Prediction of Air Specific Heat Ratios at Elevated Pressures Using a Novel Modeling Approach

摘要: An accurate and efficient model based on least-squares support vector machines (LSSVM) is developed for the determination of air specific heat ratios at elevated pressures. Additionally, coupled simulated annealing optimization strategy used to calculate optimal values LSSVM parameters. A large dataset as a function temperature pressure about 170 samples develop validate model. The leverage approach (Williams plot) determine applicability domain detect probably erroneous data points. Comparison obtained results with previously published correlation well an intelligent method demonstrates that performance presented more satisfactory than other methods.