AMPP Store - Products tagged with 'artificial intelligence'

Available for download

A Machine Vision Case Study Of U-Net Networks For Superficial Corrosion And Dirt Image Segmentation On Industrial Coated Steel Structures

Product Number: 51322-17995-SG

Author: Wesley Kaizer, Otavio Correa

Publication Date: 2022

$20.00

Convolutional deep neural networks are one of the main machine learning techniques applied to computer vision and object recognition tasks. Currently, they are very popular due to their proven effectiveness in solving image classification tasks and their significant theoretical and practical importance to the advancement of the deep learning field. Examples of successful image classification networks developed are AlexNet, VGG, and GoogLeNet.^1,2,3

Available for download

Advances In Digital Twin And AI To Predict And Manage External Corrosion - A Smart Tool For Decision Makers

Product Number: 51322-17991-SG

Author: Otavio Correa, Jorge Seleme Mariano

Publication Date: 2022

$20.00

The Brazilian cost of corrosion was estimated at 3% of the GPD in 2018, that percentage is equivalent to approximately $US 49 billion, according to an ABRACO⁽¹⁾ journal released in 2020.¹ It is estimated that from this cost $US 19 billion could have been saved through anticorrosive actions. In another research conducted by the EPRI⁽²⁾ the results showed that at least 22% of corrosion costs could be avoided through adequate mitigating actions.²

Available for download

Advances In Digital Twin And AI To Predict And Manage External Corrosion - A Smart Tool For Decision Makers

Product Number: 51322-17992-SG

Author: Otavio Correa, Jorge Seleme Mariano

Publication Date: 2022

$20.00

The Brazilian cost of corrosion was estimated at 3% of the GPD in 2018, that percentage is equivalent to approximately $US 49 billion, according to an ABRACO¹ journal released in 2020¹. It is estimated that from this cost $US 19 billion could have been saved through anticorrosive actions. In another research conducted by the EPRI² the results showed that at least 22% of corrosion costs could be avoided through adequate mitigating actions².

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

IR 4.0 Integrity Management Using Data Analytics

Product Number: MPWT19-15487

Author: Dr. Haaken Ahnfelt, Dr. Luis Caetano, Dr. Hilde Aas Nøst, Dr. Knut Nordanger, Reidar Kind, Dr. Zeeshan Lodhi, Dr. Lay Seong Teh

Publication Date: 2019

$0.00

One of the pillars of the fourth industrial revolution (4IR) is to let machines make decisions on behalf of humans; this paper describes new technology that allows machines to decide inspection programs and field validation and testing of results. The technology described is a part of integrity management, and uses data, statistics and expert decisions to design inspection programs. These inspection programs are an important part of the safeguarding of equipment to maintain production and safety.
This technology is a data-driven predictive model of material loss from corrosion, based on domain expert input and historical data in the form of non-destructive testing (NDT) tests. The technology trends is based on historical data and SME input, while accounting for uncertainties in NDT measurements, with uncertainties in historical trends and uncertainties in future trends. This produces a more realistic failure prediction to enhance existing RBIs and adds safety by improving on early detection of trends in data. In total, this enables the machine to update inspection plans autonomously, reducing the number of inspections significantly.
The paper also describes how the technology can be developed further to use production data and integrity operating windows to improve predictions, deal with localised corrosion and assess if the test points on a corrosion circuit are sufficient, can be reduced in number or should be manually evaluated by adding more test points.

Available for download

Multitask Learning Framework For Screening Of Corrosion Inhibitors For Mild Steel

Product Number: 51322-17757-SG

Author: Abhishek Agarwal, Pradeep Rathore, Dharmendr Kumar, Sri Harsha Nistala, S Sanjana, Vinay Jain, Beena Rai

Publication Date: 2022

$20.00

Corrosion of metallic structures is a ubiquitous problem in industries such as power generation, oil and gas, pulp and paper, metals processing etc. which also results in significant financial losses. According to the National Association of Corrosion Engineers (NACE) International report, the global cost of corrosion was ~ 2.5 trillion USD in 2013 - close to 3.4 percent GDP of the entire world. The use of corrosion inhibitors is one of the most effective and economical ways to mitigate corrosion of metal and alloy components. Corrosion inhibitors are substances that are added in small quantities in corrosive media to protect metal and alloy components from corrosion.

Available for download

Towards Automated Development and Evaluation of Optimal Corrosion Inhibitor Products

Product Number: 51323-18783-SG

Author: Hector Klie, Arturo Klie, Ana Ferrer, Yolanda De-Abreu

Publication Date: 2023

$20.00

In most engineering and scientific applications, machine learning (ML) or artificial intelligence (AI) methods in general, are primarily oriented to design a statistical/heuristic procedure to predict the outcome of a system under new conditions. This mechanism aims at exploring non-evident correlations between inputs and outputs that are embedded in the data. However, a large body of this effort relies on black-box function approximations (e.g., neural networks) that have shown limitations to elucidate additional insights from the underlying physical process that generated the data. Thus, this type of knowledge is generated in a data-driven manner without fully explaining the physics governing the problem.

Available for download

Using Virtual Reality to Help Teach Application Technique

Product Number: 41213-798-SG

Author: Matthew Wallace

Publication Date: 2013

$20.00

Virtual paint training systems are a needed and valuable addition to teaching methods. As the accuracy and complexity of simulations improve, the industry has begun to exploit this fusion of simulation and education. This presentation explores the next step - how to use the simulation to increase student engagement, enrich their skills development, and improve the trainees’ knowledge base.

Products tagged with 'artificial intelligence'

Association for Materials Protection and Performance