Surrogate Model with a Deep Neural Network to Evaluate Gas–Liquid Flow in a Horizontal Pipe

This study developed a data-driven surrogate model based on a deep neural network (DNN) to evaluate gas–liquid multiphase flow occurring in horizontal pipes. It estimated the liquid holdup and pressure gradient under a slip condition and different flow patterns, i.e., slug, annular, stratified flow, etc. The inputs of the surrogate modelling were related to the fluid properties and the dynamic data, e.g., superficial velocities at the inlet, while the outputs were the liquid holdup and pressure gradient observed at the outlet. The case study determined the optimal number of hidden neurons by considering the processing time and the validation error. A total of 350 experimental data were used: 279 for supervised training, 31 for validating the training performance, and 40 unknown data, not used in training and validation, were examined to forecast the liquid holdup and pressure gradient. The liquid holdups were estimated within less than 8.08% of the mean absolute percentage error, while the error of the pressure gradient was 23.76%. The R2 values confirmed the reliability of the developed model, showing 0.89 for liquid holdups and 0.98 for pressure gradients. The DNN-based surrogate model can be applicable to estimate liquid holdup and pressure gradients in a more realistic manner with a small amount of computating resources.

Download Full-text

Deep neural network-based surrogate model linked with particle swarm optimization for identification of subsurface contamination sources

10.1002/essoar.10505415.1 ◽

2020 ◽

Author(s):

Aatish Anshuman ◽

T.I. Eldho

Keyword(s):

Neural Network ◽

Particle Swarm Optimization ◽

Surrogate Model ◽

Deep Neural Network ◽

Particle Swarm ◽

Swarm Optimization ◽

Subsurface Contamination ◽

Contamination Sources

Download Full-text

Novel Spatiotemporal Feature Extraction Parallel Deep Neural Network for Forecasting Confirmed Cases of Coronavirus Disease 2019

10.1101/2020.04.30.20086538 ◽

2020 ◽

Author(s):

Chiou-Jye Huang ◽

Yamin Shen ◽

Ping-Huan Kuo ◽

Yung-Hsiang Chen

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Absolute Error ◽

Mean Absolute Percentage Error ◽

The Other ◽

Percentage Error ◽

Model Assessment ◽

Absolute Percentage Error ◽

Spatiotemporal Feature ◽

The Mean

AbstractThe coronavirus disease 2019 pandemic continues as of March 26 and spread to Europe on approximately February 24. A report from April 29 revealed 1.26 million confirmed cases and 125 928 deaths in Europe. This study proposed a novel deep neural network framework, COVID-19Net, which parallelly combines a convolutional neural network (CNN) and bidirectional gated recurrent units (GRUs). Three European countries with severe outbreaks were studied—Germany, Italy, and Spain—to extract spatiotemporal feature and predict the number of confirmed cases. The prediction results acquired from COVID-19Net were compared to those obtained using a CNN, GRU, and CNN-GRU. The mean absolute error, mean absolute percentage error, and root mean square error, which are commonly used model assessment indices, were used to compare the accuracy of the models. The results verified that COVID-19Net was notably more accurate than the other models. The mean absolute percentage error generated by COVID-19Net was 1.447 for Germany, 1.801 for Italy, and 2.828 for Spain, which were considerably lower than those of the other models. This indicated that the proposed framework can accurately predict the accumulated number of confirmed cases in the three countries and serve as a crucial reference for devising public health strategies.

Download Full-text

A method for predicting the capacity of a lithium-ion battery based on deep neural network

10.31224/osf.io/bzwkp ◽

2021 ◽

Author(s):

JamesChan

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Lithium Ion ◽

Chemical Conversion ◽

Absolute Error ◽

Production Costs ◽

Percentage Error ◽

Average Percentage ◽

True Value ◽

Battery Capacity

This paper proposes a solution to predict the capacity of the lithium-ion battery's capacity division process using deep learning methods. This solution extracts the physical observation records of part of the process steps from the chemical conversion and volumetric processes as features, and trains a Deep Neural Network (DNN) to achieve accurate prediction of battery capacity. According to the test, the average percentage absolute error (Mean Absolute Percentage Error, MAPE) of the battery capacity predicted by this model is only 0.78% compared with the true value. Combining this model with the production line can greatly reduce production time and energy consumption, and reduce battery production costs.

Download Full-text

Surrogate Model based Co-Optimization of Deep Neural Network Hardware Accelerators

10.1109/mwscas47672.2021.9531708 ◽

2021 ◽

Author(s):

Hendrik Wohrle ◽

Mariela De Lucas Alvarez ◽

Fabian Schlenke ◽

Alexander Walsemann ◽

Michael Karagounis ◽

...

