A novel water quantities allocation arithmetic in water management

A water quantities allocation arithmetic was proposed, Radial basis function neural network (RBFNN) was designed, and simulated annealing arithmetic was adopted to adjust the network weights. MATLAB program was compiled; experiments on related data have been done employing the program. All experiments have shown that the arithmetic can efficiently approach the surface with 10^-4 mm error precision, also the learning speed is quick and predictions is ideal. Trainings have been done with other networks in comparison. Back-propagation learning algorithm network does not converge until 2000 iterative procedure, and exactness design RBFNN is time-consuming and has big error. The arithmetic can approach nonlinear function by arbitrary precision, and also keep the network from getting into partial minimum.