Analysis of microchannel resistance factor based on automated simulation framework and BP neural network

In this paper, self-design automated simulation and artificial neural network (ANN) model were developed to analyze and estimate the resistance factor in rectangle cross-section microchannels. The main purpose is to obtain a universal solution method through numerical simulation which can solve the resistance factor problem for invariant cross-section microchannels. Through Python language, the automatic coalescent of preprocessing Gambit, computing software CFD and post-processing Tecplot make the simulation framework realize the automatic acquisition of microchannel resistance factor samples. Then, 100 simulation samples with different aspect ratios for Reynolds numbers ranging from 50 to 500 were obtained. After validation, the width and height of microchannels were applied as input data set of the ANN model, and the resistance factor was determined as the target data. In order to improve BP algorithm for training ANN, a new swarm evolution algorithm was realized by combining the strong point of gradient descent method, genetic algorithm and particle swarm optimization, which is called particle swarm evolution algorithm. Finally, the result of resistance factor model was established and verified by several existing measurement value of pressure drop from remarkable experimental.

[1]  Robert W. Zimmerman,et al.  Creeping flow through a pipe of varying radius , 2001 .

[2]  Howard A. Stone,et al.  Three-dimensional flows in slowly varying planar geometries , 2003, cond-mat/0306572.

[3]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[4]  Ahmet Selim Dalkılıç,et al.  Artificial neural network modeling of nanofluid flow in a microchannel heat sink using experimental data , 2017 .

[5]  W. Wang,et al.  Theoretical analysis and modeling of flow instability in a mini-channel evaporator , 2017 .

[6]  J. Welty,et al.  Pressure Drop Measurements in a Microchannel , 1998, Micro-Electro-Mechanical Systems (MEMS).

[7]  Sushanta K. Mitra,et al.  Numerical simulation of flow through microchannels with designed roughness , 2006 .

[8]  Xiaofeng Wang,et al.  Feature coefficient prediction of micro-channel based on artificial neural network , 2017 .

[9]  M. Yovanovich,et al.  Pressure Drop of Fully-Developed, Laminar Flow in Microchannels of Arbitrary Cross-Section , 2006 .

[10]  J. Teng,et al.  Experimental and numerical study on the flow characteristics in curved rectangular microchannels , 2010 .

[11]  Goran N. Jovanovic,et al.  Numerical study of flow uniformity and pressure characteristics within a microchannel array with triangular manifolds , 2013, Comput. Chem. Eng..

[12]  X. Peng,et al.  FRICTIONAL FLOW CHARACTERISTICS OF WATER FLOWING THROUGH RECTANGULAR MICROCHANNELS , 1994 .

[13]  G. Mala,et al.  Pressure-driven water flows in trapezoidal silicon microchannels , 2000 .

[14]  S. Hsieh,et al.  Liquid flow in a micro-channel , 2006 .

[15]  Masoud Rahimi,et al.  Application of ANN and GA for the Prediction and Optimization of Thermal and Flow Characteristics in a Rectangular Channel Fitted with Twisted Tape Vortex Generators , 2014 .

[16]  Predrag Stojan Hrnjak,et al.  Single phase pressure drop in microchannels , 2007 .

[17]  Yuan Wang,et al.  Flow in microchannels with rough walls: flow pattern and pressure drop , 2007 .

[18]  Omid Ali Akbari,et al.  The numerical investigation of heat transfer and pressure drop of turbulent flow in a triangular microchannel , 2017 .

[19]  Xiaoguang Fan,et al.  Experimental study on two-phase flow pressure drop during steam condensation in trapezoidal microchannels , 2016 .

[20]  Hiroshi Hasegawa,et al.  Training Artificial Neural Network Using Modification of Differential Evolution Algorithm , 2015 .

[21]  Chiang Juay Teo,et al.  An experimental study of flow friction and heat transfer in wavy microchannels with rectangular cross section , 2011 .

[22]  Mingxin Liang,et al.  Prediction Model of Total Organic Carbon Content on Hydrocarbon Source Rocks in Coal Measures Established by BP Neural Network Based on Logging Parameters , 2016 .

[23]  Huiying Wu,et al.  Friction factors in smooth trapezoidal silicon microchannels with different aspect ratios , 2003 .

[24]  Shifei Ding,et al.  An optimizing BP neural network algorithm based on genetic algorithm , 2011, Artificial Intelligence Review.

[25]  Marziyeh Hajialyani,et al.  Application of artificial neural network and genetic algorithm approaches for prediction of flow characteristic in serpentine microchannels , 2015 .

[26]  Y. Sui,et al.  Direct numerical simulation of fluid flow and heat transfer in periodic wavy channels with rectangular cross-sections , 2012 .

[27]  G. P. Peterson,et al.  Numerical simulation for steady annular condensation flow in triangular microchannels , 2008 .

[28]  Bingtao Zhao,et al.  Artificial neural network-based modeling of pressure drop coefficient for cyclone separators , 2010 .

[29]  Thanhtrung Dang,et al.  Characterization of frictional pressure drop of liquid flow through curved rectangular microchannels , 2012 .

[30]  B. Kim.  An experimental study on fully developed laminar flow and heat transfer in rectangular microchannels , 2016 .

[31]  Jung-Yeul Jung,et al.  Fluid flow and heat transfer in microchannels with rectangular cross section , 2008 .

[32]  Nazri Mohd Nawi,et al.  A New Bat Based Back-Propagation (BAT-BP) Algorithm , 2013, ICSS.

[33]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[34]  Kejun Zhu,et al.  A dynamic all parameters adaptive BP neural networks model and its application on oil reservoir prediction , 2008, Appl. Math. Comput..

[35]  Mirmanto,et al.  Pressure drop and heat transfer characteristics for single-phase developing flow of water in rectangular microchannels , 2012 .