Machine Learning Approach Using MLP and SVM Algorithms for the Fault Prediction of a Centrifugal Pump in the Oil and Gas Industry

Pier Francesco Orrù, Andrea Zoccheddu, Lorenzo Sassu, Carmine Mattia, Riccardo Cozza, Simone Arena

Sustainability · 2020 · 210 citations · 44 references

DOIFull text

Open access

Concepts

TL;DR

Accurate fault detection and classification is essential for cost‑effective, reliable operation of machinery, particularly in the oil and gas industry, where it helps extend component life and prevent costly breakdowns. The study develops a straightforward machine‑learning model for early fault prediction of a centrifugal pump in the oil and gas sector. The model is trained on denoised temperature, pressure, and vibration sensor data from the pump, using SVM and MLP algorithms implemented in KNIME. The ML model accurately identifies and classifies potential faults, detecting deviations from normal operation and providing timely fault‑prediction alerts for maintenance.

Abstract

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—the Support Vector Machine (SVM) and the Multilayer Perceptron (MLP)—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.

References

44