On-line calibration monitoring system based on data-driven model for oil well sensors

In the oilfield industry, data collected from well sensors plays an important role in performance and security applications. The quality of the measurements is directly related to the accuracy of the control actions and the optimisation of the production. On-line calibration monitoring systems can determine drifts in the sensors measurements and provide more reliable information to the user. In this paper, a robust on-line calibration monitoring system for drift correction/detection in well sensors is presented and evaluated for simulated and real data sets. Comparisons with a state-of-art monitoring system is also showed. The results indicate a promising applicability of the calibration monitoring system for the oilfield industry data.