Time and Error Analysis of Neurocomputing of Finite Element

On the basis of dynamic equations of neural networks, the stabilizing time and the computing precision in the neurocomputation of elastic problem are analyzed both theoretically and numerically. The simulation results show that there are effects of capacity C, amplifying gain beta on the stabilizing time, and the resistance R, penalty coefficient alpha on the precision. But because solving time is 10
^-12
order, it is no necessary to constrain the R, C, beta, alpha strictly when it is applied to engineering problems