Machine Learning Approach Using MLP and SVM Algorithms for the Fault Prediction of a Centrifugal Pump in the Oil and Gas Industry
| Autor: | Lorenzo Sassu, Pier Francesco Orru, Riccardo Cozza, Carmine Mattia, Simone Arena, Andrea Zoccheddu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Decision support system Computer science Geography Planning and Development oil and gas industry TJ807-830 02 engineering and technology Management Monitoring Policy and Law Machine learning computer.software_genre Fault (power engineering) TD194-195 Fault detection and isolation Predictive maintenance Renewable energy sources predictive maintenance 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering GE1-350 Artificial neural network Environmental effects of industries and plants Renewable Energy Sustainability and the Environment business.industry Process (computing) fault diagnosis Centrifugal pump Support vector machine Environmental sciences machine learning Multilayer perceptron 020201 artificial intelligence & image processing Artificial intelligence business Algorithm computer artificial neural networks |
| Zdroj: | Sustainability, Vol 12, Iss 4776, p 4776 (2020) Sustainability Volume 12 Issue 11 |
| ISSN: | 2071-1050 |
| Popis: | The demand for cost-effective, reliable and safe machinery operation requires accurate fault detection and classification to achieve an efficient maintenance strategy and increase performance. Furthermore, in strategic sectors such as the oil and gas industry, fault prediction plays a key role to extend component lifetime and reduce unplanned equipment thus preventing costly breakdowns and plant shutdowns. This paper presents the preliminary development of a simple and easy to implement machine learning (ML) model for early fault prediction of a centrifugal pump in the oil and gas industry. The data analysis is based on real-life historical data from process and equipment sensors mounted on the selected machinery. The raw sensor data, mainly from temperature, pressure and vibrations probes, are denoised, pre-processed and successively coded to train the model. To validate the learning capabilities of the ML model, two different algorithms&mdash the Support Vector Machine (SVM) and the Multilayer Perceptron (MLP)&mdash are implemented in KNIME platform. Based on these algorithms, potential faults are successfully recognized and classified ensuring good prediction accuracy. Indeed, results from this preliminary work show that the model allows us to properly detect the trends of system deviations from normal operation behavior and generate fault prediction alerts as a maintenance decision support system for operatives, aiming at avoiding possible incoming failures. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|