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.

One of the features that should be considered when designing a thermal energy storage (TES) system is its behaviour when subjected to non-continuous (partial loads) operating conditions. Indeed, the system performance can be sensibly affected by the partial charging and discharging processes. This topic is analysed in the present study by means of a two-dimensional axisymmetric numerical model implemented in COMSOL Multiphysics. A latent heat TES system consisting of a vertical concentric tube heat exchanger is simulated to investigate the effect of different partial load operating conditions on the system behaviour. The effects of different heat transfer distributions and evolutions of the solid-liquid interface, are evaluated to identify the optimal management criteria of the TES systems. The results showed that partial load strategies allow to achieve a substantial reduction in the duration of the TES (up to 50%) process against a small decrease in stored energy (up 30%). The close correlation between the energy and the duration of the TES cycle is also evaluated during the discharge using detailed maps related to the melting fraction. These maps allow for the evaluation of the most efficient load conditions considering both charging and discharging processes to satisfy a specific energy demand.

No abstract

No abstract

Està subjecte a una llicència de Reconeixement-NoComercial-SenseObraDerivada 4.