Determining Flow Friction Factor in Irrigation Pipes Using Data Mining and Artificial Intelligence Approaches

作者：Samadianfard Saeed^*; Sattari Mohammad Taghi; Kisi Ozgur; Kazemi Honeyeh

来源：Applied Artificial Intelligence, 2014, 28(8): 793-813.

DOI：10.1080/08839514.2014.952923

The implicit Colebrook-White equation has been widely used to estimate the friction factor for turbulent fluid in irrigation pipes. A fast, accurate, and robust resolution of the Colebrook-White equation is, in particular, necessary for scientific intensive computations. In this study, the performance of some artificial intelligence approaches, including gene expression programming (GEP), which is a variant of genetic programming (GP); adaptive neurofuzzy inference system (ANFIS); and artificial neural network (ANN) has been compared to the M5 model tree, which is a data mining technique and, to most available approximations, is based on root mean squared error (RMSE), mean absolute error (MAE) and correlation coefficient (R). Results show that Serghides and Buzzelli approximations with RMSE (0.00002), MAE (0.00001), and R (0.99999) values had the best performances. Among the data mining and artificial intelligence approaches, the GEP with RMSE (0.00032), MAE (0.00026), and R (0.99953) values performed better. However, all 20 explicit approximations except Wood, Churchill (full range of turbulence including laminar regime) and Rau and Kumar estimated the friction factor more accurately than the GEP.

• 出版日期2014-9-14