黄德先a; 金以慧a; 张杰b; A. J. Morrisb
HUANG Dexiana; JN Yihuia; ZHANG Jieb; A. J. Morrisb
摘要: A type of wavelet neural network, in which the scale function is adopted only, is proposed
in this paper for non-linear dynamic process modelling. Its network size is decreased
significantly and the weight coefficients can be estimated by a linear algorithm. The
wavelet neural network holds some advantages superior to other types of neural networks.
First, its network structure is easy to specify based on its theoretical analysis and
intuition. Secondly,network training does not rely on stochastic gradient type techniques
and avoids the problem of poor convergence or undesirable local minima. The excellent
statistic properties of the weight parameter estimations can be proven here. Both
theoretical analysis and simulation study show that the identification method is robust and
reliable.Furthermore, a hybrid network structure incorporating first-principle knowledge
and wavelet network is developed to solve a commonly existing problem in chemical
production processes. Applications of the hybrid network to a practical production process
demonstrates that model generalisation capability is significantly improved.