DETECTION OF MAGNETIC BODY USING ARTIFICIAL NEURAL-NETWORK WITH MODIFIED SIMULATED ANNEALING

An artificial neural network is applied to the inverse electromagnetic fields problem. In the process of the training the network, it is sug gested that the simulated annealing algorithm be used to smooth the ou tput errors before the network is trained with the error back-propagat ion algorithm. And a general way of defining the control parameters of simulated annealing is presented. As a numerical example, the artific ial neural network with the suggested training algorithm is applied to the detection of the magnetic body in magnetic field. It is shown, th rough the numerical test, that the artificial neural network is very u seful for the inverse electromagnetic field problems, especially in re al-time system and the artificial neural network trained with the sugg ested training algorithm gives much less maximum errors than that trai ned with the error back-propagation algorithm only.