Artificial Neural Network Model for Prediction of Friction Factor in Pipe Flow
David Abimbola Fadare, Nigeria Ibadan · 2009
Determination of friction factor is an essential prerequisite in pipe flow calculations. The Darcy- Weisbach equation and other analytical models have been developed for t he est imation of friction f actor. But t hese developed models are complex and involve iterative schemes w hich are time consuming. In this study, a suitable model based on artificial neural network (ANN) technique was proposed for estimation of factor to friction in pipe flow. Multilayered perceptron (MLP) neural networks with feed-forward back- propagation training algorithms were designed using the neural network toolbox for MATLAB . The input ® parameters of the networks were pipe relative roughness and Reynold's number of the flow, while t he friction f actor w as used as the output parameter. The performance of the networks was determined based the mean on absolute percentage error (MAPE), mean squared error (MSE), sum of squared errors (SSE), and correlation coefficient ( R-value). Results have shown that the network with 2-20-31-1 c onfiguration trained with the Levenberg-Marquardt ' trainlm' function had the b est performance with R-value (0.99 9), MAPE (0.68%), MSE (5.335x10 ), and SSE (3.414x10 ). A graphic user interface (GUI) with plot ting -7 -4 capabilities was developed for easy application of the model. The proposed model is suitable for modelling and prediction o f friction to factor i n p ipe fl ow for o n-line computer-based computations.