Email Document Reference

Enter your email address below and the reference for this document will be sent to shortly from webmaster@ceesi.com.

Title: Validity And Consistency Of Mpfm Data Through A Machine Learning Based System
Author: T. Barbariol, E. Feltresi, G.A. Susto,
Source: 2019 North Sea Flow Measurement Workshop
Year Published: 2019
Abstract: Despite the increased interest on Multiphase Flow Meters (MPFM) in the last decades1, the overall trust in the MPFM is still quite small, as the matter of fact less than a few percent of the oil fields worldwide employs MPFM to monitor the production2. However, monitoring the well flow and its composition has become very important as fields become economically marginal and reservoirs deplete3. Traditional methods, like oil separators, continue to be adopted despite their obvious disadvantages: they are expensive, bulky and do not allow continuous monitoring of the well performances. The reason behind this choice mainly relies on the lack of confidence in the MPFM. The separator is a conceptually simple instrument that does not require an act of faith to be trusted. On the contrary the MPFM is a complex system made up of different sensor modules that return their measurements to a flow model. The flow model processes the input data and gives back the estimated individual flow rates. Both these two stages can be prone to errors and malfunctions, but the sensor level is the most crucial and delicate. In order to overcome this mistrust, the MPFM manufacturer has to guarantee the customer the highest reliability.

In order to prevent spam and automated file downloads for documents within the Measurement Library, please follow the instructions below and then you will be able to email a reference to this article.