Prediction of permeation flux decline during MF of oily wastewater using genetic programming

Genetic programming is an orderly method for getting computers to regularly solve a problem. The genetic programming creates a computer program from an obtained data and solves the problem. In this work, treatment of oily wastewaters with synthesized mullite ceramic microfiltration membranes was studied and a new approach for modeling of the membrane flux is presented. The model used input parameters for operating conditions (flux and filtration time) and feed oily wastewater quality (oil concentration, temperature, trans-membrane pressure and cross-flow velocity). The genetic programming utilized here delivers a mathematical function for the membrane flux as a function of the independent variables stated above. Parameters for controlling and termination criterion for a run are provided by the user. Result is provided as a tree of functions and terminals. The results thus obtained from the genetic programming model demonstrated good representation of the experimental data with an average error of less than 5%.