Intelligent real-time prediction for energy and sensing applications
Publication Date
July 24, 2022
Creator
Abstract
The advancements of science and technology has been rapid since the boom of the fourth industrial revolution that began arguable about a decade ago. As smart hardware and software began to be paired together over high speed transfer of information, the world of innovation witnessed the rise of Big Data and Machine Learning.
These 2 heroes of the 21st centuries have been widely embraced and adopted in various industries, resulting in innovations and outcomes that we never could have perceived otherwise, especially in closing the gaps between probability and predictability i.e. stock market predictions and such.
However, one gigantic industry that has yet to reap on the offerings of Big Data and Machine Learning is the oil and gas industry. As extreme a form of engineering it is, methods and technologies are still primarily mechanically driven, specifically when it comes to safety and preventive measures i.e. in failure prediction efforts. Manual methods using predated technologies are still industry standard for many applications within industry.
This research takes a look at these current methods, and proposes a new way of performing failure prediction analysis using machine learning.
Item Type
ethesis
Thesis Type
MPhil
Supervisors
Subjects (LC)
Associated Schools / Departments
Department of Electrical and Electronic Engineering
eprints ID
68937
UoN Repository URI
Except where otherwise noted, this item's license is described as
File(s)![Thumbnail Image]()
Name
MPhil_Thesis_Arun_2022.pdf
Type
Full-text
Description
Examined
Size
3.36 MB
Format
Adobe PDF
Checksum (MD5)
6969d1eb2a55b32151ba329fd35babcb