DEVELOPMENT OF SOFT SENSOR TO ESTIMATE Gas Volume Fraction in the Multi-Phase Flow (Gas-Water) through the Orifice USING ARTIFICIAL INTELLIGENCE

This paper proposes a soft sensor to estimate volume fraction of the gas in the multi-phase flow (gas-water)utilizing common measurements in oil and gas production wells. The developed system addresses the limitedproduction monitoring due to using common metering facilities. It offers a cost-effective and optimumsolution to meet real-time monitoring which reduces operational costs, and acts as a back-up to well headmultiphase flow meters. The soft sensor is developed using artificial intelligence technique. The soft sensor isvalidated using actual well test data from producing wells which extracted from papers and reports, andmodel performance is analyzed using cumulative deviation and cumulative flow plots. The developed softsensor shows promising performance with a mean absolute percent error of around ۳% and less than ۵%deviation for ۹۵% of the samples.