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

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.

Application of Machine Learning Techniques in Injection Molding Quality Prediction: Implications on Sustainable Manufacturing Industry

“…The SVM uses a margin, the distance between these support vectors, to find the optimal decision boundary. It is very important to select the proper kernel function as it explains the feature space where the training data will be classified [36].…”

A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings

“…The authors concluded that the k-NN algorithm along with a GA could be a reliable diagnostic tool for bearing condition monitoring. The support vector machine (SVM) and multilayer perception (MLP) algorithms were used in [ 34 ] to analyze centrifugal pump seal leakages. The authors used the accelerometer data collected from the installation site over four years.…”

Business Intelligence and Machine Learning Methods for Predictive Maintenance in Greek railways

“…The paper also presents the progress of different types of models analyzing seven algorithms with the use of WEKA software. The data mining approach that takes place in paper [22] can help transform maintenance processes on Greek railways. The paper [22] presents the development of a simple and easy to be used model for the prediction of an early damage of an oil pump at the oil and gas industry.…”

“…The data mining approach that takes place in paper [22] can help transform maintenance processes on Greek railways. The paper [22] presents the development of a simple and easy to be used model for the prediction of an early damage of an oil pump at the oil and gas industry. The data analysis is based on real historic data from sensors.…”