The application of a neural network controller for compensating the ef
fects induced by the friction in a dc motor micromaneuvering system is
considered in this article. A backpropagation neural network operatin
g in the specialized learning mode, using the sign gradient descent al
gorithm, is employed. The input vector to the neural network controlle
r consists of the time history of the motor angular shaft velocity wit
hin a prespecified time window. The on-line training of the neural net
work is performed in the region of interest of the output domain, The
neural network output resembles that of a Pulse Width Modulated contro
ller. The effect of the number of neurons in the input and hidden laye
rs on the transient system response is explored. Experimental studies
are presented to indicate the effectiveness of the proposed algorithm.