Thermal Properties Reduced Models by ANN in Process Simulation
It’s very time-consuming to evaluate thermal properties by rigorous methods in process real-time simulation, especially when the simulated project relates to multi-units and multi-components, which takes about 70 to 80 percent of the total simulation time. We developed a new reduced method for thermal properties evaluation based on the artificial neural net(ANN), in which we established several reduced evaluation models using ANN, such as models of vapor-liquid equilibrium, models of vapor-liquid enthalpy and models of temperature calculated from given enthalpy. We used the reduced models in a dynamic distillation simulation. Compared with rigorous thermal properties models, the ANN-reduced models could save 10 to 20 times simulation time with a satisfied accuracy. The results show it’s an efficient and effective method.
KeywordsThermal Property Hide Layer Output Layer Learning Rate Training Time
Unable to display preview. Download preview PDF.
- 1.Yang, Y.Q.: Practical Chemical Process Sysytem. Chemical Industry Press (1989)Google Scholar
- 2.Storen, S., Hertzberg, T.: Local Thermodynamic Models Used In Sensitivity Estimation Of Dynamic Systems. Comp. Chem. Eng. 21, S709–S714 (1997)Google Scholar
- 4.Qu, Q., Luo, J.S., Yu, G.S., Yu, Z.H.: Application of Artificial Neural Network to Vapor Liquid Equilibrium Constant Prediction. Comp. Appl. Chem. 18(4), 383–387 (2001)Google Scholar
- 5.Wei, T.Y., Huang, R.H.: Using Neural Network to Predict the Density of Saturated Liquid. Gx. Sci. 7(3), 201–205 (2000)Google Scholar
- 6.Yang, X.: Distillation Dynamic Simulation. Master Paper. Qingdao University of Science and Technology (1998)Google Scholar