The invention provides an
artificial immune algorithm based on an RBF neural network and adaptive search. The
artificial immune algorithm comprises the following steps: S1, performing
antigen recognition, and constructing the RBF neural network; S2, constructing an
antibody-
antigen nonlinear mapping curved surface; S3, randomly generating a certain number of initial
antibody groups; S4, calculating an
antibody-
antigen structural body, and preferably selecting N antibodies to serve as antibodies to be evaluated; S5, evaluating the antibodies; S6, sorting the antibody groups, extracting the previous nA antibody groups to serve as memory cells to form a
population A, and extracting subsequent nB antibody groups to serve as populations B to be inoculated; S7, judging a termination condition, outputting a result if the termination condition is satisfied, or otherwise, executing S8; and S8, performing selection,
crossover and
mutation operations on the antibody groups excluding the
population A in the S6 to form a
population C, after
vaccination is performed on the populations B to be inoculated, forming an antibody population D via the populations B together with the populations A and C, and skipping to S4. The invention aims at providing the
artificial immune algorithm based on the RBF neural network and adaptive search, which is high in local search capability, high in convergencespeed, high in
algorithm efficiency and high in precision.