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.
- Susto, G. A. (2015). Machine learning for predictive maintenance: A multiple classifier approach. IEEE Transactions on Industrial Informatics, 812-820.Google ScholarCross Ref
- Nakamura, J. (2007). Predicting Time to Failure of Industrial Machines with Temporal Data Mining. Masters of Science - University of Washington, 15-92.Google Scholar
- Jahnke, P. (2015). Machine Learning Approaches for Failure Type Detection and Predictive Maintenance. 45-54.Google Scholar
- Gupta, D. L. (2016). m nl ad in e e V by e th rsio is n fil O e is nly m nl ad in e e V by e th rsio is n fil O e. Deep Machine Learning and Neural Networks: An Overview Chandrahas, 401-414.Google Scholar
- Goode, K. B. (2000). Plant machinery working life prediction method utilizing reliability and condition-monitoring data. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical, 109-122.Google ScholarCross Ref
- Shen Rong, Zhang Bao-wen (2018) The research of regression model in machine learning field. MATEC Web Conf. 176 01033. DOI: 10.1051/matecconf/201817601033Google Scholar
- Girolami, M. and Rogers, S. (2006) Variational Bayesian multinomial probit regression with Gaussian process priors. Neural Computation 18(8):pp. 1790-1817.Google ScholarDigital Library
Index Terms
- Predictive Analytics of Machine Failure using Linear Regression on KNIME Platform
Recommendations
Soil Moisture Prediction Using Machine Learning Techniques
CIIS '20: Proceedings of the 2020 3rd International Conference on Computational Intelligence and Intelligent SystemsAlthough - Soil moisture is the main factor in agricultural production and hydrological cycles, and its prediction is essential for rational use and management of water resources. However, soil moisture involves complicated structural characters and ...
Machine learning for air quality prediction using meteorological and traffic related features
The presence of pollutants in the air has a direct impact on our health and causes detrimental changes to our environment. Air quality monitoring is therefore of paramount importance. The high cost of the acquisition and maintenance of accurate air ...
Developing a Generalized Scaling-Law for Oil Recovery Using Machine Learning Techniques
AbstractThe universal dimensionless time is an important parameter to predict a real oil field behavior from a scaled laboratory experiment. The dimensionless time uses a group of parameters that are inherited to the properties of both fluids and rocks of ...
Comments