An Improved Perceptron based Illative Network for the Fault Signal Diagnosis
暂无分享,去创建一个
The faults signal diagnoses is one of the complex process for intelligent systems. Based on the principle of multi-layer neural network, this paper presents an improved algorithm with adaptive learning rate factors for the learning process of multi-layer perception (MLP). The improved algorithm is applied to the learning of an illative network for the faults signal diagnosing process. The simulations show the improved algorithm has good effects on speeding up learning process and bettering its learning convergence and robust performance.
[1] Erkki Oja,et al. The nonlinear PCA learning rule in independent component analysis , 1997, Neurocomputing.
[2] Ahmed El-Amawy,et al. On Fault Tolerant Training of Feedforward Neural Networks , 1997, Neural Networks.
[3] Paolo Frasconi,et al. Learning without local minima in radial basis function networks , 1995, IEEE Trans. Neural Networks.
[4] Masatake Akutagawa,et al. Analysis of a nonlinear system via internal-state of a neural network , 2005 .