiple physical and
chemical phenomena contribute to the process of corrosion, including mass-transport, electrochemical
effects, metal dissolution, grain-boundary transport, etc. For this reason, it is difficult to directly predict,
using fundamental physics or chemical principles, the corrosion rate of a metal in its environment.

Products tagged with 'machine learning'

Association for Materials Protection and Performance