Application of Artificial Intelligent Approach to Predict the Normal Boiling Point of Refrigerants

Due to the desirable and interesting applications of refrigerants in organic Rankine cycles, heat pumps, refrigeration, engineers researchers are becoming more interested refrigerant properties. One most dominant thermophysical properties these fluids is their normal boiling point (Tb). In current study, a novel extreme learning method (ELM) ensemble decision tree boosted algorithm (EDT Boosted) proposed forecast from 16 different molecular groups one topological index. To this end, total 334 data points Tb gathered prepare test ELM EDT algorithms. The visual mathematical comparisons model outputs real express that models have great potential predict refrigerant. Moreover, sensitivity analysis applied explain effectiveness input parameters on determination for refrigerants.