prediction of ro membrane performances by use of adaptive network-based fuzzy interference systems

This study aims to develop an adaptive network-based fuzzy inference system technique (anfis) and using the parameters of a complex mathematical model in the ro membrane performances. the anfis was constructed by using a subtractive clustering method to generate initial fuzzy inference systems. the model trained by 70% of the data set and then its validity is examined by remained 30% data set. the result indicated that this method could predict the performance of the ro membrane faster and more accurately than previous numerical techniques. the squared correlation coefficient between real data and predicted data of this technique was 0.9973 for separation factor, 0.9916 for np and 0.9975 nt, which are better in comparison with numerical methods, and previous artificial neural network used by the author to model these membranes. it was observed that the squash factor, reject ratio, and accept ratio has no significant effect on anfis performance. results showed that for all cases better performances achieved when this parameter has a value of more than 0.5, as 0.86 for separation factor, 0.91 for net pre flux, and 0.83 for total flux. this technique just takes a few seconds to model ro membrane performance which is very faster than other numerical methods. so, this technique could be a powerful method to predict ro membranes.