Save 20% on select titles with code HIDDEN24 - Shop The Sale Now
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
Distribution pipelines are system of main and service lines that transports the product to each individual home and business place. Typically, it operates at a lower pressure than transmission pipes, and it is not linear referenced in the database. In the meantime, distribution pipelines have more leak records available, which encourages the ability to do machine learning on them. This study applied machine learning methods, including the benchmark performance multiple linear regression (MLR) and decision tree-based extreme gradient boosting regression (XGB), to predict the corrosion-related pipeline leak time with features of pipeline and GIS-related properties. In total, over 30,000 data points were used in this study, while splitting into training and testing data sets for cross-validation. The quality of machine learning predictions was evaluated based on the statistical values, such as the coefficient of determination (R2) and root mean square error (RMSE). As a result, the machine learning algorithms find non-linear relationships in the data set, which could help decision-making in association with the probabilistic risk assessment model.
Estimating corrosion growth rate for underground pipelines is a non-linear multivariate problem. There are many potential confounding variables such as soil parameters cathodic protection AC/DC interference seasonal / climate conditions and proximity to unique geographic features such as wetlands or polluted environments. The work presented provides an approach for estimating underground corrosion growth rates using a dataset of observations from a North American pipeline operator. Extensive geospatial data is utilized that has been obtained from public and private sources and extrapolated using Inverse distance weighted (IDW) interpolation. This work presents a model using IDW to estimate parameters involving soil interference geography and climate factors for any location in North America.Using this data this work then presents several different machine learning approaches including Generalized Linear Models eXtreme Boosted Trees and Neural Networks. All three provide an accurate estimation for corrosion growth rates for an underground asset at any latitude and longitude pair in North America. Each method comes with potential benefits and pitfalls specifically; trade-offs between model accuracy and transparency. This work presents a framework for comparing geo-spatial and machine learning estimates. Findings and a framework are provided for owners to assess how to think machine learning on their own assets.
We are unable to complete this action. Please try again at a later time.
If this error continues to occur, please contact AMPP Customer Support for assistance.
Error Message:
Please login to use Standards Credits*
* AMPP Members receive Standards Credits in order to redeem eligible Standards and Reports in the Store
You are not a Member.
AMPP Members enjoy many benefits, including Standards Credits which can be used to redeem eligible Standards and Reports in the Store.
You can visit the Membership Page to learn about the benefits of membership.
You have previously purchased this item.
Go to Downloadable Products in your AMPP Store profile to find this item.
You do not have sufficient Standards Credits to claim this item.
Click on 'ADD TO CART' to purchase this item.
Your Standards Credit(s)
1
Remaining Credits
0
Please review your transaction.
Click on 'REDEEM' to use your Standards Credits to claim this item.
You have successfully redeemed:
Go to Downloadable Products in your AMPP Store Profile to find and download this item.
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.
Visual inspection is a vital component of asset management that stands to benefit from automation. Using artificial intelligence to assist inspections can increase safety reduce access costs provide objective classification and integrate with digital asset management systems. The work presented herein investigates Deep Learning for automatic detection of corrosion on steel assets. A workflow is presented that spans from dataset creation to deployment highlighting the major hurdles and remaining work required. This process can be extended to other defects with a view to complete automation of visual inspection for asset management.