Support vector machine is a new method developed recently. It has shown good
performance in many field and mostly outperformed neural networks. So SVM is introduced
to the field of intelligent modeling of helicopter, and an online modeling method for
helicopter based on SVM is proposed. It is shown by simulation that the online SVM
modeling method leads to a significant speed up in the training process, whilst maintain the
generalization precision.

Neural networks with good nonlinear mapping abilities can be applied to build simulation
model of helicopter. But they have some difficulties such as hardness of selecting network
structure, slow convergence speed, local minimum, and over-fitting. To avoid above
problems, a method for building simulation model of helicopter based on Wavelet Support
Vector Machine (WSVM) is proposed. Marr wavelet is used to construct one-dimension
wavelet kernel, and the rationality of the wavelet kernel is proved. Subsequently the wavelet …