Wavelet neural network（WNN） is a kind of neural networks

which can closely combine wavelet theory with neural network theory.It has many good abilities of function learning and dissemination with a vast range of prospects for application.The BP weight balance algorithm based on WNN is used in multi-sensor data fusion at the feature level

and then the fusion result is judged by the decision-level.This novel fusion algorithm avoids the problem that BP neural network is easy to be trapped into local minima and its convergence speed is slow

and increases the learning speed and precision.The simulation results show its effectiveness of the proposed algorithm.