For　OFDM　system,　we　proposed　a　channel　estimation　method　based　on　radial　basis　function　neural　network　(RBFNN).　The　neural　network　with　Gaussian　basis　function　is　established　according　to　the　pilot　pattern,　where　the　network　parameters　are　obtained　by　training　channel　response　of　pilot　subcarriers　as　objective　values　for　input　samples.　With　the　established　network,　channel　coefficients　of　non-pilot　subcarriers　can　be　predicted.　The　simulation　results　indicate　that　the　proposed　algorithm　performs　well　in　OFDM　systems　under　Rayleigh　multipath　fading　channel.