The third kind of generalized congruence neural network is used to diagnose fault of attitude control system

This paper uses generalized congruence function instead of transfer function of classical BP neural network, and improve convergence rate of neural network. We introduce the subsection generalized derivation, error back propagation derivation mechanism of classical BP algorithm to adjust weight vector in generalized congruence neural network, and modify generalized congruence neural network, and then can obtain the third kind of generalized congruence neural network (GCNN3). Finally, by means of fault diagnosis experiment of attitude control system, we compare approximation performance of the third kind of generalized congruence neural network with BP neural network; approximation effect and stable performance of GCNN3 is equivalent to BPNN, but convergence rate of the former is much faster than the latter.