Design and construction of an LSTM-powered high sampling rate dual-beam gamma densitometer for real-time measurement of the two-phase flow void fraction

被引：2

作者：

Boorboor, S. ^{[1
]}

Feghhi, S. A. H. ^{[1
]}

Jafari, H. ^{[1
]}

机构：

[1] Shahid Beheshti Univ, Radiat Applicat Dept, Tehran, Iran

来源：

NUCLEAR ENGINEERING AND DESIGN | 2023年 / 411卷

关键词：

NEURAL-NETWORK; REGIME; IDENTIFICATION; TRANSITIONS; PREDICTION; ERRORS; NOISE; MODEL;

D O I：

10.1016/j.nucengdes.2023.112444

中图分类号：

TL [原子能技术]; O571 [原子核物理学];

学科分类号：

0827 ; 082701 ;

摘要：

In this work, an intelligent gamma densitometer gauge for non-intrusive real-time measurement of the two-phase flow void fraction has been designed and con-structed. It has been implemented in a horizontal pipe over a wide range of gas and liquid superficial velocities. Moreover, a Long Short-Term Memory (LSTM) neural network has been used for analyzing the data sequence from a dedicated high sampling rate dual-beam gamma densitometer. This approach considerably reduced the complexity of the data processing and regression operations while providing a high capability to identify and compensate for the errors caused by intermittent, and inhomogeneous flow regimes in a real-time mode. A comprehensive sensitivity analysis has been performed to adjust the network parameters for the most accurate void fraction prediction in all studied flow regimes including slug, plug, wavy, stratified, bubbly, and semi-annular. The experimental evaluations revealed that considering a sampling time of a few seconds, the optimized model approximated the actual data with an R-squared of 0.98, and almost all measurements were carried out with the maximum absolute error of 10%. The high accuracy and relatively fast response of the proposed method make it a reliable technique for developing a high-performance real-time multiphase flow meter.

引用

页数：9

共 49 条

[1]

Åbro E, 1999, MEAS SCI TECHNOL, V10, P619, DOI 10.1088/0957-0233/10/7/308

[2] Poly-linear regression with augmented long short term memory neural network: Predicting time series data [J].

Ahmed, Supriyo ;

Chakrabortty, Ripon K. ;

Essam, Daryl L. ;

Ding, Weiping .

INFORMATION SCIENCES, 2022, 606 :573-600

[3]

Alt R., 1978, Mathematics and Computers in Simulation, V20, P37, DOI 10.1016/0378-4754(78)90052-6

[4] A Machine Learning Approach for Virtual Flow Metering and Forecasting [J].

Andrianov, Nikolai .

IFAC PAPERSONLINE, 2018, 51 (08) :191-196

[5] Pattern Recognition Techniques for Horizontal and Vertically Upward Multiphase Flow Measurement [J].

Arubi, Tesi I. M. ;

Yeung, Hoi .

7TH INTERNATIONAL SYMPOSIUM ON MEASUREMENT TECHNIQUES FOR MULTIPHASE FLOWS, 2012, 1428

[6] Slug length for high viscosity oil-gas flow in horizontal pipes: Experiments and prediction [J].

Baba, Yahaya D. ;

Aliyu, Aliyu M. ;

Archibong, Archibong E. ;

Abdulkadir, Mukhtar ;

Lao, Liyun ;

Yeung, Hoi .

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2018, 165 :397-411

[7] Functional link artificial neural network applied to active noise control of a mixture of tonal and chaotic noise [J].

Behera, Santosh Kumar ;

Das, Debi Prasad ;

Subudhi, Bidyadhar .

APPLIED SOFT COMPUTING, 2014, 23 :51-60

[8] ANALYSIS OF MULTIPHASE FLOWS USING DUAL-ENERGY GAMMA DENSITOMETRY AND NEURAL NETWORKS [J].

BISHOP, CM ;

JAMES, GD .

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 1993, 327 (2-3) :580-593

[9] Investigation of the exploitation of a fast-sampling single gamma densitometer and pattern recognition to resolve the superficial phase velocities and liquid phase water cut of vertically upward multiphase flows [J].

Blaney, Stephen ;

Yeung, Hoi .

FLOW MEASUREMENT AND INSTRUMENTATION, 2008, 19 (02) :57-66

[10]

BOURE JA, 1973, NUCL ENG DES, V25, P165, DOI 10.1016/0029-5493(73)90043-5

← 1 2 3 4 5 →