Fuzzy inference system application for oil-water flow patterns identification

TL;DR

This paper demonstrates that a fuzzy inference system can accurately predict oil-water flow patterns in pipelines, outperforming BP neural networks, enabling real-time monitoring, and reducing production costs in non-vertical wells.

Contribution

The study introduces a fuzzy inference system for flow pattern prediction, showing it is more accurate and reliable than neural networks in oil-water flow analysis.

Findings

Fuzzy inference system outperforms BP neural network in accuracy.

Real-time monitoring with fuzzy inference reduces errors.

Using fuzzy inference saves production costs and ensures safety.

Abstract

With the continuous development of the petroleum industry, long-distance transportation of oil and gas has been the norm. Due to gravity differentiation in horizontal wells and highly deviated wells (non-vertical wells), the water phase at the bottom of the pipeline will cause scaling and corrosion in the pipeline. Scaling and corrosion will make the transportation process difficult, and transportation costs will be considerably increased. Therefore, the study of the oil-water two-phase flow pattern is of great importance to oil production. In this paper, a fuzzy inference system is used to predict the flow pattern of the fluid, get the prediction result, and compares it with the prediction result of the BP neural network. From the comparison of the results, we found that the prediction results of the fuzzy inference system are more accurate and reliable than the prediction results of the BP neural network. At the same time, it can realize real-time monitoring and has less error control. Experimental results demonstrate that in the entire production logging process of non-vertical wells, the use of a fuzzy inference system to predict fluid flow patterns can greatly save production costs while ensuring the safe operation of production equipment.