基于物理混合神经网络的涡流管性能研究

打开文本图片集

天键词：涡流管；预测模型；混合神经网络；温度性能中图分类号：TP183；TP399 文献标识码：A文章编号：2096-4706（2025）08-0194-05

Abstract： Inthis paper，a hybrid neural network model is constructed by adding the physical constraint conditions of theBernoulliequationandtheNicolas formula，exploringthetemperaturechangelawof thecoldendofthevortex tubeand making corrsponding predictions.The network adoptsa multi-layer fedforward model andthe Levenberg-Marquardt learning algorithm，andtehypebolictangentfunctionisselecedasthetransferfuncion.Inadditio，thecofcientofdeteation and the Root Mean Square Eror （RMSE）areused to determine the statistical validityof the developed model，and he model's uncertainty and robustness are analyzed.The hybrid model has an index of 0.9936and anRMSEof0.3392，and also has agood performance in tersofuncertaintyand robustnessThesedata indicate thatthe modelconstructed in this paper successfully predicts the changes in the temperature of the cold end of the vortex tube and has good accuracy.

Keywords： vortex tube; predictive model; hybrid neural network; temperature performance

0 引言

涡旋管又称为Ranque-Hilsch管（RHVT），其是一种简单的装置，由一根简单的圆形管、一个或多个切向喷嘴、冷端孔和一个热端控制阀组成（如图1所示）。（剩余7218字）