Predictive Analytics of Machine Failure using Linear Regression on KNIME Platform

Pakhir, E.A. and Ayuni, N. (2021) Predictive Analytics of Machine Failure using Linear Regression on KNIME Platform. In: UNSPECIFIED.

Full text not available from this repository.
Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....

Abstract

The failure of machines at oil and gas platforms that will temporarily stop oil production commonly happens. The failure may refer to the machine that has stopped working, is not working properly, or does not meet target expectations. In this research, we are assessing the state of the condition of a turbine generator. A turbine generator is a connection of a shaft of a steam turbine or gas turbine engine connected to a high-speed electric generator to generate electricity in the process of drilling and digging. Machine failure will cause loss to the oil and gas industry due to the interruption of oil production. Hence, the purpose of this study is to predict machine failure using linear regression on KNIME platform. By predicting machine time-to-failure using machine learning, maintenance can be scheduled and performed before failure occurs. Upon measuring the accuracy of the predicted model, the result will be visualized through a dashboard for user monitoring. © 2021 ACM.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Additional Information: cited By 1; Conference of 5th International Conference on Artificial Intelligence and Virtual Reality, AIVR 2021 ; Conference Date: 23 July 2021 Through 25 July 2021; Conference Code:173651
Uncontrolled Keywords: Failure (mechanical); Gas industry; Linear regression; Machine learning; Turbogenerators, Condition; Dashboard; Gas turbine engine; Generate electricity; High Speed; KNIME; Machine failure; Oil and Gas Industry; Oil and gas platforms; Oil-production, Predictive analytics
Depositing User: Mr Ahmad Suhairi UTP
Date Deposited: 10 Nov 2023 03:29
Last Modified: 10 Nov 2023 03:29
URI: https://khub.utp.edu.my/scholars/id/eprint/14673

Actions (login required)

View Item
View Item