Use of gamma radiation and artificial neural network techniques to monitor characteristics of polyduct transport of petroleum by-products

Abstract

This study presents a methodology based on the dual-mode gamma densitometry technique in combination with artificial neural networks to simultaneously determine type and quantity of four different fluids (Gasoline, Glycerol, Kerosene and Fuel Oil) to assist operators of a fluid transport system in pipelines commonly found in the petrochemical industry, as it is necessary to continuously monitor information about the fluids being transferred. The detection system is composed of a 661.657 keV (¹³⁷Cs) gamma-ray emitting source and two NaI(Tl) scintillation detectors to record transmitted and scattered photons. The information recorded in both detectors was directly applied as input data for the artificial neural networks. The proposed intelligent system consists of three artificial neural networks capable of predicting the fluid volume percentages (purity level) with 94.6% of all data with errors less than 5% and MRE of 1.12%, as well as identifying the pair of fluids moving in the pipeline with 95.9% accuracy.

Keywords: Artificial neural network; Gamma densitometry; MCNP6 code; Petroleum by-products; Polyduct.