Research on Modern Design Technology of the Recuperator Combined With Neural Network

Abstract

The traditional recuperator design process was cumbersome and inefficient. In order to improve the design efficiency of the recuperator, the modern design methods were introduced into the design process of the recuperator. Aiming at the problem of solving the empirical parameters in the recuperator design, the modern design technology of the recuperator combined with neural network was put forward. The past similar cases were extracted through case-based reasoning as training samples of neural network. The prediction of empirical parameters was performed by using neural network, and the solution of calculation parameters was realized by formula. On this basis, the design result was output in the form of a recuperator parametric model. Finally, the feasibility and effectiveness of the proposed method were demonstrated by taking the design of a typical single-cylinder recuperator as an example.