This page has only limited features, please log in for full access.
The problem of classifying gas-liquid two-phase flow regimes from ultrasonic signals is considered. A new method, belt-shaped features (BSFs), is proposed for performing feature extraction on the preprocessed data. A convolutional neural network (CNN/ConvNet)-based classifier is then applied to categorize into one of the four flow regimes: 1) annular; 2) churn; 3) slug; or 4) bubbly. The proposed ConvNet classifier includes multiple stages of convolution and pooling layers, which both decrease the dimension and learn the classification features. Using experimental data collected from an industrial-scale multiphase flow facility, the proposed ConvNet classifier achieved 97.40%, 94.57%, and 94.94% accuracy, respectively, for the training set, testing set, and validation set. These results demonstrate the applicability of the BSF features and the ConvNet classifier for flow regime classification in industrial applications.
Somtochukwu Godfrey Nnabuife; Boyu Kuang; James F. Whidborne; Zeeshan A. Rana. Development of Gas-Liquid Flow Regimes Identification Using a Noninvasive Ultrasonic Sensor, Belt-Shape Features, and Convolutional Neural Network in an S-Shaped Riser. IEEE Transactions on Cybernetics 2021, PP, 1 -15.
AMA StyleSomtochukwu Godfrey Nnabuife, Boyu Kuang, James F. Whidborne, Zeeshan A. Rana. Development of Gas-Liquid Flow Regimes Identification Using a Noninvasive Ultrasonic Sensor, Belt-Shape Features, and Convolutional Neural Network in an S-Shaped Riser. IEEE Transactions on Cybernetics. 2021; PP (99):1-15.
Chicago/Turabian StyleSomtochukwu Godfrey Nnabuife; Boyu Kuang; James F. Whidborne; Zeeshan A. Rana. 2021. "Development of Gas-Liquid Flow Regimes Identification Using a Noninvasive Ultrasonic Sensor, Belt-Shape Features, and Convolutional Neural Network in an S-Shaped Riser." IEEE Transactions on Cybernetics PP, no. 99: 1-15.
This paper addresses the issues of slug detection and characterization in air-water two-phase flow in a vertical pipeline. A novel non-invasive measurement technique using continuous-wave Doppler ultrasound (CWDU) and bandpass power spectral density (BPSD) is proposed for multiphase flow applications and compared with the more established gamma-ray densitometry measurement. In this work, analysis using time-frequency analysis of the CWDU is performed to infer the applicability of the BPSD method for observing the slug front and trailing bubbles in a multiphase flow. The CWDU used a piezo transmitter/receiver pair with an ultrasonic frequency of 500 kHz. Signal processing on the demodulated signal of Doppler frequency was done using the Butterworth bandpass filter on the power spectral density which reveals slugs from background bubbles. The experiments were carried out in the 2” vertical pipeline-riser at the process system engineering laboratory at Cranfield University. The 2-inch test facility used in this experiment is made up of a 54.8 mm internal diameter and 10.5 m high vertical riser connected to a 40 m long horizontal pipeline. Taylor bubbles were generated using a quick-closing air valve placed at the bottom of the riser underwater flow, with rates of 0.5 litres/s, 2 litres/s, and 4 litres/s. The CWDU spectrum of the measured signal along with the BPSD method is shown to describe the distinctive nature of the slugs.
Somtochukwu Godfrey Nnabuife; Prafull Sharma; Ebuwa Iyore Aburime; Pauline Long’Or Lokidor; AbdulRauf Bello. Development of Gas-Liquid Slug Flow Measurement Using Continuous-Wave Doppler Ultrasound and Bandpass Power Spectral Density. ChemEngineering 2021, 5, 2 .
AMA StyleSomtochukwu Godfrey Nnabuife, Prafull Sharma, Ebuwa Iyore Aburime, Pauline Long’Or Lokidor, AbdulRauf Bello. Development of Gas-Liquid Slug Flow Measurement Using Continuous-Wave Doppler Ultrasound and Bandpass Power Spectral Density. ChemEngineering. 2021; 5 (1):2.