Keyword(s):

Neural Network ◽

Surrogate Model ◽

Deep Neural Network ◽

Hardware Accelerators ◽

Model Based ◽

Neural Network Hardware

Download Full-text

Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization

Computer Methods in Applied Mechanics and Engineering ◽

10.1016/j.cma.2020.113485 ◽

2021 ◽

Vol 373 ◽

pp. 113485

Author(s):

Xinshuai Zhang ◽

Fangfang Xie ◽

Tingwei Ji ◽

Zaoxu Zhu ◽

Yao Zheng

Keyword(s):

Neural Network ◽

Shape Optimization ◽

Surrogate Model ◽

Deep Neural Network ◽

Aerodynamic Shape Optimization ◽

Aerodynamic Shape

Download Full-text

Deep Neural Network for Predicting Ore Production by Truck-Haulage Systems in Open-Pit Mines

Applied Sciences ◽

10.3390/app10051657 ◽

2020 ◽

Vol 10 (5) ◽

pp. 1657 ◽

Cited By ~ 3

Author(s):

Jieun Baek ◽

Yosoon Choi

Keyword(s):

Neural Network ◽

Prediction Accuracy ◽

Deep Neural Network ◽

Training Data ◽

Open Pit ◽

Percentage Error ◽

Open Pit Mines ◽

Determination Coefficient ◽

Packet Data ◽

Hidden Layer

This paper proposes a deep neural network (DNN)-based method for predicting ore production by truck-haulage systems in open-pit mines. The proposed method utilizes two DNN models that are designed to predict ore production during the morning and afternoon haulage sessions, respectively. The configuration of the input nodes of the DNN models is based on truck-haulage conditions and corresponding operation times. To verify the efficacy of the proposed method, training data for the DNN models were generated by processing packet data collected over the two-month period December 2018 to January 2019. Subsequently, following training under different hidden-layer conditions, it was observed that the prediction accuracy of morning ore production was highest when the number of hidden layers and number of corresponding nodes were four and 50, respectively. The corresponding values of the determination coefficient and mean absolute percentage error (MAPE) were 0.99% and 4.78%, respectively. Further, the prediction accuracy of afternoon ore production was highest when the number of hidden layers was four and the corresponding number of nodes was 50. This yielded determination coefficient and MAPE values of 0.99% and 5.26%, respectively.

Download Full-text

Maldistribution and dynamic liquid holdup quantification of quadrilobe catalyst in a trickle bed reactor using gamma-ray computed tomography: Pseudo-3D modelling and empirical modelling using deep neural network

Chemical Engineering Research and Design ◽

10.1016/j.cherd.2020.09.024 ◽

2020 ◽

Vol 164 ◽

pp. 195-208

Author(s):

Binbin Qi ◽

Omar Farid ◽

Sebastián Uribe ◽

Muthanna Al-Dahhan

Keyword(s):

Neural Network ◽

Computed Tomography ◽

Deep Neural Network ◽

Gamma Ray ◽

3D Modelling ◽

Liquid Holdup ◽

Trickle Bed Reactor ◽

Empirical Modelling ◽

Trickle Bed ◽

Gamma Ray Computed Tomography

Download Full-text

Performance of Two-Phase Flow Models on the Prediction of Oscillatory Flow Conditions

Volume 8: Polar and Arctic Sciences and Technology; Petroleum Technology ◽

10.1115/omae2016-54954 ◽

2016 ◽

Author(s):

Catalina Posada ◽

Paulo Waltrich

Keyword(s):

Experimental Data ◽

Steady State ◽

Pressure Gradient ◽

Two Phase Flow ◽

Percentage Error ◽

Phase Flow ◽

Liquid Holdup ◽

Two Phase ◽

Flow Models ◽

Absolute Percentage Error

The present investigation presents a comparative study between two-phase flow models and experimental data. Experimental data was obtained using a 42 m long, 0.05 m ID tube system. The experimental data include conditions for pressures ranging from 1.2 to 2.8 bara, superficial liquid velocities 0.02–0.3 m/s, and superficial gas velocity ranges 0.17–26 m/s. The experimental data was used to evaluate the performance of steady-state empirical and mechanistic models while estimating liquid holdup and pressure gradient under steady-state and oscillatory conditions. The purpose of this analysis is first to evaluate the accuracy of the models predicting the liquid holdup and pressure gradient under steady-state conditions. Then, after evaluating the models under state-steady conditions, the same models are used to predict the same parameters for oscillatory and periodic conditions for similar gas and liquid velocities. The transient multiphase flow simulator OLGA, which has been widely used in the oil and gas industry, was implemented to model one oscillatory case to evaluate the prediction improvement while using a transient instead of a steady-state model to predict oscillatory flows. For the model with best performance for steady-state pressure gradient prediction, the absolute percentage error is 12% for Uls = 0.02 m/s and 5% for Uls = 0.3. For oscillatory conditions, the absolute percentage error is 30% for Uls = 0.02 m/s and 4% for Uls = 0.3. OLGA results underpredict the experimental pressure gradient under oscillatory conditions with errors up to 30%. Therefore, it was possible to conclude that the models can predict the average of the oscillatory data almost as well as for steady-state conditions.

Download Full-text