多相复杂系统国家重点实验室知识库

A database and forecasting models of the solubility of hydrogen sulfide (H2S) in ionic liquids (ILs) are important for the industrial processes of gas sweetening. However, the specialized H2S solubility database and accurate predictive models are scarce at present. Therefore, this study first established a comprehensive database on the solubility of H2S in ILs, which includes 1334 pieces of data covering the period from 2007 to 2016. On the basis of the database, a new model is proposed using an extreme learning machine (ELM) intelligence algorithm and the number of fragments, which are easy to obtain and thus eliminate the need to use experimental data as input parameters. A total of 1282 pieces of data for 27 ILs (including 23 imidazolium-based and four ammonium-based ILs) have been used to build and test the model. The coefficient of determination (R-2) and root-mean-square error (RMSE) of the ELM model for the test set are 0.990 and 0.0301, respectively. The results show that the established ELM model is applicable for predicting the solubility of H2S in ILs, which is important for the design, simulation, and analysis of new gas sweetening processes.