基于物理混合神經(jīng)網(wǎng)絡(luò)的渦流管性能研究

打開文本圖片集

天鍵詞：渦流管；預(yù)測(cè)模型；混合神經(jīng)網(wǎng)絡(luò)；溫度性能中圖分類號(hào)：TP183；TP399 文獻(xiàn)標(biāo)識(shí)碼：A文章編號(hào)：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

渦旋管又稱為Ranque-Hilsch管（RHVT），其是一種簡(jiǎn)單的裝置，由一根簡(jiǎn)單的圓形管、一個(gè)或多個(gè)切向噴嘴、冷端孔和一個(gè)熱端控制閥組成（如圖1所示）。（剩余7218字）