Search
Filters
Close

Search and Filter

Toggle Open/Closed
View as
Display per page
14122 total products found.
Picture for 07205 Corrosion of Stainless Steel in Sulfamic Acid Cleaning Solutions
Available for download
	Picture for Application of Artificial Intelligence in Corrosion Management
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.
Picture for Remote, Visual Inspection And Digital Analysis For External Corrosion Assessment In Refining Unit Applications
Available for download

Remote, Visual Inspection And Digital Analysis For External Corrosion Assessment In Refining Unit Applications

Product Number: 51321-16542-SG
Author: Slawomir Kus/ Sridhar Srinivasan
Publication Date: 2021
$20.00
Picture for Effect of Backing Gas Composition on Corrosion Behavior of Conventional Duplex Stainless Steel Weldments
Available for download

Effect of Backing Gas Composition on Corrosion Behavior of Conventional Duplex Stainless Steel Weldments

Product Number: 51321-16598-SG
Author: Ricardo Hernández Soto/ Abdullah M. Al-Rumaih
Publication Date: 2021
$20.00
Picture for Predicting Corrosion of Successive Feeds in Distilling Units - An Experimental Approach
Available for download

Predicting Corrosion of Successive Feeds in Distilling Units - An Experimental Approach

Product Number: 51324-20668-SG
Author: Gheorghe Bota; Ishan Patel; Peng Jin; David Young
Publication Date: 2024
$40.00
Cheap heavy crudes become attractive for oil refineries to increase their benefit margins but the corrosivity of heavy crudes compels the refinery engineers to blend them with the more expensive light sweet crudes. Crude oil blends with complex composition including organo-sulfur compounds, fatty acids, nitrogen and chlorine compounds become corrosive when processed at high temperatures due to these reactive species. Therefore, maintaining corrosion control is a constant effort in oil refineries, and it involves the use of dedicated corrosion models combined with specific experimental lab procedures and methods. This work is presenting the practical application of a lab testing procedure used for predicting the high temperature corrosivity of different crude fractions that were run successively for different time periods in a specific “flow-through” apparatus. The testing procedure consists of two distinct phases performed in the same apparatus, at the same temperature, and for different time durations. During the first phase of the test, scales are formed using a distilling fraction on metal samples and further, in the second test phase, these preformed scales on samples are exposed without interruption to a different distilling fraction. Thus, the two successive test phases, each using a different distilling fraction, are associated with the “changing feeds” in the distilling tower. Corrosive effects are evaluated by sample weight loss measured in successive fraction tests and in separate tests performed with each of the selected fractions. Experimental results are compared to predictions of a corrosion model for sulfidation and naphthenic acid corrosion.