Abstract

This paper describes the experimental test bench used in coolant flow research with application of adjusted optical laser system. It is based on the technology of pulsed particle visualization of micro tracers, i.e. Particle Image Velocimetry (PIV system) that allows for the analysis of the microstructure of the hydrodynamic liquid flow passed through the vortex inserts. Optical measurement (PIV-method) of hydro- and aerodynamic characteristics of the coolant flow allowed obtaining the velocity distribution in straight and various curved sections of the pipeline in order to reliably define the vortex formation condition and the occurrence of the pressure gradient on the outer and inner walls of the curved sections. This gives us the opportunity to verify the calculation models describing the problem of passive control (decrease) of the displacement of pipelines of power equipment, and thus to improve the reliability and safe operation of the system in general. © 2017 The Authors, published by EDP Sciences.

Abstract

Industrial pipelines must be inspected to detect typical failures, such as obstructions and deformations, during their lifetime. In the petroleum industry, the most used non-destructive technique to inspect buried pipelines is pigging. This technique consists of launching a Pipeline Inspection Gauge (PIG) inside the pipeline, which is driven by the pressure differential produced by fluid flow. The purpose of this work is to study the application of artificial neural networks to calculate the PIG&rsquo s velocity based on the pressure differential. We launch a prototype PIG inside a testing pipeline, where this PIG gathers velocity data from an odometer-based system, while a supervisory system gathers pressure data from the testing pipeline. Then we train a Multilayer Perceptron (MLP) and a Nonlinear Autoregressive Network with eXogenous Inputs (NARX) network with the gathered data to predict velocity. The results suggest it is possible to use a neural network to model the PIG&rsquo s velocity from pressure differential measurements. Our method is a new approach to the typical speed measurements based only on odometer, since the odometer is prone to fail and present poor results under some circumstances. Moreover, it can be used to provide redundancy, improving reliability of data obtained during the test. Document type: Article