Evolving ANFIS model to estimate sweet natural gas water content

Water existence in natural gas may cause difficulties in processing facilities and also transmission through pipelines. Therefore, it will be important to find a way to estimate water content values. An intelligent learning Adaptive Network-based Fuzzy Inference System (ANFIS) is introduced to estimate water content under a given temperature and pressure condition. Assessment of model's accuracy is carried out by determining mean relative error as 4.08% and R-squared value as 0.9996. Statistical analyses indicate the brilliant predictive ability of suggested ANFIS model. In addition, a comparison of our model's outcomes with other existence correlations also confirmed its satisfactory predictions.