Chicago/Turabian StyleSomtochukwu Godfrey Nnabuife; Prafull Sharma; Ebuwa Iyore Aburime; Pauline Long’Or Lokidor; AbdulRauf Bello. 2021. "Development of Gas-Liquid Slug Flow Measurement Using Continuous-Wave Doppler Ultrasound and Bandpass Power Spectral Density." ChemEngineering 5, no. 1: 2.
Multiphase flow is a prevalent topic in many disciplines, and flow regime identification is an essential foundation in multiphase flow research. Computer vision and deep learning have achieved numerous excellent models, but many have not demonstrated satisfactory performance in fundamental research, including flow regime identification. This research proposes an advanced pseudo-image feature (PIF) as the flow regime descriptor and a benchmark of multiple deep learning classifiers. The PIF simulates the image format and compactly encodes the flow regime to a pseudo-image, which explicitly displays the implicit flow regime signals. This research further evaluates three proposed and five existing popular deep learning classifiers. The proposed benchmark provides a baseline for applying deep learning in flow regime identification. The proposed fully convolutional network (FCN) classifier achieved state-of-the-art performance, and the testing and verification accuracy respectively reached 99.95% and 99.54%. This research suggests that PIF has an excellent capability for flow regime representation, and the proposed deep learning classifiers achieve superior performance in flow regime identification compared to the existing classifiers. Industries can utilize the proposed multiphase flow identification technology to obtain greater production efficiency, productivity, and financial gain.
Boyu Kuang; Somtochukwu Godfrey Nnabuife; Zeeshan Rana. Pseudo-image-feature-based identification benchmark for multi-phase flow regimes. Chemical Engineering Journal Advances 2020, 5, 100060 .
AMA StyleBoyu Kuang, Somtochukwu Godfrey Nnabuife, Zeeshan Rana. Pseudo-image-feature-based identification benchmark for multi-phase flow regimes. Chemical Engineering Journal Advances. 2020; 5 ():100060.
Chicago/Turabian StyleBoyu Kuang; Somtochukwu Godfrey Nnabuife; Zeeshan Rana. 2020. "Pseudo-image-feature-based identification benchmark for multi-phase flow regimes." Chemical Engineering Journal Advances 5, no. : 100060.
This paper presents steady-state simulation and exergy analysis of the 2-amino-2-methyl-1-propanol (AMP)-based post-combustion capture (PCC) plant. Exergy analysis provides the identification of the location, sources of thermodynamic inefficiencies, and magnitude in a thermal system. Furthermore, thermodynamic analysis of different configurations of the process helps to identify opportunities for reducing the steam requirements for each of the configurations. Exergy analysis performed for the AMP-based plant and the different configurations revealed that the rich split with intercooling configuration gave the highest exergy efficiency of 73.6%, while that of the intercooling and the reference AMP-based plant were 57.3% and 55.8% respectively. Thus, exergy analysis of flowsheeting configurations can lead to significant improvements in plant performance and lead to cost reduction for amine-based CO2 capture technologies.
Ebuwa Osagie; Aliyu M. Aliyu; Somtochukwu Godfrey Nnabuife; Osaze Omoregbe; Victor Etim; Aliyu Aliyu. Exergy Analysis and Evaluation of the Different Flowsheeting Configurations for CO2 Capture Plant Using 2-Amino-2-Methyl-1-Propanol (AMP). Processes 2019, 7, 391 .
AMA StyleEbuwa Osagie, Aliyu M. Aliyu, Somtochukwu Godfrey Nnabuife, Osaze Omoregbe, Victor Etim, Aliyu Aliyu. Exergy Analysis and Evaluation of the Different Flowsheeting Configurations for CO2 Capture Plant Using 2-Amino-2-Methyl-1-Propanol (AMP). Processes. 2019; 7 (6):391.
Chicago/Turabian StyleEbuwa Osagie; Aliyu M. Aliyu; Somtochukwu Godfrey Nnabuife; Osaze Omoregbe; Victor Etim; Aliyu Aliyu. 2019. "Exergy Analysis and Evaluation of the Different Flowsheeting Configurations for CO2 Capture Plant Using 2-Amino-2-Methyl-1-Propanol (AMP)." Processes 7, no. 6: 391.