A novel Parsimonious Genetic Programming （PGP） algorithm together with a novel aero-engine optimum data-driven dynamic start process model based on PGP is proposed. In application of this method, first, the traditio...A novel Parsimonious Genetic Programming （PGP） algorithm together with a novel aero-engine optimum data-driven dynamic start process model based on PGP is proposed. In application of this method, first, the traditional Genetic Programming（GP） is used to generate the nonlinear input-output models that are represented in a binary tree structure; then, the Orthogonal Least Squares algorithm （OLS） is used to estimate the contribution of the branches of the tree （refer to basic function term that cannot be decomposed anymore according to special rule） to the accuracy of the model, which contributes to eliminate complex redundant subtrees and enhance GP＇s convergence speed; and finally, a simple, reliable and exact linear-in-parameter nonlinear model via GP evolution is obtained. The real aero-engine start process test data simulation and the comparisons with Support Vector Machines （SVM） validate that the proposed method can generate more applicable, interpretable models and achieve comparable, even superior results to SVM.展开更多
A new dynamic non-equilibrium mixing-pool model for simulating start-up and dynamic re-sponse of a distillation column is reported.The proposed model is established on the basis ofconsidering the two dimensional flow/...A new dynamic non-equilibrium mixing-pool model for simulating start-up and dynamic re-sponse of a distillation column is reported.The proposed model is established on the basis ofconsidering the two dimensional flow/mixing behavior of actual trays in a distillation column.Com-parison is made among the computed results of the start-up time and the dynamic response time bythe proposed and five other typical models.It is found that the computed time for both dynamicprocesses is longer by the model which considers any flow/mixing pattern than by the model withoutsuch concern.The inertia effect of flow/mixing seems to be important and can not be ignored inmodeling the transient process of distillation.The proposed model,which is believed to be suitableto large column,seems somewhat useful in predicting industrial distillation dynamics.展开更多
基金National Defense Advanced Research Foundation of China
文摘A novel Parsimonious Genetic Programming （PGP） algorithm together with a novel aero-engine optimum data-driven dynamic start process model based on PGP is proposed. In application of this method, first, the traditional Genetic Programming（GP） is used to generate the nonlinear input-output models that are represented in a binary tree structure; then, the Orthogonal Least Squares algorithm （OLS） is used to estimate the contribution of the branches of the tree （refer to basic function term that cannot be decomposed anymore according to special rule） to the accuracy of the model, which contributes to eliminate complex redundant subtrees and enhance GP＇s convergence speed; and finally, a simple, reliable and exact linear-in-parameter nonlinear model via GP evolution is obtained. The real aero-engine start process test data simulation and the comparisons with Support Vector Machines （SVM） validate that the proposed method can generate more applicable, interpretable models and achieve comparable, even superior results to SVM.
文摘A new dynamic non-equilibrium mixing-pool model for simulating start-up and dynamic re-sponse of a distillation column is reported.The proposed model is established on the basis ofconsidering the two dimensional flow/mixing behavior of actual trays in a distillation column.Com-parison is made among the computed results of the start-up time and the dynamic response time bythe proposed and five other typical models.It is found that the computed time for both dynamicprocesses is longer by the model which considers any flow/mixing pattern than by the model withoutsuch concern.The inertia effect of flow/mixing seems to be important and can not be ignored inmodeling the transient process of distillation.The proposed model,which is believed to be suitableto large column,seems somewhat useful in predicting industrial distillation dynamics.
