Method for improving parameter estimation efficiency of continuous reforming model

Abstract

The invention discloses a method for improving the parameter estimation efficiency of a continuous reforming model, and the method comprises the steps: screening a rapid reaction component in a continuous reforming process, taking the rapid reaction component as a steady-state component, simplifying the calculation of a lumped model, and then carrying out the parameter estimation. Compared with a method for directly carrying out parameter estimation on an original model by using an optimization algorithm, the method can simplify calculation and remarkably improve the efficiency of model parameter estimation, so that an enterprise is helped to adjust the model more timely and effectively, and the method has important values for stabilizing and optimizing continuous reforming production and improving economic benefits of the enterprise.

Description

technical field [0001] The invention relates to the production field of refining and chemical enterprises, in particular to a method for establishing a mechanism model based on process knowledge, in particular to a method for improving the parameter estimation efficiency of a continuous reforming model. Background technique [0002] Continuous reforming is the mainstream process of catalytic reforming in refining and chemical enterprises. It is mainly used for the production of high-octane gasoline, light aromatics and hydrogen, etc., and is of great importance to the economic benefits of the entire enterprise. Process simulation of the reforming process can identify weak links in the production process, help companies optimize production operations and improve efficiency. [0003] Establishing an efficient and accurate model is an important part of the process simulation of the continuous reforming process. At present, the parameter estimation of the continuous reforming mo...

AI Technical Summary

Problems solved by technology

In response to the above problems, many studies have focused on the optimization of parameter estimation algorithms, such as using algorithms such as variable scaling method (BFGS) and Marquardt method to optimize gradient calculations. Complicated, the gradient is still difficult to calculate

Therefore, intelligent optimization algorithms such as evolutionary algorithm and swarm intelligence algorithm are used to speed up parameter estimation. Although intelligent algorithms do not rely on gradients and have fast calculation speeds, they often focus on improving the performance of the algorithm itself, which is prone to falling into local optimum and poor convergence effect. Good and other questions

Images