In recent years,the liquid membrane process has been widely investigated to remove rare earth metals.However,transport modeling of this process requires the accurate values of several parameters,which are difficult to...In recent years,the liquid membrane process has been widely investigated to remove rare earth metals.However,transport modeling of this process requires the accurate values of several parameters,which are difficult to measure.Thus,the accurate simulation of this process is a challenging task.In this study,the artificial neural network(ANN)based approach is used to model the liquid membrane process for removing dysprosium.Experimental results from a previous study were used to train the ANN.Initially,the number of neurons in the hidden layer was optimized.The minimum mean squared error between experimental results and model predictions is found with ten neurons.Model predictions were successfully validated with experimental results with correlation factor(R)of 0.9987,which confirms the authenticity of the trained network.Trained ANN was then used to study the effects of different operating parameters on transport rate.The higher volume ratio of membrane solution to feed solution(3-4)with 50-60 min of operation,higher feed pH(5),HCl concentration in stripping solution of 2 mol/L,and moderate concentration of carrier species(0.5 mol/L)with 0.5×10^(-4) mol/L dysprosium initial concentration are found to be optimum values of operating conditions for maximizing the transport rate.展开更多
文摘In recent years,the liquid membrane process has been widely investigated to remove rare earth metals.However,transport modeling of this process requires the accurate values of several parameters,which are difficult to measure.Thus,the accurate simulation of this process is a challenging task.In this study,the artificial neural network(ANN)based approach is used to model the liquid membrane process for removing dysprosium.Experimental results from a previous study were used to train the ANN.Initially,the number of neurons in the hidden layer was optimized.The minimum mean squared error between experimental results and model predictions is found with ten neurons.Model predictions were successfully validated with experimental results with correlation factor(R)of 0.9987,which confirms the authenticity of the trained network.Trained ANN was then used to study the effects of different operating parameters on transport rate.The higher volume ratio of membrane solution to feed solution(3-4)with 50-60 min of operation,higher feed pH(5),HCl concentration in stripping solution of 2 mol/L,and moderate concentration of carrier species(0.5 mol/L)with 0.5×10^(-4) mol/L dysprosium initial concentration are found to be optimum values of operating conditions for maximizing the transport rate.
