The histories of differential pressure fluctuations and their Fast Fourier Transform spectrum have close relation with the flow regimes.Unfortunately,each type of flow regime is very difficult or impossible to be dist...The histories of differential pressure fluctuations and their Fast Fourier Transform spectrum have close relation with the flow regimes.Unfortunately,each type of flow regime is very difficult or impossible to be distinguished from the other on the basis of the fluctuations or the spectrum.The present paper provides a feasible solution, which the gas-liquid two-phase flow regimes can be recognized automatically and objectively on the basis of the combination of the Counter Propagation Network (CPN) and the FFT spectrum of the differential pressure fluctuations. The CPN takes advantages of simpler algorithm and fast training processes.Furthermore,it does not require a great deal of samples.The recognition possibility is determined by the clustering results of the Kohonen layer in the CPN.With the presented test cases,the possibility can be higher than 90 percent for different liquid phase velocity.展开更多
The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformati...The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.展开更多
文摘The histories of differential pressure fluctuations and their Fast Fourier Transform spectrum have close relation with the flow regimes.Unfortunately,each type of flow regime is very difficult or impossible to be distinguished from the other on the basis of the fluctuations or the spectrum.The present paper provides a feasible solution, which the gas-liquid two-phase flow regimes can be recognized automatically and objectively on the basis of the combination of the Counter Propagation Network (CPN) and the FFT spectrum of the differential pressure fluctuations. The CPN takes advantages of simpler algorithm and fast training processes.Furthermore,it does not require a great deal of samples.The recognition possibility is determined by the clustering results of the Kohonen layer in the CPN.With the presented test cases,the possibility can be higher than 90 percent for different liquid phase velocity.
文摘The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.
